Merge branch 'main' of https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git

# Conflicts:
#	MAINTAINERS

186 files changed, 7037 insertions, 9800 deletions

diff --git a/drivers/net/amt.c b/drivers/net/amt.c
index 182a41d59a75..1f293a962b21 100644
--- a/drivers/net/amt.c
+++ b/drivers/net/amt.c
@@ -667,7 +667,7 @@ static void amt_send_discovery(struct amt_dev *amt)
 	udph		= udp_hdr(skb);
 	udph->source	= amt->gw_port;
 	udph->dest	= amt->relay_port;
-	udph->len	= htons(sizeof(*udph) + sizeof(*amtd));
+	udp_set_len_short(udph, sizeof(*udph) + sizeof(*amtd));
 	udph->check	= 0;
 	offset = skb_transport_offset(skb);
 	skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
@@ -708,11 +708,13 @@ static void amt_send_request(struct amt_dev *amt, bool v6)
 	struct iphdr *iph;
 	struct rtable *rt;
 	struct flowi4 fl4;
+	__be32 remote_ip;
 	struct sock *sk;
 	u32 len;
 	int err;
 
 	rcu_read_lock();
+	remote_ip = READ_ONCE(amt->remote_ip);
 	sk = rcu_dereference(amt->sk);
 	if (!sk)
 		goto out;
@@ -721,7 +723,7 @@ static void amt_send_request(struct amt_dev *amt, bool v6)
 		goto out;
 
 	rt = ip_route_output_ports(amt->net, &fl4, sk,
-				   amt->remote_ip, amt->local_ip,
+				   remote_ip, amt->local_ip,
 				   amt->gw_port, amt->relay_port,
 				   IPPROTO_UDP, 0,
 				   amt->stream_dev->ifindex);
@@ -758,11 +760,11 @@ static void amt_send_request(struct amt_dev *amt, bool v6)
 	udph		= udp_hdr(skb);
 	udph->source	= amt->gw_port;
 	udph->dest	= amt->relay_port;
-	udph->len	= htons(sizeof(*amtrh) + sizeof(*udph));
+	udp_set_len_short(udph, sizeof(*amtrh) + sizeof(*udph));
 	udph->check	= 0;
 	offset = skb_transport_offset(skb);
 	skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
-	udph->check = csum_tcpudp_magic(amt->local_ip, amt->remote_ip,
+	udph->check = csum_tcpudp_magic(amt->local_ip, remote_ip,
 					sizeof(*udph) + sizeof(*amtrh),
 					IPPROTO_UDP, skb->csum);
 
@@ -773,7 +775,7 @@ static void amt_send_request(struct amt_dev *amt, bool v6)
 	iph->tos	= AMT_TOS;
 	iph->frag_off	= 0;
 	iph->ttl	= ip4_dst_hoplimit(&rt->dst);
-	iph->daddr	= amt->remote_ip;
+	iph->daddr	= remote_ip;
 	iph->saddr	= amt->local_ip;
 	iph->protocol	= IPPROTO_UDP;
 	iph->tot_len	= htons(len);
@@ -962,7 +964,7 @@ static void amt_event_send_request(struct amt_dev *amt)
 		amt->qi = AMT_INIT_REQ_TIMEOUT;
 		WRITE_ONCE(amt->ready4, false);
 		WRITE_ONCE(amt->ready6, false);
-		amt->remote_ip = 0;
+		WRITE_ONCE(amt->remote_ip, 0);
 		amt_update_gw_status(amt, AMT_STATUS_INIT, false);
 		amt->req_cnt = 0;
 		amt->nonce = 0;
@@ -999,6 +1001,7 @@ static bool amt_send_membership_update(struct amt_dev *amt,
 				       struct sk_buff *skb,
 				       bool v6)
 {
+	__be32 remote_ip = READ_ONCE(amt->remote_ip);
 	struct amt_header_membership_update *amtmu;
 	struct iphdr *iph;
 	struct flowi4 fl4;
@@ -1018,13 +1021,13 @@ static bool amt_send_membership_update(struct amt_dev *amt,
 	skb_reset_inner_headers(skb);
 	memset(&fl4, 0, sizeof(struct flowi4));
 	fl4.flowi4_oif         = amt->stream_dev->ifindex;
-	fl4.daddr              = amt->remote_ip;
+	fl4.daddr              = remote_ip;
 	fl4.saddr              = amt->local_ip;
 	fl4.flowi4_dscp        = inet_dsfield_to_dscp(AMT_TOS);
 	fl4.flowi4_proto       = IPPROTO_UDP;
 	rt = ip_route_output_key(amt->net, &fl4);
 	if (IS_ERR(rt)) {
-		netdev_dbg(amt->dev, "no route to %pI4\n", &amt->remote_ip);
+		netdev_dbg(amt->dev, "no route to %pI4\n", &remote_ip);
 		return true;
 	}
 
@@ -2286,8 +2289,8 @@ static bool amt_advertisement_handler(struct amt_dev *amt, struct sk_buff *skb)
 	    amt->nonce != amta->nonce)
 		return true;
 
-	amt->remote_ip = amta->ip4;
-	netdev_dbg(amt->dev, "advertised remote ip = %pI4\n", &amt->remote_ip);
+	WRITE_ONCE(amt->remote_ip, amta->ip4);
+	netdev_dbg(amt->dev, "advertised remote ip = %pI4\n", &amta->ip4);
 	mod_delayed_work(amt_wq, &amt->req_wq, 0);
 
 	amt_update_gw_status(amt, AMT_STATUS_RECEIVED_ADVERTISEMENT, true);
@@ -2647,7 +2650,7 @@ static void amt_send_advertisement(struct amt_dev *amt, __be32 nonce,
 	udph		= udp_hdr(skb);
 	udph->source	= amt->relay_port;
 	udph->dest	= dport;
-	udph->len	= htons(sizeof(*amta) + sizeof(*udph));
+	udp_set_len_short(udph, sizeof(*amta) + sizeof(*udph));
 	udph->check	= 0;
 	offset = skb_transport_offset(skb);
 	skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
@@ -2811,6 +2814,7 @@ drop:
 static int amt_rcv(struct sock *sk, struct sk_buff *skb)
 {
 	struct amt_dev *amt;
+	__be32 remote_ip;
 	__be32 saddr;
 	int type;
 	bool err;
@@ -2822,6 +2826,7 @@ static int amt_rcv(struct sock *sk, struct sk_buff *skb)
 		kfree_skb(skb);
 		goto out;
 	}
+	remote_ip = READ_ONCE(amt->remote_ip);
 
 	skb->dev = amt->dev;
 	saddr = ip_hdr(skb)->saddr;
@@ -2846,7 +2851,7 @@ static int amt_rcv(struct sock *sk, struct sk_buff *skb)
 			}
 			goto out;
 		case AMT_MSG_MULTICAST_DATA:
-			if (saddr != amt->remote_ip) {
+			if (saddr != remote_ip) {
 				netdev_dbg(amt->dev, "Invalid Relay IP\n");
 				err = true;
 				goto drop;
@@ -2857,7 +2862,7 @@ static int amt_rcv(struct sock *sk, struct sk_buff *skb)
 			else
 				goto out;
 		case AMT_MSG_MEMBERSHIP_QUERY:
-			if (saddr != amt->remote_ip) {
+			if (saddr != remote_ip) {
 				netdev_dbg(amt->dev, "Invalid Relay IP\n");
 				err = true;
 				goto drop;
@@ -3045,7 +3050,7 @@ static int amt_dev_open(struct net_device *dev)
 	}
 
 	amt->req_cnt = 0;
-	amt->remote_ip = 0;
+	WRITE_ONCE(amt->remote_ip, 0);
 	amt->nonce = 0;
 	get_random_bytes(&amt->key, sizeof(siphash_key_t));
 
@@ -3090,7 +3095,7 @@ static int amt_dev_stop(struct net_device *dev)
 	amt->ready4 = false;
 	amt->ready6 = false;
 	amt->req_cnt = 0;
-	amt->remote_ip = 0;
+	WRITE_ONCE(amt->remote_ip, 0);
 
 	list_for_each_entry_safe(tunnel, tmp, &amt->tunnel_list, list) {
 		list_del_rcu(&tunnel->list);
@@ -3289,7 +3294,7 @@ static int amt_newlink(struct net_device *dev,
 					    "gateway port must not be 0");
 			goto err;
 		}
-		amt->remote_ip = 0;
+		WRITE_ONCE(amt->remote_ip, 0);
 		amt->discovery_ip = nla_get_in_addr(data[IFLA_AMT_DISCOVERY_IP]);
 		if (ipv4_is_loopback(amt->discovery_ip) ||
 		    ipv4_is_zeronet(amt->discovery_ip) ||
@@ -3355,8 +3360,10 @@ static size_t amt_get_size(const struct net_device *dev)
 
 static int amt_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
-	struct amt_dev *amt = netdev_priv(dev);
+	const struct amt_dev *amt = netdev_priv(dev);
+	__be32 remote_ip;
 
+	rcu_read_lock();
 	if (nla_put_u32(skb, IFLA_AMT_MODE, amt->mode))
 		goto nla_put_failure;
 	if (nla_put_be16(skb, IFLA_AMT_RELAY_PORT, amt->relay_port))
@@ -3369,15 +3376,19 @@ static int amt_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		goto nla_put_failure;
 	if (nla_put_in_addr(skb, IFLA_AMT_DISCOVERY_IP, amt->discovery_ip))
 		goto nla_put_failure;
-	if (amt->remote_ip)
-		if (nla_put_in_addr(skb, IFLA_AMT_REMOTE_IP, amt->remote_ip))
+
+	remote_ip = READ_ONCE(amt->remote_ip);
+	if (remote_ip)
+		if (nla_put_in_addr(skb, IFLA_AMT_REMOTE_IP, remote_ip))
 			goto nla_put_failure;
 	if (nla_put_u32(skb, IFLA_AMT_MAX_TUNNELS, amt->max_tunnels))
 		goto nla_put_failure;
 
+	rcu_read_unlock();
 	return 0;
 
 nla_put_failure:
+	rcu_read_unlock();
 	return -EMSGSIZE;
 }
 
diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index 5ef841c85526..c3b5ed52d877 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -36,6 +36,7 @@ static unsigned int bareudp_net_id;
 
 struct bareudp_net {
 	struct list_head        bareudp_list;
+	struct mutex		lock;
 };
 
 struct bareudp_conf {
@@ -636,10 +637,15 @@ static struct bareudp_dev *bareudp_find_dev(struct bareudp_net *bn,
 {
 	struct bareudp_dev *bareudp, *t = NULL;
 
+	mutex_lock(&bn->lock);
+
 	list_for_each_entry(bareudp, &bn->bareudp_list, next) {
 		if (conf->port == bareudp->port)
 			t = bareudp;
 	}
+
+	mutex_unlock(&bn->lock);
+
 	return t;
 }
 
@@ -675,7 +681,10 @@ static int bareudp_configure(struct net *net, struct net_device *dev,
 	if (err)
 		return err;
 
+	mutex_lock(&bn->lock);
 	list_add(&bareudp->next, &bn->bareudp_list);
+	mutex_unlock(&bn->lock);
+
 	return 0;
 }
 
@@ -692,12 +701,26 @@ static int bareudp_link_config(struct net_device *dev,
 	return 0;
 }
 
+static void __bareudp_dellink(struct net *net, struct net_device *dev,
+			      struct list_head *head)
+{
+	struct bareudp_dev *bareudp = netdev_priv(dev);
+
+	list_del_init(&bareudp->next);
+	unregister_netdevice_queue_net(net, dev, head);
+}
+
 static void bareudp_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct bareudp_dev *bareudp = netdev_priv(dev);
+	struct bareudp_net *bn;
 
-	list_del(&bareudp->next);
-	unregister_netdevice_queue(dev, head);
+	bn = net_generic(bareudp->net, bareudp_net_id);
+
+	mutex_lock(&bn->lock);
+	if (!list_empty(&bareudp->next))
+		__bareudp_dellink(dev_net(dev), dev, head);
+	mutex_unlock(&bn->lock);
 }
 
 static int bareudp_newlink(struct net_device *dev,
@@ -776,6 +799,8 @@ static __net_init int bareudp_init_net(struct net *net)
 	struct bareudp_net *bn = net_generic(net, bareudp_net_id);
 
 	INIT_LIST_HEAD(&bn->bareudp_list);
+	mutex_init(&bn->lock);
+
 	return 0;
 }
 
@@ -785,13 +810,25 @@ static void __net_exit bareudp_exit_rtnl_net(struct net *net,
 	struct bareudp_net *bn = net_generic(net, bareudp_net_id);
 	struct bareudp_dev *bareudp, *next;
 
+	mutex_lock(&bn->lock);
+
 	list_for_each_entry_safe(bareudp, next, &bn->bareudp_list, next)
-		bareudp_dellink(bareudp->dev, dev_kill_list);
+		__bareudp_dellink(net, bareudp->dev, dev_kill_list);
+
+	mutex_unlock(&bn->lock);
+}
+
+static void __net_exit bareudp_exit_net(struct net *net)
+{
+	struct bareudp_net *bn = net_generic(net, bareudp_net_id);
+
+	WARN_ON_ONCE(!list_empty(&bn->bareudp_list));
 }
 
 static struct pernet_operations bareudp_net_ops = {
 	.init = bareudp_init_net,
 	.exit_rtnl = bareudp_exit_rtnl_net,
+	.exit = bareudp_exit_net,
 	.id   = &bareudp_net_id,
 	.size = sizeof(struct bareudp_net),
 };
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index acbba08dbdfa..b8e4b4d68dd6 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -760,14 +760,14 @@ static int __agg_usable_ports(struct aggregator *agg)
 	return valid;
 }
 
-static int __agg_active_ports(struct aggregator *agg)
+static int __agg_active_ports(const struct aggregator *agg)
 {
-	struct port *port;
+	const struct port *port;
 	int active = 0;
 
 	for (port = agg->lag_ports; port;
 	     port = port->next_port_in_aggregator) {
-		if (port->is_enabled)
+		if (READ_ONCE(port->is_enabled))
 			active++;
 	}
 
@@ -2801,11 +2801,11 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
 	 * some of he adaptors(ce1000.lan) report.
 	 */
 	if (link == BOND_LINK_UP) {
-		port->is_enabled = true;
+		WRITE_ONCE(port->is_enabled, true);
 		ad_update_actor_keys(port, false);
 	} else {
 		/* link has failed */
-		port->is_enabled = false;
+		WRITE_ONCE(port->is_enabled, false);
 		ad_update_actor_keys(port, true);
 	}
 	agg = __get_first_agg(port);
@@ -2878,16 +2878,20 @@ out:
  * Returns:   0 on success
  *          < 0 on error
  */
-int __bond_3ad_get_active_agg_info(struct bonding *bond,
+int __bond_3ad_get_active_agg_info(const struct bonding *bond,
 				   struct ad_info *ad_info)
 {
-	struct aggregator *aggregator = NULL, *tmp;
+	const struct aggregator *aggregator = NULL, *tmp;
+	struct ad_slave_info *ad_slave_info;
+	const struct port *port;
 	struct list_head *iter;
 	struct slave *slave;
-	struct port *port;
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		port = &(SLAVE_AD_INFO(slave)->port);
+		ad_slave_info = SLAVE_AD_INFO(slave);
+		if (!ad_slave_info)
+			continue;
+		port = &ad_slave_info->port;
 		tmp = rcu_dereference(port->aggregator);
 		if (tmp && tmp->is_active) {
 			aggregator = tmp;
@@ -2907,7 +2911,7 @@ int __bond_3ad_get_active_agg_info(struct bonding *bond,
 	return 0;
 }
 
-int bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info)
+int bond_3ad_get_active_agg_info(const struct bonding *bond, struct ad_info *ad_info)
 {
 	int ret;
 
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 522eab060f9e..a925577c8253 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4858,12 +4858,6 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 			  __func__, slave);
 		res = dev_set_mac_address(slave->dev, addr, NULL);
 		if (res) {
-			/* TODO: consider downing the slave
-			 * and retry ?
-			 * User should expect communications
-			 * breakage anyway until ARP finish
-			 * updating, so...
-			 */
 			slave_dbg(bond_dev, slave->dev, "%s: err %d\n",
 				  __func__, res);
 			goto unwind;
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 4a11572f663d..55d2f8a539d4 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -686,53 +686,58 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		0;
 }
 
-static int bond_option_active_slave_get_ifindex(struct bonding *bond)
+static int bond_option_active_slave_get_ifindex_rcu(const struct bonding *bond)
 {
-	const struct net_device *slave;
-	int ifindex;
+	const struct net_device *dev = NULL;
+	const struct slave *slave;
 
-	rcu_read_lock();
-	slave = bond_option_active_slave_get_rcu(bond);
-	ifindex = slave ? slave->ifindex : 0;
-	rcu_read_unlock();
-	return ifindex;
+	slave = rcu_dereference(bond->curr_active_slave);
+	if (slave)
+		dev = slave->dev;
+	return dev ? dev->ifindex : 0;
 }
 
 static int bond_fill_info(struct sk_buff *skb,
 			  const struct net_device *bond_dev)
 {
-	struct bonding *bond = netdev_priv(bond_dev);
-	unsigned int packets_per_slave;
-	int ifindex, i, targets_added;
+	const struct bonding *bond = netdev_priv(bond_dev);
+	int i, targets_added, miimon, mode;
+	const struct slave *primary;
 	struct nlattr *targets;
-	struct slave *primary;
 
-	if (nla_put_u8(skb, IFLA_BOND_MODE, BOND_MODE(bond)))
+	rcu_read_lock();
+	mode = READ_ONCE(bond->params.mode);
+	if (nla_put_u8(skb, IFLA_BOND_MODE, mode))
 		goto nla_put_failure;
 
-	ifindex = bond_option_active_slave_get_ifindex(bond);
-	if (ifindex && nla_put_u32(skb, IFLA_BOND_ACTIVE_SLAVE, ifindex))
-		goto nla_put_failure;
+	if (bond_mode_uses_primary(mode)) {
+		int ifindex = bond_option_active_slave_get_ifindex_rcu(bond);
+
+		if (ifindex && nla_put_u32(skb, IFLA_BOND_ACTIVE_SLAVE, ifindex))
+			goto nla_put_failure;
+	}
 
-	if (nla_put_u32(skb, IFLA_BOND_MIIMON, bond->params.miimon))
+	miimon = READ_ONCE(bond->params.miimon);
+	if (nla_put_u32(skb, IFLA_BOND_MIIMON, miimon))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, IFLA_BOND_UPDELAY,
-			bond->params.updelay * bond->params.miimon))
+			READ_ONCE(bond->params.updelay) * miimon))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, IFLA_BOND_DOWNDELAY,
-			bond->params.downdelay * bond->params.miimon))
+			READ_ONCE(bond->params.downdelay) * miimon))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, IFLA_BOND_PEER_NOTIF_DELAY,
-			bond->params.peer_notif_delay * bond->params.miimon))
+			READ_ONCE(bond->params.peer_notif_delay) * miimon))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, 1))
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval))
+	if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL,
+			READ_ONCE(bond->params.arp_interval)))
 		goto nla_put_failure;
 
 	targets = nla_nest_start_noflag(skb, IFLA_BOND_ARP_IP_TARGET);
@@ -741,8 +746,10 @@ static int bond_fill_info(struct sk_buff *skb,
 
 	targets_added = 0;
 	for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) {
-		if (bond->params.arp_targets[i]) {
-			if (nla_put_be32(skb, i, bond->params.arp_targets[i]))
+		__be32 t = READ_ONCE(bond->params.arp_targets[i]);
+
+		if (t) {
+			if (nla_put_be32(skb, i, t))
 				goto nla_put_failure;
 			targets_added = 1;
 		}
@@ -753,11 +760,12 @@ static int bond_fill_info(struct sk_buff *skb,
 	else
 		nla_nest_cancel(skb, targets);
 
-	if (nla_put_u32(skb, IFLA_BOND_ARP_VALIDATE, bond->params.arp_validate))
+	if (nla_put_u32(skb, IFLA_BOND_ARP_VALIDATE,
+			READ_ONCE(bond->params.arp_validate)))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, IFLA_BOND_ARP_ALL_TARGETS,
-			bond->params.arp_all_targets))
+			READ_ONCE(bond->params.arp_all_targets)))
 		goto nla_put_failure;
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -767,6 +775,9 @@ static int bond_fill_info(struct sk_buff *skb,
 
 	targets_added = 0;
 	for (i = 0; i < BOND_MAX_NS_TARGETS; i++) {
+		/* Note: IPv6 addresses can not be read in an atomic READ_ONCE() yet.
+		 * We accept this minor race for the moment.
+		 */
 		if (!ipv6_addr_any(&bond->params.ns_targets[i])) {
 			if (nla_put_in6_addr(skb, i, &bond->params.ns_targets[i]))
 				goto nla_put_failure;
@@ -780,97 +791,97 @@ static int bond_fill_info(struct sk_buff *skb,
 		nla_nest_cancel(skb, targets);
 #endif
 
-	primary = rtnl_dereference(bond->primary_slave);
+	primary = rcu_dereference(bond->primary_slave);
 	if (primary &&
 	    nla_put_u32(skb, IFLA_BOND_PRIMARY, primary->dev->ifindex))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_PRIMARY_RESELECT,
-		       bond->params.primary_reselect))
+		       READ_ONCE(bond->params.primary_reselect)))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_FAIL_OVER_MAC,
-		       bond->params.fail_over_mac))
+		       READ_ONCE(bond->params.fail_over_mac)))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_XMIT_HASH_POLICY,
-		       bond->params.xmit_policy))
+		       READ_ONCE(bond->params.xmit_policy)))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, IFLA_BOND_RESEND_IGMP,
-			bond->params.resend_igmp))
+			READ_ONCE(bond->params.resend_igmp)))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_NUM_PEER_NOTIF,
-		       bond->params.num_peer_notif))
+		       READ_ONCE(bond->params.num_peer_notif)))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_ALL_SLAVES_ACTIVE,
-		       bond->params.all_slaves_active))
+		       READ_ONCE(bond->params.all_slaves_active)))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, IFLA_BOND_MIN_LINKS,
-			bond->params.min_links))
+			READ_ONCE(bond->params.min_links)))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, IFLA_BOND_LP_INTERVAL,
-			bond->params.lp_interval))
+			READ_ONCE(bond->params.lp_interval)))
 		goto nla_put_failure;
 
-	packets_per_slave = bond->params.packets_per_slave;
 	if (nla_put_u32(skb, IFLA_BOND_PACKETS_PER_SLAVE,
-			packets_per_slave))
+			READ_ONCE(bond->params.packets_per_slave)))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_AD_LACP_ACTIVE,
-		       bond->params.lacp_active))
+		       READ_ONCE(bond->params.lacp_active)))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_AD_LACP_RATE,
-		       bond->params.lacp_fast))
+		       READ_ONCE(bond->params.lacp_fast)))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_AD_SELECT,
-		       bond->params.ad_select))
+		       READ_ONCE(bond->params.ad_select)))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_TLB_DYNAMIC_LB,
-		       bond->params.tlb_dynamic_lb))
+		       READ_ONCE(bond->params.tlb_dynamic_lb)))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_MISSED_MAX,
-		       bond->params.missed_max))
+		       READ_ONCE(bond->params.missed_max)))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_COUPLED_CONTROL,
-		       bond->params.coupled_control))
+		       READ_ONCE(bond->params.coupled_control)))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_BROADCAST_NEIGH,
-		       bond->params.broadcast_neighbor))
+		       READ_ONCE(bond->params.broadcast_neighbor)))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_LACP_STRICT,
-		       bond->params.lacp_strict))
+		       READ_ONCE(bond->params.lacp_strict)))
 		goto nla_put_failure;
 
-	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
+	if (mode == BOND_MODE_8023AD) {
 		struct ad_info info;
 
 		if (capable(CAP_NET_ADMIN)) {
 			if (nla_put_u16(skb, IFLA_BOND_AD_ACTOR_SYS_PRIO,
-					bond->params.ad_actor_sys_prio))
+					READ_ONCE(bond->params.ad_actor_sys_prio)))
 				goto nla_put_failure;
 
 			if (nla_put_u16(skb, IFLA_BOND_AD_USER_PORT_KEY,
-					bond->params.ad_user_port_key))
+					READ_ONCE(bond->params.ad_user_port_key)))
 				goto nla_put_failure;
 
+			/* Small race here, this is a minor trade off. */
 			if (nla_put(skb, IFLA_BOND_AD_ACTOR_SYSTEM,
 				    ETH_ALEN, &bond->params.ad_actor_system))
 				goto nla_put_failure;
 		}
-		if (!bond_3ad_get_active_agg_info(bond, &info)) {
+		if (!__bond_3ad_get_active_agg_info(bond, &info)) {
 			struct nlattr *nest;
 
 			nest = nla_nest_start_noflag(skb, IFLA_BOND_AD_INFO);
@@ -898,9 +909,11 @@ static int bond_fill_info(struct sk_buff *skb,
 		}
 	}
 
+	rcu_read_unlock();
 	return 0;
 
 nla_put_failure:
+	rcu_read_unlock();
 	return -EMSGSIZE;
 }
 
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index e590c8dee86e..36b8d89387ee 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -934,14 +934,14 @@ static int bond_option_mode_set(struct bonding *bond,
 
 	/* don't cache arp_validate between modes */
 	WRITE_ONCE(bond->params.arp_validate, BOND_ARP_VALIDATE_NONE);
-	bond->params.mode = newval->value;
+	WRITE_ONCE(bond->params.mode, newval->value);
 
 	/* When changing mode, the bond device is down, we may reduce
 	 * the bond_bcast_neigh_enabled in bond_close() if broadcast_neighbor
 	 * enabled in 8023ad mode. Therefore, only clear broadcast_neighbor
 	 * to 0.
 	 */
-	bond->params.broadcast_neighbor = 0;
+	WRITE_ONCE(bond->params.broadcast_neighbor, 0);
 
 	if (bond->dev->reg_state == NETREG_REGISTERED) {
 		bool update = false;
@@ -1706,7 +1706,7 @@ static int bond_option_lacp_strict_set(struct bonding *bond,
 {
 	netdev_dbg(bond->dev, "Setting LACP fallback to %s (%llu)\n",
 		   newval->string, newval->value);
-	bond->params.lacp_strict = newval->value;
+	WRITE_ONCE(bond->params.lacp_strict, newval->value);
 	bond_3ad_set_carrier(bond);
 
 	return 0;
@@ -1927,7 +1927,7 @@ static int bond_option_broadcast_neigh_set(struct bonding *bond,
 	if (bond->params.broadcast_neighbor == newval->value)
 		return 0;
 
-	bond->params.broadcast_neighbor = newval->value;
+	WRITE_ONCE(bond->params.broadcast_neighbor, newval->value);
 	if (bond->dev->flags & IFF_UP) {
 		if (bond->params.broadcast_neighbor)
 			static_branch_inc(&bond_bcast_neigh_enabled);
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index cd27a7344e89..29cca7945df7 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -23,6 +23,7 @@
 #include <linux/mutex.h>
 #include <linux/phylink.h>
 #include <linux/etherdevice.h>
+#include <linux/gpio/consumer.h>
 #include <net/dsa.h>
 
 #include "b53_regs.h"
@@ -467,7 +468,7 @@ static inline void b53_arl_search_read(struct b53_device *dev, u8 idx,
 #ifdef CONFIG_BCM47XX
 
 #include <linux/bcm47xx_nvram.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
 #include <bcm47xx_board.h>
 static inline struct gpio_desc *b53_switch_get_reset_gpio(struct b53_device *dev)
 {
diff --git a/drivers/net/dsa/microchip/ksz8.c b/drivers/net/dsa/microchip/ksz8.c
index 138f2ab0774e..c4c769028a20 100644
--- a/drivers/net/dsa/microchip/ksz8.c
+++ b/drivers/net/dsa/microchip/ksz8.c
@@ -18,7 +18,7 @@
 #include <linux/delay.h>
 #include <linux/dsa/ksz_common.h>
 #include <linux/export.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/if_vlan.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -36,6 +36,52 @@
 #include "ksz8_reg.h"
 #include "ksz8.h"
 
+/* ksz88x3_drive_strengths - Drive strength mapping for KSZ8863, KSZ8873, ..
+ *			     variants.
+ * This values are documented in KSZ8873 and KSZ8863 datasheets.
+ */
+static const struct ksz_drive_strength ksz88x3_drive_strengths[] = {
+	{ 0,  8000 },
+	{ KSZ8873_DRIVE_STRENGTH_16MA, 16000 },
+};
+
+struct ksz88xx_stats_raw {
+	u64 rx;
+	u64 rx_hi;
+	u64 rx_undersize;
+	u64 rx_fragments;
+	u64 rx_oversize;
+	u64 rx_jabbers;
+	u64 rx_symbol_err;
+	u64 rx_crc_err;
+	u64 rx_align_err;
+	u64 rx_mac_ctrl;
+	u64 rx_pause;
+	u64 rx_bcast;
+	u64 rx_mcast;
+	u64 rx_ucast;
+	u64 rx_64_or_less;
+	u64 rx_65_127;
+	u64 rx_128_255;
+	u64 rx_256_511;
+	u64 rx_512_1023;
+	u64 rx_1024_1522;
+	u64 tx;
+	u64 tx_hi;
+	u64 tx_late_col;
+	u64 tx_pause;
+	u64 tx_bcast;
+	u64 tx_mcast;
+	u64 tx_ucast;
+	u64 tx_deferred;
+	u64 tx_total_col;
+	u64 tx_exc_col;
+	u64 tx_single_col;
+	u64 tx_mult_col;
+	u64 rx_discards;
+	u64 tx_discards;
+};
+
 static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set)
 {
 	ksz_rmw8(dev, addr, bits, set ? bits : 0);
@@ -158,10 +204,17 @@ static int ksz8_reset_switch(struct ksz_device *dev)
 	return 0;
 }
 
-static int ksz8863_change_mtu(struct ksz_device *dev, int frame_size)
+static int ksz88xx_change_mtu(struct dsa_switch *ds, int port, int mtu)
 {
+	struct ksz_device *dev = ds->priv;
+	int frame_size;
 	u8 ctrl2 = 0;
 
+	if (!dsa_is_cpu_port(dev->ds, port))
+		return 0;
+
+	frame_size = mtu + VLAN_ETH_HLEN + ETH_FCS_LEN;
+
 	if (frame_size <= KSZ8_LEGAL_PACKET_SIZE)
 		ctrl2 |= KSZ8863_LEGAL_PACKET_ENABLE;
 	else if (frame_size > KSZ8863_NORMAL_PACKET_SIZE)
@@ -171,11 +224,18 @@ static int ksz8863_change_mtu(struct ksz_device *dev, int frame_size)
 			KSZ8863_HUGE_PACKET_ENABLE, ctrl2);
 }
 
-static int ksz8795_change_mtu(struct ksz_device *dev, int frame_size)
+static int ksz87xx_change_mtu(struct dsa_switch *ds, int port, int mtu)
 {
+	struct ksz_device *dev = ds->priv;
 	u8 ctrl1 = 0, ctrl2 = 0;
+	u16 frame_size;
 	int ret;
 
+	if (!dsa_is_cpu_port(dev->ds, port))
+		return 0;
+
+	frame_size = mtu + VLAN_ETH_HLEN + ETH_FCS_LEN;
+
 	if (frame_size > KSZ8_LEGAL_PACKET_SIZE)
 		ctrl2 |= SW_LEGAL_PACKET_DISABLE;
 	if (frame_size > KSZ8863_NORMAL_PACKET_SIZE)
@@ -188,29 +248,14 @@ static int ksz8795_change_mtu(struct ksz_device *dev, int frame_size)
 	return ksz_rmw8(dev, REG_SW_CTRL_2, SW_LEGAL_PACKET_DISABLE, ctrl2);
 }
 
-static int ksz8_change_mtu(struct dsa_switch *ds, int port, int mtu)
+static int ksz87xx_max_mtu(struct dsa_switch *ds, int port)
 {
-	struct ksz_device *dev = ds->priv;
-	u16 frame_size;
-
-	if (!dsa_is_cpu_port(dev->ds, port))
-		return 0;
-
-	frame_size = mtu + VLAN_ETH_HLEN + ETH_FCS_LEN;
-
-	switch (dev->chip_id) {
-	case KSZ8795_CHIP_ID:
-	case KSZ8794_CHIP_ID:
-	case KSZ8765_CHIP_ID:
-		return ksz8795_change_mtu(dev, frame_size);
-	case KSZ8463_CHIP_ID:
-	case KSZ88X3_CHIP_ID:
-	case KSZ8864_CHIP_ID:
-	case KSZ8895_CHIP_ID:
-		return ksz8863_change_mtu(dev, frame_size);
-	}
+	return KSZ8795_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN;
+}
 
-	return -EOPNOTSUPP;
+static int ksz88xx_max_mtu(struct dsa_switch *ds, int port)
+{
+	return KSZ8863_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN;
 }
 
 static int ksz8_port_queue_split(struct ksz_device *dev, int port, int queues)
@@ -1746,6 +1791,159 @@ static void ksz8_port_mirror_del(struct dsa_switch *ds, int port,
 			     PORT_MIRROR_SNIFFER, false);
 }
 
+static u8 ksz8463_tc_ctrl(int port, int queue)
+{
+	u8 reg;
+
+	reg = 0xC8 + port * 4;
+	reg += ((3 - queue) / 2) * 2;
+	reg++;
+	reg -= (queue & 1);
+	return reg;
+}
+
+/**
+ * ksz88x3_tc_ets_add - Configure ETS (Enhanced Transmission Selection)
+ *                      for a port on KSZ88x3 switch
+ * @dev: Pointer to the KSZ switch device structure
+ * @port: Port number to configure
+ * @p: Pointer to offload replace parameters describing ETS bands and mapping
+ *
+ * The KSZ88x3 supports two scheduling modes: Strict Priority and
+ * Weighted Fair Queuing (WFQ). Both modes have fixed behavior:
+ *   - No configurable queue-to-priority mapping
+ *   - No weight adjustment in WFQ mode
+ *
+ * This function configures the switch to use strict priority mode by
+ * clearing the WFQ enable bit for all queues associated with ETS bands.
+ * If strict priority is not explicitly requested, the switch will default
+ * to WFQ mode.
+ *
+ * Return: 0 on success, or a negative error code on failure
+ */
+static int ksz88x3_tc_ets_add(struct ksz_device *dev, int port,
+			      struct tc_ets_qopt_offload_replace_params *p)
+{
+	int ret, band;
+
+	/* Only strict priority mode is supported for now.
+	 * WFQ is implicitly enabled when strict mode is disabled.
+	 */
+	for (band = 0; band < p->bands; band++) {
+		int queue = ksz_ets_band_to_queue(p, band);
+		u8 reg;
+
+		/* Calculate TXQ Split Control register address for this
+		 * port/queue
+		 */
+		reg = KSZ8873_TXQ_SPLIT_CTRL_REG(port, queue);
+		if (ksz_is_ksz8463(dev))
+			reg = ksz8463_tc_ctrl(port, queue);
+
+		/* Clear WFQ enable bit to select strict priority scheduling */
+		ret = ksz_rmw8(dev, reg, KSZ8873_TXQ_WFQ_ENABLE, 0);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * ksz88x3_tc_ets_del - Reset ETS (Enhanced Transmission Selection) config
+ *                      for a port on KSZ88x3 switch
+ * @dev: Pointer to the KSZ switch device structure
+ * @port: Port number to reset
+ *
+ * The KSZ88x3 supports only fixed scheduling modes: Strict Priority or
+ * Weighted Fair Queuing (WFQ), with no reconfiguration of weights or
+ * queue mapping. This function resets the port’s scheduling mode to
+ * the default, which is WFQ, by enabling the WFQ bit for all queues.
+ *
+ * Return: 0 on success, or a negative error code on failure
+ */
+static int ksz88x3_tc_ets_del(struct ksz_device *dev, int port)
+{
+	int ret, queue;
+
+	/* Iterate over all transmit queues for this port */
+	for (queue = 0; queue < dev->info->num_tx_queues; queue++) {
+		u8 reg;
+
+		/* Calculate TXQ Split Control register address for this
+		 * port/queue
+		 */
+		reg = KSZ8873_TXQ_SPLIT_CTRL_REG(port, queue);
+		if (ksz_is_ksz8463(dev))
+			reg = ksz8463_tc_ctrl(port, queue);
+
+		/* Set WFQ enable bit to revert back to default scheduling
+		 * mode
+		 */
+		ret = ksz_rmw8(dev, reg, KSZ8873_TXQ_WFQ_ENABLE,
+			       KSZ8873_TXQ_WFQ_ENABLE);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int ksz8_tc_setup_qdisc_ets(struct dsa_switch *ds, int port,
+				   struct tc_ets_qopt_offload *qopt)
+{
+	struct ksz_device *dev = ds->priv;
+	int ret;
+
+	if (!(ksz_is_ksz88x3(dev) || ksz_is_ksz8463(dev)))
+		return -EOPNOTSUPP;
+
+	if (qopt->parent != TC_H_ROOT) {
+		dev_err(dev->dev, "Parent should be \"root\"\n");
+		return -EOPNOTSUPP;
+	}
+
+	switch (qopt->command) {
+	case TC_ETS_REPLACE:
+		ret = ksz_tc_ets_validate(dev, port, &qopt->replace_params);
+		if (ret)
+			return ret;
+
+		return ksz88x3_tc_ets_add(dev, port, &qopt->replace_params);
+	case TC_ETS_DESTROY:
+		return ksz88x3_tc_ets_del(dev, port);
+	case TC_ETS_STATS:
+	case TC_ETS_GRAFT:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int ksz87xx_setup_tc(struct dsa_switch *ds, int port,
+			    enum tc_setup_type type, void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_QDISC_CBS:
+		return ksz_setup_tc_cbs(ds, port, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int ksz8_setup_tc(struct dsa_switch *ds, int port,
+			 enum tc_setup_type type, void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_QDISC_CBS:
+		return ksz_setup_tc_cbs(ds, port, type_data);
+	case TC_SETUP_QDISC_ETS:
+		return ksz8_tc_setup_qdisc_ets(ds, port, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static void ksz8795_cpu_interface_select(struct ksz_device *dev, int port)
 {
 	struct ksz_port *p = &dev->ports[port];
@@ -2053,6 +2251,171 @@ static int ksz8_enable_stp_addr(struct ksz_device *dev)
 	return ksz8_w_sta_mac_table(dev, 0, &alu);
 }
 
+static void ksz88xx_r_mib_stats64(struct ksz_device *dev, int port)
+{
+	struct ethtool_pause_stats *pstats;
+	struct rtnl_link_stats64 *stats;
+	struct ksz88xx_stats_raw *raw;
+	struct ksz_port_mib *mib;
+
+	mib = &dev->ports[port].mib;
+	stats = &mib->stats64;
+	pstats = &mib->pause_stats;
+	raw = (struct ksz88xx_stats_raw *)mib->counters;
+
+	spin_lock(&mib->stats64_lock);
+
+	stats->rx_packets = raw->rx_bcast + raw->rx_mcast + raw->rx_ucast +
+		raw->rx_pause;
+	stats->tx_packets = raw->tx_bcast + raw->tx_mcast + raw->tx_ucast +
+		raw->tx_pause;
+
+	/* HW counters are counting bytes + FCS which is not acceptable
+	 * for rtnl_link_stats64 interface
+	 */
+	stats->rx_bytes = raw->rx + raw->rx_hi - stats->rx_packets * ETH_FCS_LEN;
+	stats->tx_bytes = raw->tx + raw->tx_hi - stats->tx_packets * ETH_FCS_LEN;
+
+	stats->rx_length_errors = raw->rx_undersize + raw->rx_fragments +
+		raw->rx_oversize;
+
+	stats->rx_crc_errors = raw->rx_crc_err;
+	stats->rx_frame_errors = raw->rx_align_err;
+	stats->rx_dropped = raw->rx_discards;
+	stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors +
+		stats->rx_frame_errors  + stats->rx_dropped;
+
+	stats->tx_window_errors = raw->tx_late_col;
+	stats->tx_fifo_errors = raw->tx_discards;
+	stats->tx_aborted_errors = raw->tx_exc_col;
+	stats->tx_errors = stats->tx_window_errors + stats->tx_fifo_errors +
+		stats->tx_aborted_errors;
+
+	stats->multicast = raw->rx_mcast;
+	stats->collisions = raw->tx_total_col;
+
+	pstats->tx_pause_frames = raw->tx_pause;
+	pstats->rx_pause_frames = raw->rx_pause;
+
+	spin_unlock(&mib->stats64_lock);
+}
+
+/**
+ * ksz88x3_drive_strength_write() - Set the drive strength configuration for
+ *				    KSZ8863 compatible chip variants.
+ * @dev:       ksz device
+ * @props:     Array of drive strength properties to be set
+ * @num_props: Number of properties in the array
+ *
+ * This function applies the specified drive strength settings to KSZ88X3 chip
+ * variants (KSZ8873, KSZ8863).
+ * It ensures the configurations align with what the chip variant supports and
+ * warns or errors out on unsupported settings.
+ *
+ * Return: 0 on success, error code otherwise
+ */
+static int ksz88x3_drive_strength_write(struct ksz_device *dev,
+					struct ksz_driver_strength_prop *props,
+					int num_props)
+{
+	size_t array_size = ARRAY_SIZE(ksz88x3_drive_strengths);
+	int microamp;
+	int i, ret;
+
+	for (i = 0; i < num_props; i++) {
+		if (props[i].value == -1 || i == KSZ_DRIVER_STRENGTH_IO)
+			continue;
+
+		dev_warn(dev->dev, "%s is not supported by this chip variant\n",
+			 props[i].name);
+	}
+
+	microamp = props[KSZ_DRIVER_STRENGTH_IO].value;
+	ret = ksz_drive_strength_to_reg(ksz88x3_drive_strengths, array_size,
+					microamp);
+	if (ret < 0) {
+		ksz_drive_strength_error(dev, ksz88x3_drive_strengths,
+					 array_size, microamp);
+		return ret;
+	}
+
+	return ksz_rmw8(dev, KSZ8873_REG_GLOBAL_CTRL_12,
+			KSZ8873_DRIVE_STRENGTH_16MA, ret);
+}
+
+/**
+ * ksz8_parse_drive_strength() - Extract and apply drive strength configurations
+ *				 from device tree properties.
+ * @dev:	ksz device
+ *
+ * This function reads the specified drive strength properties from the
+ * device tree, validates against the supported chip variants, and sets
+ * them accordingly. An error should be critical here, as the drive strength
+ * settings are crucial for EMI compliance.
+ *
+ * Return: 0 on success, error code otherwise
+ */
+static int ksz8_parse_drive_strength(struct ksz_device *dev)
+{
+	struct ksz_driver_strength_prop of_props[] = {
+		[KSZ_DRIVER_STRENGTH_HI] = {
+			.name = "microchip,hi-drive-strength-microamp",
+			.offset = SW_HI_SPEED_DRIVE_STRENGTH_S,
+			.value = -1,
+		},
+		[KSZ_DRIVER_STRENGTH_LO] = {
+			.name = "microchip,lo-drive-strength-microamp",
+			.offset = SW_LO_SPEED_DRIVE_STRENGTH_S,
+			.value = -1,
+		},
+		[KSZ_DRIVER_STRENGTH_IO] = {
+			.name = "microchip,io-drive-strength-microamp",
+			.offset = 0, /* don't care */
+			.value = -1,
+		},
+	};
+	struct device_node *np = dev->dev->of_node;
+	bool have_any_prop = false;
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(of_props); i++) {
+		ret = of_property_read_u32(np, of_props[i].name,
+					   &of_props[i].value);
+		if (ret && ret != -EINVAL)
+			dev_warn(dev->dev, "Failed to read %s\n",
+				 of_props[i].name);
+		if (ret)
+			continue;
+
+		have_any_prop = true;
+	}
+
+	if (!have_any_prop)
+		return 0;
+
+	switch (dev->chip_id) {
+	case KSZ88X3_CHIP_ID:
+		return ksz88x3_drive_strength_write(dev, of_props,
+						    ARRAY_SIZE(of_props));
+	case KSZ8795_CHIP_ID:
+	case KSZ8794_CHIP_ID:
+	case KSZ8765_CHIP_ID:
+		return ksz_drive_strength_write(dev, of_props,
+						ARRAY_SIZE(of_props));
+	default:
+		/* KSZ8864, KSZ8895 */
+		for (i = 0; i < ARRAY_SIZE(of_props); i++) {
+			if (of_props[i].value == -1)
+				continue;
+
+			dev_warn(dev->dev, "%s is not supported by this chip variant\n",
+				 of_props[i].name);
+		}
+	}
+
+	return 0;
+}
+
 static int ksz8_setup(struct dsa_switch *ds)
 {
 	struct ksz_device *dev = ds->priv;
@@ -2075,7 +2438,7 @@ static int ksz8_setup(struct dsa_switch *ds)
 		return ret;
 	}
 
-	ret = ksz_parse_drive_strength(dev);
+	ret = ksz8_parse_drive_strength(dev);
 	if (ret)
 		return ret;
 
@@ -2551,8 +2914,8 @@ const struct dsa_switch_ops ksz8463_switch_ops = {
 	.port_mirror_del	= ksz8_port_mirror_del,
 	.get_stats64		= ksz_get_stats64,
 	.get_pause_stats	= ksz_get_pause_stats,
-	.port_change_mtu	= ksz8_change_mtu,
-	.port_max_mtu		= ksz_max_mtu,
+	.port_change_mtu	= ksz88xx_change_mtu,
+	.port_max_mtu		= ksz88xx_max_mtu,
 	.suspend		= ksz_suspend,
 	.resume			= ksz_resume,
 	.get_ts_info		= ksz_get_ts_info,
@@ -2560,7 +2923,7 @@ const struct dsa_switch_ops ksz8463_switch_ops = {
 	.port_hwtstamp_set	= ksz_hwtstamp_set,
 	.port_txtstamp		= ksz_port_txtstamp,
 	.port_rxtstamp		= ksz_port_rxtstamp,
-	.port_setup_tc		= ksz_setup_tc,
+	.port_setup_tc		= ksz8_setup_tc,
 	.port_get_default_prio	= ksz_port_get_default_prio,
 	.port_set_default_prio	= ksz_port_set_default_prio,
 	.port_get_dscp_prio	= ksz_port_get_dscp_prio,
@@ -2601,8 +2964,8 @@ const struct dsa_switch_ops ksz87xx_switch_ops = {
 	.port_mirror_del	= ksz8_port_mirror_del,
 	.get_stats64		= ksz_get_stats64,
 	.get_pause_stats	= ksz_get_pause_stats,
-	.port_change_mtu	= ksz8_change_mtu,
-	.port_max_mtu		= ksz_max_mtu,
+	.port_change_mtu	= ksz87xx_change_mtu,
+	.port_max_mtu		= ksz87xx_max_mtu,
 	.suspend		= ksz_suspend,
 	.resume			= ksz_resume,
 	.get_ts_info		= ksz_get_ts_info,
@@ -2610,7 +2973,7 @@ const struct dsa_switch_ops ksz87xx_switch_ops = {
 	.port_hwtstamp_set	= ksz_hwtstamp_set,
 	.port_txtstamp		= ksz_port_txtstamp,
 	.port_rxtstamp		= ksz_port_rxtstamp,
-	.port_setup_tc		= ksz_setup_tc,
+	.port_setup_tc		= ksz87xx_setup_tc,
 	.port_get_default_prio	= ksz_port_get_default_prio,
 	.port_set_default_prio	= ksz_port_set_default_prio,
 	.port_get_dscp_prio	= ksz_port_get_dscp_prio,
@@ -2652,8 +3015,8 @@ const struct dsa_switch_ops ksz88xx_switch_ops = {
 	.port_mirror_del	= ksz8_port_mirror_del,
 	.get_stats64		= ksz_get_stats64,
 	.get_pause_stats	= ksz_get_pause_stats,
-	.port_change_mtu	= ksz8_change_mtu,
-	.port_max_mtu		= ksz_max_mtu,
+	.port_change_mtu	= ksz88xx_change_mtu,
+	.port_max_mtu		= ksz88xx_max_mtu,
 	.get_wol		= ksz_get_wol,
 	.set_wol		= ksz_set_wol,
 	.suspend		= ksz_suspend,
@@ -2663,7 +3026,7 @@ const struct dsa_switch_ops ksz88xx_switch_ops = {
 	.port_hwtstamp_set	= ksz_hwtstamp_set,
 	.port_txtstamp		= ksz_port_txtstamp,
 	.port_rxtstamp		= ksz_port_rxtstamp,
-	.port_setup_tc		= ksz_setup_tc,
+	.port_setup_tc		= ksz8_setup_tc,
 	.port_get_default_prio	= ksz_port_get_default_prio,
 	.port_set_default_prio	= ksz_port_set_default_prio,
 	.port_get_dscp_prio	= ksz_port_get_dscp_prio,
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index f3f0c98dfb5a..3ee995545c57 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -15,6 +15,7 @@
 #include <linux/if_hsr.h>
 #include <linux/if_vlan.h>
 #include <net/dsa.h>
+#include <net/ieee8021q.h>
 #include <net/switchdev.h>
 
 #include "ksz9477_reg.h"
@@ -60,6 +61,11 @@ static int ksz9477_change_mtu(struct dsa_switch *ds, int port, int mtu)
 				  REG_SW_MTU_MASK, frame_size);
 }
 
+int ksz9477_max_mtu(struct dsa_switch *ds, int port)
+{
+	return KSZ9477_MAX_FRAME_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN;
+}
+
 static int ksz9477_wait_vlan_ctrl_ready(struct ksz_device *dev)
 {
 	unsigned int val;
@@ -478,8 +484,8 @@ static int ksz9477_half_duplex_monitor(struct ksz_device *dev, int port,
 	return ret;
 }
 
-int ksz9477_errata_monitor(struct ksz_device *dev, int port,
-			   u64 tx_late_col)
+static int ksz9477_errata_monitor(struct ksz_device *dev, int port,
+				  u64 tx_late_col)
 {
 	u8 status;
 	int ret;
@@ -497,6 +503,24 @@ int ksz9477_errata_monitor(struct ksz_device *dev, int port,
 	return ret;
 }
 
+static void ksz9477_r_mib_stats64(struct ksz_device *dev, int port)
+{
+	struct ksz_stats_raw *raw;
+	struct ksz_port_mib *mib;
+	int ret;
+
+	ksz_r_mib_stats64(dev, port);
+
+	if (dev->info->phy_errata_9477 && !ksz_is_sgmii_port(dev, port)) {
+		mib = &dev->ports[port].mib;
+		raw = (struct ksz_stats_raw *)mib->counters;
+
+		ret = ksz9477_errata_monitor(dev, port, raw->tx_late_col);
+		if (ret)
+			dev_err(dev->dev, "Failed to monitor transmission halt\n");
+	}
+};
+
 void ksz9477_port_init_cnt(struct ksz_device *dev, int port)
 {
 	struct ksz_port_mib *mib = &dev->ports[port].mib;
@@ -1176,6 +1200,58 @@ void ksz9477_port_mirror_del(struct dsa_switch *ds, int port,
 			     PORT_MIRROR_SNIFFER, false);
 }
 
+static bool ksz9477_get_gbit(struct ksz_device *dev, int port)
+{
+	const u8 *bitval = dev->info->xmii_ctrl1;
+	const u16 *regs = dev->info->regs;
+	bool gbit = false;
+	u8 data8;
+	bool val;
+
+	ksz_pread8(dev, port, regs[P_XMII_CTRL_1], &data8);
+
+	val = FIELD_GET(P_GMII_1GBIT_M, data8);
+
+	if (val == bitval[P_GMII_1GBIT])
+		gbit = true;
+
+	return gbit;
+}
+
+static phy_interface_t ksz9477_get_xmii(struct ksz_device *dev, int port,
+					bool gbit)
+{
+	const u8 *bitval = dev->info->xmii_ctrl1;
+	const u16 *regs = dev->info->regs;
+	phy_interface_t interface;
+	u8 data8;
+	u8 val;
+
+	ksz_pread8(dev, port, regs[P_XMII_CTRL_1], &data8);
+
+	val = FIELD_GET(P_MII_SEL_M, data8);
+
+	if (val == bitval[P_MII_SEL]) {
+		if (gbit)
+			interface = PHY_INTERFACE_MODE_GMII;
+		else
+			interface = PHY_INTERFACE_MODE_MII;
+	} else if (val == bitval[P_RMII_SEL]) {
+		interface = PHY_INTERFACE_MODE_RMII;
+	} else {
+		interface = PHY_INTERFACE_MODE_RGMII;
+		if (data8 & P_RGMII_ID_EG_ENABLE)
+			interface = PHY_INTERFACE_MODE_RGMII_TXID;
+		if (data8 & P_RGMII_ID_IG_ENABLE) {
+			interface = PHY_INTERFACE_MODE_RGMII_RXID;
+			if (data8 & P_RGMII_ID_EG_ENABLE)
+				interface = PHY_INTERFACE_MODE_RGMII_ID;
+		}
+	}
+
+	return interface;
+}
+
 static phy_interface_t ksz9477_get_interface(struct ksz_device *dev, int port)
 {
 	phy_interface_t interface;
@@ -1184,9 +1260,9 @@ static phy_interface_t ksz9477_get_interface(struct ksz_device *dev, int port)
 	if (dev->info->internal_phy[port])
 		return PHY_INTERFACE_MODE_NA;
 
-	gbit = ksz_get_gbit(dev, port);
+	gbit = ksz9477_get_gbit(dev, port);
 
-	interface = ksz_get_xmii(dev, port, gbit);
+	interface = ksz9477_get_xmii(dev, port, gbit);
 
 	return interface;
 }
@@ -1335,6 +1411,28 @@ static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 	ksz_pwrite8(dev, port, regs[REG_PORT_PME_CTRL], 0);
 }
 
+int ksz9477_set_default_prio_queue_mapping(struct ksz_device *dev, int port)
+{
+	u32 queue_map = 0;
+	int ipm;
+
+	for (ipm = 0; ipm < dev->info->num_ipms; ipm++) {
+		int queue;
+
+		/* Traffic Type (TT) is corresponding to the Internal Priority
+		 * Map (IPM) in the switch. Traffic Class (TC) is
+		 * corresponding to the queue in the switch.
+		 */
+		queue = ieee8021q_tt_to_tc(ipm, dev->info->num_tx_queues);
+		if (queue < 0)
+			return queue;
+
+		queue_map |= queue << (ipm * KSZ9477_PORT_TC_MAP_S);
+	}
+
+	return ksz_pwrite32(dev, port, KSZ9477_PORT_MRI_TC_MAP__4, queue_map);
+}
+
 static int ksz9477_dsa_port_setup(struct dsa_switch *ds, int port)
 {
 	struct ksz_device *dev = ds->priv;
@@ -1517,6 +1615,58 @@ int ksz9477_enable_stp_addr(struct ksz_device *dev)
 	return 0;
 }
 
+/**
+ * ksz9477_parse_drive_strength() - Extract and apply drive strength
+ *				    configurations from device tree properties.
+ * @dev:	ksz device
+ *
+ * This function reads the specified drive strength properties from the
+ * device tree, validates against the supported chip variants, and sets
+ * them accordingly. An error should be critical here, as the drive strength
+ * settings are crucial for EMI compliance.
+ *
+ * Return: 0 on success, error code otherwise
+ */
+static int ksz9477_parse_drive_strength(struct ksz_device *dev)
+{
+	struct ksz_driver_strength_prop of_props[] = {
+		[KSZ_DRIVER_STRENGTH_HI] = {
+			.name = "microchip,hi-drive-strength-microamp",
+			.offset = SW_HI_SPEED_DRIVE_STRENGTH_S,
+			.value = -1,
+		},
+		[KSZ_DRIVER_STRENGTH_LO] = {
+			.name = "microchip,lo-drive-strength-microamp",
+			.offset = SW_LO_SPEED_DRIVE_STRENGTH_S,
+			.value = -1,
+		},
+		[KSZ_DRIVER_STRENGTH_IO] = {
+			.name = "microchip,io-drive-strength-microamp",
+			.offset = 0, /* don't care */
+			.value = -1,
+		},
+	};
+	struct device_node *np = dev->dev->of_node;
+	bool have_any_prop = false;
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(of_props); i++) {
+		ret = of_property_read_u32(np, of_props[i].name,
+					   &of_props[i].value);
+		if (ret && ret != -EINVAL)
+			dev_warn(dev->dev, "Failed to read %s\n",
+				 of_props[i].name);
+		if (ret)
+			continue;
+
+		have_any_prop = true;
+	}
+
+	if (!have_any_prop)
+		return 0;
+
+	return ksz_drive_strength_write(dev, of_props, ARRAY_SIZE(of_props));
+}
 static int ksz9477_setup(struct dsa_switch *ds)
 {
 	struct ksz_device *dev = ds->priv;
@@ -1539,7 +1689,7 @@ static int ksz9477_setup(struct dsa_switch *ds)
 		return ret;
 	}
 
-	ret = ksz_parse_drive_strength(dev);
+	ret = ksz9477_parse_drive_strength(dev);
 	if (ret)
 		return ret;
 
@@ -2052,7 +2202,7 @@ const struct ksz_dev_ops ksz9477_dev_ops = {
 	.cfg_port_member = ksz9477_cfg_port_member,
 	.r_mib_cnt = ksz9477_r_mib_cnt,
 	.r_mib_pkt = ksz9477_r_mib_pkt,
-	.r_mib_stat64 = ksz_r_mib_stats64,
+	.r_mib_stat64 = ksz9477_r_mib_stats64,
 	.freeze_mib = ksz9477_freeze_mib,
 	.port_init_cnt = ksz9477_port_init_cnt,
 	.pme_write8 = ksz_write8,
@@ -2098,7 +2248,7 @@ const struct dsa_switch_ops ksz9477_switch_ops = {
 	.get_stats64		= ksz_get_stats64,
 	.get_pause_stats	= ksz_get_pause_stats,
 	.port_change_mtu	= ksz9477_change_mtu,
-	.port_max_mtu		= ksz_max_mtu,
+	.port_max_mtu		= ksz9477_max_mtu,
 	.get_wol		= ksz_get_wol,
 	.set_wol		= ksz_set_wol,
 	.suspend		= ksz_suspend,
diff --git a/drivers/net/dsa/microchip/ksz9477.h b/drivers/net/dsa/microchip/ksz9477.h
index 92a1d889224d..a84c000000e6 100644
--- a/drivers/net/dsa/microchip/ksz9477.h
+++ b/drivers/net/dsa/microchip/ksz9477.h
@@ -21,6 +21,7 @@ void ksz9477_freeze_mib(struct ksz_device *dev, int port, bool freeze);
 void ksz9477_port_init_cnt(struct ksz_device *dev, int port);
 int ksz9477_port_vlan_filtering(struct dsa_switch *ds, int port,
 				bool flag, struct netlink_ext_ack *extack);
+int ksz9477_max_mtu(struct dsa_switch *ds, int port);
 int ksz9477_port_vlan_add(struct dsa_switch *ds, int port,
 			  const struct switchdev_obj_port_vlan *vlan,
 			  struct netlink_ext_ack *extack);
@@ -31,8 +32,6 @@ int ksz9477_port_mirror_add(struct dsa_switch *ds, int port,
 			    bool ingress, struct netlink_ext_ack *extack);
 void ksz9477_port_mirror_del(struct dsa_switch *ds, int port,
 			     struct dsa_mall_mirror_tc_entry *mirror);
-int ksz9477_errata_monitor(struct ksz_device *dev, int port,
-			   u64 tx_late_col);
 int ksz9477_fdb_dump(struct dsa_switch *ds, int port,
 		     dsa_fdb_dump_cb_t *cb, void *data);
 int ksz9477_fdb_add(struct dsa_switch *ds, int port,
@@ -45,6 +44,7 @@ int ksz9477_mdb_del(struct dsa_switch *ds, int port,
 		    const struct switchdev_obj_port_mdb *mdb, struct dsa_db db);
 int ksz9477_enable_stp_addr(struct ksz_device *dev);
 void ksz9477_port_queue_split(struct ksz_device *dev, int port);
+int ksz9477_set_default_prio_queue_mapping(struct ksz_device *dev, int port);
 
 int ksz9477_port_acl_init(struct ksz_device *dev, int port);
 void ksz9477_port_acl_free(struct ksz_device *dev, int port);
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index d1726778bb48..ff4dd51f6cb0 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -37,82 +37,6 @@
 
 #define MIB_COUNTER_NUM 0x20
 
-struct ksz_stats_raw {
-	u64 rx_hi;
-	u64 rx_undersize;
-	u64 rx_fragments;
-	u64 rx_oversize;
-	u64 rx_jabbers;
-	u64 rx_symbol_err;
-	u64 rx_crc_err;
-	u64 rx_align_err;
-	u64 rx_mac_ctrl;
-	u64 rx_pause;
-	u64 rx_bcast;
-	u64 rx_mcast;
-	u64 rx_ucast;
-	u64 rx_64_or_less;
-	u64 rx_65_127;
-	u64 rx_128_255;
-	u64 rx_256_511;
-	u64 rx_512_1023;
-	u64 rx_1024_1522;
-	u64 rx_1523_2000;
-	u64 rx_2001;
-	u64 tx_hi;
-	u64 tx_late_col;
-	u64 tx_pause;
-	u64 tx_bcast;
-	u64 tx_mcast;
-	u64 tx_ucast;
-	u64 tx_deferred;
-	u64 tx_total_col;
-	u64 tx_exc_col;
-	u64 tx_single_col;
-	u64 tx_mult_col;
-	u64 rx_total;
-	u64 tx_total;
-	u64 rx_discards;
-	u64 tx_discards;
-};
-
-struct ksz88xx_stats_raw {
-	u64 rx;
-	u64 rx_hi;
-	u64 rx_undersize;
-	u64 rx_fragments;
-	u64 rx_oversize;
-	u64 rx_jabbers;
-	u64 rx_symbol_err;
-	u64 rx_crc_err;
-	u64 rx_align_err;
-	u64 rx_mac_ctrl;
-	u64 rx_pause;
-	u64 rx_bcast;
-	u64 rx_mcast;
-	u64 rx_ucast;
-	u64 rx_64_or_less;
-	u64 rx_65_127;
-	u64 rx_128_255;
-	u64 rx_256_511;
-	u64 rx_512_1023;
-	u64 rx_1024_1522;
-	u64 tx;
-	u64 tx_hi;
-	u64 tx_late_col;
-	u64 tx_pause;
-	u64 tx_bcast;
-	u64 tx_mcast;
-	u64 tx_ucast;
-	u64 tx_deferred;
-	u64 tx_total_col;
-	u64 tx_exc_col;
-	u64 tx_single_col;
-	u64 tx_mult_col;
-	u64 rx_discards;
-	u64 tx_discards;
-};
-
 static const struct ksz_mib_names ksz88xx_mib_names[] = {
 	{ 0x00, "rx" },
 	{ 0x01, "rx_hi" },
@@ -189,28 +113,6 @@ static const struct ksz_mib_names ksz9477_mib_names[] = {
 	{ 0x83, "tx_discards" },
 };
 
-struct ksz_driver_strength_prop {
-	const char *name;
-	int offset;
-	int value;
-};
-
-enum ksz_driver_strength_type {
-	KSZ_DRIVER_STRENGTH_HI,
-	KSZ_DRIVER_STRENGTH_LO,
-	KSZ_DRIVER_STRENGTH_IO,
-};
-
-/**
- * struct ksz_drive_strength - drive strength mapping
- * @reg_val:	register value
- * @microamp:	microamp value
- */
-struct ksz_drive_strength {
-	u32 reg_val;
-	u32 microamp;
-};
-
 /* ksz9477_drive_strengths - Drive strength mapping for KSZ9477 variants
  *
  * This values are not documented in KSZ9477 variants but confirmed by
@@ -246,15 +148,6 @@ static const struct ksz_drive_strength ksz9477_drive_strengths[] = {
 	{ SW_DRIVE_STRENGTH_28MA, 28000 },
 };
 
-/* ksz88x3_drive_strengths - Drive strength mapping for KSZ8863, KSZ8873, ..
- *			     variants.
- * This values are documented in KSZ8873 and KSZ8863 datasheets.
- */
-static const struct ksz_drive_strength ksz88x3_drive_strengths[] = {
-	{ 0,  8000 },
-	{ KSZ8873_DRIVE_STRENGTH_16MA, 16000 },
-};
-
 /**
  * ksz_phylink_mac_disable_tx_lpi() - Callback to signal LPI support (Dummy)
  * @config: phylink config structure
@@ -2013,7 +1906,6 @@ void ksz_r_mib_stats64(struct ksz_device *dev, int port)
 	struct rtnl_link_stats64 *stats;
 	struct ksz_stats_raw *raw;
 	struct ksz_port_mib *mib;
-	int ret;
 
 	mib = &dev->ports[port].mib;
 	stats = &mib->stats64;
@@ -2055,61 +1947,6 @@ void ksz_r_mib_stats64(struct ksz_device *dev, int port)
 	pstats->rx_pause_frames = raw->rx_pause;
 
 	spin_unlock(&mib->stats64_lock);
-
-	if (dev->info->phy_errata_9477 && !ksz_is_sgmii_port(dev, port)) {
-		ret = ksz9477_errata_monitor(dev, port, raw->tx_late_col);
-		if (ret)
-			dev_err(dev->dev, "Failed to monitor transmission halt\n");
-	}
-}
-
-void ksz88xx_r_mib_stats64(struct ksz_device *dev, int port)
-{
-	struct ethtool_pause_stats *pstats;
-	struct rtnl_link_stats64 *stats;
-	struct ksz88xx_stats_raw *raw;
-	struct ksz_port_mib *mib;
-
-	mib = &dev->ports[port].mib;
-	stats = &mib->stats64;
-	pstats = &mib->pause_stats;
-	raw = (struct ksz88xx_stats_raw *)mib->counters;
-
-	spin_lock(&mib->stats64_lock);
-
-	stats->rx_packets = raw->rx_bcast + raw->rx_mcast + raw->rx_ucast +
-		raw->rx_pause;
-	stats->tx_packets = raw->tx_bcast + raw->tx_mcast + raw->tx_ucast +
-		raw->tx_pause;
-
-	/* HW counters are counting bytes + FCS which is not acceptable
-	 * for rtnl_link_stats64 interface
-	 */
-	stats->rx_bytes = raw->rx + raw->rx_hi - stats->rx_packets * ETH_FCS_LEN;
-	stats->tx_bytes = raw->tx + raw->tx_hi - stats->tx_packets * ETH_FCS_LEN;
-
-	stats->rx_length_errors = raw->rx_undersize + raw->rx_fragments +
-		raw->rx_oversize;
-
-	stats->rx_crc_errors = raw->rx_crc_err;
-	stats->rx_frame_errors = raw->rx_align_err;
-	stats->rx_dropped = raw->rx_discards;
-	stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors +
-		stats->rx_frame_errors  + stats->rx_dropped;
-
-	stats->tx_window_errors = raw->tx_late_col;
-	stats->tx_fifo_errors = raw->tx_discards;
-	stats->tx_aborted_errors = raw->tx_exc_col;
-	stats->tx_errors = stats->tx_window_errors + stats->tx_fifo_errors +
-		stats->tx_aborted_errors;
-
-	stats->multicast = raw->rx_mcast;
-	stats->collisions = raw->tx_total_col;
-
-	pstats->tx_pause_frames = raw->tx_pause;
-	pstats->rx_pause_frames = raw->rx_pause;
-
-	spin_unlock(&mib->stats64_lock);
 }
 
 void ksz_get_stats64(struct dsa_switch *ds, int port,
@@ -2885,28 +2722,6 @@ void ksz_port_bridge_leave(struct dsa_switch *ds, int port,
 	 */
 }
 
-int ksz9477_set_default_prio_queue_mapping(struct ksz_device *dev, int port)
-{
-	u32 queue_map = 0;
-	int ipm;
-
-	for (ipm = 0; ipm < dev->info->num_ipms; ipm++) {
-		int queue;
-
-		/* Traffic Type (TT) is corresponding to the Internal Priority
-		 * Map (IPM) in the switch. Traffic Class (TC) is
-		 * corresponding to the queue in the switch.
-		 */
-		queue = ieee8021q_tt_to_tc(ipm, dev->info->num_tx_queues);
-		if (queue < 0)
-			return queue;
-
-		queue_map |= queue << (ipm * KSZ9477_PORT_TC_MAP_S);
-	}
-
-	return ksz_pwrite32(dev, port, KSZ9477_PORT_MRI_TC_MAP__4, queue_map);
-}
-
 void ksz_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
 {
 	struct ksz_device *dev = ds->priv;
@@ -2984,40 +2799,6 @@ int ksz_port_bridge_flags(struct dsa_switch *ds, int port,
 	return 0;
 }
 
-int ksz_max_mtu(struct dsa_switch *ds, int port)
-{
-	struct ksz_device *dev = ds->priv;
-
-	switch (dev->chip_id) {
-	case KSZ8795_CHIP_ID:
-	case KSZ8794_CHIP_ID:
-	case KSZ8765_CHIP_ID:
-		return KSZ8795_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN;
-	case KSZ8463_CHIP_ID:
-	case KSZ88X3_CHIP_ID:
-	case KSZ8864_CHIP_ID:
-	case KSZ8895_CHIP_ID:
-		return KSZ8863_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN;
-	case KSZ8563_CHIP_ID:
-	case KSZ8567_CHIP_ID:
-	case KSZ9477_CHIP_ID:
-	case KSZ9563_CHIP_ID:
-	case KSZ9567_CHIP_ID:
-	case KSZ9893_CHIP_ID:
-	case KSZ9896_CHIP_ID:
-	case KSZ9897_CHIP_ID:
-	case LAN9370_CHIP_ID:
-	case LAN9371_CHIP_ID:
-	case LAN9372_CHIP_ID:
-	case LAN9373_CHIP_ID:
-	case LAN9374_CHIP_ID:
-	case LAN9646_CHIP_ID:
-		return KSZ9477_MAX_FRAME_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN;
-	}
-
-	return -EOPNOTSUPP;
-}
-
 int ksz_set_mac_eee(struct dsa_switch *ds, int port,
 		    struct ethtool_keee *e)
 {
@@ -3086,39 +2867,6 @@ void ksz_set_xmii(struct ksz_device *dev, int port, phy_interface_t interface)
 	ksz_pwrite8(dev, port, regs[P_XMII_CTRL_1], data8);
 }
 
-phy_interface_t ksz_get_xmii(struct ksz_device *dev, int port, bool gbit)
-{
-	const u8 *bitval = dev->info->xmii_ctrl1;
-	const u16 *regs = dev->info->regs;
-	phy_interface_t interface;
-	u8 data8;
-	u8 val;
-
-	ksz_pread8(dev, port, regs[P_XMII_CTRL_1], &data8);
-
-	val = FIELD_GET(P_MII_SEL_M, data8);
-
-	if (val == bitval[P_MII_SEL]) {
-		if (gbit)
-			interface = PHY_INTERFACE_MODE_GMII;
-		else
-			interface = PHY_INTERFACE_MODE_MII;
-	} else if (val == bitval[P_RMII_SEL]) {
-		interface = PHY_INTERFACE_MODE_RMII;
-	} else {
-		interface = PHY_INTERFACE_MODE_RGMII;
-		if (data8 & P_RGMII_ID_EG_ENABLE)
-			interface = PHY_INTERFACE_MODE_RGMII_TXID;
-		if (data8 & P_RGMII_ID_IG_ENABLE) {
-			interface = PHY_INTERFACE_MODE_RGMII_RXID;
-			if (data8 & P_RGMII_ID_EG_ENABLE)
-				interface = PHY_INTERFACE_MODE_RGMII_ID;
-		}
-	}
-
-	return interface;
-}
-
 bool ksz_phylink_need_config(struct phylink_config *config,
 			     unsigned int mode)
 {
@@ -3154,24 +2902,6 @@ void ksz_phylink_mac_config(struct phylink_config *config,
 		ksz_set_xmii(dev, port, state->interface);
 }
 
-bool ksz_get_gbit(struct ksz_device *dev, int port)
-{
-	const u8 *bitval = dev->info->xmii_ctrl1;
-	const u16 *regs = dev->info->regs;
-	bool gbit = false;
-	u8 data8;
-	bool val;
-
-	ksz_pread8(dev, port, regs[P_XMII_CTRL_1], &data8);
-
-	val = FIELD_GET(P_GMII_1GBIT_M, data8);
-
-	if (val == bitval[P_GMII_1GBIT])
-		gbit = true;
-
-	return gbit;
-}
-
 static int ksz_switch_detect(struct ksz_device *dev)
 {
 	u8 id1, id2, id4;
@@ -3264,7 +2994,7 @@ static int ksz_switch_detect(struct ksz_device *dev)
 			break;
 		default:
 			dev_err(dev->dev,
-				"unsupported switch detected %x)\n", id32);
+				"unsupported switch detected (0x%x)\n", id32);
 			return -ENODEV;
 		}
 	}
@@ -3314,8 +3044,8 @@ static int ksz_setup_tc_mode(struct ksz_device *dev, int port, u8 scheduler,
 			   FIELD_PREP(MTI_SHAPING_M, shaper));
 }
 
-static int ksz_setup_tc_cbs(struct dsa_switch *ds, int port,
-			    struct tc_cbs_qopt_offload *qopt)
+int ksz_setup_tc_cbs(struct dsa_switch *ds, int port,
+		     struct tc_cbs_qopt_offload *qopt)
 {
 	struct ksz_device *dev = ds->priv;
 	int ret;
@@ -3380,8 +3110,8 @@ static int ksz_disable_egress_rate_limit(struct ksz_device *dev, int port)
 	return 0;
 }
 
-static int ksz_ets_band_to_queue(struct tc_ets_qopt_offload_replace_params *p,
-				 int band)
+int ksz_ets_band_to_queue(struct tc_ets_qopt_offload_replace_params *p,
+			  int band)
 {
 	/* Compared to queues, bands prioritize packets differently. In strict
 	 * priority mode, the lowest priority is assigned to Queue 0 while the
@@ -3390,104 +3120,6 @@ static int ksz_ets_band_to_queue(struct tc_ets_qopt_offload_replace_params *p,
 	return p->bands - 1 - band;
 }
 
-static u8 ksz8463_tc_ctrl(int port, int queue)
-{
-	u8 reg;
-
-	reg = 0xC8 + port * 4;
-	reg += ((3 - queue) / 2) * 2;
-	reg++;
-	reg -= (queue & 1);
-	return reg;
-}
-
-/**
- * ksz88x3_tc_ets_add - Configure ETS (Enhanced Transmission Selection)
- *                      for a port on KSZ88x3 switch
- * @dev: Pointer to the KSZ switch device structure
- * @port: Port number to configure
- * @p: Pointer to offload replace parameters describing ETS bands and mapping
- *
- * The KSZ88x3 supports two scheduling modes: Strict Priority and
- * Weighted Fair Queuing (WFQ). Both modes have fixed behavior:
- *   - No configurable queue-to-priority mapping
- *   - No weight adjustment in WFQ mode
- *
- * This function configures the switch to use strict priority mode by
- * clearing the WFQ enable bit for all queues associated with ETS bands.
- * If strict priority is not explicitly requested, the switch will default
- * to WFQ mode.
- *
- * Return: 0 on success, or a negative error code on failure
- */
-static int ksz88x3_tc_ets_add(struct ksz_device *dev, int port,
-			      struct tc_ets_qopt_offload_replace_params *p)
-{
-	int ret, band;
-
-	/* Only strict priority mode is supported for now.
-	 * WFQ is implicitly enabled when strict mode is disabled.
-	 */
-	for (band = 0; band < p->bands; band++) {
-		int queue = ksz_ets_band_to_queue(p, band);
-		u8 reg;
-
-		/* Calculate TXQ Split Control register address for this
-		 * port/queue
-		 */
-		reg = KSZ8873_TXQ_SPLIT_CTRL_REG(port, queue);
-		if (ksz_is_ksz8463(dev))
-			reg = ksz8463_tc_ctrl(port, queue);
-
-		/* Clear WFQ enable bit to select strict priority scheduling */
-		ret = ksz_rmw8(dev, reg, KSZ8873_TXQ_WFQ_ENABLE, 0);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-/**
- * ksz88x3_tc_ets_del - Reset ETS (Enhanced Transmission Selection) config
- *                      for a port on KSZ88x3 switch
- * @dev: Pointer to the KSZ switch device structure
- * @port: Port number to reset
- *
- * The KSZ88x3 supports only fixed scheduling modes: Strict Priority or
- * Weighted Fair Queuing (WFQ), with no reconfiguration of weights or
- * queue mapping. This function resets the port’s scheduling mode to
- * the default, which is WFQ, by enabling the WFQ bit for all queues.
- *
- * Return: 0 on success, or a negative error code on failure
- */
-static int ksz88x3_tc_ets_del(struct ksz_device *dev, int port)
-{
-	int ret, queue;
-
-	/* Iterate over all transmit queues for this port */
-	for (queue = 0; queue < dev->info->num_tx_queues; queue++) {
-		u8 reg;
-
-		/* Calculate TXQ Split Control register address for this
-		 * port/queue
-		 */
-		reg = KSZ8873_TXQ_SPLIT_CTRL_REG(port, queue);
-		if (ksz_is_ksz8463(dev))
-			reg = ksz8463_tc_ctrl(port, queue);
-
-		/* Set WFQ enable bit to revert back to default scheduling
-		 * mode
-		 */
-		ret = ksz_rmw8(dev, reg, KSZ8873_TXQ_WFQ_ENABLE,
-			       KSZ8873_TXQ_WFQ_ENABLE);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
 static int ksz_queue_set_strict(struct ksz_device *dev, int port, int queue)
 {
 	int ret;
@@ -3580,8 +3212,8 @@ static int ksz_tc_ets_del(struct ksz_device *dev, int port)
 	return ksz9477_set_default_prio_queue_mapping(dev, port);
 }
 
-static int ksz_tc_ets_validate(struct ksz_device *dev, int port,
-			       struct tc_ets_qopt_offload_replace_params *p)
+int ksz_tc_ets_validate(struct ksz_device *dev, int port,
+			struct tc_ets_qopt_offload_replace_params *p)
 {
 	int band;
 
@@ -3622,9 +3254,6 @@ static int ksz_tc_setup_qdisc_ets(struct dsa_switch *ds, int port,
 	struct ksz_device *dev = ds->priv;
 	int ret;
 
-	if (is_ksz8(dev) && !(ksz_is_ksz88x3(dev) || ksz_is_ksz8463(dev)))
-		return -EOPNOTSUPP;
-
 	if (qopt->parent != TC_H_ROOT) {
 		dev_err(dev->dev, "Parent should be \"root\"\n");
 		return -EOPNOTSUPP;
@@ -3636,16 +3265,9 @@ static int ksz_tc_setup_qdisc_ets(struct dsa_switch *ds, int port,
 		if (ret)
 			return ret;
 
-		if (ksz_is_ksz88x3(dev) || ksz_is_ksz8463(dev))
-			return ksz88x3_tc_ets_add(dev, port,
-						  &qopt->replace_params);
-		else
-			return ksz_tc_ets_add(dev, port, &qopt->replace_params);
+		return ksz_tc_ets_add(dev, port, &qopt->replace_params);
 	case TC_ETS_DESTROY:
-		if (ksz_is_ksz88x3(dev) || ksz_is_ksz8463(dev))
-			return ksz88x3_tc_ets_del(dev, port);
-		else
-			return ksz_tc_ets_del(dev, port);
+		return ksz_tc_ets_del(dev, port);
 	case TC_ETS_STATS:
 	case TC_ETS_GRAFT:
 		return -EOPNOTSUPP;
@@ -3705,6 +3327,34 @@ int ksz_handle_wake_reason(struct ksz_device *dev, int port)
 }
 
 /**
+ * ksz_is_port_mac_global_usable - Check if the MAC address on a given port
+ *                                 can be used as a global address.
+ * @ds: Pointer to the DSA switch structure.
+ * @port: The port number on which the MAC address is to be checked.
+ *
+ * This function examines the MAC address set on the specified port and
+ * determines if it can be used as a global address for the switch.
+ *
+ * Return: true if the port's MAC address can be used as a global address, false
+ * otherwise.
+ */
+static bool ksz_is_port_mac_global_usable(struct dsa_switch *ds, int port)
+{
+	struct net_device *user = dsa_to_port(ds, port)->user;
+	const unsigned char *addr = user->dev_addr;
+	struct ksz_switch_macaddr *switch_macaddr;
+	struct ksz_device *dev = ds->priv;
+
+	ASSERT_RTNL();
+
+	switch_macaddr = dev->switch_macaddr;
+	if (switch_macaddr && !ether_addr_equal(switch_macaddr->addr, addr))
+		return false;
+
+	return true;
+}
+
+/**
  * ksz_get_wol - Get Wake-on-LAN settings for a specified port.
  * @ds: The dsa_switch structure.
  * @port: The port number.
@@ -3898,34 +3548,6 @@ int ksz_port_set_mac_address(struct dsa_switch *ds, int port,
 }
 
 /**
- * ksz_is_port_mac_global_usable - Check if the MAC address on a given port
- *                                 can be used as a global address.
- * @ds: Pointer to the DSA switch structure.
- * @port: The port number on which the MAC address is to be checked.
- *
- * This function examines the MAC address set on the specified port and
- * determines if it can be used as a global address for the switch.
- *
- * Return: true if the port's MAC address can be used as a global address, false
- * otherwise.
- */
-bool ksz_is_port_mac_global_usable(struct dsa_switch *ds, int port)
-{
-	struct net_device *user = dsa_to_port(ds, port)->user;
-	const unsigned char *addr = user->dev_addr;
-	struct ksz_switch_macaddr *switch_macaddr;
-	struct ksz_device *dev = ds->priv;
-
-	ASSERT_RTNL();
-
-	switch_macaddr = dev->switch_macaddr;
-	if (switch_macaddr && !ether_addr_equal(switch_macaddr->addr, addr))
-		return false;
-
-	return true;
-}
-
-/**
  * ksz_switch_macaddr_get - Program the switch's MAC address register.
  * @ds: DSA switch instance.
  * @port: Port number.
@@ -4132,8 +3754,8 @@ static void ksz_parse_rgmii_delay(struct ksz_device *dev, int port_num,
  * Returns: If found, the corresponding register value for that drive strength
  * is returned. Otherwise, -EINVAL is returned indicating an invalid value.
  */
-static int ksz_drive_strength_to_reg(const struct ksz_drive_strength *array,
-				     size_t array_size, int microamp)
+int ksz_drive_strength_to_reg(const struct ksz_drive_strength *array,
+			      size_t array_size, int microamp)
 {
 	int i;
 
@@ -4156,9 +3778,9 @@ static int ksz_drive_strength_to_reg(const struct ksz_drive_strength *array,
  * is detected. It lists out all the supported drive strength values for
  * reference in the error message.
  */
-static void ksz_drive_strength_error(struct ksz_device *dev,
-				     const struct ksz_drive_strength *array,
-				     size_t array_size, int microamp)
+void ksz_drive_strength_error(struct ksz_device *dev,
+			      const struct ksz_drive_strength *array,
+			      size_t array_size, int microamp)
 {
 	char supported_values[100];
 	size_t remaining_size;
@@ -4185,8 +3807,8 @@ static void ksz_drive_strength_error(struct ksz_device *dev,
 }
 
 /**
- * ksz9477_drive_strength_write() - Set the drive strength for specific KSZ9477
- *				    chip variants.
+ * ksz_drive_strength_write() - Set the drive strength for specific KSZ9477
+ *				and the KSZ87xx chip variants.
  * @dev:       ksz device
  * @props:     Array of drive strength properties to be applied
  * @num_props: Number of properties in the array
@@ -4197,9 +3819,9 @@ static void ksz_drive_strength_error(struct ksz_device *dev,
  *
  * Return: 0 on successful configuration, a negative error code on failure.
  */
-static int ksz9477_drive_strength_write(struct ksz_device *dev,
-					struct ksz_driver_strength_prop *props,
-					int num_props)
+int ksz_drive_strength_write(struct ksz_device *dev,
+			     struct ksz_driver_strength_prop *props,
+			     int num_props)
 {
 	size_t array_size = ARRAY_SIZE(ksz9477_drive_strengths);
 	int i, ret, reg;
@@ -4236,130 +3858,6 @@ static int ksz9477_drive_strength_write(struct ksz_device *dev,
 	return ksz_rmw8(dev, reg, mask, val);
 }
 
-/**
- * ksz88x3_drive_strength_write() - Set the drive strength configuration for
- *				    KSZ8863 compatible chip variants.
- * @dev:       ksz device
- * @props:     Array of drive strength properties to be set
- * @num_props: Number of properties in the array
- *
- * This function applies the specified drive strength settings to KSZ88X3 chip
- * variants (KSZ8873, KSZ8863).
- * It ensures the configurations align with what the chip variant supports and
- * warns or errors out on unsupported settings.
- *
- * Return: 0 on success, error code otherwise
- */
-static int ksz88x3_drive_strength_write(struct ksz_device *dev,
-					struct ksz_driver_strength_prop *props,
-					int num_props)
-{
-	size_t array_size = ARRAY_SIZE(ksz88x3_drive_strengths);
-	int microamp;
-	int i, ret;
-
-	for (i = 0; i < num_props; i++) {
-		if (props[i].value == -1 || i == KSZ_DRIVER_STRENGTH_IO)
-			continue;
-
-		dev_warn(dev->dev, "%s is not supported by this chip variant\n",
-			 props[i].name);
-	}
-
-	microamp = props[KSZ_DRIVER_STRENGTH_IO].value;
-	ret = ksz_drive_strength_to_reg(ksz88x3_drive_strengths, array_size,
-					microamp);
-	if (ret < 0) {
-		ksz_drive_strength_error(dev, ksz88x3_drive_strengths,
-					 array_size, microamp);
-		return ret;
-	}
-
-	return ksz_rmw8(dev, KSZ8873_REG_GLOBAL_CTRL_12,
-			KSZ8873_DRIVE_STRENGTH_16MA, ret);
-}
-
-/**
- * ksz_parse_drive_strength() - Extract and apply drive strength configurations
- *				from device tree properties.
- * @dev:	ksz device
- *
- * This function reads the specified drive strength properties from the
- * device tree, validates against the supported chip variants, and sets
- * them accordingly. An error should be critical here, as the drive strength
- * settings are crucial for EMI compliance.
- *
- * Return: 0 on success, error code otherwise
- */
-int ksz_parse_drive_strength(struct ksz_device *dev)
-{
-	struct ksz_driver_strength_prop of_props[] = {
-		[KSZ_DRIVER_STRENGTH_HI] = {
-			.name = "microchip,hi-drive-strength-microamp",
-			.offset = SW_HI_SPEED_DRIVE_STRENGTH_S,
-			.value = -1,
-		},
-		[KSZ_DRIVER_STRENGTH_LO] = {
-			.name = "microchip,lo-drive-strength-microamp",
-			.offset = SW_LO_SPEED_DRIVE_STRENGTH_S,
-			.value = -1,
-		},
-		[KSZ_DRIVER_STRENGTH_IO] = {
-			.name = "microchip,io-drive-strength-microamp",
-			.offset = 0, /* don't care */
-			.value = -1,
-		},
-	};
-	struct device_node *np = dev->dev->of_node;
-	bool have_any_prop = false;
-	int i, ret;
-
-	for (i = 0; i < ARRAY_SIZE(of_props); i++) {
-		ret = of_property_read_u32(np, of_props[i].name,
-					   &of_props[i].value);
-		if (ret && ret != -EINVAL)
-			dev_warn(dev->dev, "Failed to read %s\n",
-				 of_props[i].name);
-		if (ret)
-			continue;
-
-		have_any_prop = true;
-	}
-
-	if (!have_any_prop)
-		return 0;
-
-	switch (dev->chip_id) {
-	case KSZ88X3_CHIP_ID:
-		return ksz88x3_drive_strength_write(dev, of_props,
-						    ARRAY_SIZE(of_props));
-	case KSZ8795_CHIP_ID:
-	case KSZ8794_CHIP_ID:
-	case KSZ8765_CHIP_ID:
-	case KSZ8563_CHIP_ID:
-	case KSZ8567_CHIP_ID:
-	case KSZ9477_CHIP_ID:
-	case KSZ9563_CHIP_ID:
-	case KSZ9567_CHIP_ID:
-	case KSZ9893_CHIP_ID:
-	case KSZ9896_CHIP_ID:
-	case KSZ9897_CHIP_ID:
-	case LAN9646_CHIP_ID:
-		return ksz9477_drive_strength_write(dev, of_props,
-						    ARRAY_SIZE(of_props));
-	default:
-		for (i = 0; i < ARRAY_SIZE(of_props); i++) {
-			if (of_props[i].value == -1)
-				continue;
-
-			dev_warn(dev->dev, "%s is not supported by this chip variant\n",
-				 of_props[i].name);
-		}
-	}
-
-	return 0;
-}
-
 static int ksz8463_configure_straps_spi(struct ksz_device *dev)
 {
 	struct pinctrl *pinctrl;
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index b4a5673ba365..acaf70e6f393 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -14,6 +14,7 @@
 #include <linux/phy.h>
 #include <linux/regmap.h>
 #include <net/dsa.h>
+#include <net/pkt_cls.h>
 #include <linux/irq.h>
 #include <linux/platform_data/microchip-ksz.h>
 
@@ -40,6 +41,45 @@ struct vlan_table {
 	u32 table[3];
 };
 
+struct ksz_stats_raw {
+	u64 rx_hi;
+	u64 rx_undersize;
+	u64 rx_fragments;
+	u64 rx_oversize;
+	u64 rx_jabbers;
+	u64 rx_symbol_err;
+	u64 rx_crc_err;
+	u64 rx_align_err;
+	u64 rx_mac_ctrl;
+	u64 rx_pause;
+	u64 rx_bcast;
+	u64 rx_mcast;
+	u64 rx_ucast;
+	u64 rx_64_or_less;
+	u64 rx_65_127;
+	u64 rx_128_255;
+	u64 rx_256_511;
+	u64 rx_512_1023;
+	u64 rx_1024_1522;
+	u64 rx_1523_2000;
+	u64 rx_2001;
+	u64 tx_hi;
+	u64 tx_late_col;
+	u64 tx_pause;
+	u64 tx_bcast;
+	u64 tx_mcast;
+	u64 tx_ucast;
+	u64 tx_deferred;
+	u64 tx_total_col;
+	u64 tx_exc_col;
+	u64 tx_single_col;
+	u64 tx_mult_col;
+	u64 rx_total;
+	u64 tx_total;
+	u64 rx_discards;
+	u64 tx_discards;
+};
+
 struct ksz_port_mib {
 	struct mutex cnt_mutex;		/* structure access */
 	u8 cnt_ptr;
@@ -393,12 +433,8 @@ int ksz_switch_resume(struct device *dev);
 void ksz_teardown(struct dsa_switch *ds);
 
 void ksz_init_mib_timer(struct ksz_device *dev);
-bool ksz_is_port_mac_global_usable(struct dsa_switch *ds, int port);
 void ksz_r_mib_stats64(struct ksz_device *dev, int port);
-void ksz88xx_r_mib_stats64(struct ksz_device *dev, int port);
 void ksz_port_stp_state_set(struct dsa_switch *ds, int port, u8 state);
-bool ksz_get_gbit(struct ksz_device *dev, int port);
-phy_interface_t ksz_get_xmii(struct ksz_device *dev, int port, bool gbit);
 extern const struct ksz_chip_data ksz_switch_chips[];
 int ksz_switch_macaddr_get(struct dsa_switch *ds, int port,
 			   struct netlink_ext_ack *extack);
@@ -443,11 +479,15 @@ void ksz_phylink_mac_link_down(struct phylink_config *config,
 			       unsigned int mode,
 			       phy_interface_t interface);
 
-int ksz_max_mtu(struct dsa_switch *ds, int port);
-
 int ksz_set_mac_eee(struct dsa_switch *ds, int port,
 		    struct ethtool_keee *e);
 
+int ksz_ets_band_to_queue(struct tc_ets_qopt_offload_replace_params *p,
+			  int band);
+int ksz_setup_tc_cbs(struct dsa_switch *ds, int port,
+		     struct tc_cbs_qopt_offload *qopt);
+int ksz_tc_ets_validate(struct ksz_device *dev, int port,
+			struct tc_ets_qopt_offload_replace_params *p);
 int ksz_setup_tc(struct dsa_switch *ds, int port,
 		 enum tc_setup_type type, void *type_data);
 
@@ -471,8 +511,37 @@ int ksz_mdio_register(struct ksz_device *dev);
 int ksz_pirq_setup(struct ksz_device *dev, u8 p);
 int ksz_girq_setup(struct ksz_device *dev);
 void ksz_irq_free(struct ksz_irq *kirq);
-int ksz_parse_drive_strength(struct ksz_device *dev);
-int ksz9477_set_default_prio_queue_mapping(struct ksz_device *dev, int port);
+
+struct ksz_driver_strength_prop {
+	const char *name;
+	int offset;
+	int value;
+};
+
+enum ksz_driver_strength_type {
+	KSZ_DRIVER_STRENGTH_HI,
+	KSZ_DRIVER_STRENGTH_LO,
+	KSZ_DRIVER_STRENGTH_IO,
+};
+
+/**
+ * struct ksz_drive_strength - drive strength mapping
+ * @reg_val:	register value
+ * @microamp:	microamp value
+ */
+struct ksz_drive_strength {
+	u32 reg_val;
+	u32 microamp;
+};
+
+void ksz_drive_strength_error(struct ksz_device *dev,
+			      const struct ksz_drive_strength *array,
+			      size_t array_size, int microamp);
+int ksz_drive_strength_to_reg(const struct ksz_drive_strength *array,
+			      size_t array_size, int microamp);
+int ksz_drive_strength_write(struct ksz_device *dev,
+			     struct ksz_driver_strength_prop *props,
+			     int num_props);
 
 /* Common register access functions */
 static inline struct regmap *ksz_regmap_8(struct ksz_device *dev)
diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c
index 8b98039320ad..5bdf829a6e38 100644
--- a/drivers/net/dsa/microchip/ksz_ptp.c
+++ b/drivers/net/dsa/microchip/ksz_ptp.c
@@ -1101,8 +1101,10 @@ static void ksz_ptp_msg_irq_free(struct ksz_port *port, u8 n)
 
 static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n)
 {
-	u16 ts_reg[] = {REG_PTP_PORT_PDRESP_TS, REG_PTP_PORT_XDELAY_TS,
-			REG_PTP_PORT_SYNC_TS};
+	static const u16 ts_reg[] = {
+		REG_PTP_PORT_PDRESP_TS, REG_PTP_PORT_XDELAY_TS,
+		REG_PTP_PORT_SYNC_TS
+	};
 	static const char * const name[] = {"pdresp-msg", "xdreq-msg",
 					    "sync-msg"};
 	const struct ksz_dev_ops *ops = port->ksz_dev->dev_ops;
diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c
index 8eb5337b0c10..86ce3a86705f 100644
--- a/drivers/net/dsa/microchip/lan937x_main.c
+++ b/drivers/net/dsa/microchip/lan937x_main.c
@@ -787,10 +787,6 @@ static int lan937x_setup(struct dsa_switch *ds)
 		return ret;
 	}
 
-	ret = ksz_parse_drive_strength(dev);
-	if (ret)
-		return ret;
-
 	/* set broadcast storm protection 10% rate */
 	storm_mask = BROADCAST_STORM_RATE;
 	storm_rate = (BROADCAST_STORM_VALUE * BROADCAST_STORM_PROT_RATE) / 100;
@@ -983,7 +979,7 @@ const struct dsa_switch_ops lan937x_switch_ops = {
 	.get_stats64		= ksz_get_stats64,
 	.get_pause_stats	= ksz_get_pause_stats,
 	.port_change_mtu	= lan937x_change_mtu,
-	.port_max_mtu		= ksz_max_mtu,
+	.port_max_mtu		= ksz9477_max_mtu,
 	.suspend		= ksz_suspend,
 	.resume			= ksz_resume,
 	.get_ts_info		= ksz_get_ts_info,
diff --git a/drivers/net/dsa/mt7530-mmio.c b/drivers/net/dsa/mt7530-mmio.c
index 119fdd863d91..fd68b1cd0630 100644
--- a/drivers/net/dsa/mt7530-mmio.c
+++ b/drivers/net/dsa/mt7530-mmio.c
@@ -12,6 +12,7 @@
 static const struct of_device_id mt7988_of_match[] = {
 	{ .compatible = "airoha,an7583-switch", .data = &mt753x_table[ID_AN7583], },
 	{ .compatible = "airoha,en7581-switch", .data = &mt753x_table[ID_EN7581], },
+	{ .compatible = "econet,en7528-switch", .data = &mt753x_table[ID_EN7528], },
 	{ .compatible = "mediatek,mt7988-switch", .data = &mt753x_table[ID_MT7988], },
 	{ /* sentinel */ },
 };
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 3c2a3029b10c..6c8ed00ee9e7 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2912,6 +2912,30 @@ static void en7581_mac_port_get_caps(struct dsa_switch *ds, int port,
 	}
 }
 
+static void en7528_mac_port_get_caps(struct dsa_switch *ds, int port,
+				     struct phylink_config *config)
+{
+	switch (port) {
+	/* Ports which are connected to switch PHYs. There is no MII pinout. */
+	case 1 ... 4:
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  config->supported_interfaces);
+
+		config->mac_capabilities |= MAC_10 | MAC_100 | MAC_1000FD;
+		break;
+
+	/* Port 6 is connected to SoC's GMAC at 1000 Mbps full duplex. There
+	 * is no MII pinout.
+	 */
+	case 6:
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  config->supported_interfaces);
+
+		config->mac_capabilities |= MAC_1000FD;
+		break;
+	}
+}
+
 static void
 mt7530_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
 		  phy_interface_t interface)
@@ -3101,17 +3125,24 @@ static void mt753x_phylink_get_caps(struct dsa_switch *ds, int port,
 				    struct phylink_config *config)
 {
 	struct mt7530_priv *priv = ds->priv;
-	u32 eeecr;
 
 	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE;
 
-	config->lpi_capabilities = MAC_100FD | MAC_1000FD | MAC_2500FD;
-
-	eeecr = mt7530_read(priv, MT753X_PMEEECR_P(port));
-	/* tx_lpi_timer should be in microseconds. The time units for
-	 * LPI threshold are unspecified.
+	/* The EN7528 GPHYs report EEE capability, but negotiating EEE with
+	 * common link partners (e.g. Realtek GbE NICs) results in an unstable
+	 * link with dropped frames. Leave the LPI capabilities empty so that
+	 * phylink disables EEE on these PHYs and refuses to enable it from
+	 * userspace.
 	 */
-	config->lpi_timer_default = FIELD_GET(LPI_THRESH_MASK, eeecr);
+	if (priv->id != ID_EN7528) {
+		u32 eeecr = mt7530_read(priv, MT753X_PMEEECR_P(port));
+
+		config->lpi_capabilities = MAC_100FD | MAC_1000FD | MAC_2500FD;
+		/* tx_lpi_timer should be in microseconds. The time units for
+		 * LPI threshold are unspecified.
+		 */
+		config->lpi_timer_default = FIELD_GET(LPI_THRESH_MASK, eeecr);
+	}
 
 	priv->info->mac_port_get_caps(ds, port, config);
 }
@@ -3254,7 +3285,8 @@ mt753x_conduit_state_change(struct dsa_switch *ds,
 	 * forwarded to the numerically smallest CPU port whose conduit
 	 * interface is up.
 	 */
-	if (priv->id != ID_MT7530 && priv->id != ID_MT7621)
+	if (priv->id != ID_MT7530 && priv->id != ID_MT7621 &&
+	    priv->id != ID_EN7528)
 		return;
 
 	mask = BIT(cpu_dp->index);
@@ -3459,6 +3491,16 @@ const struct mt753x_info mt753x_table[] = {
 		.phy_write_c45 = mt7531_ind_c45_phy_write,
 		.mac_port_get_caps = en7581_mac_port_get_caps,
 	},
+	[ID_EN7528] = {
+		.id = ID_EN7528,
+		.pcs_ops = &mt7530_pcs_ops,
+		.sw_setup = mt7988_setup,
+		.phy_read_c22 = mt7531_ind_c22_phy_read,
+		.phy_write_c22 = mt7531_ind_c22_phy_write,
+		.phy_read_c45 = mt7531_ind_c45_phy_read,
+		.phy_write_c45 = mt7531_ind_c45_phy_write,
+		.mac_port_get_caps = en7528_mac_port_get_caps,
+	},
 };
 EXPORT_SYMBOL_GPL(mt753x_table);
 
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index dd33b0df3419..5f1e841f42c0 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -21,6 +21,7 @@ enum mt753x_id {
 	ID_MT7988 = 3,
 	ID_EN7581 = 4,
 	ID_AN7583 = 5,
+	ID_EN7528 = 6,
 };
 
 #define	NUM_TRGMII_CTRL			5
diff --git a/drivers/net/dsa/qca/qca8k-leds.c b/drivers/net/dsa/qca/qca8k-leds.c
index ef496e345a4e..0ada28377f46 100644
--- a/drivers/net/dsa/qca/qca8k-leds.c
+++ b/drivers/net/dsa/qca/qca8k-leds.c
@@ -457,6 +457,9 @@ qca8k_setup_led_ctrl(struct qca8k_priv *priv)
 	int ret;
 
 	ports = device_get_named_child_node(priv->dev, "ports");
+	if (!ports)
+		ports = device_get_named_child_node(priv->dev, "ethernet-ports");
+
 	if (!ports) {
 		dev_info(priv->dev, "No ports node specified in device tree!");
 		return 0;
diff --git a/drivers/net/dsa/realtek/rtl8365mb_main.c b/drivers/net/dsa/realtek/rtl8365mb_main.c
index 5ac091bf93c9..d1ba0cc9426f 100644
--- a/drivers/net/dsa/realtek/rtl8365mb_main.c
+++ b/drivers/net/dsa/realtek/rtl8365mb_main.c
@@ -40,7 +40,8 @@
  * driver has only been tested with a fixed-link, but in principle it should not
  * matter.
  *
- * NOTE: Currently, only the RGMII interface is implemented in this driver.
+ * NOTE: Currently, only the RGMII, SGMII and HSGMII interfaces are implemented
+ * in this driver.
  *
  * The interrupt line is asserted on link UP/DOWN events. The driver creates a
  * custom irqchip to handle this interrupt and demultiplex the events by reading
@@ -94,11 +95,13 @@
 #include <linux/bitops.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
+#include <linux/mii.h>
 #include <linux/mutex.h>
 #include <linux/of_irq.h>
 #include <linux/regmap.h>
 #include <linux/if_bridge.h>
 #include <linux/if_vlan.h>
+#include <linux/phylink.h>
 
 #include "realtek.h"
 #include "realtek-smi.h"
@@ -129,6 +132,7 @@
 
 /* Chip reset register */
 #define RTL8365MB_CHIP_RESET_REG	0x1322
+#define RTL8365MB_CHIP_RESET_DW8051_MASK	0x0010
 #define RTL8365MB_CHIP_RESET_SW_MASK	0x0002
 #define RTL8365MB_CHIP_RESET_HW_MASK	0x0001
 
@@ -238,6 +242,88 @@
 #define   RTL8365MB_EXT_RGMXF_RXDELAY_MASK	0x0007
 #define   RTL8365MB_EXT_RGMXF_TXDELAY_MASK	0x0008
 
+/* External interface line rate bypass register - one bit per external
+ * interface, indexed by the external port number with port 5 (the first
+ * external port) as the base. Other RTL8367 families index this register
+ * differently (e.g. the RTL8367R uses (id + 1) % 2), so this mapping only
+ * holds for the RTL8367C-style parts this driver supports.
+ */
+#define RTL8365MB_BYPASS_LINE_RATE_REG		0x03F7
+#define RTL8365MB_BYPASS_LINE_RATE_MASK(_port)	BIT((_port) - 5)
+
+/* Port 6 ingress and egress rate limiter registers. Each limit is a 19-bit
+ * value in units of 8 Kbps, split across a 16-bit LSB register (CTRL0) and a
+ * 3-bit MSB field (CTRL1). The chip resets them to 0x1FFFF; see
+ * rtl8365mb_sds_raise_rate_limits().
+ */
+#define RTL8365MB_INGRESSBW_PORT6_RATE_CTRL0_REG	0x00CF
+#define RTL8365MB_INGRESSBW_PORT6_RATE_CTRL1_REG	0x00D0
+#define   RTL8365MB_INGRESSBW_PORT6_RATE_CTRL1_MASK	0x0007
+#define RTL8365MB_PORT6_EGRESSBW_CTRL0_REG		0x0398
+#define RTL8365MB_PORT6_EGRESSBW_CTRL1_REG		0x0399
+#define   RTL8365MB_PORT6_EGRESSBW_CTRL1_MASK		0x0007
+
+/* SerDes indirect access registers */
+#define RTL8365MB_SDS_INDACS_CMD_REG		0x6600
+#define   RTL8365MB_SDS_INDACS_CMD_BUSY_MASK	0x0100
+#define   RTL8365MB_SDS_INDACS_CMD_RUN_MASK	0x0080
+#define   RTL8365MB_SDS_INDACS_CMD_WR_MASK	0x0040
+#define RTL8365MB_SDS_INDACS_ADR_REG		0x6601
+#define RTL8365MB_SDS_INDACS_DATA_REG		0x6602
+
+/* SerDes miscellaneous configuration register */
+#define RTL8365MB_SDS_MISC_REG				0x1D11
+#define   RTL8365MB_SDS_MISC_SGMII_RXFC_MASK		0x4000
+#define   RTL8365MB_SDS_MISC_SGMII_TXFC_MASK		0x2000
+#define   RTL8365MB_SDS_MISC_MAC8_SEL_HSGMII_MASK	0x0800
+#define   RTL8365MB_SDS_MISC_SGMII_FDUP_MASK		0x0400
+#define   RTL8365MB_SDS_MISC_SGMII_LINK_MASK		0x0200
+#define   RTL8365MB_SDS_MISC_SGMII_SPD_MASK		0x0180
+#define   RTL8365MB_SDS_MISC_MAC8_SEL_SGMII_MASK	0x0040
+
+/* SerDes internal registers, accessed via the SDS_INDACS registers. The BMCR
+ * data path reset holds BMCR_ANENABLE | BMCR_ISOLATE while toggling the
+ * vendor-specific low bits from phase 1 to phase 2, which triggers a data path
+ * reset and PLL resync.
+ */
+#define RTL8365MB_SDS_REG_BMCR			0x0000
+#define   RTL8365MB_SDS_BMCR_DPRST_PHASE1	(BMCR_ANENABLE | BMCR_ISOLATE | 0x1)
+#define   RTL8365MB_SDS_BMCR_DPRST_PHASE2	(BMCR_ANENABLE | BMCR_ISOLATE | 0x3)
+#define RTL8365MB_SDS_REG_NWAY			0x0002
+#define   RTL8365MB_SDS_NWAY_EN_MASK		0x0200
+#define   RTL8365MB_SDS_NWAY_RESTART_MASK	0x0100
+#define RTL8365MB_SDS_REG_RESET			0x0003
+#define   RTL8365MB_SDS_RESET_DEASSERT		0x7106
+#define RTL8365MB_SDS_REG_LINK_STATUS		0x003d
+#define   RTL8365MB_SDS_LINK_STATUS_LINK_MASK	0x0010
+
+/* The embedded SerDes can only be muxed to external interface 1 (MAC8),
+ * which is port 6.
+ */
+#define RTL8365MB_SDS_EXT_INTERFACE_ID		1
+#define RTL8365MB_SDS_EXT_INTERFACE_PORT	6
+
+/* Line rate bypass bit for the SerDes external interface */
+#define RTL8365MB_SDS_BYPASS_LINE_RATE_MASK \
+	RTL8365MB_BYPASS_LINE_RATE_MASK(RTL8365MB_SDS_EXT_INTERFACE_PORT)
+
+/* SerDes tuning parameter variant selector. The vendor driver picks between
+ * two sets of SerDes tuning parameters based on this chip option. Reading it
+ * requires first arming the read by writing a magic key to the arm register,
+ * then disarming it afterwards.
+ */
+#define RTL8365MB_SDS_OPTION_ARM_REG		0x13C0
+#define   RTL8365MB_SDS_OPTION_ARM_KEY		0x0249
+#define RTL8365MB_SDS_OPTION_REG		0x13C1
+
+/* Embedded DW8051 microcontroller control registers. The microcontroller
+ * can run firmware to manage the SerDes link, but this driver keeps it in
+ * reset and disabled: phylink already performs the link management that
+ * the firmware would otherwise do.
+ */
+#define RTL8365MB_MISC_CFG0_REG			0x130C
+#define   RTL8365MB_MISC_CFG0_DW8051_EN_MASK	0x0020
+
 /* External interface port speed values - used in DIGITAL_INTERFACE_FORCE */
 #define RTL8365MB_PORT_SPEED_10M	0
 #define RTL8365MB_PORT_SPEED_100M	1
@@ -551,6 +637,30 @@ static const struct rtl8365mb_jam_tbl_entry rtl8365mb_init_jam_common[] = {
 	{ 0x1D32, 0x0002 },
 };
 
+/* SGMII SerDes tuning parameters, lifted from the vendor driver sources. The
+ * vendor driver keeps two variants of this table and selects between them
+ * based on the chip option register; these are the values for a non-zero
+ * option, which is what RTL8367S parts seen so far report. See
+ * rtl8365mb_sds_probe_option().
+ */
+static const struct rtl8365mb_jam_tbl_entry rtl8365mb_sds_jam_sgmii[] = {
+	{ 0x0480, 0x04D7 }, { 0x0481, 0xF994 }, { 0x0482, 0x2420 },
+	{ 0x0483, 0x6960 }, { 0x0484, 0x9728 }, { 0x0423, 0x9D85 },
+	{ 0x0424, 0xD810 }, { 0x002E, 0x83F2 },
+};
+
+/* HSGMII SerDes tuning parameters, lifted from the vendor driver sources. As
+ * with the SGMII table, the vendor driver keeps several variants and selects
+ * one based on the chip option register; these are the values for a non-zero
+ * option, which is what RTL8367S parts seen so far report. See
+ * rtl8365mb_sds_probe_option().
+ */
+static const struct rtl8365mb_jam_tbl_entry rtl8365mb_sds_jam_hsgmii[] = {
+	{ 0x0500, 0x82F0 }, { 0x0501, 0xF195 }, { 0x0502, 0x31A2 },
+	{ 0x0503, 0x7960 }, { 0x0504, 0x9728 }, { 0x0423, 0x9D85 },
+	{ 0x0424, 0xD810 }, { 0x0001, 0x0F80 }, { 0x002E, 0x83F2 },
+};
+
 enum rtl8365mb_phy_interface_mode {
 	RTL8365MB_PHY_INTERFACE_MODE_INVAL = 0,
 	RTL8365MB_PHY_INTERFACE_MODE_INTERNAL = BIT(0),
@@ -730,6 +840,9 @@ struct rtl8365mb_port {
  * @cpu: CPU tagging and CPU port configuration for this chip
  * @mib_lock: prevent concurrent reads of MIB counters
  * @ports: per-port data
+ * @pcs: PCS for the SerDes external interface
+ * @sds_supported: SerDes tuning parameters match the chip option, so the
+ *                 SerDes interface modes can be advertised
  *
  * Private data for this driver.
  */
@@ -740,8 +853,12 @@ struct rtl8365mb {
 	struct rtl8365mb_cpu cpu;
 	struct mutex mib_lock;
 	struct rtl8365mb_port ports[RTL8365MB_MAX_NUM_PORTS];
+	struct phylink_pcs pcs;
+	bool sds_supported;
 };
 
+#define pcs_to_rtl8365mb(_pcs) container_of((_pcs), struct rtl8365mb, pcs)
+
 static int rtl8365mb_phy_poll_busy(struct realtek_priv *priv)
 {
 	u32 val;
@@ -1042,6 +1159,391 @@ static int rtl8365mb_ext_config_rgmii(struct realtek_priv *priv, int port,
 	return 0;
 }
 
+static int rtl8365mb_sds_write(struct realtek_priv *priv, u16 addr, u16 data)
+{
+	int ret;
+
+	ret = regmap_write(priv->map, RTL8365MB_SDS_INDACS_DATA_REG, data);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(priv->map, RTL8365MB_SDS_INDACS_ADR_REG, addr);
+	if (ret)
+		return ret;
+
+	/* The SerDes indirect access engine completes the command within the
+	 * register write transaction, so there is no need to wait or poll for
+	 * completion before the next access, matching the vendor driver.
+	 */
+	return regmap_write(priv->map, RTL8365MB_SDS_INDACS_CMD_REG,
+			    RTL8365MB_SDS_INDACS_CMD_RUN_MASK |
+			    RTL8365MB_SDS_INDACS_CMD_WR_MASK);
+}
+
+static int rtl8365mb_sds_read(struct realtek_priv *priv, u16 addr, u16 *data)
+{
+	u32 val;
+	int ret;
+
+	ret = regmap_write(priv->map, RTL8365MB_SDS_INDACS_ADR_REG, addr);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(priv->map, RTL8365MB_SDS_INDACS_CMD_REG,
+			   RTL8365MB_SDS_INDACS_CMD_RUN_MASK);
+	if (ret)
+		return ret;
+
+	/* Wait for the indirect read to complete: the engine clears the BUSY
+	 * bit once the data register holds the result.
+	 */
+	ret = regmap_read_poll_timeout(priv->map, RTL8365MB_SDS_INDACS_CMD_REG,
+				       val,
+				       !(val & RTL8365MB_SDS_INDACS_CMD_BUSY_MASK),
+				       10, 1000);
+	if (ret)
+		return ret;
+
+	ret = regmap_read(priv->map, RTL8365MB_SDS_INDACS_DATA_REG, &val);
+	if (ret)
+		return ret;
+
+	*data = val;
+
+	return 0;
+}
+
+/* The vendor driver selects between two sets of SerDes tuning parameters based
+ * on the chip option register. Only the variant for a non-zero option has been
+ * tested on real hardware - the RTL8367S parts seen so far all report 1. The
+ * variant for option 0 uses different tuning values that cannot be verified,
+ * so probe the option once at setup and only advertise the SerDes interface
+ * modes when the tuning parameters are known to match, so that an unsupported
+ * variant fails at phylink validation time rather than when configuring the
+ * link.
+ */
+static int rtl8365mb_sds_probe_option(struct realtek_priv *priv)
+{
+	struct rtl8365mb *mb = priv->chip_data;
+	const struct rtl8365mb_extint *extint;
+	u32 option;
+	int ret;
+	int i;
+
+	/* Nothing to probe if no external interface is wired to the SerDes */
+	for (i = 0; i < RTL8365MB_MAX_NUM_EXTINTS; i++) {
+		extint = &mb->chip_info->extints[i];
+
+		if (extint->supported_interfaces &
+		    (RTL8365MB_PHY_INTERFACE_MODE_SGMII |
+		     RTL8365MB_PHY_INTERFACE_MODE_HSGMII))
+			break;
+	}
+	if (i == RTL8365MB_MAX_NUM_EXTINTS)
+		return 0;
+
+	ret = regmap_write(priv->map, RTL8365MB_SDS_OPTION_ARM_REG,
+			   RTL8365MB_SDS_OPTION_ARM_KEY);
+	if (ret)
+		return ret;
+
+	ret = regmap_read(priv->map, RTL8365MB_SDS_OPTION_REG, &option);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(priv->map, RTL8365MB_SDS_OPTION_ARM_REG, 0);
+	if (ret)
+		return ret;
+
+	if (option == 0) {
+		dev_warn(priv->dev,
+			 "unsupported SerDes tuning variant (chip option 0), disabling SerDes interface modes\n");
+		return 0;
+	}
+
+	mb->sds_supported = true;
+
+	return 0;
+}
+
+/* The vendor driver raises the port 6 ingress and egress rate limiters to
+ * their maximum in its switch init, unconditionally for the whole chip
+ * family. The chip reset in rtl8365mb_setup() puts them back to their reset
+ * default of 0x1FFFF, a ~1.048 Gbps limit which caps the aggregate
+ * throughput of an HSGMII CPU port at roughly 1 Gbps. The vendor
+ * documentation describes the reset default as disabling the limiter, but
+ * the cap has been observed on hardware. Raise them likewise, to 0x7FFFF
+ * (~4.19 Gbps, above the HSGMII line rate). The related HSGMII scheduler
+ * line rate register (LINE_RATE_HSG_H, 0x03FA) is already set to its
+ * maximum by the common init jam table.
+ */
+static int rtl8365mb_sds_raise_rate_limits(struct realtek_priv *priv)
+{
+	int ret;
+
+	ret = regmap_write(priv->map, RTL8365MB_INGRESSBW_PORT6_RATE_CTRL0_REG,
+			   0xFFFF);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(priv->map,
+				 RTL8365MB_INGRESSBW_PORT6_RATE_CTRL1_REG,
+				 RTL8365MB_INGRESSBW_PORT6_RATE_CTRL1_MASK,
+				 RTL8365MB_INGRESSBW_PORT6_RATE_CTRL1_MASK);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(priv->map, RTL8365MB_PORT6_EGRESSBW_CTRL0_REG,
+			   0xFFFF);
+	if (ret)
+		return ret;
+
+	return regmap_update_bits(priv->map, RTL8365MB_PORT6_EGRESSBW_CTRL1_REG,
+				  RTL8365MB_PORT6_EGRESSBW_CTRL1_MASK,
+				  RTL8365MB_PORT6_EGRESSBW_CTRL1_MASK);
+}
+
+static int rtl8365mb_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode,
+				phy_interface_t interface,
+				const unsigned long *advertising,
+				bool permit_pause_to_mac)
+{
+	const struct rtl8365mb_jam_tbl_entry *sds_jam;
+	const int id = RTL8365MB_SDS_EXT_INTERFACE_ID;
+	struct rtl8365mb *mb = pcs_to_rtl8365mb(pcs);
+	struct realtek_priv *priv;
+	size_t sds_jam_size;
+	u32 mode;
+	u16 val;
+	int ret;
+	int i;
+
+	priv = mb->priv;
+
+	if (interface == PHY_INTERFACE_MODE_2500BASEX) {
+		sds_jam = rtl8365mb_sds_jam_hsgmii;
+		sds_jam_size = ARRAY_SIZE(rtl8365mb_sds_jam_hsgmii);
+		mode = RTL8365MB_EXT_PORT_MODE_HSGMII;
+	} else {
+		sds_jam = rtl8365mb_sds_jam_sgmii;
+		sds_jam_size = ARRAY_SIZE(rtl8365mb_sds_jam_sgmii);
+		mode = RTL8365MB_EXT_PORT_MODE_SGMII;
+	}
+
+	/* Hold the embedded DW8051 microcontroller in reset and keep it
+	 * disabled. The vendor driver loads firmware into it to manage the
+	 * SerDes link, but the firmware only duplicates work that phylink
+	 * already does: it polls the port status and forces the external
+	 * interface configuration in the very registers this driver manages.
+	 * Letting it run would race with phylink.
+	 */
+	ret = regmap_update_bits(priv->map, RTL8365MB_CHIP_RESET_REG,
+				 RTL8365MB_CHIP_RESET_DW8051_MASK,
+				 RTL8365MB_CHIP_RESET_DW8051_MASK);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(priv->map, RTL8365MB_MISC_CFG0_REG,
+				 RTL8365MB_MISC_CFG0_DW8051_EN_MASK, 0);
+	if (ret)
+		return ret;
+
+	/* The vendor driver clears the line rate bypass for all interface
+	 * modes except TMII.
+	 */
+	ret = regmap_update_bits(priv->map, RTL8365MB_BYPASS_LINE_RATE_REG,
+				 RTL8365MB_SDS_BYPASS_LINE_RATE_MASK, 0);
+	if (ret)
+		return ret;
+
+	/* Tune the SerDes with vendor-prescribed parameters */
+	for (i = 0; i < sds_jam_size; i++) {
+		ret = rtl8365mb_sds_write(priv, sds_jam[i].reg,
+					  sds_jam[i].val);
+		if (ret)
+			return ret;
+	}
+
+	/* Mux the SerDes to MAC8 in the requested mode */
+	ret = regmap_update_bits(priv->map, RTL8365MB_SDS_MISC_REG,
+				 RTL8365MB_SDS_MISC_MAC8_SEL_SGMII_MASK |
+					 RTL8365MB_SDS_MISC_MAC8_SEL_HSGMII_MASK,
+				 mode == RTL8365MB_EXT_PORT_MODE_SGMII ?
+					 RTL8365MB_SDS_MISC_MAC8_SEL_SGMII_MASK :
+					 RTL8365MB_SDS_MISC_MAC8_SEL_HSGMII_MASK);
+	if (ret)
+		return ret;
+
+	val = mode << RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET(id);
+	ret = regmap_update_bits(priv->map,
+				 RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(id),
+				 RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(id),
+				 val);
+	if (ret)
+		return ret;
+
+	/* Take the SerDes out of reset. The vendor driver does this only
+	 * after the SerDes mux and the interface mode are configured.
+	 */
+	ret = rtl8365mb_sds_write(priv, RTL8365MB_SDS_REG_RESET,
+				  RTL8365MB_SDS_RESET_DEASSERT);
+	if (ret)
+		return ret;
+
+	/* Reset the SerDes data path and resync its PLL, mirroring what the
+	 * vendor firmware does right after deasserting the SerDes reset.
+	 * This flushes the FIFOs and ensures a clean state for the link,
+	 * preventing silent drops and CRC errors.
+	 */
+	ret = rtl8365mb_sds_write(priv, RTL8365MB_SDS_REG_BMCR,
+				  RTL8365MB_SDS_BMCR_DPRST_PHASE1);
+	if (ret)
+		return ret;
+
+	ret = rtl8365mb_sds_write(priv, RTL8365MB_SDS_REG_BMCR,
+				  RTL8365MB_SDS_BMCR_DPRST_PHASE2);
+	if (ret)
+		return ret;
+
+	/* Keep SGMII in-band autonegotiation disabled: the link parameters are
+	 * forced from rtl8365mb_pcs_link_up() instead.
+	 */
+	ret = rtl8365mb_sds_read(priv, RTL8365MB_SDS_REG_NWAY, &val);
+	if (ret)
+		return ret;
+
+	val &= ~RTL8365MB_SDS_NWAY_EN_MASK;
+	val |= RTL8365MB_SDS_NWAY_RESTART_MASK;
+
+	return rtl8365mb_sds_write(priv, RTL8365MB_SDS_REG_NWAY, val);
+}
+
+static bool rtl8365mb_interface_is_serdes(phy_interface_t interface)
+{
+	return interface == PHY_INTERFACE_MODE_SGMII ||
+	       interface == PHY_INTERFACE_MODE_2500BASEX;
+}
+
+static unsigned int rtl8365mb_pcs_inband_caps(struct phylink_pcs *pcs,
+					      phy_interface_t interface)
+{
+	/* In-band autonegotiation is not implemented; the link is always
+	 * forced. Report that to phylink so that it never selects an
+	 * in-band-enabled negotiation mode for this PCS.
+	 */
+	return LINK_INBAND_DISABLE;
+}
+
+static void rtl8365mb_pcs_get_state(struct phylink_pcs *pcs,
+				    unsigned int neg_mode,
+				    struct phylink_link_state *state)
+{
+	struct rtl8365mb *mb = pcs_to_rtl8365mb(pcs);
+	struct realtek_priv *priv = mb->priv;
+	u16 status;
+	u32 val;
+	int ret;
+
+	/* In-band autonegotiation is not implemented, so the link parameters are
+	 * forced from rtl8365mb_pcs_link_up(). The real link state must still be
+	 * read from the SerDes itself: the embedded DW8051 microcontroller that
+	 * the vendor firmware uses to poll the SerDes is kept disabled (see
+	 * rtl8365mb_pcs_config()), so the link status register can be read
+	 * directly through the SDS_INDACS window without racing the auto-poll.
+	 */
+	ret = rtl8365mb_sds_read(priv, RTL8365MB_SDS_REG_LINK_STATUS, &status);
+	if (ret) {
+		state->link = false;
+		return;
+	}
+
+	state->link = !!(status & RTL8365MB_SDS_LINK_STATUS_LINK_MASK);
+	state->an_complete = state->link;
+	if (!state->link)
+		return;
+
+	/* The speed and duplex are forced; read them back from the values
+	 * programmed into the SerDes MISC register.
+	 */
+	ret = regmap_read(priv->map, RTL8365MB_SDS_MISC_REG, &val);
+	if (ret) {
+		state->link = false;
+		return;
+	}
+
+	state->duplex = (val & RTL8365MB_SDS_MISC_SGMII_FDUP_MASK) ?
+				DUPLEX_FULL : DUPLEX_HALF;
+
+	switch (FIELD_GET(RTL8365MB_SDS_MISC_SGMII_SPD_MASK, val)) {
+	case RTL8365MB_PORT_SPEED_1000M:
+		state->speed =
+			state->interface == PHY_INTERFACE_MODE_2500BASEX ?
+				SPEED_2500 : SPEED_1000;
+		break;
+	case RTL8365MB_PORT_SPEED_100M:
+		state->speed = SPEED_100;
+		break;
+	case RTL8365MB_PORT_SPEED_10M:
+		state->speed = SPEED_10;
+		break;
+	}
+}
+
+static void rtl8365mb_pcs_link_up(struct phylink_pcs *pcs,
+				  unsigned int neg_mode,
+				  phy_interface_t interface, int speed,
+				  int duplex)
+{
+	struct rtl8365mb *mb = pcs_to_rtl8365mb(pcs);
+	struct realtek_priv *priv = mb->priv;
+	u32 mask = RTL8365MB_SDS_MISC_SGMII_FDUP_MASK |
+		   RTL8365MB_SDS_MISC_SGMII_LINK_MASK |
+		   RTL8365MB_SDS_MISC_SGMII_SPD_MASK;
+	u32 val = RTL8365MB_SDS_MISC_SGMII_LINK_MASK;
+	u32 r_speed;
+	int ret;
+
+	/* The speed field has no value for 2.5 Gbps: the rate is determined by
+	 * the HSGMII SerDes configuration, and the vendor driver programs the
+	 * 1 Gbps value here.
+	 */
+	if (speed == SPEED_2500 || speed == SPEED_1000) {
+		r_speed = RTL8365MB_PORT_SPEED_1000M;
+	} else if (speed == SPEED_100) {
+		r_speed = RTL8365MB_PORT_SPEED_100M;
+	} else if (speed == SPEED_10) {
+		r_speed = RTL8365MB_PORT_SPEED_10M;
+	} else {
+		dev_err(priv->dev, "unsupported SerDes speed %s\n",
+			phy_speed_to_str(speed));
+		return;
+	}
+
+	val |= FIELD_PREP(RTL8365MB_SDS_MISC_SGMII_SPD_MASK, r_speed);
+
+	if (duplex == DUPLEX_FULL)
+		val |= RTL8365MB_SDS_MISC_SGMII_FDUP_MASK;
+
+	/* pcs_link_up() carries no pause information, so the SerDes flow
+	 * control bits are programmed together with the MAC external interface
+	 * force from rtl8365mb_phylink_mac_link_up(), where the resolved pause
+	 * modes are known.
+	 */
+	ret = regmap_update_bits(priv->map, RTL8365MB_SDS_MISC_REG, mask, val);
+	if (ret) {
+		dev_err(priv->dev, "failed to force SerDes link: %pe\n",
+			ERR_PTR(ret));
+		return;
+	}
+}
+
+static const struct phylink_pcs_ops rtl8365mb_pcs_ops = {
+	.pcs_inband_caps = rtl8365mb_pcs_inband_caps,
+	.pcs_config = rtl8365mb_pcs_config,
+	.pcs_get_state = rtl8365mb_pcs_get_state,
+	.pcs_link_up = rtl8365mb_pcs_link_up,
+};
+
 static int rtl8365mb_ext_config_forcemode(struct realtek_priv *priv, int port,
 					  bool link, int speed, int duplex,
 					  bool tx_pause, bool rx_pause)
@@ -1065,7 +1567,11 @@ static int rtl8365mb_ext_config_forcemode(struct realtek_priv *priv, int port,
 		r_rx_pause = rx_pause ? 1 : 0;
 		r_tx_pause = tx_pause ? 1 : 0;
 
-		if (speed == SPEED_1000) {
+		/* The speed field has no value for 2.5 Gbps: the rate is
+		 * determined by the HSGMII SerDes configuration, and the
+		 * vendor driver programs the 1 Gbps value here.
+		 */
+		if (speed == SPEED_2500 || speed == SPEED_1000) {
 			r_speed = RTL8365MB_PORT_SPEED_1000M;
 		} else if (speed == SPEED_100) {
 			r_speed = RTL8365MB_PORT_SPEED_100M;
@@ -1118,6 +1624,8 @@ static void rtl8365mb_phylink_get_caps(struct dsa_switch *ds, int port,
 {
 	const struct rtl8365mb_extint *extint =
 		rtl8365mb_get_port_extint(ds->priv, port);
+	struct realtek_priv *priv = ds->priv;
+	struct rtl8365mb *mb = priv->chip_data;
 
 	config->mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE |
 				   MAC_10 | MAC_100 | MAC_1000FD;
@@ -1141,6 +1649,32 @@ static void rtl8365mb_phylink_get_caps(struct dsa_switch *ds, int port,
 
 	if (extint->supported_interfaces & RTL8365MB_PHY_INTERFACE_MODE_RGMII)
 		phy_interface_set_rgmii(config->supported_interfaces);
+
+	if (extint->supported_interfaces & RTL8365MB_PHY_INTERFACE_MODE_SGMII &&
+	    mb->sds_supported)
+		__set_bit(PHY_INTERFACE_MODE_SGMII,
+			  config->supported_interfaces);
+
+	if (extint->supported_interfaces & RTL8365MB_PHY_INTERFACE_MODE_HSGMII &&
+	    mb->sds_supported) {
+		__set_bit(PHY_INTERFACE_MODE_2500BASEX,
+			  config->supported_interfaces);
+		config->mac_capabilities |= MAC_2500FD;
+	}
+}
+
+static struct phylink_pcs *
+rtl8365mb_phylink_mac_select_pcs(struct phylink_config *config,
+				 phy_interface_t interface)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct realtek_priv *priv = dp->ds->priv;
+	struct rtl8365mb *mb = priv->chip_data;
+
+	if (rtl8365mb_interface_is_serdes(interface))
+		return &mb->pcs;
+
+	return NULL;
 }
 
 static void rtl8365mb_phylink_mac_config(struct phylink_config *config,
@@ -1168,6 +1702,12 @@ static void rtl8365mb_phylink_mac_config(struct phylink_config *config,
 		return;
 	}
 
+	/* SGMII and 2500base-x are handled by the SerDes PCS, configured
+	 * through the phylink_pcs ops, so nothing to do here for them.
+	 */
+	if (rtl8365mb_interface_is_serdes(state->interface))
+		return;
+
 	/* TODO: Implement MII and RMII modes, which the RTL8365MB-VC also
 	 * supports
 	 */
@@ -1188,7 +1728,13 @@ static void rtl8365mb_phylink_mac_link_down(struct phylink_config *config,
 	p = &mb->ports[port];
 	cancel_delayed_work_sync(&p->mib_work);
 
-	if (phy_interface_mode_is_rgmii(interface)) {
+	/* phylink has no pcs_link_down callback, so on the SerDes path only the
+	 * MAC external interface force is reset here. Clearing the MAC force is
+	 * enough to bring the link down; the SerDes keeps presenting its last
+	 * forced state until the next pcs_link_up() reprograms it.
+	 */
+	if (phy_interface_mode_is_rgmii(interface) ||
+	    rtl8365mb_interface_is_serdes(interface)) {
 		ret = rtl8365mb_ext_config_forcemode(priv, port, false, 0, 0,
 						     false, false);
 		if (ret)
@@ -1218,14 +1764,51 @@ static void rtl8365mb_phylink_mac_link_up(struct phylink_config *config,
 	p = &mb->ports[port];
 	schedule_delayed_work(&p->mib_work, 0);
 
-	if (phy_interface_mode_is_rgmii(interface)) {
+	/* The SerDes forced link state is programmed by the PCS in
+	 * rtl8365mb_pcs_link_up(); here only the MAC external interface force
+	 * is configured, for both RGMII and SerDes.
+	 */
+	if (phy_interface_mode_is_rgmii(interface) ||
+	    rtl8365mb_interface_is_serdes(interface)) {
 		ret = rtl8365mb_ext_config_forcemode(priv, port, true, speed,
 						     duplex, tx_pause,
 						     rx_pause);
-		if (ret)
+		if (ret) {
 			dev_err(priv->dev,
 				"failed to force mode on port %d: %pe\n", port,
 				ERR_PTR(ret));
+			return;
+		}
+
+		/* The SerDes has its own pause enables; program them from
+		 * the resolved pause modes, as the vendor driver does when
+		 * forcing the link on a SerDes external interface. These
+		 * bits, not the MAC force pause bits, gate pause on the
+		 * SerDes external interface: flow control testing shows
+		 * that pause frames are only emitted with the SerDes TXFC
+		 * bit set, while the MAC force pause bits alone have no
+		 * effect on this port. This is done here rather than in
+		 * rtl8365mb_pcs_link_up() because pcs_link_up() carries no
+		 * pause information.
+		 */
+		if (rtl8365mb_interface_is_serdes(interface)) {
+			u32 val = 0;
+
+			if (tx_pause)
+				val |= RTL8365MB_SDS_MISC_SGMII_TXFC_MASK;
+			if (rx_pause)
+				val |= RTL8365MB_SDS_MISC_SGMII_RXFC_MASK;
+
+			ret = regmap_update_bits(priv->map,
+						 RTL8365MB_SDS_MISC_REG,
+						 RTL8365MB_SDS_MISC_SGMII_TXFC_MASK |
+							 RTL8365MB_SDS_MISC_SGMII_RXFC_MASK,
+						 val);
+			if (ret)
+				dev_err(priv->dev,
+					"failed to force SerDes pause modes on port %d: %pe\n",
+					port, ERR_PTR(ret));
+		}
 
 		return;
 	}
@@ -2419,6 +3002,14 @@ static int rtl8365mb_setup(struct dsa_switch *ds)
 	mb = priv->chip_data;
 	cpu = &mb->cpu;
 
+	mb->pcs.ops = &rtl8365mb_pcs_ops;
+
+	/* The SerDes has no link interrupt wired up, so phylink must poll the
+	 * PCS for link changes when it tracks the link through pcs_get_state()
+	 * (in-band mode with autonegotiation disabled).
+	 */
+	mb->pcs.poll = true;
+
 	ret = rtl8365mb_reset_chip(priv);
 	if (ret) {
 		dev_err(priv->dev, "failed to reset chip: %pe\n",
@@ -2426,6 +3017,13 @@ static int rtl8365mb_setup(struct dsa_switch *ds)
 		goto out_error;
 	}
 
+	ret = rtl8365mb_sds_probe_option(priv);
+	if (ret) {
+		dev_err(priv->dev, "failed to probe SerDes chip option: %pe\n",
+			ERR_PTR(ret));
+		goto out_error;
+	}
+
 	/* Configure switch to vendor-defined initial state */
 	ret = rtl8365mb_switch_init(priv);
 	if (ret) {
@@ -2434,6 +3032,16 @@ static int rtl8365mb_setup(struct dsa_switch *ds)
 		goto out_error;
 	}
 
+	if (mb->sds_supported) {
+		ret = rtl8365mb_sds_raise_rate_limits(priv);
+		if (ret) {
+			dev_err(priv->dev,
+				"failed to raise port rate limits: %pe\n",
+				ERR_PTR(ret));
+			goto out_error;
+		}
+	}
+
 	/* Set up cascading IRQs */
 	ret = rtl8365mb_irq_setup(priv);
 	if (ret == -EPROBE_DEFER)
@@ -2658,6 +3266,7 @@ static int rtl8365mb_detect(struct realtek_priv *priv)
 }
 
 static const struct phylink_mac_ops rtl8365mb_phylink_mac_ops = {
+	.mac_select_pcs = rtl8365mb_phylink_mac_select_pcs,
 	.mac_config = rtl8365mb_phylink_mac_config,
 	.mac_link_down = rtl8365mb_phylink_mac_link_down,
 	.mac_link_up = rtl8365mb_phylink_mac_link_up,
diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c
index 103039fe3086..d2fa8ff6a5d0 100644
--- a/drivers/net/dsa/realtek/rtl8366rb.c
+++ b/drivers/net/dsa/realtek/rtl8366rb.c
@@ -791,11 +791,87 @@ static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv)
 	return ret;
 }
 
+static int rtl8366rb_port_set_isolation(struct realtek_priv *priv, int port,
+					u32 mask)
+{
+	/* Bit 0 enables isolation so set this if we enable isolation
+	 * any of the ports an clear it if we disable on all of them.
+	 */
+	if (mask)
+		mask = RTL8366RB_PORT_ISO_PORTS(mask) | RTL8366RB_PORT_ISO_EN;
+
+	return regmap_write(priv->map, RTL8366RB_PORT_ISO(port),
+			    mask);
+}
+
+static int rtl8366rb_port_add_isolation(struct realtek_priv *priv, int port,
+					u32 mask)
+{
+	/* We assume isolation bit is on */
+	return regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port),
+				  RTL8366RB_PORT_ISO_PORTS(mask),
+				  RTL8366RB_PORT_ISO_PORTS(mask));
+}
+
+static int rtl8366rb_port_remove_isolation(struct realtek_priv *priv, int port,
+					   u32 mask)
+{
+	return regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port),
+				  RTL8366RB_PORT_ISO_PORTS(mask), 0);
+}
+
+static void
+rtl8366rb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
+{
+	struct realtek_priv *priv = ds->priv;
+	u32 val;
+	int i;
+
+	switch (state) {
+	case BR_STATE_DISABLED:
+		val = RTL8366RB_STP_STATE_DISABLED;
+		break;
+	case BR_STATE_BLOCKING:
+	case BR_STATE_LISTENING:
+		val = RTL8366RB_STP_STATE_BLOCKING;
+		break;
+	case BR_STATE_LEARNING:
+		val = RTL8366RB_STP_STATE_LEARNING;
+		break;
+	case BR_STATE_FORWARDING:
+		val = RTL8366RB_STP_STATE_FORWARDING;
+		break;
+	default:
+		dev_err(priv->dev, "unknown bridge state requested\n");
+		return;
+	}
+
+	/* Set the same status for the port on all the FIDs */
+	for (i = 0; i < RTL8366RB_NUM_FIDS; i++) {
+		regmap_update_bits(priv->map, RTL8366RB_STP_STATE_BASE + i,
+				   RTL8366RB_STP_STATE_MASK(port),
+				   RTL8366RB_STP_STATE(port, val));
+	}
+}
+
+static int rtl8366rb_port_set_learning(struct realtek_priv *priv, int port,
+				       bool enable)
+{
+	/* Notice inverted semantics in this register: setting a bit disables
+	 * learning instead of enabling it.
+	 */
+	return regmap_update_bits(priv->map, RTL8366RB_PORT_LEARNDIS_CTRL,
+				  BIT(port), enable ? 0 : BIT(port));
+}
+
 static int rtl8366rb_setup(struct dsa_switch *ds)
 {
 	struct realtek_priv *priv = ds->priv;
 	const struct rtl8366rb_jam_tbl_entry *jam_table;
+	u32 downports_mask = 0;
 	struct rtl8366rb *rb;
+	u32 upports_mask = 0;
+	struct dsa_port *dp;
 	u32 chip_ver = 0;
 	u32 chip_id = 0;
 	int jam_size;
@@ -866,20 +942,58 @@ static int rtl8366rb_setup(struct dsa_switch *ds)
 	if (ret)
 		return ret;
 
-	/* Isolate all user ports so they can only send packets to itself and the CPU port */
-	for (i = 0; i < RTL8366RB_PORT_NUM_CPU; i++) {
-		ret = regmap_write(priv->map, RTL8366RB_PORT_ISO(i),
-				   RTL8366RB_PORT_ISO_PORTS(BIT(RTL8366RB_PORT_NUM_CPU)) |
-				   RTL8366RB_PORT_ISO_EN);
+	/* Start with all ports blocked, including unused ports */
+	dsa_switch_for_each_port(dp, ds) {
+		/* Set the initial STP state of all ports to DISABLED, otherwise
+		 * ports will still forward frames to the CPU despite being
+		 * administratively down by default.
+		 */
+		rtl8366rb_port_stp_state_set(ds, dp->index, BR_STATE_DISABLED);
+
+		/* Start with all ports completely isolated */
+		ret = rtl8366rb_port_set_isolation(priv, dp->index, 0);
+		if (ret)
+			return ret;
+
+		/* Disable learning */
+		ret = rtl8366rb_port_set_learning(priv, dp->index, false);
+		if (ret)
+			return ret;
+
+		/* Collect CPU ports. If we support cascade switches, it should
+		 * also include the upstream DSA ports.
+		 */
+		if (!dsa_port_is_cpu(dp))
+			continue;
+
+		upports_mask |= BIT(dp->index);
+	}
+
+	/* Configure user ports */
+	dsa_switch_for_each_port(dp, ds) {
+		if (!dsa_port_is_user(dp))
+			continue;
+
+		/* Forward only to the CPU */
+		ret = rtl8366rb_port_set_isolation(priv, dp->index, upports_mask);
+		if (ret)
+			return ret;
+
+		/* If we support cascade switches, it should also include the
+		 * downstream DSA ports.
+		 */
+		downports_mask |= BIT(dp->index);
+	}
+
+	/* Configure CPU ports. If we support cascade switches, this will also
+	 * include DSA ports.
+	 */
+	dsa_switch_for_each_cpu_port(dp, ds) {
+		/* Forward to all user ports */
+		ret = rtl8366rb_port_set_isolation(priv, dp->index, downports_mask);
 		if (ret)
 			return ret;
 	}
-	/* CPU port can send packets to all ports */
-	ret = regmap_write(priv->map, RTL8366RB_PORT_ISO(RTL8366RB_PORT_NUM_CPU),
-			   RTL8366RB_PORT_ISO_PORTS(dsa_user_ports(ds)) |
-			   RTL8366RB_PORT_ISO_EN);
-	if (ret)
-		return ret;
 
 	/* Set up the "green ethernet" feature */
 	ret = rtl8366rb_jam_table(rtl8366rb_green_jam,
@@ -938,12 +1052,6 @@ static int rtl8366rb_setup(struct dsa_switch *ds)
 			rb->max_mtu[i] = ETH_DATA_LEN;
 	}
 
-	/* Disable learning for all ports */
-	ret = regmap_write(priv->map, RTL8366RB_PORT_LEARNDIS_CTRL,
-			   RTL8366RB_PORT_ALL);
-	if (ret)
-		return ret;
-
 	/* Enable auto ageing for all ports */
 	ret = regmap_write(priv->map, RTL8366RB_SECURITY_CTRL, 0);
 	if (ret)
@@ -1184,70 +1292,6 @@ rtl8366rb_port_disable(struct dsa_switch *ds, int port)
 		return;
 }
 
-static int
-rtl8366rb_port_bridge_join(struct dsa_switch *ds, int port,
-			   struct dsa_bridge bridge,
-			   bool *tx_fwd_offload,
-			   struct netlink_ext_ack *extack)
-{
-	struct realtek_priv *priv = ds->priv;
-	unsigned int port_bitmap = 0;
-	int ret, i;
-
-	/* Loop over all other ports than the current one */
-	for (i = 0; i < RTL8366RB_PORT_NUM_CPU; i++) {
-		/* Current port handled last */
-		if (i == port)
-			continue;
-		/* Not on this bridge */
-		if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge))
-			continue;
-		/* Join this port to each other port on the bridge */
-		ret = regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(i),
-					 RTL8366RB_PORT_ISO_PORTS(BIT(port)),
-					 RTL8366RB_PORT_ISO_PORTS(BIT(port)));
-		if (ret)
-			dev_err(priv->dev, "failed to join port %d\n", port);
-
-		port_bitmap |= BIT(i);
-	}
-
-	/* Set the bits for the ports we can access */
-	return regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port),
-				  RTL8366RB_PORT_ISO_PORTS(port_bitmap),
-				  RTL8366RB_PORT_ISO_PORTS(port_bitmap));
-}
-
-static void
-rtl8366rb_port_bridge_leave(struct dsa_switch *ds, int port,
-			    struct dsa_bridge bridge)
-{
-	struct realtek_priv *priv = ds->priv;
-	unsigned int port_bitmap = 0;
-	int ret, i;
-
-	/* Loop over all other ports than this one */
-	for (i = 0; i < RTL8366RB_PORT_NUM_CPU; i++) {
-		/* Current port handled last */
-		if (i == port)
-			continue;
-		/* Not on this bridge */
-		if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge))
-			continue;
-		/* Remove this port from any other port on the bridge */
-		ret = regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(i),
-					 RTL8366RB_PORT_ISO_PORTS(BIT(port)), 0);
-		if (ret)
-			dev_err(priv->dev, "failed to leave port %d\n", port);
-
-		port_bitmap |= BIT(i);
-	}
-
-	/* Clear the bits for the ports we can not access, leave ourselves */
-	regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port),
-			   RTL8366RB_PORT_ISO_PORTS(port_bitmap), 0);
-}
-
 /**
  * rtl8366rb_drop_untagged() - make the switch drop untagged and C-tagged frames
  * @priv: SMI state container
@@ -1306,59 +1350,6 @@ rtl8366rb_port_pre_bridge_flags(struct dsa_switch *ds, int port,
 	return 0;
 }
 
-static int
-rtl8366rb_port_bridge_flags(struct dsa_switch *ds, int port,
-			    struct switchdev_brport_flags flags,
-			    struct netlink_ext_ack *extack)
-{
-	struct realtek_priv *priv = ds->priv;
-	int ret;
-
-	if (flags.mask & BR_LEARNING) {
-		ret = regmap_update_bits(priv->map, RTL8366RB_PORT_LEARNDIS_CTRL,
-					 BIT(port),
-					 (flags.val & BR_LEARNING) ? 0 : BIT(port));
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-static void
-rtl8366rb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
-{
-	struct realtek_priv *priv = ds->priv;
-	u32 val;
-	int i;
-
-	switch (state) {
-	case BR_STATE_DISABLED:
-		val = RTL8366RB_STP_STATE_DISABLED;
-		break;
-	case BR_STATE_BLOCKING:
-	case BR_STATE_LISTENING:
-		val = RTL8366RB_STP_STATE_BLOCKING;
-		break;
-	case BR_STATE_LEARNING:
-		val = RTL8366RB_STP_STATE_LEARNING;
-		break;
-	case BR_STATE_FORWARDING:
-		val = RTL8366RB_STP_STATE_FORWARDING;
-		break;
-	default:
-		dev_err(priv->dev, "unknown bridge state requested\n");
-		return;
-	}
-
-	/* Set the same status for the port on all the FIDs */
-	for (i = 0; i < RTL8366RB_NUM_FIDS; i++) {
-		regmap_update_bits(priv->map, RTL8366RB_STP_STATE_BASE + i,
-				   RTL8366RB_STP_STATE_MASK(port),
-				   RTL8366RB_STP_STATE(port, val));
-	}
-}
-
 static void
 rtl8366rb_port_fast_age(struct dsa_switch *ds, int port)
 {
@@ -1801,15 +1792,15 @@ static const struct dsa_switch_ops rtl8366rb_switch_ops = {
 	.get_strings = rtl8366_get_strings,
 	.get_ethtool_stats = rtl8366_get_ethtool_stats,
 	.get_sset_count = rtl8366_get_sset_count,
-	.port_bridge_join = rtl8366rb_port_bridge_join,
-	.port_bridge_leave = rtl8366rb_port_bridge_leave,
+	.port_bridge_join = rtl83xx_port_bridge_join,
+	.port_bridge_leave = rtl83xx_port_bridge_leave,
 	.port_vlan_filtering = rtl8366rb_vlan_filtering,
 	.port_vlan_add = rtl8366_vlan_add,
 	.port_vlan_del = rtl8366_vlan_del,
 	.port_enable = rtl8366rb_port_enable,
 	.port_disable = rtl8366rb_port_disable,
 	.port_pre_bridge_flags = rtl8366rb_port_pre_bridge_flags,
-	.port_bridge_flags = rtl8366rb_port_bridge_flags,
+	.port_bridge_flags = rtl83xx_port_bridge_flags,
 	.port_stp_state_set = rtl8366rb_port_stp_state_set,
 	.port_fast_age = rtl8366rb_port_fast_age,
 	.port_change_mtu = rtl8366rb_change_mtu,
@@ -1830,6 +1821,9 @@ static const struct realtek_ops rtl8366rb_ops = {
 	.is_vlan_valid	= rtl8366rb_is_vlan_valid,
 	.enable_vlan	= rtl8366rb_enable_vlan,
 	.enable_vlan4k	= rtl8366rb_enable_vlan4k,
+	.port_add_isolation = rtl8366rb_port_add_isolation,
+	.port_remove_isolation = rtl8366rb_port_remove_isolation,
+	.port_set_learning = rtl8366rb_port_set_learning,
 	.phy_read	= rtl8366rb_phy_read,
 	.phy_write	= rtl8366rb_phy_write,
 };
diff --git a/drivers/net/dsa/realtek/rtl83xx.c b/drivers/net/dsa/realtek/rtl83xx.c
index 71124ecca92f..90843d52c5a8 100644
--- a/drivers/net/dsa/realtek/rtl83xx.c
+++ b/drivers/net/dsa/realtek/rtl83xx.c
@@ -356,9 +356,6 @@ int rtl83xx_port_bridge_join(struct dsa_switch *ds, int port,
 	if (!priv->ops->port_add_isolation)
 		return -EOPNOTSUPP;
 
-	if (!priv->ops->port_set_learning)
-		return -EOPNOTSUPP;
-
 	dev_dbg(priv->dev, "bridge %d join port %d\n", bridge.num, port);
 
 	/* Add this port to the isolation group of every other port
@@ -396,9 +393,11 @@ int rtl83xx_port_bridge_join(struct dsa_switch *ds, int port,
 			goto undo_self_isolation;
 	}
 
-	ret = priv->ops->port_set_learning(priv, port, true);
-	if (ret)
-		goto undo_efid;
+	if (priv->ops->port_set_learning) {
+		ret = priv->ops->port_set_learning(priv, port, true);
+		if (ret)
+			goto undo_efid;
+	}
 
 	return 0;
 
@@ -443,9 +442,6 @@ void rtl83xx_port_bridge_leave(struct dsa_switch *ds, int port,
 	if (!priv->ops->port_remove_isolation)
 		return;
 
-	if (!priv->ops->port_set_learning)
-		return;
-
 	dev_dbg(priv->dev, "bridge %d leave port %d\n", bridge.num, port);
 
 	/* Remove this port from the isolation group of every other
@@ -474,11 +470,13 @@ void rtl83xx_port_bridge_leave(struct dsa_switch *ds, int port,
 	 * downstream DSA ports from the isolation group.
 	 */
 
-	ret = priv->ops->port_set_learning(priv, port, false);
-	if (ret)
-		dev_err(priv->dev,
-			"failed to disable learning on port %d: %pe\n",
-			port, ERR_PTR(ret));
+	if (priv->ops->port_set_learning) {
+		ret = priv->ops->port_set_learning(priv, port, false);
+		if (ret)
+			dev_err(priv->dev,
+				"failed to disable learning on port %d: %pe\n",
+				port, ERR_PTR(ret));
+	}
 
 	/* Remove those ports from the isolation group of this port */
 	ret = priv->ops->port_remove_isolation(priv, port, mask);
diff --git a/drivers/net/dsa/yt921x.h b/drivers/net/dsa/yt921x.h
index 555046526669..5f3b99e189c4 100644
--- a/drivers/net/dsa/yt921x.h
+++ b/drivers/net/dsa/yt921x.h
@@ -854,7 +854,7 @@ enum yt921x_fdb_entry_status {
 #define YT921X_PORT_NUM			11
 
 #define yt921x_port_is_internal(port) ((port) < 8)
-#define yt921x_port_is_external(port) (8 <= (port) && (port) < 9)
+#define yt921x_port_is_external(port) ((port) == 8 || (port) == 9)
 
 struct yt921x_mib {
 	u64 rx_broadcast;
diff --git a/drivers/net/ethernet/adi/Kconfig b/drivers/net/ethernet/adi/Kconfig
index 760a9a60bc15..bdb8ff7d15da 100644
--- a/drivers/net/ethernet/adi/Kconfig
+++ b/drivers/net/ethernet/adi/Kconfig
@@ -26,4 +26,16 @@ config ADIN1110
 	  Say yes here to build support for Analog Devices ADIN1110
 	  Low Power 10BASE-T1L Ethernet MAC-PHY.
 
+config ADIN1140
+	tristate "Analog Devices ADIN1140 MAC-PHY"
+	depends on SPI
+	select ADIN1140_PHY
+	select OA_TC6
+	help
+	  Say yes here to build support for Analog Devices, Inc. ADIN1140
+	  10BASE-T1S Ethernet MAC-PHY.
+
+	  To compile this driver as a module, choose M here. The module will be
+	  called adin1140.
+
 endif # NET_VENDOR_ADI
diff --git a/drivers/net/ethernet/adi/Makefile b/drivers/net/ethernet/adi/Makefile
index d0383d94303c..0390ca8ccc49 100644
--- a/drivers/net/ethernet/adi/Makefile
+++ b/drivers/net/ethernet/adi/Makefile
@@ -4,3 +4,4 @@
 #
 
 obj-$(CONFIG_ADIN1110) += adin1110.o
+obj-$(CONFIG_ADIN1140) += adin1140.o
diff --git a/drivers/net/ethernet/adi/adin1140.c b/drivers/net/ethernet/adi/adin1140.c
new file mode 100644
index 000000000000..93710baca151
--- /dev/null
+++ b/drivers/net/ethernet/adi/adin1140.c
@@ -0,0 +1,791 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Driver for Analog Devices, Inc. ADIN1140 10BASE-T1S MAC-PHY
+ *
+ * Copyright 2026 Analog Devices Inc.
+ */
+
+#include <linux/cleanup.h>
+#include <linux/etherdevice.h>
+#include <linux/kernel.h>
+#include <linux/mdio.h>
+#include <linux/module.h>
+#include <linux/oa_tc6.h>
+#include <linux/phy.h>
+
+#define ADIN1140_MAC_CONFIG2_STAT_CLR_RD	BIT(6)
+#define ADIN1140_MAC_CONFIG2_FWD_UNK2HOST	BIT(2)
+
+#define ADIN1140_MAC_P1_LOOP_ADDR_REG	0xC4
+
+#define ADIN1140_MAC_ADDR_FILT_UPR_REG		0x50
+#define ADIN1140_MAC_ADDR_FILT_APPLY2PORT1	BIT(30)
+#define ADIN1140_MAC_ADDR_FILT_TO_HOST		BIT(16)
+
+#define ADIN1140_MAC_ADDR_FILT_LWR_REG		0x51
+
+#define ADIN1140_MAC_ADDR_MASK_UPR_REG	0x70
+#define ADIN1140_MAC_ADDR_MASK_LWR_REG	0x71
+
+#define ADIN1140_MAC_FILT_MC_SLOT	0U
+#define ADIN1140_MAC_FILT_BC_SLOT	1U
+#define ADIN1140_MAC_FILT_UC_SLOT	2U
+#define ADIN1140_MAC_FILT_MAX_SLOT	16U
+#define ADIN1140_MAC_FILT_MASK_LIMIT	2U
+
+#define ADIN1140_MAC_RX_FRAME_CNT		0xA1
+#define ADIN1140_MAC_RX_BC_FRAME_CNT		0xA2
+#define ADIN1140_MAC_RX_MC_FRAME_CNT		0xA3
+#define ADIN1140_MAC_RX_CRC_ERR_CNT		0xA5
+#define ADIN1140_MAC_RX_ALIGN_ERR_CNT		0xA6
+#define ADIN1140_MAC_RX_PREAMBLE_ERR_CNT	0xA7
+#define ADIN1140_MAC_RX_SHORT_ERR_CNT		0xA8
+#define ADIN1140_MAC_RX_LONG_ERR_CNT		0xA9
+#define ADIN1140_MAC_RX_PHY_ERR_CNT		0xAA
+#define ADIN1140_MAC_RX_DRP_FULL_CNT		0xAB
+#define ADIN1140_MAC_RX_DRP_FILTER_CNT		0xAD
+#define ADIN1140_MAC_RX_IFG_ERR_CNT		0xAE
+#define ADIN1140_MAC_TX_FRAME_CNT		0xB1
+#define ADIN1140_MAC_TX_BC_FRAME_CNT		0xB2
+#define ADIN1140_MAC_TX_MC_FRAME_CNT		0xB3
+#define ADIN1140_MAC_TX_SINGLE_COL_CNT		0xB5
+#define ADIN1140_MAC_TX_MULTI_COL_CNT		0xB6
+#define ADIN1140_MAC_TX_DEFERRED_CNT		0xB7
+#define ADIN1140_MAC_TX_LATE_COL_CNT		0xB8
+#define ADIN1140_MAC_TX_EXCESS_COL_CNT		0xB9
+#define ADIN1140_MAC_TX_UNDERRUN_CNT		0xBA
+
+/* ADIN1140_MAC_FILT_MAX_SLOT - 3 (multicast, broadcast and unicast
+ * reserved slots)
+ */
+#define ADIN1140_MAC_FILT_AVAIL	13U
+
+#define ADIN1140_PHY_CTRL_DEFAULT	0x1000
+#define ADIN1140_PHY_STATUS_DEFAULT	0x082D
+#define ADIN1140_PHY_ID1		0x0283
+#define ADIN1140_PHY_ID2		0xBE00
+
+#define ADIN1140_STATS_CHECK_DELAY	(3 * HZ)
+
+enum adin1140_statistics_entry {
+	rx_frames,
+	rx_bc_frames,
+	rx_mc_frames,
+	rx_crc_errors,
+	rx_align_errors,
+	rx_preamble_errors,
+	rx_short_frame_errors,
+	rx_long_frame_errors,
+	rx_phy_errors,
+	rx_fifo_full_dropped,
+	rx_addr_filter_dropped,
+	rx_ifg_errors,
+	tx_frames,
+	tx_bc_frames,
+	tx_mc_frames,
+	tx_single_collision,
+	tx_multi_collision,
+	tx_deferred,
+	tx_late_collision,
+	tx_excess_collision,
+	tx_underrun,
+	ADIN1140_STATS_CNT,
+};
+
+struct adin1140_statistics_reg {
+	const char *name;
+	enum adin1140_statistics_entry idx;
+};
+
+struct adin1140_priv {
+	struct net_device *netdev;
+	struct oa_tc6 *tc6;
+	struct mii_bus *mdiobus;
+	struct phy_device *phydev;
+	struct delayed_work stats_work;
+
+	/* Protects stats[] from concurrent updates in adin1140_stats_work
+	 * and reads in the get_stats functions
+	 */
+	spinlock_t stat_lock;
+	u64 stats[ADIN1140_STATS_CNT];
+};
+
+static const u32 adin1140_stat_regs[] = {
+	[rx_frames] = ADIN1140_MAC_RX_FRAME_CNT,
+	[rx_bc_frames] = ADIN1140_MAC_RX_BC_FRAME_CNT,
+	[rx_mc_frames] = ADIN1140_MAC_RX_MC_FRAME_CNT,
+	[rx_crc_errors] = ADIN1140_MAC_RX_CRC_ERR_CNT,
+	[rx_align_errors] = ADIN1140_MAC_RX_ALIGN_ERR_CNT,
+	[rx_preamble_errors] = ADIN1140_MAC_RX_PREAMBLE_ERR_CNT,
+	[rx_short_frame_errors]	= ADIN1140_MAC_RX_SHORT_ERR_CNT,
+	[rx_long_frame_errors] = ADIN1140_MAC_RX_LONG_ERR_CNT,
+	[rx_phy_errors] = ADIN1140_MAC_RX_PHY_ERR_CNT,
+	[rx_fifo_full_dropped] = ADIN1140_MAC_RX_DRP_FULL_CNT,
+	[rx_addr_filter_dropped] = ADIN1140_MAC_RX_DRP_FILTER_CNT,
+	[rx_ifg_errors] = ADIN1140_MAC_RX_IFG_ERR_CNT,
+	[tx_frames] = ADIN1140_MAC_TX_FRAME_CNT,
+	[tx_bc_frames] = ADIN1140_MAC_TX_BC_FRAME_CNT,
+	[tx_mc_frames] = ADIN1140_MAC_TX_MC_FRAME_CNT,
+	[tx_single_collision] = ADIN1140_MAC_TX_SINGLE_COL_CNT,
+	[tx_multi_collision] = ADIN1140_MAC_TX_MULTI_COL_CNT,
+	[tx_deferred] = ADIN1140_MAC_TX_DEFERRED_CNT,
+	[tx_late_collision] = ADIN1140_MAC_TX_LATE_COL_CNT,
+	[tx_excess_collision] = ADIN1140_MAC_TX_EXCESS_COL_CNT,
+	[tx_underrun] = ADIN1140_MAC_TX_UNDERRUN_CNT,
+};
+
+static const struct adin1140_statistics_reg adin1140_stats[] = {
+	{.name = "rx_preamble_errors", .idx = rx_preamble_errors},
+	{.name = "rx_ifg_errors", .idx = rx_ifg_errors},
+};
+
+static int adin1140_mac_filter_set(struct adin1140_priv *priv,
+				   const u8 *addr, const u8 *mask,
+				   u8 slot)
+{
+	u32 reg_address;
+	u32 val;
+	int ret;
+
+	if (slot >= ADIN1140_MAC_FILT_MAX_SLOT)
+		return -ENOSPC;
+
+	reg_address = ADIN1140_MAC_ADDR_FILT_UPR_REG + 2 * slot;
+
+	ret = oa_tc6_write_register_mms(priv->tc6, OA_TC6_MAC_MMS1,
+					reg_address,
+					get_unaligned_be16(&addr[0]) |
+					ADIN1140_MAC_ADDR_FILT_APPLY2PORT1 |
+					ADIN1140_MAC_ADDR_FILT_TO_HOST);
+	if (ret)
+		return ret;
+
+	reg_address = ADIN1140_MAC_ADDR_FILT_LWR_REG + 2 * slot;
+	ret = oa_tc6_write_register_mms(priv->tc6, OA_TC6_MAC_MMS1,
+					reg_address,
+					get_unaligned_be32(&addr[2]));
+	if (ret)
+		return ret;
+
+	/* Only the first 2 destination MAC filter slots support masking.
+	 * For the other entries, the destination address in the received
+	 * frame must match exactly.
+	 */
+	if (slot >= ADIN1140_MAC_FILT_MASK_LIMIT)
+		return 0;
+
+	val = get_unaligned_be16(&mask[0]);
+	reg_address = ADIN1140_MAC_ADDR_MASK_UPR_REG + (2 * slot);
+
+	ret = oa_tc6_write_register_mms(priv->tc6, OA_TC6_MAC_MMS1,
+					reg_address, val);
+	if (ret)
+		return ret;
+
+	val = get_unaligned_be32(&mask[2]);
+	reg_address = ADIN1140_MAC_ADDR_MASK_LWR_REG + (2 * slot);
+
+	return oa_tc6_write_register_mms(priv->tc6, OA_TC6_MAC_MMS1,
+					 reg_address, val);
+}
+
+static int adin1140_mac_filter_clear(struct adin1140_priv *priv, u8 slot)
+{
+	u8 mask[ETH_ALEN];
+	u8 addr[ETH_ALEN];
+
+	memset(mask, 0xFF, ETH_ALEN);
+	memset(addr, 0x0, ETH_ALEN);
+
+	return adin1140_mac_filter_set(priv, addr, mask, slot);
+}
+
+static int adin1140_filter_unicast(struct adin1140_priv *priv)
+{
+	/* Only the first 2 filter slots support masking, so no unicast
+	 * address will ever need a mask. The first slots are used for the
+	 * all multicast and broadcast filter.
+	 */
+	return adin1140_mac_filter_set(priv, priv->netdev->dev_addr, NULL,
+				       ADIN1140_MAC_FILT_UC_SLOT);
+}
+
+static int adin1140_filter_all_multicast(struct adin1140_priv *priv, bool en)
+{
+	u8 multicast_addr[ETH_ALEN] = {1, 0, 0, 0, 0, 0};
+
+	if (en)
+		return adin1140_mac_filter_set(priv, multicast_addr,
+					       multicast_addr,
+					       ADIN1140_MAC_FILT_MC_SLOT);
+
+	return adin1140_mac_filter_clear(priv, ADIN1140_MAC_FILT_MC_SLOT);
+}
+
+static int adin1140_filter_broadcast(struct adin1140_priv *priv, bool enabled)
+{
+	u8 mask[ETH_ALEN];
+
+	if (enabled) {
+		memset(mask, 0xFF, ETH_ALEN);
+		return adin1140_mac_filter_set(priv, mask, mask,
+					       ADIN1140_MAC_FILT_BC_SLOT);
+	}
+
+	return adin1140_mac_filter_clear(priv, ADIN1140_MAC_FILT_BC_SLOT);
+}
+
+static int adin1140_default_filter_config(struct adin1140_priv *priv)
+{
+	int ret;
+
+	ret = adin1140_filter_broadcast(priv, true);
+	if (ret)
+		return ret;
+
+	return adin1140_filter_unicast(priv);
+}
+
+static int adin1140_promiscuous_mode(struct adin1140_priv *priv, bool enabled)
+{
+	int ret;
+	u32 val;
+
+	ret = oa_tc6_read_register(priv->tc6, OA_TC6_REG_CONFIG2, &val);
+	if (ret)
+		return ret;
+
+	if (enabled)
+		val |= ADIN1140_MAC_CONFIG2_FWD_UNK2HOST;
+	else
+		val &= ~ADIN1140_MAC_CONFIG2_FWD_UNK2HOST;
+
+	return oa_tc6_write_register(priv->tc6, OA_TC6_REG_CONFIG2, val);
+}
+
+static int adin1140_rx_mode(struct net_device *dev,
+			    struct netdev_hw_addr_list *uc,
+			    struct netdev_hw_addr_list *mc)
+{
+	struct adin1140_priv *priv = netdev_priv(dev);
+	struct netdev_hw_addr *ha;
+	bool all_multi, promisc;
+	u32 mac_addrs;
+	u8 slot, i;
+	int ret;
+
+	/* The ADIN1140 has 16 dest MAC address filter slots:
+	 * 0 - reserved for all multicast filter.
+	 * 1 - reserved for broadcast filter.
+	 * 2 - reserved for the device's own unicast MAC.
+	 * 3 -> 15 - available for other unicast/multicast filters.
+	 */
+
+	mac_addrs = netdev_hw_addr_list_count(uc);
+	all_multi = false;
+	promisc = false;
+
+	if (priv->netdev->flags & IFF_PROMISC)
+		promisc = true;
+	else if (priv->netdev->flags & IFF_ALLMULTI)
+		all_multi = true;
+	else
+		mac_addrs += netdev_hw_addr_list_count(mc);
+
+	if (mac_addrs > ADIN1140_MAC_FILT_AVAIL) {
+		/* The filter table is full. Enable promisc mode. */
+		promisc = true;
+	}
+
+	ret = adin1140_promiscuous_mode(priv, promisc);
+	if (ret)
+		return ret;
+
+	ret = adin1140_filter_all_multicast(priv, all_multi);
+	if (ret)
+		return ret;
+
+	slot = ADIN1140_MAC_FILT_UC_SLOT + 1;
+	if (!promisc) {
+		netdev_hw_addr_list_for_each(ha, uc) {
+			ret = adin1140_mac_filter_set(priv, ha->addr, NULL,
+						      slot);
+			if (ret)
+				return ret;
+
+			slot++;
+		}
+
+		if (!all_multi) {
+			netdev_hw_addr_list_for_each(ha, mc) {
+				ret = adin1140_mac_filter_set(priv, ha->addr,
+							      NULL, slot);
+				if (ret)
+					return ret;
+
+				slot++;
+			}
+		}
+	}
+
+	for (i = slot; i < ADIN1140_MAC_FILT_MAX_SLOT; i++) {
+		ret = adin1140_mac_filter_clear(priv, i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void adin1140_stats_work(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct adin1140_priv *priv;
+	u32 reg_val;
+	int ret;
+	u32 i;
+
+	priv = container_of(dwork, struct adin1140_priv, stats_work);
+
+	for (i = 0; i < ARRAY_SIZE(adin1140_stat_regs); i++) {
+		ret = oa_tc6_read_register_mms(priv->tc6, OA_TC6_MAC_MMS1,
+					       adin1140_stat_regs[i],
+					       &reg_val);
+		if (ret)
+			goto out;
+
+		scoped_guard(spinlock, &priv->stat_lock)
+			priv->stats[i] += reg_val;
+	}
+
+out:
+	schedule_delayed_work(dwork, ADIN1140_STATS_CHECK_DELAY);
+}
+
+static int adin1140_configure(struct adin1140_priv *priv)
+{
+	u32 reg_val;
+	int ret;
+
+	ret = oa_tc6_zero_align_receive_frame_enable(priv->tc6);
+	if (ret)
+		return ret;
+
+	/* Disable MAC loopback */
+	ret = oa_tc6_write_register_mms(priv->tc6, OA_TC6_MAC_MMS1,
+					ADIN1140_MAC_P1_LOOP_ADDR_REG, 0x0);
+	if (ret)
+		return ret;
+
+	ret = oa_tc6_read_register(priv->tc6, OA_TC6_REG_CONFIG2, &reg_val);
+	if (ret)
+		return ret;
+
+	reg_val |= ADIN1140_MAC_CONFIG2_STAT_CLR_RD;
+
+	ret = oa_tc6_write_register(priv->tc6, OA_TC6_REG_CONFIG2, reg_val);
+	if (ret)
+		return ret;
+
+	return adin1140_default_filter_config(priv);
+}
+
+static int adin1140_open(struct net_device *netdev)
+{
+	struct adin1140_priv *priv = netdev_priv(netdev);
+
+	schedule_delayed_work(&priv->stats_work, ADIN1140_STATS_CHECK_DELAY);
+
+	phy_start(netdev->phydev);
+	netif_start_queue(netdev);
+
+	return 0;
+}
+
+static int adin1140_close(struct net_device *netdev)
+{
+	struct adin1140_priv *priv = netdev_priv(netdev);
+
+	cancel_delayed_work_sync(&priv->stats_work);
+
+	netif_stop_queue(netdev);
+	phy_stop(netdev->phydev);
+
+	return 0;
+}
+
+static netdev_tx_t adin1140_start_xmit(struct sk_buff *skb,
+				       struct net_device *netdev)
+{
+	struct adin1140_priv *priv = netdev_priv(netdev);
+
+	/* The MAC doesn't automatically pad the frame to a 60 byte minimum
+	 * size in case the host sends a shorter skb, so we have to do it in
+	 * the driver. The FCS will be added by the MAC.
+	 */
+	if (skb_put_padto(skb, ETH_ZLEN))
+		return NETDEV_TX_OK;
+
+	return oa_tc6_start_xmit(priv->tc6, skb);
+}
+
+static int adin1140_set_mac_address(struct net_device *netdev, void *addr)
+{
+	struct adin1140_priv *priv = netdev_priv(netdev);
+	struct sockaddr *address = addr;
+	u8 mask[ETH_ALEN];
+	int ret;
+
+	ret = eth_prepare_mac_addr_change(netdev, addr);
+	if (ret < 0)
+		return ret;
+
+	if (ether_addr_equal(address->sa_data, netdev->dev_addr))
+		return 0;
+
+	memset(mask, 0xFF, ETH_ALEN);
+	ret = adin1140_mac_filter_set(priv, address->sa_data, mask,
+				      ADIN1140_MAC_FILT_UC_SLOT);
+	if (ret)
+		return ret;
+
+	eth_commit_mac_addr_change(netdev, addr);
+
+	return 0;
+}
+
+static void __adin1140_ndo_get_stats64(struct adin1140_priv *priv,
+				       struct rtnl_link_stats64 *storage)
+{
+	storage->rx_errors = priv->stats[rx_crc_errors] +
+			     priv->stats[rx_align_errors] +
+			     priv->stats[rx_preamble_errors] +
+			     priv->stats[rx_short_frame_errors] +
+			     priv->stats[rx_long_frame_errors] +
+			     priv->stats[rx_phy_errors] +
+			     priv->stats[rx_ifg_errors];
+
+	storage->tx_errors = priv->stats[tx_excess_collision] +
+			     priv->stats[tx_underrun];
+
+	storage->rx_dropped = priv->stats[rx_fifo_full_dropped] +
+			      priv->stats[rx_addr_filter_dropped];
+
+	storage->multicast = priv->stats[rx_mc_frames];
+
+	storage->collisions = priv->stats[tx_single_collision] +
+			      priv->stats[tx_multi_collision];
+
+	storage->rx_length_errors = priv->stats[rx_short_frame_errors] +
+				    priv->stats[rx_long_frame_errors];
+	storage->rx_over_errors = priv->stats[rx_fifo_full_dropped];
+	storage->rx_crc_errors = priv->stats[rx_crc_errors];
+	storage->rx_frame_errors = priv->stats[rx_align_errors];
+	storage->rx_missed_errors = priv->stats[rx_fifo_full_dropped];
+
+	storage->tx_aborted_errors = priv->stats[tx_excess_collision];
+	storage->tx_fifo_errors = priv->stats[tx_underrun];
+	storage->tx_window_errors = priv->stats[tx_late_collision];
+}
+
+static void adin1140_ndo_get_stats64(struct net_device *dev,
+				     struct rtnl_link_stats64 *storage)
+{
+	struct adin1140_priv *priv = netdev_priv(dev);
+
+	storage->rx_packets = priv->netdev->stats.rx_packets;
+	storage->tx_packets = priv->netdev->stats.tx_packets;
+
+	storage->rx_bytes = priv->netdev->stats.rx_bytes;
+	storage->tx_bytes = priv->netdev->stats.tx_bytes;
+
+	scoped_guard(spinlock, &priv->stat_lock)
+		__adin1140_ndo_get_stats64(priv, storage);
+}
+
+static void adin1140_get_drvinfo(struct net_device *netdev,
+				 struct ethtool_drvinfo *info)
+{
+	strscpy(info->driver, "ADIN1140", sizeof(info->driver));
+	strscpy(info->bus_info, dev_name(netdev->dev.parent),
+		sizeof(info->bus_info));
+}
+
+static void adin1140_get_ethtool_stats(struct net_device *netdev,
+				       struct ethtool_stats *stats, u64 *data)
+{
+	struct adin1140_priv *priv = netdev_priv(netdev);
+	u32 i;
+
+	scoped_guard(spinlock, &priv->stat_lock) {
+		for (i = 0; i < ARRAY_SIZE(adin1140_stats); i++)
+			data[i] = priv->stats[adin1140_stats[i].idx];
+	}
+}
+
+static void adin1140_get_ethtool_strings(struct net_device *netdev, u32 sset,
+					 u8 *p)
+{
+	u32 i;
+
+	switch (sset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < ARRAY_SIZE(adin1140_stats); i++)
+			ethtool_puts(&p, adin1140_stats[i].name);
+
+		break;
+	}
+}
+
+static int adin1140_get_sset_count(struct net_device *netdev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+		return ARRAY_SIZE(adin1140_stats);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void __adin1140_eth_mac_stats(struct adin1140_priv *priv,
+				     struct ethtool_eth_mac_stats *mac_stats)
+{
+	mac_stats->FramesReceivedOK = priv->stats[rx_frames];
+	mac_stats->BroadcastFramesReceivedOK = priv->stats[rx_bc_frames];
+	mac_stats->MulticastFramesReceivedOK = priv->stats[rx_mc_frames];
+	mac_stats->FrameCheckSequenceErrors = priv->stats[rx_crc_errors];
+	mac_stats->AlignmentErrors = priv->stats[rx_align_errors];
+	mac_stats->FrameTooLongErrors = priv->stats[rx_long_frame_errors];
+	mac_stats->FramesLostDueToIntMACRcvError =
+					priv->stats[rx_fifo_full_dropped];
+	mac_stats->FramesTransmittedOK = priv->stats[tx_frames];
+	mac_stats->BroadcastFramesXmittedOK = priv->stats[tx_bc_frames];
+	mac_stats->MulticastFramesXmittedOK = priv->stats[tx_mc_frames];
+	mac_stats->SingleCollisionFrames = priv->stats[tx_single_collision];
+	mac_stats->MultipleCollisionFrames = priv->stats[tx_multi_collision];
+	mac_stats->FramesWithDeferredXmissions = priv->stats[tx_deferred];
+	mac_stats->LateCollisions = priv->stats[tx_late_collision];
+	mac_stats->FramesAbortedDueToXSColls =
+					priv->stats[tx_excess_collision];
+	mac_stats->FramesLostDueToIntMACXmitError = priv->stats[tx_underrun];
+}
+
+static void adin1140_get_eth_mac_stats(struct net_device *netdev,
+				       struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct adin1140_priv *priv = netdev_priv(netdev);
+
+	scoped_guard(spinlock, &priv->stat_lock)
+		__adin1140_eth_mac_stats(priv, mac_stats);
+}
+
+static int adin1140_mdiobus_read(struct mii_bus *bus, int addr, int regnum)
+{
+	/* The ADIN1140's standard PHY C22 register map (OA TC6 0xFF00 -
+	 * 0xFF1F), of which only 0xFF00 - 0xFF03 are implemented) cannot be
+	 * accessed while frames are being received by the PHY. In case this
+	 * happens the CONFIG0 and CONFIG2 register values will get corrupted,
+	 * getting a random value. Both reads and writes cause the same
+	 * behavior. This is a workaround that avoids MDIO accesses all
+	 * together. Since this is a 10BASE-T1S PHY, only the loopback and
+	 * reset (AN) bits in the control register (0x0) can be written.
+	 * These functionalities have custom implementations in the PHY
+	 * driver. C45 accesses do not cause this issue.
+	 */
+
+	switch (regnum) {
+	case MII_BMCR:
+		return ADIN1140_PHY_CTRL_DEFAULT;
+	case MII_BMSR:
+		return ADIN1140_PHY_STATUS_DEFAULT;
+	case MII_PHYSID1:
+		return ADIN1140_PHY_ID1;
+	case MII_PHYSID2:
+		return ADIN1140_PHY_ID2;
+	default:
+		return 0xFFFF;
+	}
+}
+
+static int adin1140_mdiobus_write(struct mii_bus *bus, int addr, int regnum,
+				  u16 val)
+{
+	return -EIO;
+}
+
+static int adin1140_mdio_register(struct adin1140_priv *priv,
+				  struct spi_device *spidev)
+{
+	priv->mdiobus = devm_mdiobus_alloc(&spidev->dev);
+	if (!priv->mdiobus)
+		return dev_err_probe(&spidev->dev, -ENOMEM,
+				     "MDIO bus alloc failed\n");
+
+	priv->mdiobus->name = "adin1140-mdiobus";
+	priv->mdiobus->priv = priv->tc6;
+	priv->mdiobus->parent = &spidev->dev;
+	priv->mdiobus->phy_mask = GENMASK(31, 1);
+	priv->mdiobus->read = adin1140_mdiobus_read;
+	priv->mdiobus->write = adin1140_mdiobus_write;
+	priv->mdiobus->read_c45 = oa_tc6_mdiobus_read_c45;
+	priv->mdiobus->write_c45 = oa_tc6_mdiobus_write_c45;
+
+	snprintf(priv->mdiobus->id, MII_BUS_ID_SIZE, "adin1140-%s.%u",
+		 dev_name(&spidev->dev), spi_get_chipselect(spidev, 0));
+
+	return devm_mdiobus_register(&spidev->dev, priv->mdiobus);
+}
+
+static void adin1140_handle_link_change(struct net_device *netdev)
+{
+	phy_print_status(netdev->phydev);
+}
+
+static void adin1140_phy_remove(void *data)
+{
+	phy_disconnect(data);
+}
+
+static int adin1140_phy_init(struct adin1140_priv *priv,
+			     struct spi_device *spidev)
+{
+	int ret;
+
+	ret = adin1140_mdio_register(priv, spidev);
+	if (ret)
+		return ret;
+
+	priv->phydev = phy_find_first(priv->mdiobus);
+	if (!priv->phydev)
+		return dev_err_probe(&spidev->dev, -ENODEV, "No PHY found\n");
+
+	priv->phydev->is_internal = true;
+	ret = phy_connect_direct(priv->netdev, priv->phydev,
+				 &adin1140_handle_link_change,
+				 PHY_INTERFACE_MODE_INTERNAL);
+	if (ret)
+		return dev_err_probe(&spidev->dev, ret,
+				     "Can't attach PHY to %s\n",
+				     priv->mdiobus->id);
+
+	ret = devm_add_action_or_reset(&spidev->dev, adin1140_phy_remove,
+				       priv->phydev);
+	if (ret)
+		return ret;
+
+	phy_attached_info(priv->phydev);
+
+	return 0;
+}
+
+static const struct ethtool_ops adin1140_ethtool_ops = {
+	.get_drvinfo = adin1140_get_drvinfo,
+	.get_link = ethtool_op_get_link,
+	.get_ethtool_stats = adin1140_get_ethtool_stats,
+	.get_sset_count = adin1140_get_sset_count,
+	.get_strings = adin1140_get_ethtool_strings,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
+	.get_eth_mac_stats = adin1140_get_eth_mac_stats,
+};
+
+static const struct net_device_ops adin1140_netdev_ops = {
+	.ndo_open = adin1140_open,
+	.ndo_stop = adin1140_close,
+	.ndo_start_xmit	= adin1140_start_xmit,
+	.ndo_set_mac_address = adin1140_set_mac_address,
+	.ndo_validate_addr = eth_validate_addr,
+	.ndo_set_rx_mode_async = adin1140_rx_mode,
+	.ndo_eth_ioctl = phy_do_ioctl_running,
+	.ndo_get_stats64 = adin1140_ndo_get_stats64,
+};
+
+static void adin1140_oa_tc6_remove(void *data)
+{
+	oa_tc6_exit(data);
+}
+
+static int adin1140_probe(struct spi_device *spi)
+{
+	struct oa_tc6_quirks tc6_quirks = {};
+	struct net_device *netdev;
+	struct adin1140_priv *priv;
+	int ret;
+
+	netdev = devm_alloc_etherdev(&spi->dev, sizeof(struct adin1140_priv));
+	if (!netdev)
+		return -ENOMEM;
+
+	priv = netdev_priv(netdev);
+	priv->netdev = netdev;
+	spi_set_drvdata(spi, priv);
+	spin_lock_init(&priv->stat_lock);
+
+	tc6_quirks.quirk_flags = OA_TC6_BROKEN_PHY;
+
+	priv->tc6 = oa_tc6_init(spi, netdev, &tc6_quirks);
+	if (!priv->tc6)
+		return -ENODEV;
+
+	ret = devm_add_action_or_reset(&spi->dev, adin1140_oa_tc6_remove,
+				       priv->tc6);
+	if (ret)
+		return ret;
+
+	ret = adin1140_phy_init(priv, spi);
+	if (ret)
+		return ret;
+
+	if (device_get_ethdev_address(&spi->dev, netdev))
+		eth_hw_addr_random(netdev);
+
+	ret = adin1140_configure(priv);
+	if (ret)
+		return ret;
+
+	INIT_DELAYED_WORK(&priv->stats_work, adin1140_stats_work);
+
+	netdev->if_port = IF_PORT_10BASET;
+	netdev->irq = spi->irq;
+	netdev->netdev_ops = &adin1140_netdev_ops;
+	netdev->ethtool_ops = &adin1140_ethtool_ops;
+	netdev->netns_immutable = true;
+	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE |
+			      IFF_UNICAST_FLT;
+
+	ret = devm_register_netdev(&spi->dev, netdev);
+	if (ret)
+		return dev_err_probe(&spi->dev, ret,
+				     "Failed to register netdev");
+
+	return 0;
+}
+
+static const struct spi_device_id adin1140_spi_id[] = {
+	{ .name = "ad3306" },
+	{ .name = "adin1140" },
+	{},
+};
+MODULE_DEVICE_TABLE(spi, adin1140_spi_id);
+
+static const struct of_device_id adin1140_match_table[] = {
+	{ .compatible = "adi,ad3306" },
+	{ .compatible = "adi,adin1140" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, adin1140_match_table);
+
+static struct spi_driver adin1140_driver = {
+	.driver = {
+		.name = "adin1140",
+		.of_match_table = adin1140_match_table,
+	 },
+	.probe = adin1140_probe,
+	.id_table = adin1140_spi_id,
+};
+module_spi_driver(adin1140_driver);
+
+MODULE_DESCRIPTION("Analog Devices, Inc. ADIN1140 10BASE-T1S MAC-PHY");
+MODULE_AUTHOR("Ciprian Regus <ciprian.regus@analog.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index f6396925722d..e4c3644dd6ec 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -331,7 +331,7 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
 					struct airoha_foe_entry *hwe,
 					struct net_device *netdev, int type,
 					struct airoha_flow_data *data,
-					int l4proto)
+					int l4proto, u8 priority)
 {
 	u32 qdata = FIELD_PREP(AIROHA_FOE_SHAPER_ID, 0x7f), ports_pad, val;
 	int wlan_etype = -EINVAL, dsa_port = airoha_get_dsa_port(&netdev);
@@ -386,7 +386,9 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
 			 */
 			channel = dsa_port >= 0 ? dsa_port : port->id;
 			channel = channel % AIROHA_NUM_QOS_CHANNELS;
-			qdata |= FIELD_PREP(AIROHA_FOE_CHANNEL, channel);
+			priority = priority % AIROHA_NUM_QOS_QUEUES;
+			qdata |= FIELD_PREP(AIROHA_FOE_CHANNEL, channel) |
+				 FIELD_PREP(AIROHA_FOE_QID, priority);
 
 			val |= FIELD_PREP(AIROHA_FOE_IB2_PSE_PORT, pse_port) |
 			       AIROHA_FOE_IB2_PSE_QOS;
@@ -1079,10 +1081,10 @@ static int airoha_ppe_flow_offload_replace(struct airoha_eth *eth,
 	struct airoha_flow_data data = {};
 	struct net_device *odev = NULL;
 	struct flow_action_entry *act;
+	u8 l4proto = 0, priority = 0;
 	struct airoha_foe_entry hwe;
 	int err, i, offload_type;
 	u16 addr_type = 0;
-	u8 l4proto = 0;
 
 	if (rhashtable_lookup(&eth->flow_table, &f->cookie,
 			      airoha_flow_table_params))
@@ -1177,7 +1179,7 @@ static int airoha_ppe_flow_offload_replace(struct airoha_eth *eth,
 		return -EINVAL;
 
 	err = airoha_ppe_foe_entry_prepare(eth, &hwe, odev, offload_type,
-					   &data, l4proto);
+					   &data, l4proto, priority);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index fc7341a5cbb7..42174249ef61 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -15,7 +15,7 @@
 #include <linux/clk.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/mii.h>
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 3b2951030a38..507db46daf2b 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -7,7 +7,7 @@
  *	    Keyur Chudgar <kchudgar@apm.com>
  */
 
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include "xgene_enet_main.h"
 #include "xgene_enet_hw.h"
 #include "xgene_enet_sgmac.h"
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 5b2640bd31c3..5a9742fd3ddf 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -4742,13 +4742,13 @@ int bnx2x_alloc_mem_bp(struct bnx2x *bp)
 
 	/* fp array: RSS plus CNIC related L2 queues */
 	fp_array_size = BNX2X_MAX_RSS_COUNT(bp) + CNIC_SUPPORT(bp);
-	bp->fp_array_size = fp_array_size;
-	BNX2X_DEV_INFO("fp_array_size %d\n", bp->fp_array_size);
-
-	fp = kzalloc_objs(*fp, bp->fp_array_size);
+	BNX2X_DEV_INFO("fp_array_size %d\n", fp_array_size);
+	fp = kzalloc_objs(*fp, fp_array_size);
 	if (!fp)
 		goto alloc_err;
 	bp->fp = fp;
+	bp->fp_array_size = fp_array_size;
+
 	for (i = 0; i < bp->fp_array_size; i++) {
 		fp[i].tpa_info =
 			kzalloc_objs(struct bnx2x_agg_info,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 07a908a2c72f..d560524d317d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -26,6 +26,7 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/crc32c.h>
+#include <linux/slab.h>
 #include "bnx2x.h"
 #include "bnx2x_cmn.h"
 #include "bnx2x_sp.h"
@@ -2664,7 +2665,7 @@ static void bnx2x_free_groups(struct list_head *mcast_group_list)
 				      struct bnx2x_mcast_elem_group,
 				      mcast_group_link);
 		list_del(&current_mcast_group->mcast_group_link);
-		free_page((unsigned long)current_mcast_group);
+		kfree(current_mcast_group);
 	}
 }
 
@@ -2713,8 +2714,7 @@ static int bnx2x_mcast_enqueue_cmd(struct bnx2x *bp,
 				total_elems = BNX2X_MCAST_BINS_NUM;
 		}
 		while (total_elems > 0) {
-			elem_group = (struct bnx2x_mcast_elem_group *)
-				     __get_free_page(GFP_ATOMIC | __GFP_ZERO);
+			elem_group = kzalloc(PAGE_SIZE, GFP_ATOMIC);
 			if (!elem_group) {
 				bnx2x_free_groups(&new_cmd->group_head);
 				kfree(new_cmd);
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 8e19add764db..8b75004ba7c9 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -3006,7 +3006,6 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	txqent->hdr.wi.reserved = 0;
 	txqent->hdr.wi.num_vectors = vectors;
 
-	head_unmap->skb = skb;
 	head_unmap->nvecs = 0;
 
 	/* Program the vectors */
@@ -3018,6 +3017,7 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 		BNAD_UPDATE_CTR(bnad, tx_skb_map_failed);
 		return NETDEV_TX_OK;
 	}
+	head_unmap->skb = skb;
 	BNA_SET_DMA_ADDR(dma_addr, &txqent->vector[0].host_addr);
 	txqent->vector[0].length = htons(len);
 	dma_unmap_addr_set(&unmap->vectors[0], dma_addr, dma_addr);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 6871127427fa..29d7b786e51e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -33,6 +33,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/string_choices.h>
 #include "cxgb4.h"
 #include "t4_regs.h"
 #include "t4_values.h"
@@ -4867,7 +4868,7 @@ static void mem_intr_handler(struct adapter *adapter, int idx)
 		if (printk_ratelimit())
 			dev_warn(adapter->pdev_dev,
 				 "%u %s correctable ECC data error%s\n",
-				 cnt, name[idx], cnt > 1 ? "s" : "");
+				 cnt, name[idx], str_plural(cnt));
 	}
 	if (v & ECC_UE_INT_CAUSE_F)
 		dev_alert(adapter->pdev_dev,
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index dd4f60031d0c..33e7a99d3e49 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -25,6 +25,9 @@
 
 #define DEFAULT_VLAN_ID			1
 
+static struct notifier_block dpaa2_switch_port_switchdev_nb;
+static struct notifier_block dpaa2_switch_port_switchdev_blocking_nb;
+
 static u16 dpaa2_switch_port_get_fdb_id(struct ethsw_port_priv *port_priv)
 {
 	return port_priv->fdb->fdb_id;
@@ -51,6 +54,17 @@ dpaa2_switch_filter_block_get_unused(struct ethsw_core *ethsw)
 	return NULL;
 }
 
+static struct dpaa2_switch_lag *
+dpaa2_switch_lag_get_unused(struct ethsw_core *ethsw)
+{
+	int i;
+
+	for (i = 0; i < ethsw->sw_attr.num_ifs; i++)
+		if (!ethsw->lags[i].in_use)
+			return &ethsw->lags[i];
+	return NULL;
+}
+
 static bool dpaa2_switch_fdb_in_use_by_others(struct ethsw_core *ethsw,
 					      struct dpaa2_switch_fdb *fdb,
 					      struct ethsw_port_priv *except)
@@ -71,9 +85,9 @@ static struct dpaa2_switch_fdb *
 dpaa2_switch_fdb_for_join(struct ethsw_port_priv *port_priv,
 			  struct net_device *upper_dev)
 {
-	struct ethsw_port_priv *other_port_priv;
-	struct net_device *other_dev;
-	struct list_head *iter;
+	struct ethsw_port_priv *other_port_priv = NULL;
+	struct net_device *other_dev, *other_dev2;
+	struct list_head *iter, *iter2;
 
 	/* The below call to netdev_for_each_lower_dev() demands the RTNL lock
 	 * being held. Assert on it so that it's easier to catch new code
@@ -82,17 +96,32 @@ dpaa2_switch_fdb_for_join(struct ethsw_port_priv *port_priv,
 	ASSERT_RTNL();
 
 	/* If part of a bridge, use the FDB of the first dpaa2 switch interface
-	 * to be present in that bridge
+	 * to be present in that bridge. The search descends one level through
+	 * a bridged bond's lowers as well.
 	 */
 	netdev_for_each_lower_dev(upper_dev, other_dev, iter) {
-		if (!dpaa2_switch_port_dev_check(other_dev))
-			continue;
+		if (netif_is_lag_master(other_dev)) {
+			netdev_for_each_lower_dev(other_dev, other_dev2, iter2) {
+				if (!dpaa2_switch_port_dev_check(other_dev2))
+					continue;
 
-		if (other_dev == port_priv->netdev)
-			continue;
+				if (other_dev2 == port_priv->netdev)
+					continue;
 
-		other_port_priv = netdev_priv(other_dev);
-		return other_port_priv->fdb;
+				other_port_priv = netdev_priv(other_dev2);
+				break;
+			}
+		} else {
+			if (!dpaa2_switch_port_dev_check(other_dev))
+				continue;
+
+			if (other_dev == port_priv->netdev)
+				continue;
+
+			other_port_priv = netdev_priv(other_dev);
+		}
+		if (other_port_priv)
+			return other_port_priv->fdb;
 	}
 
 	return port_priv->fdb;
@@ -537,6 +566,103 @@ static int dpaa2_switch_port_fdb_del_mc(struct ethsw_port_priv *port_priv,
 	return err;
 }
 
+static int dpaa2_switch_port_fdb_add(struct ethsw_port_priv *port_priv,
+				     const unsigned char *addr)
+{
+	int err;
+
+	if (is_unicast_ether_addr(addr))
+		err = dpaa2_switch_port_fdb_add_uc(port_priv, addr);
+	else
+		err = dpaa2_switch_port_fdb_add_mc(port_priv, addr);
+
+	return err;
+}
+
+static int dpaa2_switch_port_fdb_del(struct ethsw_port_priv *port_priv,
+				     const unsigned char *addr)
+{
+	if (is_unicast_ether_addr(addr))
+		return dpaa2_switch_port_fdb_del_uc(port_priv, addr);
+	else
+		return dpaa2_switch_port_fdb_del_mc(port_priv, addr);
+}
+
+static struct dpaa2_mac_addr *
+dpaa2_switch_mac_addr_find(struct list_head *addr_list,
+			   const unsigned char *addr, u16 vid)
+{
+	struct dpaa2_mac_addr *a;
+
+	list_for_each_entry(a, addr_list, list)
+		if (ether_addr_equal(a->addr, addr) && a->vid == vid)
+			return a;
+
+	return NULL;
+}
+
+static int dpaa2_switch_lag_fdb_add(struct dpaa2_switch_lag *lag,
+				    const unsigned char *addr, u16 vid)
+{
+	struct ethsw_port_priv *port_priv = lag->primary;
+	struct dpaa2_mac_addr *a;
+	int err = 0;
+
+	mutex_lock(&lag->fdb_lock);
+
+	a = dpaa2_switch_mac_addr_find(&lag->fdbs, addr, vid);
+	if (a) {
+		refcount_inc(&a->refcount);
+		goto out;
+	}
+
+	a = kzalloc(sizeof(*a), GFP_KERNEL);
+	if (!a) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = dpaa2_switch_port_fdb_add(port_priv, addr);
+	if (err) {
+		kfree(a);
+		goto out;
+	}
+
+	ether_addr_copy(a->addr, addr);
+	a->vid = vid;
+	refcount_set(&a->refcount, 1);
+	list_add_tail(&a->list, &lag->fdbs);
+
+out:
+	mutex_unlock(&lag->fdb_lock);
+
+	return err;
+}
+
+static void dpaa2_switch_lag_fdb_del(struct dpaa2_switch_lag *lag,
+				     const unsigned char *addr, u16 vid)
+{
+	struct ethsw_port_priv *port_priv = lag->primary;
+	struct dpaa2_mac_addr *a;
+
+	mutex_lock(&lag->fdb_lock);
+
+	a = dpaa2_switch_mac_addr_find(&lag->fdbs, addr, vid);
+	if (!a)
+		goto out;
+
+	if (!refcount_dec_and_test(&a->refcount))
+		goto out;
+
+	list_del(&a->list);
+	kfree(a);
+
+	dpaa2_switch_port_fdb_del(port_priv, addr);
+
+out:
+	mutex_unlock(&lag->fdb_lock);
+}
+
 static void dpaa2_switch_port_get_stats(struct net_device *netdev,
 					struct rtnl_link_stats64 *stats)
 {
@@ -1485,6 +1611,33 @@ bool dpaa2_switch_port_dev_check(const struct net_device *netdev)
 	return netdev->netdev_ops == &dpaa2_switch_port_ops;
 }
 
+static bool dpaa2_switch_foreign_dev_check(const struct net_device *dev,
+					   const struct net_device *foreign_dev)
+{
+	struct ethsw_port_priv *port_priv = netdev_priv(dev);
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct ethsw_port_priv *other_port;
+	int i;
+
+	if (netif_is_bridge_master(foreign_dev))
+		if (port_priv->fdb->bridge_dev == foreign_dev)
+			return false;
+
+	if (netif_is_bridge_port(foreign_dev)) {
+		for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+			other_port = ethsw->ports[i];
+
+			if (!other_port)
+				continue;
+			if (dpaa2_switch_port_offloads_bridge_port(other_port,
+								   foreign_dev))
+				return false;
+		}
+	}
+
+	return true;
+}
+
 static int dpaa2_switch_port_connect_mac(struct ethsw_port_priv *port_priv)
 {
 	struct fsl_mc_device *dpsw_port_dev, *dpmac_dev;
@@ -1861,51 +2014,32 @@ int dpaa2_switch_port_vlans_add(struct net_device *netdev,
 					  vlan->changed);
 }
 
-static int dpaa2_switch_port_lookup_address(struct net_device *netdev, int is_uc,
-					    const unsigned char *addr)
-{
-	struct netdev_hw_addr_list *list = (is_uc) ? &netdev->uc : &netdev->mc;
-	struct netdev_hw_addr *ha;
-
-	netif_addr_lock_bh(netdev);
-	list_for_each_entry(ha, &list->list, list) {
-		if (ether_addr_equal(ha->addr, addr)) {
-			netif_addr_unlock_bh(netdev);
-			return 1;
-		}
-	}
-	netif_addr_unlock_bh(netdev);
-	return 0;
-}
-
 static int dpaa2_switch_port_mdb_add(struct net_device *netdev,
 				     const struct switchdev_obj_port_mdb *mdb)
 {
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
-	int err;
+	struct dpaa2_switch_lag *lag;
 
-	/* Check if address is already set on this port */
-	if (dpaa2_switch_port_lookup_address(netdev, 0, mdb->addr))
-		return -EEXIST;
-
-	err = dpaa2_switch_port_fdb_add_mc(port_priv, mdb->addr);
-	if (err)
-		return err;
-
-	err = dev_mc_add(netdev, mdb->addr);
-	if (err) {
-		netdev_err(netdev, "dev_mc_add err %d\n", err);
-		dpaa2_switch_port_fdb_del_mc(port_priv, mdb->addr);
-	}
-
-	return err;
+	lag = rtnl_dereference(port_priv->lag);
+	if (lag)
+		return dpaa2_switch_lag_fdb_add(lag, mdb->addr, mdb->vid);
+	else
+		return dpaa2_switch_port_fdb_add(port_priv, mdb->addr);
 }
 
-static int dpaa2_switch_port_obj_add(struct net_device *netdev,
-				     const struct switchdev_obj *obj)
+static int dpaa2_switch_port_obj_add(struct net_device *netdev, const void *ctx,
+				     const struct switchdev_obj *obj,
+				     struct netlink_ext_ack *extack)
 {
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
 	int err;
 
+	if (ctx && ctx != port_priv)
+		return 0;
+
+	if (!dpaa2_switch_port_offloads_bridge_port(port_priv, obj->orig_dev))
+		return -EOPNOTSUPP;
+
 	switch (obj->id) {
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
 		err = dpaa2_switch_port_vlans_add(netdev,
@@ -2001,29 +2135,29 @@ static int dpaa2_switch_port_mdb_del(struct net_device *netdev,
 				     const struct switchdev_obj_port_mdb *mdb)
 {
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
-	int err;
-
-	if (!dpaa2_switch_port_lookup_address(netdev, 0, mdb->addr))
-		return -ENOENT;
-
-	err = dpaa2_switch_port_fdb_del_mc(port_priv, mdb->addr);
-	if (err)
-		return err;
+	struct dpaa2_switch_lag *lag;
 
-	err = dev_mc_del(netdev, mdb->addr);
-	if (err) {
-		netdev_err(netdev, "dev_mc_del err %d\n", err);
-		return err;
-	}
+	lag = rtnl_dereference(port_priv->lag);
+	if (lag)
+		dpaa2_switch_lag_fdb_del(lag, mdb->addr, mdb->vid);
+	else
+		dpaa2_switch_port_fdb_del(port_priv, mdb->addr);
 
-	return err;
+	return 0;
 }
 
-static int dpaa2_switch_port_obj_del(struct net_device *netdev,
+static int dpaa2_switch_port_obj_del(struct net_device *netdev, const void *ctx,
 				     const struct switchdev_obj *obj)
 {
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
 	int err;
 
+	if (ctx && ctx != port_priv)
+		return 0;
+
+	if (!dpaa2_switch_port_offloads_bridge_port(port_priv, obj->orig_dev))
+		return -EOPNOTSUPP;
+
 	switch (obj->id) {
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
 		err = dpaa2_switch_port_vlans_del(netdev, SWITCHDEV_OBJ_PORT_VLAN(obj));
@@ -2049,6 +2183,21 @@ static int dpaa2_switch_port_attr_set_event(struct net_device *netdev,
 	return notifier_from_errno(err);
 }
 
+static struct net_device *
+dpaa2_switch_port_to_bridge_port(struct ethsw_port_priv *port_priv)
+{
+	struct dpaa2_switch_lag *lag;
+
+	if (!port_priv->fdb->bridge_dev)
+		return NULL;
+
+	lag = rtnl_dereference(port_priv->lag);
+	if (lag)
+		return lag->bond_dev;
+
+	return port_priv->netdev;
+}
+
 static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 					 struct net_device *upper_dev,
 					 struct netlink_ext_ack *extack)
@@ -2056,6 +2205,7 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
 	struct dpaa2_switch_fdb *old_fdb = port_priv->fdb;
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct net_device *brport_dev;
 	bool learn_ena;
 	int err;
 
@@ -2067,7 +2217,8 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 	dpaa2_switch_port_set_fdb(port_priv, upper_dev, true);
 
 	/* Inherit the initial bridge port learning state */
-	learn_ena = br_port_flag_is_set(netdev, BR_LEARNING);
+	brport_dev = dpaa2_switch_port_to_bridge_port(port_priv);
+	learn_ena = br_port_flag_is_set(brport_dev, BR_LEARNING);
 	err = dpaa2_switch_port_set_learning(port_priv, learn_ena);
 	port_priv->learn_ena = learn_ena;
 
@@ -2081,8 +2232,11 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 	if (err)
 		goto err_egress_flood;
 
-	err = switchdev_bridge_port_offload(netdev, netdev, NULL,
-					    NULL, NULL, false, extack);
+	brport_dev = dpaa2_switch_port_to_bridge_port(port_priv);
+	err = switchdev_bridge_port_offload(brport_dev, netdev, port_priv,
+					    &dpaa2_switch_port_switchdev_nb,
+					    &dpaa2_switch_port_switchdev_blocking_nb,
+					    false, extack);
 	if (err)
 		goto err_switchdev_offload;
 
@@ -2116,7 +2270,22 @@ static int dpaa2_switch_port_restore_rxvlan(struct net_device *vdev, int vid, vo
 
 static void dpaa2_switch_port_pre_bridge_leave(struct net_device *netdev)
 {
-	switchdev_bridge_port_unoffload(netdev, NULL, NULL, NULL);
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct net_device *brport_dev;
+
+	brport_dev = dpaa2_switch_port_to_bridge_port(port_priv);
+	if (!brport_dev)
+		return;
+
+	switchdev_bridge_port_unoffload(brport_dev, port_priv,
+					&dpaa2_switch_port_switchdev_nb,
+					&dpaa2_switch_port_switchdev_blocking_nb);
+
+	/* Make sure that any FDB add/del operations are completed before the
+	 * bridge layout changes
+	 */
+	flush_workqueue(ethsw->workqueue);
 }
 
 static int dpaa2_switch_port_bridge_leave(struct net_device *netdev)
@@ -2178,30 +2347,53 @@ static int dpaa2_switch_port_bridge_leave(struct net_device *netdev)
 					  false);
 }
 
+static int
+dpaa2_switch_have_vlan_upper(struct net_device *upper_dev,
+			     __always_unused struct netdev_nested_priv *priv)
+{
+	return is_vlan_dev(upper_dev);
+}
+
 static int dpaa2_switch_prevent_bridging_with_8021q_upper(struct net_device *netdev)
 {
-	struct net_device *upper_dev;
-	struct list_head *iter;
+	struct netdev_nested_priv priv = {};
 
 	/* RCU read lock not necessary because we have write-side protection
-	 * (rtnl_mutex), however a non-rcu iterator does not exist.
+	 * (rtnl_mutex), however a non-rcu iterator does not exist. Walk the
+	 * entire upper chain so that a VLAN device stacked on a intermediate
+	 * bond is caught too.
 	 */
-	netdev_for_each_upper_dev_rcu(netdev, upper_dev, iter)
-		if (is_vlan_dev(upper_dev))
-			return -EOPNOTSUPP;
+	if (netdev_walk_all_upper_dev_rcu(netdev, dpaa2_switch_have_vlan_upper,
+					  &priv))
+		return -EOPNOTSUPP;
 
 	return 0;
 }
 
+static int dpaa2_switch_check_dpsw_instance(struct net_device *dev,
+					    struct netdev_nested_priv *priv)
+{
+	struct ethsw_port_priv *port_priv = (struct ethsw_port_priv *)priv->data;
+	struct ethsw_port_priv *other_priv = netdev_priv(dev);
+
+	if (!dpaa2_switch_port_dev_check(dev))
+		return 0;
+
+	if (other_priv->ethsw_data == port_priv->ethsw_data)
+		return 0;
+
+	return 1;
+}
+
 static int
 dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev,
 					  struct net_device *upper_dev,
 					  struct netlink_ext_ack *extack)
 {
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
-	struct ethsw_port_priv *other_port_priv;
-	struct net_device *other_dev;
-	struct list_head *iter;
+	struct netdev_nested_priv data = {
+		.data = (void *)port_priv,
+	};
 	int err;
 
 	if (!br_vlan_enabled(upper_dev)) {
@@ -2216,6 +2408,70 @@ dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev,
 		return err;
 	}
 
+	err = netdev_walk_all_lower_dev(upper_dev,
+					dpaa2_switch_check_dpsw_instance,
+					&data);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Interface from a different DPSW is in the bridge already");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int dpaa2_switch_pre_lag_join(struct net_device *netdev,
+				     struct net_device *upper_dev,
+				     struct netdev_lag_upper_info *info,
+				     struct netlink_ext_ack *extack)
+{
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct ethsw_port_priv *other_port_priv;
+	struct dpaa2_switch_lag *lag = NULL;
+	struct dpsw_lag_cfg cfg = {0};
+	struct net_device *other_dev;
+	int i, num_ifs = 0, err;
+	struct list_head *iter;
+
+	if (!(ethsw->features & ETHSW_FEATURE_LAG_OFFLOAD)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "LAG offload is supported only for DPSW >= v8.13");
+		return -EOPNOTSUPP;
+	}
+
+	if (info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Can only offload LAG using hash TX type");
+		return -EOPNOTSUPP;
+	}
+
+	if (info->hash_type != NETDEV_LAG_HASH_L23) {
+		NL_SET_ERR_MSG_MOD(extack, "Can only offload L2+L3 Tx hash");
+		return -EOPNOTSUPP;
+	}
+
+	if (!dpaa2_switch_port_has_mac(port_priv)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Only switch interfaces connected to MACs can be under a LAG");
+		return -EINVAL;
+	}
+
+	if (vlan_uses_dev(upper_dev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot join a LAG upper that has a VLAN");
+		return -EOPNOTSUPP;
+	}
+
+	for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+		if (!ethsw->lags[i].in_use)
+			continue;
+		if (ethsw->lags[i].bond_dev != upper_dev)
+			continue;
+		lag = &ethsw->lags[i];
+		break;
+	}
+
 	netdev_for_each_lower_dev(upper_dev, other_dev, iter) {
 		if (!dpaa2_switch_port_dev_check(other_dev))
 			continue;
@@ -2223,9 +2479,248 @@ dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev,
 		other_port_priv = netdev_priv(other_dev);
 		if (other_port_priv->ethsw_data != port_priv->ethsw_data) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Interface from a different DPSW is in the bridge already");
+					   "Interface from a different DPSW is in the bond already");
 			return -EINVAL;
 		}
+
+		cfg.if_id[num_ifs++] = other_port_priv->idx;
+
+		if (num_ifs >= DPSW_MAX_LAG_IFS) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Cannot add more than 8 DPAA2 switch ports under the same bond");
+			return -EINVAL;
+		}
+	}
+
+	if (lag) {
+		cfg.group_id = lag->id;
+		cfg.if_id[num_ifs++] = port_priv->idx;
+		cfg.num_ifs = num_ifs;
+		cfg.phase = DPSW_LAG_SET_PHASE_CHECK;
+
+		err = dpsw_lag_set(ethsw->mc_io, 0, ethsw->dpsw_handle, &cfg);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Cannot offload LAG configuration");
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static void dpaa2_switch_port_set_lag_group(struct ethsw_port_priv *port_priv,
+					    struct net_device *bond_dev)
+{
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct ethsw_port_priv *other_port_priv = NULL;
+	struct dpaa2_switch_lag *lag = NULL;
+	struct dpaa2_switch_lag *other_lag;
+	struct net_device *other_dev;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(bond_dev, other_dev, iter) {
+		if (!dpaa2_switch_port_dev_check(other_dev))
+			continue;
+
+		other_port_priv = netdev_priv(other_dev);
+		other_lag = rtnl_dereference(other_port_priv->lag);
+		if (!other_lag)
+			continue;
+
+		if (other_lag->bond_dev == bond_dev) {
+			rcu_assign_pointer(port_priv->lag, other_lag);
+			return;
+		}
+	}
+
+	/* This is the first interface to be added under a bond device. Find an
+	 * unused LAG group. No need to check for NULL since there are the same
+	 * amount of DPSW ports as LAG groups, meaning that each port can have
+	 * its own LAG group.
+	 */
+	lag = dpaa2_switch_lag_get_unused(ethsw);
+	lag->in_use = true;
+	lag->bond_dev = bond_dev;
+	lag->primary = port_priv;
+	rcu_assign_pointer(port_priv->lag, lag);
+}
+
+static bool dpaa2_switch_port_in_lag(struct ethsw_port_priv *port_priv,
+				     struct net_device *bond_dev)
+{
+	struct dpaa2_switch_lag *lag;
+
+	if (!port_priv)
+		return false;
+
+	lag = rtnl_dereference(port_priv->lag);
+	return lag && lag->bond_dev == bond_dev;
+}
+
+static int dpaa2_switch_set_lag_cfg(struct net_device *bond_dev, u8 lag_id,
+				    struct ethsw_core *ethsw)
+{
+	struct dpaa2_switch_lag *lag = &ethsw->lags[lag_id - 1];
+	struct ethsw_port_priv *primary, *port_priv;
+	struct ethsw_port_priv *new_primary = NULL;
+	struct dpsw_lag_cfg cfg = {0};
+	struct dpaa2_mac_addr *a;
+	u8 num_ifs = 0;
+	int err, i;
+
+	cfg.group_id = lag_id;
+
+	/* Determine the primary port. The caller clears ->lag on the port that
+	 * is leaving, so a NULL ->lag on the current primary means it is the
+	 * one leaving: elect the first remaining member as the new primary.
+	 * Otherwise keep the current primary.
+	 */
+	if (rtnl_dereference(lag->primary->lag)) {
+		primary = lag->primary;
+	} else {
+		primary = NULL;
+		for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+			if (dpaa2_switch_port_in_lag(ethsw->ports[i], bond_dev)) {
+				new_primary = ethsw->ports[i];
+				primary = new_primary;
+				break;
+			}
+		}
+	}
+
+	/* Build the interface list, always placing the primary first */
+	if (primary)
+		cfg.if_id[num_ifs++] = primary->idx;
+	for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+		port_priv = ethsw->ports[i];
+		if (port_priv == primary)
+			continue;
+		if (!dpaa2_switch_port_in_lag(port_priv, bond_dev))
+			continue;
+
+		cfg.if_id[num_ifs++] = port_priv->idx;
+	}
+	cfg.num_ifs = num_ifs;
+
+	/* No more interfaces under this LAG group, mark it as not in use. Wait
+	 * for a grace period so that any readers of the lag structure finished.
+	 */
+	if (!num_ifs) {
+		synchronize_net();
+
+		lag->bond_dev = NULL;
+		lag->primary = NULL;
+		lag->in_use = false;
+	}
+
+	/* When the primary changes, migrate the FDB entries from the old
+	 * primary to the new one: remove them before reconfiguring the LAG in
+	 * hardware and re-add them on the new primary afterwards. We do not
+	 * touch any refcounting since the intention is to change the HW entry,
+	 * not the parallel software tracking.
+	 */
+	if (new_primary) {
+		mutex_lock(&lag->fdb_lock);
+		list_for_each_entry(a, &lag->fdbs, list)
+			dpaa2_switch_port_fdb_del(lag->primary, a->addr);
+		mutex_unlock(&lag->fdb_lock);
+	}
+
+	err = dpsw_lag_set(ethsw->mc_io, 0, ethsw->dpsw_handle, &cfg);
+	if (err)
+		return err;
+
+	if (new_primary) {
+		mutex_lock(&lag->fdb_lock);
+		list_for_each_entry(a, &lag->fdbs, list) {
+			err = dpaa2_switch_port_fdb_add(new_primary, a->addr);
+			if (err)
+				netdev_err(new_primary->netdev, "Unable to migrate FDB\n");
+		}
+		mutex_unlock(&lag->fdb_lock);
+
+		synchronize_net();
+		lag->primary = new_primary;
+	}
+
+	return 0;
+}
+
+static int dpaa2_switch_port_bond_join(struct net_device *netdev,
+				       struct net_device *bond_dev,
+				       struct netdev_lag_upper_info *info,
+				       struct netlink_ext_ack *extack)
+{
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct net_device *bridge_dev;
+	struct dpaa2_switch_lag *lag;
+	int err = 0;
+	u8 lag_id;
+
+	/* Setup the port_priv->lag pointer for this switch port */
+	dpaa2_switch_port_set_lag_group(port_priv, bond_dev);
+
+	/* Create the LAG configuration and apply it in MC */
+	lag = rtnl_dereference(port_priv->lag);
+	lag_id = lag->id;
+	err = dpaa2_switch_set_lag_cfg(bond_dev, lag_id, ethsw);
+	if (err)
+		goto err_lag_cfg;
+
+	/* If the bond device is a switch port, join the bridge as well */
+	bridge_dev = netdev_master_upper_dev_get(bond_dev);
+	if (!bridge_dev || !netif_is_bridge_master(bridge_dev))
+		return 0;
+
+	err = dpaa2_switch_port_bridge_join(netdev, bridge_dev, extack);
+	if (err)
+		goto err_lag_cfg;
+
+	return err;
+
+err_lag_cfg:
+	rcu_assign_pointer(port_priv->lag, NULL);
+	dpaa2_switch_set_lag_cfg(bond_dev, lag_id, ethsw);
+
+	return err;
+}
+
+static int dpaa2_switch_port_bond_leave(struct net_device *netdev,
+					struct net_device *bond_dev)
+{
+	struct net_device *bridge_dev = netdev_master_upper_dev_get(bond_dev);
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	struct dpaa2_switch_lag *lag = rtnl_dereference(port_priv->lag);
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct net_device *brpdev;
+	bool learn_ena;
+	int err;
+
+	if (!lag)
+		return 0;
+
+	/* Recreate the LAG configuration for the LAG group that we left. */
+	rcu_assign_pointer(port_priv->lag, NULL);
+	dpaa2_switch_set_lag_cfg(bond_dev, lag->id, ethsw);
+
+	if (bridge_dev && netif_is_bridge_master(bridge_dev)) {
+		/* Make sure that the new primary inherits the learning state */
+		if (lag->primary) {
+			brpdev = dpaa2_switch_port_to_bridge_port(lag->primary);
+			learn_ena = br_port_flag_is_set(brpdev, BR_LEARNING);
+			err = dpaa2_switch_port_set_learning(lag->primary,
+							     learn_ena);
+			if (err)
+				return err;
+			lag->primary->learn_ena = learn_ena;
+		}
+
+		/* In case the bond is a bridge port, leave the upper bridge as
+		 * well.
+		 */
+		return dpaa2_switch_port_bridge_leave(netdev);
 	}
 
 	return 0;
@@ -2235,8 +2730,8 @@ static int dpaa2_switch_port_prechangeupper(struct net_device *netdev,
 					    struct netdev_notifier_changeupper_info *info)
 {
 	struct ethsw_port_priv *port_priv;
+	struct net_device *upper_dev, *br;
 	struct netlink_ext_ack *extack;
-	struct net_device *upper_dev;
 	int err;
 
 	if (!dpaa2_switch_port_dev_check(netdev))
@@ -2253,6 +2748,24 @@ static int dpaa2_switch_port_prechangeupper(struct net_device *netdev,
 
 		if (!info->linking)
 			dpaa2_switch_port_pre_bridge_leave(netdev);
+	} else if (netif_is_lag_master(upper_dev)) {
+		if (!info->linking) {
+			if (netif_is_bridge_port(upper_dev))
+				dpaa2_switch_port_pre_bridge_leave(netdev);
+			return 0;
+		}
+
+		if (netif_is_bridge_port(upper_dev)) {
+			br = netdev_master_upper_dev_get(upper_dev);
+			err = dpaa2_switch_prechangeupper_sanity_checks(netdev,
+									br,
+									extack);
+			if (err)
+				return err;
+		}
+
+		return dpaa2_switch_pre_lag_join(netdev, upper_dev,
+						 info->upper_info, extack);
 	} else if (is_vlan_dev(upper_dev)) {
 		port_priv = netdev_priv(netdev);
 		if (port_priv->fdb->bridge_dev) {
@@ -2284,6 +2797,80 @@ static int dpaa2_switch_port_changeupper(struct net_device *netdev,
 							     extack);
 		else
 			return dpaa2_switch_port_bridge_leave(netdev);
+	} else if (netif_is_lag_master(upper_dev)) {
+		if (info->linking)
+			return dpaa2_switch_port_bond_join(netdev, upper_dev,
+							   info->upper_info,
+							   extack);
+		else
+			return dpaa2_switch_port_bond_leave(netdev, upper_dev);
+	}
+
+	return 0;
+}
+
+static int
+dpaa2_switch_lag_prechangeupper(struct net_device *netdev,
+				struct netdev_notifier_changeupper_info *info)
+{
+	struct net_device *lower;
+	struct list_head *iter;
+	int err = 0;
+
+	if (!netif_is_lag_master(netdev))
+		return 0;
+
+	netdev_for_each_lower_dev(netdev, lower, iter) {
+		if (!dpaa2_switch_port_dev_check(lower))
+			continue;
+
+		err = dpaa2_switch_port_prechangeupper(lower, info);
+		if (err)
+			return err;
+	}
+
+	return err;
+}
+
+static int
+dpaa2_switch_lag_changeupper(struct net_device *netdev,
+			     struct netdev_notifier_changeupper_info *info)
+{
+	struct net_device *lower;
+	struct list_head *iter;
+	int err = 0;
+
+	if (!netif_is_lag_master(netdev))
+		return 0;
+
+	netdev_for_each_lower_dev(netdev, lower, iter) {
+		if (!dpaa2_switch_port_dev_check(lower))
+			continue;
+
+		err = dpaa2_switch_port_changeupper(lower, info);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int
+dpaa2_switch_port_changelowerstate(struct net_device *netdev,
+				   struct netdev_lag_lower_state_info *linfo)
+{
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	int err;
+
+	if (!rtnl_dereference(port_priv->lag))
+		return 0;
+
+	err = dpsw_if_set_lag_state(ethsw->mc_io, 0, ethsw->dpsw_handle,
+				    port_priv->idx, linfo->tx_enabled ? 1 : 0);
+	if (err) {
+		netdev_err(netdev, "dpsw_if_set_lag_state() = %d\n", err);
+		return err;
 	}
 
 	return 0;
@@ -2293,6 +2880,7 @@ static int dpaa2_switch_port_netdevice_event(struct notifier_block *nb,
 					     unsigned long event, void *ptr)
 {
 	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	struct netdev_notifier_changelowerstate_info *info;
 	int err = 0;
 
 	switch (event) {
@@ -2301,13 +2889,29 @@ static int dpaa2_switch_port_netdevice_event(struct notifier_block *nb,
 		if (err)
 			return notifier_from_errno(err);
 
+		err = dpaa2_switch_lag_prechangeupper(netdev, ptr);
+		if (err)
+			return notifier_from_errno(err);
+
 		break;
 	case NETDEV_CHANGEUPPER:
 		err = dpaa2_switch_port_changeupper(netdev, ptr);
 		if (err)
 			return notifier_from_errno(err);
 
+		err = dpaa2_switch_lag_changeupper(netdev, ptr);
+		if (err)
+			return notifier_from_errno(err);
+
 		break;
+	case NETDEV_CHANGELOWERSTATE:
+		info = ptr;
+		if (!dpaa2_switch_port_dev_check(netdev))
+			break;
+
+		err = dpaa2_switch_port_changelowerstate(netdev,
+							 info->lower_state_info);
+		return notifier_from_errno(err);
 	}
 
 	return NOTIFY_DONE;
@@ -2317,80 +2921,97 @@ struct ethsw_switchdev_event_work {
 	struct work_struct work;
 	struct switchdev_notifier_fdb_info fdb_info;
 	struct net_device *dev;
+	struct net_device *orig_dev;
 	unsigned long event;
+	u16 vid;
 };
 
 static void dpaa2_switch_event_work(struct work_struct *work)
 {
 	struct ethsw_switchdev_event_work *switchdev_work =
 		container_of(work, struct ethsw_switchdev_event_work, work);
+	struct net_device *orig_dev = switchdev_work->orig_dev;
 	struct net_device *dev = switchdev_work->dev;
+	struct ethsw_port_priv *port_priv = netdev_priv(dev);
 	struct switchdev_notifier_fdb_info *fdb_info;
+	struct dpaa2_switch_lag *lag;
 	int err;
 
-	rtnl_lock();
 	fdb_info = &switchdev_work->fdb_info;
 
+	/* The lag structures are freed only from dpaa2_switch_remove(), which
+	 * first flushes this workqueue, so the pointer stays valid for the
+	 * lifetime of the work item. Only the dereference needs the RCU
+	 * read-side lock; the FDB helpers below can sleep and must run outside
+	 * of it.
+	 */
+	rcu_read_lock();
+	lag = rcu_dereference(port_priv->lag);
+	rcu_read_unlock();
+
 	switch (switchdev_work->event) {
 	case SWITCHDEV_FDB_ADD_TO_DEVICE:
-		if (!fdb_info->added_by_user || fdb_info->is_local)
-			break;
-		if (is_unicast_ether_addr(fdb_info->addr))
-			err = dpaa2_switch_port_fdb_add_uc(netdev_priv(dev),
-							   fdb_info->addr);
+		if (lag)
+			err = dpaa2_switch_lag_fdb_add(lag, fdb_info->addr,
+						       switchdev_work->vid);
 		else
-			err = dpaa2_switch_port_fdb_add_mc(netdev_priv(dev),
-							   fdb_info->addr);
+			err = dpaa2_switch_port_fdb_add(port_priv,
+							fdb_info->addr);
 		if (err)
 			break;
 		fdb_info->offloaded = true;
-		call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, dev,
+		call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, orig_dev,
 					 &fdb_info->info, NULL);
 		break;
 	case SWITCHDEV_FDB_DEL_TO_DEVICE:
-		if (!fdb_info->added_by_user || fdb_info->is_local)
-			break;
-		if (is_unicast_ether_addr(fdb_info->addr))
-			dpaa2_switch_port_fdb_del_uc(netdev_priv(dev), fdb_info->addr);
+		if (lag)
+			dpaa2_switch_lag_fdb_del(lag, fdb_info->addr,
+						 switchdev_work->vid);
 		else
-			dpaa2_switch_port_fdb_del_mc(netdev_priv(dev), fdb_info->addr);
+			dpaa2_switch_port_fdb_del(port_priv, fdb_info->addr);
 		break;
 	}
 
-	rtnl_unlock();
 	kfree(switchdev_work->fdb_info.addr);
 	kfree(switchdev_work);
 	dev_put(dev);
+	dev_put(orig_dev);
 }
 
-/* Called under rcu_read_lock() */
-static int dpaa2_switch_port_event(struct notifier_block *nb,
-				   unsigned long event, void *ptr)
+static int
+dpaa2_switch_port_fdb_event(struct net_device *dev,
+			    struct net_device *orig_dev,
+			    unsigned long event, const void *ctx,
+			    const struct switchdev_notifier_fdb_info *fdb_info)
 {
-	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
 	struct ethsw_port_priv *port_priv = netdev_priv(dev);
 	struct ethsw_switchdev_event_work *switchdev_work;
-	struct switchdev_notifier_fdb_info *fdb_info = ptr;
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
 
-	if (event == SWITCHDEV_PORT_ATTR_SET)
-		return dpaa2_switch_port_attr_set_event(dev, ptr);
+	if (ctx && ctx != port_priv)
+		return 0;
 
-	if (!dpaa2_switch_port_dev_check(dev))
-		return NOTIFY_DONE;
+	/* For the moment, do nothing with entries towards foreign devices */
+	if (dpaa2_switch_foreign_dev_check(dev, orig_dev))
+		return 0;
+
+	if (!fdb_info->added_by_user || fdb_info->is_local)
+		return 0;
 
 	switchdev_work = kzalloc_obj(*switchdev_work, GFP_ATOMIC);
 	if (!switchdev_work)
-		return NOTIFY_BAD;
+		return -ENOMEM;
 
 	INIT_WORK(&switchdev_work->work, dpaa2_switch_event_work);
 	switchdev_work->dev = dev;
 	switchdev_work->event = event;
+	switchdev_work->orig_dev = orig_dev;
+	switchdev_work->vid = fdb_info->vid;
 
 	switch (event) {
 	case SWITCHDEV_FDB_ADD_TO_DEVICE:
 	case SWITCHDEV_FDB_DEL_TO_DEVICE:
-		memcpy(&switchdev_work->fdb_info, ptr,
+		memcpy(&switchdev_work->fdb_info, fdb_info,
 		       sizeof(switchdev_work->fdb_info));
 		switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC);
 		if (!switchdev_work->fdb_info.addr)
@@ -2401,52 +3022,61 @@ static int dpaa2_switch_port_event(struct notifier_block *nb,
 
 		/* Take a reference on the device to avoid being freed. */
 		dev_hold(dev);
+		dev_hold(orig_dev);
 		break;
 	default:
 		kfree(switchdev_work);
-		return NOTIFY_DONE;
+		return 0;
 	}
 
 	queue_work(ethsw->workqueue, &switchdev_work->work);
 
-	return NOTIFY_DONE;
+	return 0;
 
 err_addr_alloc:
 	kfree(switchdev_work);
-	return NOTIFY_BAD;
+	return -ENOMEM;
 }
 
-static int dpaa2_switch_port_obj_event(unsigned long event,
-				       struct net_device *netdev,
-				       struct switchdev_notifier_port_obj_info *port_obj_info)
+/* Called under rcu_read_lock() */
+static int dpaa2_switch_port_event(struct notifier_block *nb,
+				   unsigned long event, void *ptr)
 {
-	int err = -EOPNOTSUPP;
-
-	if (!dpaa2_switch_port_dev_check(netdev))
-		return NOTIFY_DONE;
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	int err;
 
 	switch (event) {
-	case SWITCHDEV_PORT_OBJ_ADD:
-		err = dpaa2_switch_port_obj_add(netdev, port_obj_info->obj);
-		break;
-	case SWITCHDEV_PORT_OBJ_DEL:
-		err = dpaa2_switch_port_obj_del(netdev, port_obj_info->obj);
-		break;
+	case SWITCHDEV_PORT_ATTR_SET:
+		return dpaa2_switch_port_attr_set_event(dev, ptr);
+	case SWITCHDEV_FDB_ADD_TO_DEVICE:
+	case SWITCHDEV_FDB_DEL_TO_DEVICE:
+		err = switchdev_handle_fdb_event_to_device(dev, event, ptr,
+							   dpaa2_switch_port_dev_check,
+							   dpaa2_switch_foreign_dev_check,
+							   dpaa2_switch_port_fdb_event);
+		return notifier_from_errno(err);
+	default:
+		return NOTIFY_DONE;
 	}
-
-	port_obj_info->handled = true;
-	return notifier_from_errno(err);
 }
 
 static int dpaa2_switch_port_blocking_event(struct notifier_block *nb,
 					    unsigned long event, void *ptr)
 {
 	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	int err;
 
 	switch (event) {
 	case SWITCHDEV_PORT_OBJ_ADD:
+		err = switchdev_handle_port_obj_add(dev, ptr,
+						    dpaa2_switch_port_dev_check,
+						    dpaa2_switch_port_obj_add);
+		return notifier_from_errno(err);
 	case SWITCHDEV_PORT_OBJ_DEL:
-		return dpaa2_switch_port_obj_event(event, dev, ptr);
+		err = switchdev_handle_port_obj_del(dev, ptr,
+						    dpaa2_switch_port_dev_check,
+						    dpaa2_switch_port_obj_del);
+		return notifier_from_errno(err);
 	case SWITCHDEV_PORT_ATTR_SET:
 		return dpaa2_switch_port_attr_set_event(dev, ptr);
 	}
@@ -2491,19 +3121,22 @@ static void dpaa2_switch_rx(struct dpaa2_switch_fq *fq,
 	dma_addr_t addr = dpaa2_fd_get_addr(fd);
 	struct ethsw_core *ethsw = fq->ethsw;
 	struct ethsw_port_priv *port_priv;
+	struct dpaa2_switch_lag *lag;
 	struct net_device *netdev;
 	struct vlan_ethhdr *hdr;
 	struct sk_buff *skb;
 	u16 vlan_tci, vid;
 	int if_id, err;
 	void *vaddr;
+	u64 flc;
 
 	vaddr = dpaa2_iova_to_virt(ethsw->iommu_domain, addr);
 	dma_unmap_page(ethsw->dev, addr, DPAA2_SWITCH_RX_BUF_SIZE,
 		       DMA_FROM_DEVICE);
 
 	/* get switch ingress interface ID */
-	if_id = upper_32_bits(dpaa2_fd_get_flc(fd)) & 0x0000FFFF;
+	flc = dpaa2_fd_get_flc(fd);
+	if_id = DPAA2_ETHSW_FLC_IF_ID(flc);
 	if (if_id >= ethsw->sw_attr.num_ifs) {
 		dev_err(ethsw->dev, "Frame received from unknown interface!\n");
 		goto err_free_fd;
@@ -2542,12 +3175,20 @@ static void dpaa2_switch_rx(struct dpaa2_switch_fq *fq,
 		}
 	}
 
-	skb->dev = netdev;
+	rcu_read_lock();
+
+	lag = rcu_dereference(port_priv->lag);
+	if (DPAA2_ETHSW_FLC_IMPRECISE_IF_ID(flc) && lag)
+		skb->dev = lag->bond_dev;
+	else
+		skb->dev = netdev;
 	skb->protocol = eth_type_trans(skb, skb->dev);
 
 	/* Setup the offload_fwd_mark only if the port is under a bridge */
 	skb->offload_fwd_mark = !!(port_priv->fdb->bridge_dev);
 
+	rcu_read_unlock();
+
 	netif_receive_skb(skb);
 
 	return;
@@ -2562,6 +3203,9 @@ static void dpaa2_switch_detect_features(struct ethsw_core *ethsw)
 
 	if (ethsw->major > 8 || (ethsw->major == 8 && ethsw->minor >= 6))
 		ethsw->features |= ETHSW_FEATURE_MAC_ADDR;
+
+	if (ethsw->major > 8 || (ethsw->major == 8 && ethsw->minor >= 13))
+		ethsw->features |= ETHSW_FEATURE_LAG_OFFLOAD;
 }
 
 static int dpaa2_switch_setup_fqs(struct ethsw_core *ethsw)
@@ -3196,17 +3840,15 @@ err_close:
 	return err;
 }
 
-/* Add an ACL to redirect frames with specific destination MAC address to
- * control interface
- */
+/* Add an ACL to redirect frames to control interface based on the dst MAC */
 static int dpaa2_switch_port_trap_mac_addr(struct ethsw_port_priv *port_priv,
-					   const char *mac)
+					   const u8 *mac, const u8 *mask)
 {
 	struct dpaa2_switch_acl_entry acl_entry = {0};
 
 	/* Match on the destination MAC address */
 	ether_addr_copy(acl_entry.key.match.l2_dest_mac, mac);
-	eth_broadcast_addr(acl_entry.key.mask.l2_dest_mac);
+	ether_addr_copy(acl_entry.key.mask.l2_dest_mac, mask);
 
 	/* Trap to CPU */
 	acl_entry.cfg.precedence = 0;
@@ -3217,7 +3859,8 @@ static int dpaa2_switch_port_trap_mac_addr(struct ethsw_port_priv *port_priv,
 
 static int dpaa2_switch_port_init(struct ethsw_port_priv *port_priv, u16 port)
 {
-	const char stpa[ETH_ALEN] = {0x01, 0x80, 0xc2, 0x00, 0x00, 0x00};
+	const u8 ll_mac[ETH_ALEN] = {0x01, 0x80, 0xc2, 0x00, 0x00, 0x00};
+	const u8 ll_mask[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xf0};
 	struct switchdev_obj_port_vlan vlan = {
 		.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
 		.vid = DEFAULT_VLAN_ID,
@@ -3292,7 +3935,7 @@ static int dpaa2_switch_port_init(struct ethsw_port_priv *port_priv, u16 port)
 	if (err)
 		return err;
 
-	err = dpaa2_switch_port_trap_mac_addr(port_priv, stpa);
+	err = dpaa2_switch_port_trap_mac_addr(port_priv, ll_mac, ll_mask);
 	if (err)
 		return err;
 
@@ -3332,6 +3975,9 @@ static void dpaa2_switch_remove(struct fsl_mc_device *sw_dev)
 	dev = &sw_dev->dev;
 	ethsw = dev_get_drvdata(dev);
 
+	/* Make sure that all events were handled before we kfree anything */
+	flush_workqueue(ethsw->workqueue);
+
 	dpaa2_switch_teardown_irqs(sw_dev);
 
 	dpsw_disable(ethsw->mc_io, 0, ethsw->dpsw_handle);
@@ -3345,12 +3991,15 @@ static void dpaa2_switch_remove(struct fsl_mc_device *sw_dev)
 	for (i = 0; i < DPAA2_SWITCH_RX_NUM_FQS; i++)
 		netif_napi_del(&ethsw->fq[i].napi);
 
-	for (i = 0; i < ethsw->sw_attr.num_ifs; i++)
+	for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
 		dpaa2_switch_remove_port(ethsw, i);
+		mutex_destroy(&ethsw->lags[i].fdb_lock);
+	}
 
 	kfree(ethsw->fdbs);
 	kfree(ethsw->filter_blocks);
 	kfree(ethsw->ports);
+	kfree(ethsw->lags);
 
 	dpaa2_switch_teardown(sw_dev);
 
@@ -3378,6 +4027,7 @@ static int dpaa2_switch_probe_port(struct ethsw_core *ethsw,
 	port_priv = netdev_priv(port_netdev);
 	port_priv->netdev = port_netdev;
 	port_priv->ethsw_data = ethsw;
+	rcu_assign_pointer(port_priv->lag, NULL);
 
 	mutex_init(&port_priv->mac_lock);
 
@@ -3485,6 +4135,21 @@ static int dpaa2_switch_probe(struct fsl_mc_device *sw_dev)
 		goto err_free_fdbs;
 	}
 
+	ethsw->lags = kcalloc(ethsw->sw_attr.num_ifs, sizeof(*ethsw->lags),
+			      GFP_KERNEL);
+	if (!ethsw->lags) {
+		err = -ENOMEM;
+		goto err_free_filter;
+	}
+	for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+		ethsw->lags[i].bond_dev = NULL;
+		ethsw->lags[i].ethsw = ethsw;
+		ethsw->lags[i].id = i + 1;
+		ethsw->lags[i].in_use = 0;
+		mutex_init(&ethsw->lags[i].fdb_lock);
+		INIT_LIST_HEAD(&ethsw->lags[i].fdbs);
+	}
+
 	for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
 		err = dpaa2_switch_probe_port(ethsw, i);
 		if (err)
@@ -3531,6 +4196,10 @@ err_stop:
 err_free_netdev:
 	for (i--; i >= 0; i--)
 		dpaa2_switch_remove_port(ethsw, i);
+	for (i = 0; i < ethsw->sw_attr.num_ifs; i++)
+		mutex_destroy(&ethsw->lags[i].fdb_lock);
+	kfree(ethsw->lags);
+err_free_filter:
 	kfree(ethsw->filter_blocks);
 err_free_fdbs:
 	kfree(ethsw->fdbs);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h
index 42b3ca73f55d..63b702b0000c 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h
@@ -41,7 +41,8 @@
 #define ETHSW_MAX_FRAME_LENGTH	(DPAA2_MFL - VLAN_ETH_HLEN - ETH_FCS_LEN)
 #define ETHSW_L2_MAX_FRM(mtu)	((mtu) + VLAN_ETH_HLEN + ETH_FCS_LEN)
 
-#define ETHSW_FEATURE_MAC_ADDR	BIT(0)
+#define ETHSW_FEATURE_MAC_ADDR		BIT(0)
+#define ETHSW_FEATURE_LAG_OFFLOAD	BIT(1)
 
 /* Number of receive queues (one RX and one TX_CONF) */
 #define DPAA2_SWITCH_RX_NUM_FQS	2
@@ -86,6 +87,9 @@
 
 #define DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE	256
 
+#define DPAA2_ETHSW_FLC_IF_ID(flc)		(((flc) >> 32) & GENMASK(15, 0))
+#define DPAA2_ETHSW_FLC_IMPRECISE_IF_ID(flc)	((flc) & BIT_ULL(63))
+
 extern const struct ethtool_ops dpaa2_switch_port_ethtool_ops;
 
 struct ethsw_core;
@@ -99,12 +103,30 @@ struct dpaa2_switch_fq {
 	u32 fqid;
 };
 
+struct dpaa2_mac_addr {
+	unsigned char addr[ETH_ALEN];
+	u16 vid;
+	refcount_t refcount;
+	struct list_head list;
+};
+
 struct dpaa2_switch_fdb {
 	struct net_device	*bridge_dev;
 	u16			fdb_id;
 	bool			in_use;
 };
 
+struct dpaa2_switch_lag {
+	struct ethsw_core	*ethsw;
+	struct net_device	*bond_dev;
+	bool			in_use;
+	u8			id;
+	struct ethsw_port_priv	*primary;
+	/* Protects the list of fdbs installed on this LAG */
+	struct mutex		fdb_lock;
+	struct list_head	fdbs;
+};
+
 struct dpaa2_switch_acl_entry {
 	struct list_head	list;
 	u16			prio;
@@ -163,6 +185,8 @@ struct ethsw_port_priv {
 	struct dpaa2_mac	*mac;
 	/* Protects against changes to port_priv->mac */
 	struct mutex		mac_lock;
+
+	struct dpaa2_switch_lag __rcu *lag;
 };
 
 /* Switch data */
@@ -190,6 +214,8 @@ struct ethsw_core {
 	struct dpaa2_switch_fdb		*fdbs;
 	struct dpaa2_switch_filter_block *filter_blocks;
 	u16				mirror_port;
+
+	struct dpaa2_switch_lag		*lags;
 };
 
 static inline int dpaa2_switch_get_index(struct ethsw_core *ethsw,
@@ -274,4 +300,18 @@ int dpaa2_switch_block_offload_mirror(struct dpaa2_switch_filter_block *block,
 
 int dpaa2_switch_block_unoffload_mirror(struct dpaa2_switch_filter_block *block,
 					struct ethsw_port_priv *port_priv);
+
+static inline bool
+dpaa2_switch_port_offloads_bridge_port(struct ethsw_port_priv *port_priv,
+				       const struct net_device *dev)
+{
+	struct dpaa2_switch_lag *lag = rcu_dereference_rtnl(port_priv->lag);
+
+	if (lag && lag->bond_dev == dev)
+		return true;
+	if (port_priv->netdev == dev)
+		return true;
+	return false;
+}
+
 #endif	/* __ETHSW_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h
index 397d55f2bd99..9a2055c64983 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h
@@ -12,7 +12,7 @@
 
 /* DPSW Version */
 #define DPSW_VER_MAJOR		8
-#define DPSW_VER_MINOR		9
+#define DPSW_VER_MINOR		13
 
 #define DPSW_CMD_BASE_VERSION	1
 #define DPSW_CMD_VERSION_2	2
@@ -92,11 +92,14 @@
 #define DPSW_CMDID_CTRL_IF_SET_POOLS        DPSW_CMD_ID(0x0A1)
 #define DPSW_CMDID_CTRL_IF_ENABLE           DPSW_CMD_ID(0x0A2)
 #define DPSW_CMDID_CTRL_IF_DISABLE          DPSW_CMD_ID(0x0A3)
+#define DPSW_CMDID_SET_LAG                  DPSW_CMD_V2(0x0A4)
 #define DPSW_CMDID_CTRL_IF_SET_QUEUE        DPSW_CMD_ID(0x0A6)
 
 #define DPSW_CMDID_SET_EGRESS_FLOOD         DPSW_CMD_ID(0x0AC)
 #define DPSW_CMDID_IF_SET_LEARNING_MODE     DPSW_CMD_ID(0x0AD)
 
+#define DPSW_CMDID_IF_SET_LAG_STATE         DPSW_CMD_ID(0x0B0)
+
 /* Macros for accessing command fields smaller than 1byte */
 #define DPSW_MASK(field)        \
 	GENMASK(DPSW_##field##_SHIFT + DPSW_##field##_SIZE - 1, \
@@ -552,5 +555,18 @@ struct dpsw_cmd_if_reflection {
 	/* only 2 bits from the LSB */
 	u8 filter;
 };
+
+struct dpsw_cmd_lag {
+	u8 group_id;
+	u8 num_ifs;
+	u8 pad[6];
+	u8 if_id[DPSW_MAX_LAG_IFS];
+	u8 phase;
+};
+
+struct dpsw_cmd_if_set_lag_state {
+	__le16 if_id;
+	u8 tx_enabled;
+};
 #pragma pack(pop)
 #endif /* __FSL_DPSW_CMD_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpsw.c b/drivers/net/ethernet/freescale/dpaa2/dpsw.c
index ab921d75deb2..f75cbdce42ba 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpsw.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpsw.c
@@ -1659,3 +1659,63 @@ int dpsw_if_remove_reflection(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
 
 	return mc_send_command(mc_io, &cmd);
 }
+
+/**
+ * dpsw_lag_set() - Set LAG configuration
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPSW object
+ * @cfg:	pointer to LAG configuration
+ *
+ * Return:   '0' on Success; Error code otherwise.
+ */
+int dpsw_lag_set(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+		 const struct dpsw_lag_cfg *cfg)
+{
+	struct fsl_mc_command cmd = { 0 };
+	struct dpsw_cmd_lag *cmd_params;
+	int i = 0;
+
+	cmd.header = mc_encode_cmd_header(DPSW_CMDID_SET_LAG, cmd_flags, token);
+
+	if (cfg->num_ifs > DPSW_MAX_LAG_IFS)
+		return -EOPNOTSUPP;
+
+	cmd_params = (struct dpsw_cmd_lag *)cmd.params;
+	cmd_params->group_id = cfg->group_id;
+	cmd_params->num_ifs = cfg->num_ifs;
+	cmd_params->phase = cfg->phase;
+
+	for (i = 0; i < cfg->num_ifs; i++)
+		cmd_params->if_id[i] = cfg->if_id[i];
+
+	return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_if_set_lag_state() - Change per port LAG state
+ * @mc_io:      Pointer to MC portal's I/O object
+ * @cmd_flags:  Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:      Token of DPSW object
+ * @if_id:      ID of the switch interface
+ * @tx_enabled: Value of the per port LAG state
+ *     - 0 if the interface will not be active as part of the LAG group
+ *     - 1 if the interface will be active in the LAG group
+ *
+ * Return:   '0' on Success; Error code otherwise.
+ */
+int dpsw_if_set_lag_state(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+			  u16 if_id, u8 tx_enabled)
+{
+	struct dpsw_cmd_if_set_lag_state *cmd_params;
+	struct fsl_mc_command cmd = { 0 };
+
+	cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_SET_LAG_STATE,
+					  cmd_flags, token);
+
+	cmd_params = (struct dpsw_cmd_if_set_lag_state *)cmd.params;
+	cmd_params->if_id = cpu_to_le16(if_id);
+	cmd_params->tx_enabled = tx_enabled;
+
+	return mc_send_command(mc_io, &cmd);
+}
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpsw.h b/drivers/net/ethernet/freescale/dpaa2/dpsw.h
index b90bd363f47a..89f0267de8e9 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpsw.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpsw.h
@@ -20,6 +20,8 @@ struct fsl_mc_io;
 
 #define DPSW_MAX_IF		64
 
+#define DPSW_MAX_LAG_IFS	8
+
 int dpsw_open(struct fsl_mc_io *mc_io, u32 cmd_flags, int dpsw_id, u16 *token);
 
 int dpsw_close(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token);
@@ -788,4 +790,32 @@ int dpsw_if_add_reflection(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
 
 int dpsw_if_remove_reflection(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
 			      u16 if_id, const struct dpsw_reflection_cfg *cfg);
+
+/* Link Aggregation Group configuration */
+
+#define DPSW_LAG_SET_PHASE_APPLY 0
+#define DPSW_LAG_SET_PHASE_CHECK 1
+
+/**
+ * struct dpsw_lag_cfg - Configuration structure for a LAG group
+ * @group_id: Link aggregation group ID. Valid values are in the
+ * [1, DPSW_MAX_LAG_IFS] range.
+ * @num_ifs: Number of interfaces in this LAG group, valid range is
+ * [0, DPSW_MAX_LAG_IFS].
+ * @if_id: Array containing the interface IDs of the ports part of a LAG group
+ * @phase: Use DPSW_LAG_SET_PHASE_APPLY for LAG configuration processing or
+ * DPSW_LAG_SET_PHASE_CHECK for LAG configuration validation.
+ */
+struct dpsw_lag_cfg {
+	u8 group_id;
+	u8 num_ifs;
+	u8 if_id[DPSW_MAX_LAG_IFS];
+	u8 phase;
+};
+
+int dpsw_lag_set(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+		 const struct dpsw_lag_cfg *cfg);
+
+int dpsw_if_set_lag_state(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+			  u16 if_id, u8 tx_enabled);
 #endif /* __FSL_DPSW_H */
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
index 0ae314994676..4382af937e2e 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
@@ -155,6 +155,7 @@ netdev_tx_t hbg_net_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	buffer->skb = skb;
 	buffer->skb_len = skb->len;
 	if (unlikely(hbg_dma_map(buffer))) {
+		buffer->skb = NULL;
 		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index 635b3a95dd82..3c4e4e8ca140 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -563,7 +563,7 @@ u32 hns_rcb_get_rx_coalesced_frames(
 u32 hns_rcb_get_tx_coalesced_frames(
 	struct rcb_common_cb *rcb_common, u32 port_idx)
 {
-	u64 reg;
+	u32 reg;
 
 	reg = RCB_CFG_PKTLINE_REG + (port_idx + HNS_RCB_TX_PKTLINE_OFFSET) * 4;
 	return dsaf_read_dev(rcb_common, reg);
@@ -634,7 +634,7 @@ int hns_rcb_set_tx_coalesced_frames(
 {
 	u32 old_waterline =
 		hns_rcb_get_tx_coalesced_frames(rcb_common, port_idx);
-	u64 reg;
+	u32 reg;
 
 	if (coalesced_frames == old_waterline)
 		return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index a8798eecd9fb..4286af9239b0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -602,6 +602,10 @@ typedef int (*read_func)(struct seq_file *s, void *data);
  *   Config wake on lan
  * dbg_get_read_func
  *   Return the read func for debugfs seq file
+ * set_pfc_prevention_tout
+ *   Set PFC storm prevention timeout
+ * get_pfc_prevention_tout
+ *   Get PFC storm prevention timeout
  */
 struct hnae3_ae_ops {
 	int (*init_ae_dev)(struct hnae3_ae_dev *ae_dev);
@@ -810,6 +814,8 @@ struct hnae3_ae_ops {
 	int (*hwtstamp_set)(struct hnae3_handle *handle,
 			    struct kernel_hwtstamp_config *config,
 			    struct netlink_ext_ack *extack);
+	int (*set_pfc_prevention_tout)(struct hnae3_handle *handle, u16 times);
+	int (*get_pfc_prevention_tout)(struct hnae3_handle *handle, u16 *times);
 };
 
 struct hnae3_dcb_ops {
@@ -891,6 +897,14 @@ struct hnae3_roce_private_info {
 	unsigned long state;
 };
 
+struct hnae3_pfc_storm_para {
+	u32 dir;
+	u32 enable;
+	u32 period_ms;
+	u32 times;
+	u32 recovery_period_ms;
+};
+
 #define HNAE3_SUPPORT_APP_LOOPBACK    BIT(0)
 #define HNAE3_SUPPORT_PHY_LOOPBACK    BIT(1)
 #define HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK	BIT(2)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h
index 2c2a2f1e0d7a..6dde07dde1e8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h
@@ -314,6 +314,9 @@ enum hclge_opcode_type {
 
 	/* Query link diagnosis info command */
 	HCLGE_OPC_QUERY_LINK_DIAGNOSIS	= 0x702A,
+
+	/* Config pause storm param command */
+	HCLGE_OPC_CFG_PAUSE_STORM_PARA = 0x7019,
 };
 
 enum hclge_comm_cmd_return_status {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 442f15476af3..e7318f236315 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -1895,6 +1895,12 @@ static int hns3_get_tunable(struct net_device *netdev,
 	case ETHTOOL_TX_COPYBREAK_BUF_SIZE:
 		*(u32 *)data = h->kinfo.tx_spare_buf_size;
 		break;
+	case ETHTOOL_PFC_PREVENTION_TOUT:
+		if (!h->ae_algo->ops->get_pfc_prevention_tout)
+			return -EOPNOTSUPP;
+
+		ret = h->ae_algo->ops->get_pfc_prevention_tout(h, (u16 *)data);
+		break;
 	default:
 		ret = -EOPNOTSUPP;
 		break;
@@ -2021,6 +2027,12 @@ static int hns3_set_tunable(struct net_device *netdev,
 				    priv->ring->tx_spare->len);
 
 		break;
+	case ETHTOOL_PFC_PREVENTION_TOUT:
+		if (!h->ae_algo->ops->set_pfc_prevention_tout)
+			return -EOPNOTSUPP;
+
+		ret = h->ae_algo->ops->set_pfc_prevention_tout(h, *(u16 *)data);
+		break;
 	default:
 		ret = -EOPNOTSUPP;
 		break;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 4ce92ddefcde..1c029dc32ab8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -890,6 +890,15 @@ struct hclge_query_wol_supported_cmd {
 	u8 rsv[20];
 };
 
+struct hclge_pfc_storm_para_cmd {
+	__le32 dir;
+	__le32 enable;
+	__le32 period_ms;
+	__le32 times;
+	__le32 recovery_period_ms;
+	__le32 rsv;
+};
+
 struct hclge_hw;
 int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index fc8587c80813..a08d8a35aef9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -3524,6 +3524,122 @@ static int hclge_set_vf_link_state(struct hnae3_handle *handle, int vf,
 	return ret;
 }
 
+static int hclge_set_pfc_storm_para(struct hclge_dev *hdev,
+				    struct hnae3_pfc_storm_para *para)
+{
+	struct hclge_pfc_storm_para_cmd *para_cmd;
+	struct hclge_desc desc;
+	int ret;
+
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3)
+		return -EOPNOTSUPP;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_PAUSE_STORM_PARA,
+				   false);
+	para_cmd = (struct hclge_pfc_storm_para_cmd *)desc.data;
+	para_cmd->dir = cpu_to_le32(para->dir);
+	para_cmd->enable = cpu_to_le32(para->enable);
+	para_cmd->period_ms = cpu_to_le32(para->period_ms);
+	para_cmd->times = cpu_to_le32(para->times);
+	para_cmd->recovery_period_ms = cpu_to_le32(para->recovery_period_ms);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"failed to set pfc storm para, ret = %d\n", ret);
+	return ret;
+}
+
+static int hclge_get_pfc_storm_para(struct hclge_dev *hdev,
+				    struct hnae3_pfc_storm_para *para)
+{
+	struct hclge_pfc_storm_para_cmd *para_cmd;
+	struct hclge_desc desc;
+	int ret;
+
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3)
+		return -EOPNOTSUPP;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_PAUSE_STORM_PARA, true);
+	para_cmd = (struct hclge_pfc_storm_para_cmd *)desc.data;
+	para_cmd->dir = cpu_to_le32(para->dir);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get pfc storm para, ret = %d\n", ret);
+		return ret;
+	}
+
+	para->enable = le32_to_cpu(para_cmd->enable);
+	para->period_ms = le32_to_cpu(para_cmd->period_ms);
+	para->times = le32_to_cpu(para_cmd->times);
+	para->recovery_period_ms = le32_to_cpu(para_cmd->recovery_period_ms);
+
+	return 0;
+}
+
+static int hclge_enable_pfc_storm_prevent(struct hclge_dev *hdev,
+					  int dir, bool enable)
+{
+	struct hnae3_pfc_storm_para para = {0};
+	int ret;
+
+	para.dir = dir;
+	ret = hclge_get_pfc_storm_para(hdev, &para);
+	if (ret)
+		return ret;
+
+	para.enable = enable;
+	return hclge_set_pfc_storm_para(hdev, &para);
+}
+
+static int hclge_set_pfc_prevention_tout(struct hnae3_handle *h, u16 times)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+	struct hnae3_pfc_storm_para para;
+	int ret;
+
+	if (times > HCLGE_MAX_PFC_PREVENTION_TOUT) {
+		dev_err(&hdev->pdev->dev,
+			"times %u should be no more than %u!\n",
+			times, HCLGE_MAX_PFC_PREVENTION_TOUT);
+		return -EINVAL;
+	}
+
+	para.dir = HCLGE_DIR_TX;
+	ret = hclge_get_pfc_storm_para(hdev, &para);
+	if (ret)
+		return ret;
+
+	para.enable = times ? 1 : 0;
+	para.times = (u32)times;
+	ret = hclge_set_pfc_storm_para(hdev, &para);
+	if (ret)
+		return ret;
+
+	hdev->pfc_prevention_tout = times;
+
+	return 0;
+}
+
+static int hclge_get_pfc_prevention_tout(struct hnae3_handle *h, u16 *times)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+	struct hnae3_pfc_storm_para para;
+	int ret;
+
+	para.dir = HCLGE_DIR_TX;
+	ret = hclge_get_pfc_storm_para(hdev, &para);
+	if (ret)
+		return ret;
+
+	*times = para.enable ? (u16)para.times : 0;
+
+	return 0;
+}
+
 static void hclge_set_reset_pending(struct hclge_dev *hdev,
 				    enum hnae3_reset_type reset_type)
 {
@@ -4317,6 +4433,26 @@ static int hclge_reset_prepare(struct hclge_dev *hdev)
 	return hclge_reset_prepare_wait(hdev);
 }
 
+static void hclge_restore_pfc_storm_prevention_tout(struct hclge_dev *hdev)
+{
+	struct hnae3_handle *handle = &hdev->vport[0].nic;
+	int ret;
+
+	ret = hclge_enable_pfc_storm_prevent(hdev, HCLGE_DIR_RX, false);
+	if (ret == -EOPNOTSUPP)
+		return;
+	else if (ret)
+		dev_warn(&hdev->pdev->dev,
+			 "failed to disable rx pfc storm prevent, ret = %d\n",
+			 ret);
+
+	ret = hclge_set_pfc_prevention_tout(handle, hdev->pfc_prevention_tout);
+	if (ret)
+		dev_warn(&hdev->pdev->dev,
+			 "failed to set tx pfc storm prevent, ret = %d\n",
+			 ret);
+}
+
 static int hclge_reset_rebuild(struct hclge_dev *hdev)
 {
 	int ret;
@@ -9278,6 +9414,32 @@ static int hclge_init_wol(struct hclge_dev *hdev)
 	return hclge_update_wol(hdev);
 }
 
+static void hclge_init_pfc_prevention_tout(struct hclge_dev *hdev)
+{
+	struct hnae3_handle *handle = &hdev->vport[0].nic;
+	u16 times;
+	int ret;
+
+	ret = hclge_enable_pfc_storm_prevent(hdev, HCLGE_DIR_RX, false);
+	if (ret == -EOPNOTSUPP)
+		return;
+	else if (ret)
+		dev_warn(&hdev->pdev->dev,
+			 "failed to disable rx pfc storm prevent, ret = %d\n",
+			 ret);
+
+	ret = hclge_get_pfc_prevention_tout(handle, &times);
+	if (ret) {
+		dev_warn(&hdev->pdev->dev,
+			 "failed to get tx pfc prevention timeout, ret = %d\n",
+			 ret);
+		times = HCLGE_DEFAULT_PFC_PREVENTION_TOUT;
+	}
+
+	hdev->pfc_prevention_tout = times;
+	hdev->pfc_prevention_tout_default = times;
+}
+
 static void hclge_get_wol(struct hnae3_handle *handle,
 			  struct ethtool_wolinfo *wol)
 {
@@ -9547,6 +9709,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		dev_warn(&pdev->dev,
 			 "failed to wake on lan init, ret = %d\n", ret);
 
+	hclge_init_pfc_prevention_tout(hdev);
+
 	ret = hclge_devlink_init(hdev);
 	if (ret)
 		goto err_ptp_uninit;
@@ -9946,6 +10110,8 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 		dev_warn(&pdev->dev,
 			 "failed to update wol config, ret = %d\n", ret);
 
+	hclge_restore_pfc_storm_prevention_tout(hdev);
+
 	dev_info(&pdev->dev, "Reset done, %s driver initialization finished.\n",
 		 HCLGE_DRIVER_NAME);
 
@@ -9977,6 +10143,10 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hclge_config_nic_hw_error(hdev, false);
 	hclge_config_rocee_ras_interrupt(hdev, false);
 
+	/* Restore hw default values for the next initialization */
+	hclge_set_pfc_prevention_tout(&hdev->vport->nic,
+				      hdev->pfc_prevention_tout_default);
+
 	hclge_comm_cmd_uninit(hdev->ae_dev, &hdev->hw.hw);
 	hclge_misc_irq_uninit(hdev);
 	hclge_devlink_uninit(hdev);
@@ -10539,6 +10709,8 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_wol = hclge_set_wol,
 	.hwtstamp_get = hclge_ptp_get_cfg,
 	.hwtstamp_set = hclge_ptp_set_cfg,
+	.set_pfc_prevention_tout = hclge_set_pfc_prevention_tout,
+	.get_pfc_prevention_tout = hclge_get_pfc_prevention_tout,
 };
 
 static struct hnae3_ae_algo ae_algo = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 7419481422c3..0cee8947f6b4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -346,6 +346,11 @@ enum hclge_link_fail_code {
 #define HCLGE_LINK_STATUS_DOWN 0
 #define HCLGE_LINK_STATUS_UP   1
 
+#define HCLGE_DIR_RX 0
+#define HCLGE_DIR_TX 1
+#define HCLGE_MAX_PFC_PREVENTION_TOUT		2000
+#define HCLGE_DEFAULT_PFC_PREVENTION_TOUT	1000
+
 #define HCLGE_PG_NUM		4
 #define HCLGE_SCH_MODE_SP	0
 #define HCLGE_SCH_MODE_DWRR	1
@@ -898,6 +903,8 @@ struct hclge_dev {
 	u16 vf_rss_size_max;		/* HW defined VF max RSS task queue */
 	u16 pf_rss_size_max;		/* HW defined PF max RSS task queue */
 	u32 tx_spare_buf_size;		/* HW defined TX spare buffer size */
+	u16 pfc_prevention_tout;	/* User config, restored after reset */
+	u16 pfc_prevention_tout_default; /* HW default, to avoid stale state */
 
 	u16 fdir_pf_filter_count; /* Num of guaranteed filters for this PF */
 	u16 num_alloc_vport;		/* Num vports this driver supports */
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c
index 9306bf0020ca..5739ecb08d0d 100644
--- a/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c
@@ -578,8 +578,6 @@ static netdev_tx_t hinic3_send_one_skb(struct sk_buff *skb,
 		*wqe_combo.task = task;
 
 	tx_info = &txq->tx_info[pi];
-	tx_info->skb = skb;
-	tx_info->wqebb_cnt = wqebb_cnt;
 
 	err = hinic3_tx_map_skb(netdev, skb, txq, tx_info, &wqe_combo);
 	if (err) {
@@ -589,6 +587,9 @@ static netdev_tx_t hinic3_send_one_skb(struct sk_buff *skb,
 		goto err_drop_pkt;
 	}
 
+	tx_info->skb = skb;
+	tx_info->wqebb_cnt = wqebb_cnt;
+
 	netif_subqueue_sent(netdev, txq->sq->q_id, skb->len);
 	netif_subqueue_maybe_stop(netdev, txq->sq->q_id,
 				  hinic3_wq_free_wqebbs(&txq->sq->wq),
diff --git a/drivers/net/ethernet/ibm/Kconfig b/drivers/net/ethernet/ibm/Kconfig
index 4f4b23465c47..8e55faac2035 100644
--- a/drivers/net/ethernet/ibm/Kconfig
+++ b/drivers/net/ethernet/ibm/Kconfig
@@ -42,15 +42,6 @@ config IBMVETH_KUNIT_TEST
 
 source "drivers/net/ethernet/ibm/emac/Kconfig"
 
-config EHEA
-	tristate "eHEA Ethernet support"
-	depends on IBMEBUS && SPARSEMEM
-	help
-	  This driver supports the IBM pSeries eHEA ethernet adapter.
-
-	  To compile the driver as a module, choose M here. The module
-	  will be called ehea.
-
 config IBMVNIC
 	tristate "IBM Virtual NIC support"
 	depends on PPC_PSERIES
diff --git a/drivers/net/ethernet/ibm/Makefile b/drivers/net/ethernet/ibm/Makefile
index 1d17d0c33d4d..c7e5d891c946 100644
--- a/drivers/net/ethernet/ibm/Makefile
+++ b/drivers/net/ethernet/ibm/Makefile
@@ -6,4 +6,3 @@
 obj-$(CONFIG_IBMVETH) += ibmveth.o
 obj-$(CONFIG_IBMVNIC) += ibmvnic.o
 obj-$(CONFIG_IBM_EMAC) += emac/
-obj-$(CONFIG_EHEA) += ehea/
diff --git a/drivers/net/ethernet/ibm/ehea/Makefile b/drivers/net/ethernet/ibm/ehea/Makefile
deleted file mode 100644
index 9e1e5c7aafe2..000000000000
--- a/drivers/net/ethernet/ibm/ehea/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile for the eHEA ethernet device driver for IBM eServer System p
-#
-ehea-y = ehea_main.o ehea_phyp.o ehea_qmr.o ehea_ethtool.o
-obj-$(CONFIG_EHEA) += ehea.o
-
diff --git a/drivers/net/ethernet/ibm/ehea/ehea.h b/drivers/net/ethernet/ibm/ehea/ehea.h
deleted file mode 100644
index 208c440a602b..000000000000
--- a/drivers/net/ethernet/ibm/ehea/ehea.h
+++ /dev/null
@@ -1,477 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  linux/drivers/net/ethernet/ibm/ehea/ehea.h
- *
- *  eHEA ethernet device driver for IBM eServer System p
- *
- *  (C) Copyright IBM Corp. 2006
- *
- *  Authors:
- *       Christoph Raisch <raisch@de.ibm.com>
- *       Jan-Bernd Themann <themann@de.ibm.com>
- *       Thomas Klein <tklein@de.ibm.com>
- */
-
-#ifndef __EHEA_H__
-#define __EHEA_H__
-
-#include <linux/module.h>
-#include <linux/ethtool.h>
-#include <linux/vmalloc.h>
-#include <linux/if_vlan.h>
-#include <linux/platform_device.h>
-
-#include <asm/ibmebus.h>
-#include <asm/io.h>
-
-#define DRV_NAME	"ehea"
-#define DRV_VERSION	"EHEA_0107"
-
-/* eHEA capability flags */
-#define DLPAR_PORT_ADD_REM 1
-#define DLPAR_MEM_ADD      2
-#define DLPAR_MEM_REM      4
-#define EHEA_CAPABILITIES  (DLPAR_PORT_ADD_REM | DLPAR_MEM_ADD | DLPAR_MEM_REM)
-
-#define EHEA_MSG_DEFAULT (NETIF_MSG_LINK | NETIF_MSG_TIMER \
-	| NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR)
-
-#define EHEA_MAX_ENTRIES_RQ1 32767
-#define EHEA_MAX_ENTRIES_RQ2 16383
-#define EHEA_MAX_ENTRIES_RQ3 16383
-#define EHEA_MAX_ENTRIES_SQ  32767
-#define EHEA_MIN_ENTRIES_QP  127
-
-#define EHEA_SMALL_QUEUES
-
-#ifdef EHEA_SMALL_QUEUES
-#define EHEA_MAX_CQE_COUNT      1023
-#define EHEA_DEF_ENTRIES_SQ     1023
-#define EHEA_DEF_ENTRIES_RQ1    1023
-#define EHEA_DEF_ENTRIES_RQ2    1023
-#define EHEA_DEF_ENTRIES_RQ3    511
-#else
-#define EHEA_MAX_CQE_COUNT      4080
-#define EHEA_DEF_ENTRIES_SQ     4080
-#define EHEA_DEF_ENTRIES_RQ1    8160
-#define EHEA_DEF_ENTRIES_RQ2    2040
-#define EHEA_DEF_ENTRIES_RQ3    2040
-#endif
-
-#define EHEA_MAX_ENTRIES_EQ 20
-
-#define EHEA_SG_SQ  2
-#define EHEA_SG_RQ1 1
-#define EHEA_SG_RQ2 0
-#define EHEA_SG_RQ3 0
-
-#define EHEA_MAX_PACKET_SIZE    9022	/* for jumbo frames */
-#define EHEA_RQ2_PKT_SIZE       2048
-#define EHEA_L_PKT_SIZE         256	/* low latency */
-
-/* Send completion signaling */
-
-/* Protection Domain Identifier */
-#define EHEA_PD_ID        0xaabcdeff
-
-#define EHEA_RQ2_THRESHOLD 	   1
-#define EHEA_RQ3_THRESHOLD	   4	/* use RQ3 threshold of 2048 bytes */
-
-#define EHEA_SPEED_10G         10000
-#define EHEA_SPEED_1G           1000
-#define EHEA_SPEED_100M          100
-#define EHEA_SPEED_10M            10
-#define EHEA_SPEED_AUTONEG         0
-
-/* Broadcast/Multicast registration types */
-#define EHEA_BCMC_SCOPE_ALL	0x08
-#define EHEA_BCMC_SCOPE_SINGLE	0x00
-#define EHEA_BCMC_MULTICAST	0x04
-#define EHEA_BCMC_BROADCAST	0x00
-#define EHEA_BCMC_UNTAGGED	0x02
-#define EHEA_BCMC_TAGGED	0x00
-#define EHEA_BCMC_VLANID_ALL	0x01
-#define EHEA_BCMC_VLANID_SINGLE	0x00
-
-#define EHEA_CACHE_LINE          128
-
-/* Memory Regions */
-#define EHEA_MR_ACC_CTRL       0x00800000
-
-#define EHEA_BUSMAP_START      0x8000000000000000ULL
-#define EHEA_INVAL_ADDR        0xFFFFFFFFFFFFFFFFULL
-#define EHEA_DIR_INDEX_SHIFT 13                   /* 8k Entries in 64k block */
-#define EHEA_TOP_INDEX_SHIFT (EHEA_DIR_INDEX_SHIFT * 2)
-#define EHEA_MAP_ENTRIES (1 << EHEA_DIR_INDEX_SHIFT)
-#define EHEA_MAP_SIZE (0x10000)                   /* currently fixed map size */
-#define EHEA_INDEX_MASK (EHEA_MAP_ENTRIES - 1)
-
-
-#define EHEA_WATCH_DOG_TIMEOUT 10*HZ
-
-/* utility functions */
-
-void ehea_dump(void *adr, int len, char *msg);
-
-#define EHEA_BMASK(pos, length) (((pos) << 16) + (length))
-
-#define EHEA_BMASK_IBM(from, to) (((63 - to) << 16) + ((to) - (from) + 1))
-
-#define EHEA_BMASK_SHIFTPOS(mask) (((mask) >> 16) & 0xffff)
-
-#define EHEA_BMASK_MASK(mask) \
-	(0xffffffffffffffffULL >> ((64 - (mask)) & 0xffff))
-
-#define EHEA_BMASK_SET(mask, value) \
-	((EHEA_BMASK_MASK(mask) & ((u64)(value))) << EHEA_BMASK_SHIFTPOS(mask))
-
-#define EHEA_BMASK_GET(mask, value) \
-	(EHEA_BMASK_MASK(mask) & (((u64)(value)) >> EHEA_BMASK_SHIFTPOS(mask)))
-
-/*
- * Generic ehea page
- */
-struct ehea_page {
-	u8 entries[PAGE_SIZE];
-};
-
-/*
- * Generic queue in linux kernel virtual memory
- */
-struct hw_queue {
-	u64 current_q_offset;		/* current queue entry */
-	struct ehea_page **queue_pages;	/* array of pages belonging to queue */
-	u32 qe_size;			/* queue entry size */
-	u32 queue_length;      		/* queue length allocated in bytes */
-	u32 pagesize;
-	u32 toggle_state;		/* toggle flag - per page */
-	u32 reserved;			/* 64 bit alignment */
-};
-
-/*
- * For pSeries this is a 64bit memory address where
- * I/O memory is mapped into CPU address space
- */
-struct h_epa {
-	void __iomem *addr;
-};
-
-struct h_epa_user {
-	u64 addr;
-};
-
-struct h_epas {
-	struct h_epa kernel;	/* kernel space accessible resource,
-				   set to 0 if unused */
-	struct h_epa_user user;	/* user space accessible resource
-				   set to 0 if unused */
-};
-
-/*
- * Memory map data structures
- */
-struct ehea_dir_bmap
-{
-	u64 ent[EHEA_MAP_ENTRIES];
-};
-struct ehea_top_bmap
-{
-	struct ehea_dir_bmap *dir[EHEA_MAP_ENTRIES];
-};
-struct ehea_bmap
-{
-	struct ehea_top_bmap *top[EHEA_MAP_ENTRIES];
-};
-
-struct ehea_qp;
-struct ehea_cq;
-struct ehea_eq;
-struct ehea_port;
-struct ehea_av;
-
-/*
- * Queue attributes passed to ehea_create_qp()
- */
-struct ehea_qp_init_attr {
-	/* input parameter */
-	u32 qp_token;           /* queue token */
-	u8 low_lat_rq1;
-	u8 signalingtype;       /* cqe generation flag */
-	u8 rq_count;            /* num of receive queues */
-	u8 eqe_gen;             /* eqe generation flag */
-	u16 max_nr_send_wqes;   /* max number of send wqes */
-	u16 max_nr_rwqes_rq1;   /* max number of receive wqes */
-	u16 max_nr_rwqes_rq2;
-	u16 max_nr_rwqes_rq3;
-	u8 wqe_size_enc_sq;
-	u8 wqe_size_enc_rq1;
-	u8 wqe_size_enc_rq2;
-	u8 wqe_size_enc_rq3;
-	u8 swqe_imm_data_len;   /* immediate data length for swqes */
-	u16 port_nr;
-	u16 rq2_threshold;
-	u16 rq3_threshold;
-	u64 send_cq_handle;
-	u64 recv_cq_handle;
-	u64 aff_eq_handle;
-
-	/* output parameter */
-	u32 qp_nr;
-	u16 act_nr_send_wqes;
-	u16 act_nr_rwqes_rq1;
-	u16 act_nr_rwqes_rq2;
-	u16 act_nr_rwqes_rq3;
-	u8 act_wqe_size_enc_sq;
-	u8 act_wqe_size_enc_rq1;
-	u8 act_wqe_size_enc_rq2;
-	u8 act_wqe_size_enc_rq3;
-	u32 nr_sq_pages;
-	u32 nr_rq1_pages;
-	u32 nr_rq2_pages;
-	u32 nr_rq3_pages;
-	u32 liobn_sq;
-	u32 liobn_rq1;
-	u32 liobn_rq2;
-	u32 liobn_rq3;
-};
-
-/*
- * Event Queue attributes, passed as parameter
- */
-struct ehea_eq_attr {
-	u32 type;
-	u32 max_nr_of_eqes;
-	u8 eqe_gen;        /* generate eqe flag */
-	u64 eq_handle;
-	u32 act_nr_of_eqes;
-	u32 nr_pages;
-	u32 ist1;          /* Interrupt service token */
-	u32 ist2;
-	u32 ist3;
-	u32 ist4;
-};
-
-
-/*
- * Event Queue
- */
-struct ehea_eq {
-	struct ehea_adapter *adapter;
-	struct hw_queue hw_queue;
-	u64 fw_handle;
-	struct h_epas epas;
-	spinlock_t spinlock;
-	struct ehea_eq_attr attr;
-};
-
-/*
- * HEA Queues
- */
-struct ehea_qp {
-	struct ehea_adapter *adapter;
-	u64 fw_handle;			/* QP handle for firmware calls */
-	struct hw_queue hw_squeue;
-	struct hw_queue hw_rqueue1;
-	struct hw_queue hw_rqueue2;
-	struct hw_queue hw_rqueue3;
-	struct h_epas epas;
-	struct ehea_qp_init_attr init_attr;
-};
-
-/*
- * Completion Queue attributes
- */
-struct ehea_cq_attr {
-	/* input parameter */
-	u32 max_nr_of_cqes;
-	u32 cq_token;
-	u64 eq_handle;
-
-	/* output parameter */
-	u32 act_nr_of_cqes;
-	u32 nr_pages;
-};
-
-/*
- * Completion Queue
- */
-struct ehea_cq {
-	struct ehea_adapter *adapter;
-	u64 fw_handle;
-	struct hw_queue hw_queue;
-	struct h_epas epas;
-	struct ehea_cq_attr attr;
-};
-
-/*
- * Memory Region
- */
-struct ehea_mr {
-	struct ehea_adapter *adapter;
-	u64 handle;
-	u64 vaddr;
-	u32 lkey;
-};
-
-/*
- * Port state information
- */
-struct port_stats {
-	int poll_receive_errors;
-	int queue_stopped;
-	int err_tcp_cksum;
-	int err_ip_cksum;
-	int err_frame_crc;
-};
-
-#define EHEA_IRQ_NAME_SIZE 20
-
-/*
- * Queue SKB Array
- */
-struct ehea_q_skb_arr {
-	struct sk_buff **arr;		/* skb array for queue */
-	int len;                	/* array length */
-	int index;			/* array index */
-	int os_skbs;			/* rq2/rq3 only: outstanding skbs */
-};
-
-/*
- * Port resources
- */
-struct ehea_port_res {
-	struct napi_struct napi;
-	struct port_stats p_stats;
-	struct ehea_mr send_mr;       	/* send memory region */
-	struct ehea_mr recv_mr;       	/* receive memory region */
-	struct ehea_port *port;
-	char int_recv_name[EHEA_IRQ_NAME_SIZE];
-	char int_send_name[EHEA_IRQ_NAME_SIZE];
-	struct ehea_qp *qp;
-	struct ehea_cq *send_cq;
-	struct ehea_cq *recv_cq;
-	struct ehea_eq *eq;
-	struct ehea_q_skb_arr rq1_skba;
-	struct ehea_q_skb_arr rq2_skba;
-	struct ehea_q_skb_arr rq3_skba;
-	struct ehea_q_skb_arr sq_skba;
-	int sq_skba_size;
-	int swqe_refill_th;
-	atomic_t swqe_avail;
-	int swqe_ll_count;
-	u32 swqe_id_counter;
-	u64 tx_packets;
-	u64 tx_bytes;
-	u64 rx_packets;
-	u64 rx_bytes;
-	int sq_restart_flag;
-};
-
-
-#define EHEA_MAX_PORTS 16
-
-#define EHEA_NUM_PORTRES_FW_HANDLES    6  /* QP handle, SendCQ handle,
-					     RecvCQ handle, EQ handle,
-					     SendMR handle, RecvMR handle */
-#define EHEA_NUM_PORT_FW_HANDLES       1  /* EQ handle */
-#define EHEA_NUM_ADAPTER_FW_HANDLES    2  /* MR handle, NEQ handle */
-
-struct ehea_adapter {
-	u64 handle;
-	struct platform_device *ofdev;
-	struct ehea_port *port[EHEA_MAX_PORTS];
-	struct ehea_eq *neq;       /* notification event queue */
-	struct tasklet_struct neq_tasklet;
-	struct ehea_mr mr;
-	u32 pd;                    /* protection domain */
-	u64 max_mc_mac;            /* max number of multicast mac addresses */
-	int active_ports;
-	struct list_head list;
-};
-
-
-struct ehea_mc_list {
-	struct list_head list;
-	u64 macaddr;
-};
-
-/* kdump support */
-struct ehea_fw_handle_entry {
-	u64 adh;               /* Adapter Handle */
-	u64 fwh;               /* Firmware Handle */
-};
-
-struct ehea_fw_handle_array {
-	struct ehea_fw_handle_entry *arr;
-	int num_entries;
-	struct mutex lock;
-};
-
-struct ehea_bcmc_reg_entry {
-	u64 adh;               /* Adapter Handle */
-	u32 port_id;           /* Logical Port Id */
-	u8 reg_type;           /* Registration Type */
-	u64 macaddr;
-};
-
-struct ehea_bcmc_reg_array {
-	struct ehea_bcmc_reg_entry *arr;
-	int num_entries;
-	spinlock_t lock;
-};
-
-#define EHEA_PORT_UP 1
-#define EHEA_PORT_DOWN 0
-#define EHEA_PHY_LINK_UP 1
-#define EHEA_PHY_LINK_DOWN 0
-#define EHEA_MAX_PORT_RES 16
-struct ehea_port {
-	struct ehea_adapter *adapter;	 /* adapter that owns this port */
-	struct net_device *netdev;
-	struct rtnl_link_stats64 stats;
-	struct ehea_port_res port_res[EHEA_MAX_PORT_RES];
-	struct platform_device  ofdev; /* Open Firmware Device */
-	struct ehea_mc_list *mc_list;	 /* Multicast MAC addresses */
-	struct ehea_eq *qp_eq;
-	struct work_struct reset_task;
-	struct delayed_work stats_work;
-	struct mutex port_lock;
-	char int_aff_name[EHEA_IRQ_NAME_SIZE];
-	int allmulti;			 /* Indicates IFF_ALLMULTI state */
-	int promisc;		 	 /* Indicates IFF_PROMISC state */
-	int num_mcs;
-	int resets;
-	unsigned long flags;
-	u64 mac_addr;
-	u32 logical_port_id;
-	u32 port_speed;
-	u32 msg_enable;
-	u32 sig_comp_iv;
-	u32 state;
-	u8 phy_link;
-	u8 full_duplex;
-	u8 autoneg;
-	u8 num_def_qps;
-	wait_queue_head_t swqe_avail_wq;
-	wait_queue_head_t restart_wq;
-};
-
-struct port_res_cfg {
-	int max_entries_rcq;
-	int max_entries_scq;
-	int max_entries_sq;
-	int max_entries_rq1;
-	int max_entries_rq2;
-	int max_entries_rq3;
-};
-
-enum ehea_flag_bits {
-	__EHEA_STOP_XFER,
-	__EHEA_DISABLE_PORT_RESET
-};
-
-void ehea_set_ethtool_ops(struct net_device *netdev);
-int ehea_sense_port_attr(struct ehea_port *port);
-int ehea_set_portspeed(struct ehea_port *port, u32 port_speed);
-
-#endif	/* __EHEA_H__ */
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c b/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c
deleted file mode 100644
index 1db5b6790a41..000000000000
--- a/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c
+++ /dev/null
@@ -1,277 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  linux/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c
- *
- *  eHEA ethernet device driver for IBM eServer System p
- *
- *  (C) Copyright IBM Corp. 2006
- *
- *  Authors:
- *       Christoph Raisch <raisch@de.ibm.com>
- *       Jan-Bernd Themann <themann@de.ibm.com>
- *       Thomas Klein <tklein@de.ibm.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include "ehea.h"
-#include "ehea_phyp.h"
-
-static int ehea_get_link_ksettings(struct net_device *dev,
-				   struct ethtool_link_ksettings *cmd)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	u32 supported, advertising;
-	u32 speed;
-	int ret;
-
-	ret = ehea_sense_port_attr(port);
-
-	if (ret)
-		return ret;
-
-	if (netif_carrier_ok(dev)) {
-		switch (port->port_speed) {
-		case EHEA_SPEED_10M:
-			speed = SPEED_10;
-			break;
-		case EHEA_SPEED_100M:
-			speed = SPEED_100;
-			break;
-		case EHEA_SPEED_1G:
-			speed = SPEED_1000;
-			break;
-		case EHEA_SPEED_10G:
-			speed = SPEED_10000;
-			break;
-		default:
-			speed = -1;
-			break; /* BUG */
-		}
-		cmd->base.duplex = port->full_duplex == 1 ?
-						     DUPLEX_FULL : DUPLEX_HALF;
-	} else {
-		speed = SPEED_UNKNOWN;
-		cmd->base.duplex = DUPLEX_UNKNOWN;
-	}
-	cmd->base.speed = speed;
-
-	if (cmd->base.speed == SPEED_10000) {
-		supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE);
-		advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE);
-		cmd->base.port = PORT_FIBRE;
-	} else {
-		supported = (SUPPORTED_1000baseT_Full | SUPPORTED_100baseT_Full
-			       | SUPPORTED_100baseT_Half | SUPPORTED_10baseT_Full
-			       | SUPPORTED_10baseT_Half | SUPPORTED_Autoneg
-			       | SUPPORTED_TP);
-		advertising = (ADVERTISED_1000baseT_Full | ADVERTISED_Autoneg
-				 | ADVERTISED_TP);
-		cmd->base.port = PORT_TP;
-	}
-
-	cmd->base.autoneg = port->autoneg == 1 ?
-		AUTONEG_ENABLE : AUTONEG_DISABLE;
-
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
-						supported);
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
-						advertising);
-
-	return 0;
-}
-
-static int ehea_set_link_ksettings(struct net_device *dev,
-				   const struct ethtool_link_ksettings *cmd)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	int ret = 0;
-	u32 sp;
-
-	if (cmd->base.autoneg == AUTONEG_ENABLE) {
-		sp = EHEA_SPEED_AUTONEG;
-		goto doit;
-	}
-
-	switch (cmd->base.speed) {
-	case SPEED_10:
-		if (cmd->base.duplex == DUPLEX_FULL)
-			sp = H_SPEED_10M_F;
-		else
-			sp = H_SPEED_10M_H;
-		break;
-
-	case SPEED_100:
-		if (cmd->base.duplex == DUPLEX_FULL)
-			sp = H_SPEED_100M_F;
-		else
-			sp = H_SPEED_100M_H;
-		break;
-
-	case SPEED_1000:
-		if (cmd->base.duplex == DUPLEX_FULL)
-			sp = H_SPEED_1G_F;
-		else
-			ret = -EINVAL;
-		break;
-
-	case SPEED_10000:
-		if (cmd->base.duplex == DUPLEX_FULL)
-			sp = H_SPEED_10G_F;
-		else
-			ret = -EINVAL;
-		break;
-
-	default:
-			ret = -EINVAL;
-		break;
-	}
-
-	if (ret)
-		goto out;
-doit:
-	ret = ehea_set_portspeed(port, sp);
-
-	if (!ret)
-		netdev_info(dev,
-			    "Port speed successfully set: %dMbps %s Duplex\n",
-			    port->port_speed,
-			    port->full_duplex == 1 ? "Full" : "Half");
-out:
-	return ret;
-}
-
-static int ehea_nway_reset(struct net_device *dev)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	int ret;
-
-	ret = ehea_set_portspeed(port, EHEA_SPEED_AUTONEG);
-
-	if (!ret)
-		netdev_info(port->netdev,
-			    "Port speed successfully set: %dMbps %s Duplex\n",
-			    port->port_speed,
-			    port->full_duplex == 1 ? "Full" : "Half");
-	return ret;
-}
-
-static void ehea_get_drvinfo(struct net_device *dev,
-			       struct ethtool_drvinfo *info)
-{
-	strscpy(info->driver, DRV_NAME, sizeof(info->driver));
-	strscpy(info->version, DRV_VERSION, sizeof(info->version));
-}
-
-static u32 ehea_get_msglevel(struct net_device *dev)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	return port->msg_enable;
-}
-
-static void ehea_set_msglevel(struct net_device *dev, u32 value)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	port->msg_enable = value;
-}
-
-static const char ehea_ethtool_stats_keys[][ETH_GSTRING_LEN] = {
-	{"sig_comp_iv"},
-	{"swqe_refill_th"},
-	{"port resets"},
-	{"Receive errors"},
-	{"TCP cksum errors"},
-	{"IP cksum errors"},
-	{"Frame cksum errors"},
-	{"num SQ stopped"},
-	{"PR0 free_swqes"},
-	{"PR1 free_swqes"},
-	{"PR2 free_swqes"},
-	{"PR3 free_swqes"},
-	{"PR4 free_swqes"},
-	{"PR5 free_swqes"},
-	{"PR6 free_swqes"},
-	{"PR7 free_swqes"},
-	{"PR8 free_swqes"},
-	{"PR9 free_swqes"},
-	{"PR10 free_swqes"},
-	{"PR11 free_swqes"},
-	{"PR12 free_swqes"},
-	{"PR13 free_swqes"},
-	{"PR14 free_swqes"},
-	{"PR15 free_swqes"},
-};
-
-static void ehea_get_strings(struct net_device *dev, u32 stringset, u8 *data)
-{
-	if (stringset == ETH_SS_STATS) {
-		memcpy(data, &ehea_ethtool_stats_keys,
-		       sizeof(ehea_ethtool_stats_keys));
-	}
-}
-
-static int ehea_get_sset_count(struct net_device *dev, int sset)
-{
-	switch (sset) {
-	case ETH_SS_STATS:
-		return ARRAY_SIZE(ehea_ethtool_stats_keys);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static void ehea_get_ethtool_stats(struct net_device *dev,
-				     struct ethtool_stats *stats, u64 *data)
-{
-	int i, k, tmp;
-	struct ehea_port *port = netdev_priv(dev);
-
-	for (i = 0; i < ehea_get_sset_count(dev, ETH_SS_STATS); i++)
-		data[i] = 0;
-	i = 0;
-
-	data[i++] = port->sig_comp_iv;
-	data[i++] = port->port_res[0].swqe_refill_th;
-	data[i++] = port->resets;
-
-	for (k = 0, tmp = 0; k < EHEA_MAX_PORT_RES; k++)
-		tmp += port->port_res[k].p_stats.poll_receive_errors;
-	data[i++] = tmp;
-
-	for (k = 0, tmp = 0; k < EHEA_MAX_PORT_RES; k++)
-		tmp += port->port_res[k].p_stats.err_tcp_cksum;
-	data[i++] = tmp;
-
-	for (k = 0, tmp = 0; k < EHEA_MAX_PORT_RES; k++)
-		tmp += port->port_res[k].p_stats.err_ip_cksum;
-	data[i++] = tmp;
-
-	for (k = 0, tmp = 0; k < EHEA_MAX_PORT_RES; k++)
-		tmp += port->port_res[k].p_stats.err_frame_crc;
-	data[i++] = tmp;
-
-	for (k = 0, tmp = 0; k < EHEA_MAX_PORT_RES; k++)
-		tmp += port->port_res[k].p_stats.queue_stopped;
-	data[i++] = tmp;
-
-	for (k = 0; k < 16; k++)
-		data[i++] = atomic_read(&port->port_res[k].swqe_avail);
-}
-
-static const struct ethtool_ops ehea_ethtool_ops = {
-	.get_drvinfo = ehea_get_drvinfo,
-	.get_msglevel = ehea_get_msglevel,
-	.set_msglevel = ehea_set_msglevel,
-	.get_link = ethtool_op_get_link,
-	.get_strings = ehea_get_strings,
-	.get_sset_count = ehea_get_sset_count,
-	.get_ethtool_stats = ehea_get_ethtool_stats,
-	.nway_reset = ehea_nway_reset,		/* Restart autonegotiation */
-	.get_link_ksettings = ehea_get_link_ksettings,
-	.set_link_ksettings = ehea_set_link_ksettings,
-};
-
-void ehea_set_ethtool_ops(struct net_device *netdev)
-{
-	netdev->ethtool_ops = &ehea_ethtool_ops;
-}
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_hw.h b/drivers/net/ethernet/ibm/ehea/ehea_hw.h
deleted file mode 100644
index 590933a45d65..000000000000
--- a/drivers/net/ethernet/ibm/ehea/ehea_hw.h
+++ /dev/null
@@ -1,253 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  linux/drivers/net/ethernet/ibm/ehea/ehea_hw.h
- *
- *  eHEA ethernet device driver for IBM eServer System p
- *
- *  (C) Copyright IBM Corp. 2006
- *
- *  Authors:
- *       Christoph Raisch <raisch@de.ibm.com>
- *       Jan-Bernd Themann <themann@de.ibm.com>
- *       Thomas Klein <tklein@de.ibm.com>
- */
-
-#ifndef __EHEA_HW_H__
-#define __EHEA_HW_H__
-
-#define QPX_SQA_VALUE   EHEA_BMASK_IBM(48, 63)
-#define QPX_RQ1A_VALUE  EHEA_BMASK_IBM(48, 63)
-#define QPX_RQ2A_VALUE  EHEA_BMASK_IBM(48, 63)
-#define QPX_RQ3A_VALUE  EHEA_BMASK_IBM(48, 63)
-
-#define QPTEMM_OFFSET(x) offsetof(struct ehea_qptemm, x)
-
-struct ehea_qptemm {
-	u64 qpx_hcr;
-	u64 qpx_c;
-	u64 qpx_herr;
-	u64 qpx_aer;
-	u64 qpx_sqa;
-	u64 qpx_sqc;
-	u64 qpx_rq1a;
-	u64 qpx_rq1c;
-	u64 qpx_st;
-	u64 qpx_aerr;
-	u64 qpx_tenure;
-	u64 qpx_reserved1[(0x098 - 0x058) / 8];
-	u64 qpx_portp;
-	u64 qpx_reserved2[(0x100 - 0x0A0) / 8];
-	u64 qpx_t;
-	u64 qpx_sqhp;
-	u64 qpx_sqptp;
-	u64 qpx_reserved3[(0x140 - 0x118) / 8];
-	u64 qpx_sqwsize;
-	u64 qpx_reserved4[(0x170 - 0x148) / 8];
-	u64 qpx_sqsize;
-	u64 qpx_reserved5[(0x1B0 - 0x178) / 8];
-	u64 qpx_sigt;
-	u64 qpx_wqecnt;
-	u64 qpx_rq1hp;
-	u64 qpx_rq1ptp;
-	u64 qpx_rq1size;
-	u64 qpx_reserved6[(0x220 - 0x1D8) / 8];
-	u64 qpx_rq1wsize;
-	u64 qpx_reserved7[(0x240 - 0x228) / 8];
-	u64 qpx_pd;
-	u64 qpx_scqn;
-	u64 qpx_rcqn;
-	u64 qpx_aeqn;
-	u64 reserved49;
-	u64 qpx_ram;
-	u64 qpx_reserved8[(0x300 - 0x270) / 8];
-	u64 qpx_rq2a;
-	u64 qpx_rq2c;
-	u64 qpx_rq2hp;
-	u64 qpx_rq2ptp;
-	u64 qpx_rq2size;
-	u64 qpx_rq2wsize;
-	u64 qpx_rq2th;
-	u64 qpx_rq3a;
-	u64 qpx_rq3c;
-	u64 qpx_rq3hp;
-	u64 qpx_rq3ptp;
-	u64 qpx_rq3size;
-	u64 qpx_rq3wsize;
-	u64 qpx_rq3th;
-	u64 qpx_lpn;
-	u64 qpx_reserved9[(0x400 - 0x378) / 8];
-	u64 reserved_ext[(0x500 - 0x400) / 8];
-	u64 reserved2[(0x1000 - 0x500) / 8];
-};
-
-#define MRx_HCR_LPARID_VALID EHEA_BMASK_IBM(0, 0)
-
-#define MRMWMM_OFFSET(x) offsetof(struct ehea_mrmwmm, x)
-
-struct ehea_mrmwmm {
-	u64 mrx_hcr;
-	u64 mrx_c;
-	u64 mrx_herr;
-	u64 mrx_aer;
-	u64 mrx_pp;
-	u64 reserved1;
-	u64 reserved2;
-	u64 reserved3;
-	u64 reserved4[(0x200 - 0x40) / 8];
-	u64 mrx_ctl[64];
-};
-
-#define QPEDMM_OFFSET(x) offsetof(struct ehea_qpedmm, x)
-
-struct ehea_qpedmm {
-
-	u64 reserved0[(0x400) / 8];
-	u64 qpedx_phh;
-	u64 qpedx_ppsgp;
-	u64 qpedx_ppsgu;
-	u64 qpedx_ppdgp;
-	u64 qpedx_ppdgu;
-	u64 qpedx_aph;
-	u64 qpedx_apsgp;
-	u64 qpedx_apsgu;
-	u64 qpedx_apdgp;
-	u64 qpedx_apdgu;
-	u64 qpedx_apav;
-	u64 qpedx_apsav;
-	u64 qpedx_hcr;
-	u64 reserved1[4];
-	u64 qpedx_rrl0;
-	u64 qpedx_rrrkey0;
-	u64 qpedx_rrva0;
-	u64 reserved2;
-	u64 qpedx_rrl1;
-	u64 qpedx_rrrkey1;
-	u64 qpedx_rrva1;
-	u64 reserved3;
-	u64 qpedx_rrl2;
-	u64 qpedx_rrrkey2;
-	u64 qpedx_rrva2;
-	u64 reserved4;
-	u64 qpedx_rrl3;
-	u64 qpedx_rrrkey3;
-	u64 qpedx_rrva3;
-};
-
-#define CQX_FECADDER EHEA_BMASK_IBM(32, 63)
-#define CQX_FEC_CQE_CNT EHEA_BMASK_IBM(32, 63)
-#define CQX_N1_GENERATE_COMP_EVENT EHEA_BMASK_IBM(0, 0)
-#define CQX_EP_EVENT_PENDING EHEA_BMASK_IBM(0, 0)
-
-#define CQTEMM_OFFSET(x) offsetof(struct ehea_cqtemm, x)
-
-struct ehea_cqtemm {
-	u64 cqx_hcr;
-	u64 cqx_c;
-	u64 cqx_herr;
-	u64 cqx_aer;
-	u64 cqx_ptp;
-	u64 cqx_tp;
-	u64 cqx_fec;
-	u64 cqx_feca;
-	u64 cqx_ep;
-	u64 cqx_eq;
-	u64 reserved1;
-	u64 cqx_n0;
-	u64 cqx_n1;
-	u64 reserved2[(0x1000 - 0x60) / 8];
-};
-
-#define EQTEMM_OFFSET(x) offsetof(struct ehea_eqtemm, x)
-
-struct ehea_eqtemm {
-	u64 eqx_hcr;
-	u64 eqx_c;
-	u64 eqx_herr;
-	u64 eqx_aer;
-	u64 eqx_ptp;
-	u64 eqx_tp;
-	u64 eqx_ssba;
-	u64 eqx_psba;
-	u64 eqx_cec;
-	u64 eqx_meql;
-	u64 eqx_xisbi;
-	u64 eqx_xisc;
-	u64 eqx_it;
-};
-
-/*
- * These access functions will be changed when the dissuccsion about
- * the new access methods for POWER has settled.
- */
-
-static inline u64 epa_load(struct h_epa epa, u32 offset)
-{
-	return __raw_readq((void __iomem *)(epa.addr + offset));
-}
-
-static inline void epa_store(struct h_epa epa, u32 offset, u64 value)
-{
-	__raw_writeq(value, (void __iomem *)(epa.addr + offset));
-	epa_load(epa, offset);	/* synchronize explicitly to eHEA */
-}
-
-static inline void epa_store_acc(struct h_epa epa, u32 offset, u64 value)
-{
-	__raw_writeq(value, (void __iomem *)(epa.addr + offset));
-}
-
-#define epa_store_cq(epa, offset, value)\
-	epa_store(epa, CQTEMM_OFFSET(offset), value)
-#define epa_load_cq(epa, offset)\
-	epa_load(epa, CQTEMM_OFFSET(offset))
-
-static inline void ehea_update_sqa(struct ehea_qp *qp, u16 nr_wqes)
-{
-	struct h_epa epa = qp->epas.kernel;
-	epa_store_acc(epa, QPTEMM_OFFSET(qpx_sqa),
-		      EHEA_BMASK_SET(QPX_SQA_VALUE, nr_wqes));
-}
-
-static inline void ehea_update_rq3a(struct ehea_qp *qp, u16 nr_wqes)
-{
-	struct h_epa epa = qp->epas.kernel;
-	epa_store_acc(epa, QPTEMM_OFFSET(qpx_rq3a),
-		      EHEA_BMASK_SET(QPX_RQ1A_VALUE, nr_wqes));
-}
-
-static inline void ehea_update_rq2a(struct ehea_qp *qp, u16 nr_wqes)
-{
-	struct h_epa epa = qp->epas.kernel;
-	epa_store_acc(epa, QPTEMM_OFFSET(qpx_rq2a),
-		      EHEA_BMASK_SET(QPX_RQ2A_VALUE, nr_wqes));
-}
-
-static inline void ehea_update_rq1a(struct ehea_qp *qp, u16 nr_wqes)
-{
-	struct h_epa epa = qp->epas.kernel;
-	epa_store_acc(epa, QPTEMM_OFFSET(qpx_rq1a),
-		      EHEA_BMASK_SET(QPX_RQ3A_VALUE, nr_wqes));
-}
-
-static inline void ehea_update_feca(struct ehea_cq *cq, u32 nr_cqes)
-{
-	struct h_epa epa = cq->epas.kernel;
-	epa_store_acc(epa, CQTEMM_OFFSET(cqx_feca),
-		      EHEA_BMASK_SET(CQX_FECADDER, nr_cqes));
-}
-
-static inline void ehea_reset_cq_n1(struct ehea_cq *cq)
-{
-	struct h_epa epa = cq->epas.kernel;
-	epa_store_cq(epa, cqx_n1,
-		     EHEA_BMASK_SET(CQX_N1_GENERATE_COMP_EVENT, 1));
-}
-
-static inline void ehea_reset_cq_ep(struct ehea_cq *my_cq)
-{
-	struct h_epa epa = my_cq->epas.kernel;
-	epa_store_acc(epa, CQTEMM_OFFSET(cqx_ep),
-		      EHEA_BMASK_SET(CQX_EP_EVENT_PENDING, 0));
-}
-
-#endif	/* __EHEA_HW_H__ */
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
deleted file mode 100644
index bfc8699a05b9..000000000000
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ /dev/null
@@ -1,3581 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  linux/drivers/net/ethernet/ibm/ehea/ehea_main.c
- *
- *  eHEA ethernet device driver for IBM eServer System p
- *
- *  (C) Copyright IBM Corp. 2006
- *
- *  Authors:
- *	 Christoph Raisch <raisch@de.ibm.com>
- *	 Jan-Bernd Themann <themann@de.ibm.com>
- *	 Thomas Klein <tklein@de.ibm.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/device.h>
-#include <linux/in.h>
-#include <linux/ip.h>
-#include <linux/tcp.h>
-#include <linux/udp.h>
-#include <linux/if.h>
-#include <linux/list.h>
-#include <linux/slab.h>
-#include <linux/if_ether.h>
-#include <linux/notifier.h>
-#include <linux/reboot.h>
-#include <linux/memory.h>
-#include <asm/kexec.h>
-#include <linux/mutex.h>
-#include <linux/prefetch.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
-
-#include <net/ip.h>
-
-#include "ehea.h"
-#include "ehea_qmr.h"
-#include "ehea_phyp.h"
-
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Christoph Raisch <raisch@de.ibm.com>");
-MODULE_DESCRIPTION("IBM eServer HEA Driver");
-MODULE_VERSION(DRV_VERSION);
-
-
-static int msg_level = -1;
-static int rq1_entries = EHEA_DEF_ENTRIES_RQ1;
-static int rq2_entries = EHEA_DEF_ENTRIES_RQ2;
-static int rq3_entries = EHEA_DEF_ENTRIES_RQ3;
-static int sq_entries = EHEA_DEF_ENTRIES_SQ;
-static int use_mcs = 1;
-static int prop_carrier_state;
-
-module_param(msg_level, int, 0);
-module_param(rq1_entries, int, 0);
-module_param(rq2_entries, int, 0);
-module_param(rq3_entries, int, 0);
-module_param(sq_entries, int, 0);
-module_param(prop_carrier_state, int, 0);
-module_param(use_mcs, int, 0);
-
-MODULE_PARM_DESC(msg_level, "msg_level");
-MODULE_PARM_DESC(prop_carrier_state, "Propagate carrier state of physical "
-		 "port to stack. 1:yes, 0:no.  Default = 0 ");
-MODULE_PARM_DESC(rq3_entries, "Number of entries for Receive Queue 3 "
-		 "[2^x - 1], x = [7..14]. Default = "
-		 __MODULE_STRING(EHEA_DEF_ENTRIES_RQ3) ")");
-MODULE_PARM_DESC(rq2_entries, "Number of entries for Receive Queue 2 "
-		 "[2^x - 1], x = [7..14]. Default = "
-		 __MODULE_STRING(EHEA_DEF_ENTRIES_RQ2) ")");
-MODULE_PARM_DESC(rq1_entries, "Number of entries for Receive Queue 1 "
-		 "[2^x - 1], x = [7..14]. Default = "
-		 __MODULE_STRING(EHEA_DEF_ENTRIES_RQ1) ")");
-MODULE_PARM_DESC(sq_entries, " Number of entries for the Send Queue  "
-		 "[2^x - 1], x = [7..14]. Default = "
-		 __MODULE_STRING(EHEA_DEF_ENTRIES_SQ) ")");
-MODULE_PARM_DESC(use_mcs, " Multiple receive queues, 1: enable, 0: disable, "
-		 "Default = 1");
-
-static int port_name_cnt;
-static LIST_HEAD(adapter_list);
-static unsigned long ehea_driver_flags;
-static DEFINE_MUTEX(dlpar_mem_lock);
-static struct ehea_fw_handle_array ehea_fw_handles;
-static struct ehea_bcmc_reg_array ehea_bcmc_regs;
-
-
-static int ehea_probe_adapter(struct platform_device *dev);
-
-static void ehea_remove(struct platform_device *dev);
-
-static const struct of_device_id ehea_module_device_table[] = {
-	{
-		.name = "lhea",
-		.compatible = "IBM,lhea",
-	},
-	{
-		.type = "network",
-		.compatible = "IBM,lhea-ethernet",
-	},
-	{},
-};
-MODULE_DEVICE_TABLE(of, ehea_module_device_table);
-
-static const struct of_device_id ehea_device_table[] = {
-	{
-		.name = "lhea",
-		.compatible = "IBM,lhea",
-	},
-	{},
-};
-MODULE_DEVICE_TABLE(of, ehea_device_table);
-
-static struct platform_driver ehea_driver = {
-	.driver = {
-		.name = "ehea",
-		.owner = THIS_MODULE,
-		.of_match_table = ehea_device_table,
-	},
-	.probe = ehea_probe_adapter,
-	.remove = ehea_remove,
-};
-
-void ehea_dump(void *adr, int len, char *msg)
-{
-	int x;
-	unsigned char *deb = adr;
-	for (x = 0; x < len; x += 16) {
-		pr_info("%s adr=%p ofs=%04x %016llx %016llx\n",
-			msg, deb, x, *((u64 *)&deb[0]), *((u64 *)&deb[8]));
-		deb += 16;
-	}
-}
-
-static void ehea_schedule_port_reset(struct ehea_port *port)
-{
-	if (!test_bit(__EHEA_DISABLE_PORT_RESET, &port->flags))
-		schedule_work(&port->reset_task);
-}
-
-static void ehea_update_firmware_handles(void)
-{
-	struct ehea_fw_handle_entry *arr = NULL;
-	struct ehea_adapter *adapter;
-	int num_adapters = 0;
-	int num_ports = 0;
-	int num_portres = 0;
-	int i = 0;
-	int num_fw_handles, k, l;
-
-	/* Determine number of handles */
-	mutex_lock(&ehea_fw_handles.lock);
-
-	list_for_each_entry(adapter, &adapter_list, list) {
-		num_adapters++;
-
-		for (k = 0; k < EHEA_MAX_PORTS; k++) {
-			struct ehea_port *port = adapter->port[k];
-
-			if (!port || (port->state != EHEA_PORT_UP))
-				continue;
-
-			num_ports++;
-			num_portres += port->num_def_qps;
-		}
-	}
-
-	num_fw_handles = num_adapters * EHEA_NUM_ADAPTER_FW_HANDLES +
-			 num_ports * EHEA_NUM_PORT_FW_HANDLES +
-			 num_portres * EHEA_NUM_PORTRES_FW_HANDLES;
-
-	if (num_fw_handles) {
-		arr = kzalloc_objs(*arr, num_fw_handles);
-		if (!arr)
-			goto out;  /* Keep the existing array */
-	} else
-		goto out_update;
-
-	list_for_each_entry(adapter, &adapter_list, list) {
-		if (num_adapters == 0)
-			break;
-
-		for (k = 0; k < EHEA_MAX_PORTS; k++) {
-			struct ehea_port *port = adapter->port[k];
-
-			if (!port || (port->state != EHEA_PORT_UP) ||
-			    (num_ports == 0))
-				continue;
-
-			for (l = 0; l < port->num_def_qps; l++) {
-				struct ehea_port_res *pr = &port->port_res[l];
-
-				arr[i].adh = adapter->handle;
-				arr[i++].fwh = pr->qp->fw_handle;
-				arr[i].adh = adapter->handle;
-				arr[i++].fwh = pr->send_cq->fw_handle;
-				arr[i].adh = adapter->handle;
-				arr[i++].fwh = pr->recv_cq->fw_handle;
-				arr[i].adh = adapter->handle;
-				arr[i++].fwh = pr->eq->fw_handle;
-				arr[i].adh = adapter->handle;
-				arr[i++].fwh = pr->send_mr.handle;
-				arr[i].adh = adapter->handle;
-				arr[i++].fwh = pr->recv_mr.handle;
-			}
-			arr[i].adh = adapter->handle;
-			arr[i++].fwh = port->qp_eq->fw_handle;
-			num_ports--;
-		}
-
-		arr[i].adh = adapter->handle;
-		arr[i++].fwh = adapter->neq->fw_handle;
-
-		if (adapter->mr.handle) {
-			arr[i].adh = adapter->handle;
-			arr[i++].fwh = adapter->mr.handle;
-		}
-		num_adapters--;
-	}
-
-out_update:
-	kfree(ehea_fw_handles.arr);
-	ehea_fw_handles.arr = arr;
-	ehea_fw_handles.num_entries = i;
-out:
-	mutex_unlock(&ehea_fw_handles.lock);
-}
-
-static void ehea_update_bcmc_registrations(void)
-{
-	unsigned long flags;
-	struct ehea_bcmc_reg_entry *arr = NULL;
-	struct ehea_adapter *adapter;
-	struct ehea_mc_list *mc_entry;
-	int num_registrations = 0;
-	int i = 0;
-	int k;
-
-	spin_lock_irqsave(&ehea_bcmc_regs.lock, flags);
-
-	/* Determine number of registrations */
-	list_for_each_entry(adapter, &adapter_list, list)
-		for (k = 0; k < EHEA_MAX_PORTS; k++) {
-			struct ehea_port *port = adapter->port[k];
-
-			if (!port || (port->state != EHEA_PORT_UP))
-				continue;
-
-			num_registrations += 2;	/* Broadcast registrations */
-
-			list_for_each_entry(mc_entry, &port->mc_list->list,list)
-				num_registrations += 2;
-		}
-
-	if (num_registrations) {
-		arr = kzalloc_objs(*arr, num_registrations, GFP_ATOMIC);
-		if (!arr)
-			goto out;  /* Keep the existing array */
-	} else
-		goto out_update;
-
-	list_for_each_entry(adapter, &adapter_list, list) {
-		for (k = 0; k < EHEA_MAX_PORTS; k++) {
-			struct ehea_port *port = adapter->port[k];
-
-			if (!port || (port->state != EHEA_PORT_UP))
-				continue;
-
-			if (num_registrations == 0)
-				goto out_update;
-
-			arr[i].adh = adapter->handle;
-			arr[i].port_id = port->logical_port_id;
-			arr[i].reg_type = EHEA_BCMC_BROADCAST |
-					  EHEA_BCMC_UNTAGGED;
-			arr[i++].macaddr = port->mac_addr;
-
-			arr[i].adh = adapter->handle;
-			arr[i].port_id = port->logical_port_id;
-			arr[i].reg_type = EHEA_BCMC_BROADCAST |
-					  EHEA_BCMC_VLANID_ALL;
-			arr[i++].macaddr = port->mac_addr;
-			num_registrations -= 2;
-
-			list_for_each_entry(mc_entry,
-					    &port->mc_list->list, list) {
-				if (num_registrations == 0)
-					goto out_update;
-
-				arr[i].adh = adapter->handle;
-				arr[i].port_id = port->logical_port_id;
-				arr[i].reg_type = EHEA_BCMC_MULTICAST |
-						  EHEA_BCMC_UNTAGGED;
-				if (mc_entry->macaddr == 0)
-					arr[i].reg_type |= EHEA_BCMC_SCOPE_ALL;
-				arr[i++].macaddr = mc_entry->macaddr;
-
-				arr[i].adh = adapter->handle;
-				arr[i].port_id = port->logical_port_id;
-				arr[i].reg_type = EHEA_BCMC_MULTICAST |
-						  EHEA_BCMC_VLANID_ALL;
-				if (mc_entry->macaddr == 0)
-					arr[i].reg_type |= EHEA_BCMC_SCOPE_ALL;
-				arr[i++].macaddr = mc_entry->macaddr;
-				num_registrations -= 2;
-			}
-		}
-	}
-
-out_update:
-	kfree(ehea_bcmc_regs.arr);
-	ehea_bcmc_regs.arr = arr;
-	ehea_bcmc_regs.num_entries = i;
-out:
-	spin_unlock_irqrestore(&ehea_bcmc_regs.lock, flags);
-}
-
-static void ehea_get_stats64(struct net_device *dev,
-			     struct rtnl_link_stats64 *stats)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	u64 rx_packets = 0, tx_packets = 0, rx_bytes = 0, tx_bytes = 0;
-	int i;
-
-	for (i = 0; i < port->num_def_qps; i++) {
-		rx_packets += port->port_res[i].rx_packets;
-		rx_bytes   += port->port_res[i].rx_bytes;
-	}
-
-	for (i = 0; i < port->num_def_qps; i++) {
-		tx_packets += port->port_res[i].tx_packets;
-		tx_bytes   += port->port_res[i].tx_bytes;
-	}
-
-	stats->tx_packets = tx_packets;
-	stats->rx_bytes = rx_bytes;
-	stats->tx_bytes = tx_bytes;
-	stats->rx_packets = rx_packets;
-
-	stats->multicast = port->stats.multicast;
-	stats->rx_errors = port->stats.rx_errors;
-}
-
-static void ehea_update_stats(struct work_struct *work)
-{
-	struct ehea_port *port =
-		container_of(work, struct ehea_port, stats_work.work);
-	struct net_device *dev = port->netdev;
-	struct rtnl_link_stats64 *stats = &port->stats;
-	struct hcp_ehea_port_cb2 *cb2;
-	u64 hret;
-
-	cb2 = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!cb2) {
-		netdev_err(dev, "No mem for cb2. Some interface statistics were not updated\n");
-		goto resched;
-	}
-
-	hret = ehea_h_query_ehea_port(port->adapter->handle,
-				      port->logical_port_id,
-				      H_PORT_CB2, H_PORT_CB2_ALL, cb2);
-	if (hret != H_SUCCESS) {
-		netdev_err(dev, "query_ehea_port failed\n");
-		goto out_herr;
-	}
-
-	if (netif_msg_hw(port))
-		ehea_dump(cb2, sizeof(*cb2), "net_device_stats");
-
-	stats->multicast = cb2->rxmcp;
-	stats->rx_errors = cb2->rxuerr;
-
-out_herr:
-	free_page((unsigned long)cb2);
-resched:
-	schedule_delayed_work(&port->stats_work,
-			      round_jiffies_relative(msecs_to_jiffies(1000)));
-}
-
-static void ehea_refill_rq1(struct ehea_port_res *pr, int index, int nr_of_wqes)
-{
-	struct sk_buff **skb_arr_rq1 = pr->rq1_skba.arr;
-	struct net_device *dev = pr->port->netdev;
-	int max_index_mask = pr->rq1_skba.len - 1;
-	int fill_wqes = pr->rq1_skba.os_skbs + nr_of_wqes;
-	int adder = 0;
-	int i;
-
-	pr->rq1_skba.os_skbs = 0;
-
-	if (unlikely(test_bit(__EHEA_STOP_XFER, &ehea_driver_flags))) {
-		if (nr_of_wqes > 0)
-			pr->rq1_skba.index = index;
-		pr->rq1_skba.os_skbs = fill_wqes;
-		return;
-	}
-
-	for (i = 0; i < fill_wqes; i++) {
-		if (!skb_arr_rq1[index]) {
-			skb_arr_rq1[index] = netdev_alloc_skb(dev,
-							      EHEA_L_PKT_SIZE);
-			if (!skb_arr_rq1[index]) {
-				pr->rq1_skba.os_skbs = fill_wqes - i;
-				break;
-			}
-		}
-		index--;
-		index &= max_index_mask;
-		adder++;
-	}
-
-	if (adder == 0)
-		return;
-
-	/* Ring doorbell */
-	ehea_update_rq1a(pr->qp, adder);
-}
-
-static void ehea_init_fill_rq1(struct ehea_port_res *pr, int nr_rq1a)
-{
-	struct sk_buff **skb_arr_rq1 = pr->rq1_skba.arr;
-	struct net_device *dev = pr->port->netdev;
-	int i;
-
-	if (nr_rq1a > pr->rq1_skba.len) {
-		netdev_err(dev, "NR_RQ1A bigger than skb array len\n");
-		return;
-	}
-
-	for (i = 0; i < nr_rq1a; i++) {
-		skb_arr_rq1[i] = netdev_alloc_skb(dev, EHEA_L_PKT_SIZE);
-		if (!skb_arr_rq1[i])
-			break;
-	}
-	/* Ring doorbell */
-	ehea_update_rq1a(pr->qp, i - 1);
-}
-
-static int ehea_refill_rq_def(struct ehea_port_res *pr,
-			      struct ehea_q_skb_arr *q_skba, int rq_nr,
-			      int num_wqes, int wqe_type, int packet_size)
-{
-	struct net_device *dev = pr->port->netdev;
-	struct ehea_qp *qp = pr->qp;
-	struct sk_buff **skb_arr = q_skba->arr;
-	struct ehea_rwqe *rwqe;
-	int i, index, max_index_mask, fill_wqes;
-	int adder = 0;
-	int ret = 0;
-
-	fill_wqes = q_skba->os_skbs + num_wqes;
-	q_skba->os_skbs = 0;
-
-	if (unlikely(test_bit(__EHEA_STOP_XFER, &ehea_driver_flags))) {
-		q_skba->os_skbs = fill_wqes;
-		return ret;
-	}
-
-	index = q_skba->index;
-	max_index_mask = q_skba->len - 1;
-	for (i = 0; i < fill_wqes; i++) {
-		u64 tmp_addr;
-		struct sk_buff *skb;
-
-		skb = netdev_alloc_skb_ip_align(dev, packet_size);
-		if (!skb) {
-			q_skba->os_skbs = fill_wqes - i;
-			if (q_skba->os_skbs == q_skba->len - 2) {
-				netdev_info(pr->port->netdev,
-					    "rq%i ran dry - no mem for skb\n",
-					    rq_nr);
-				ret = -ENOMEM;
-			}
-			break;
-		}
-
-		skb_arr[index] = skb;
-		tmp_addr = ehea_map_vaddr(skb->data);
-		if (tmp_addr == -1) {
-			dev_consume_skb_any(skb);
-			q_skba->os_skbs = fill_wqes - i;
-			ret = 0;
-			break;
-		}
-
-		rwqe = ehea_get_next_rwqe(qp, rq_nr);
-		rwqe->wr_id = EHEA_BMASK_SET(EHEA_WR_ID_TYPE, wqe_type)
-			    | EHEA_BMASK_SET(EHEA_WR_ID_INDEX, index);
-		rwqe->sg_list[0].l_key = pr->recv_mr.lkey;
-		rwqe->sg_list[0].vaddr = tmp_addr;
-		rwqe->sg_list[0].len = packet_size;
-		rwqe->data_segments = 1;
-
-		index++;
-		index &= max_index_mask;
-		adder++;
-	}
-
-	q_skba->index = index;
-	if (adder == 0)
-		goto out;
-
-	/* Ring doorbell */
-	iosync();
-	if (rq_nr == 2)
-		ehea_update_rq2a(pr->qp, adder);
-	else
-		ehea_update_rq3a(pr->qp, adder);
-out:
-	return ret;
-}
-
-
-static int ehea_refill_rq2(struct ehea_port_res *pr, int nr_of_wqes)
-{
-	return ehea_refill_rq_def(pr, &pr->rq2_skba, 2,
-				  nr_of_wqes, EHEA_RWQE2_TYPE,
-				  EHEA_RQ2_PKT_SIZE);
-}
-
-
-static int ehea_refill_rq3(struct ehea_port_res *pr, int nr_of_wqes)
-{
-	return ehea_refill_rq_def(pr, &pr->rq3_skba, 3,
-				  nr_of_wqes, EHEA_RWQE3_TYPE,
-				  EHEA_MAX_PACKET_SIZE);
-}
-
-static inline int ehea_check_cqe(struct ehea_cqe *cqe, int *rq_num)
-{
-	*rq_num = (cqe->type & EHEA_CQE_TYPE_RQ) >> 5;
-	if ((cqe->status & EHEA_CQE_STAT_ERR_MASK) == 0)
-		return 0;
-	if (((cqe->status & EHEA_CQE_STAT_ERR_TCP) != 0) &&
-	    (cqe->header_length == 0))
-		return 0;
-	return -EINVAL;
-}
-
-static inline void ehea_fill_skb(struct net_device *dev,
-				 struct sk_buff *skb, struct ehea_cqe *cqe,
-				 struct ehea_port_res *pr)
-{
-	int length = cqe->num_bytes_transfered - 4;	/*remove CRC */
-
-	skb_put(skb, length);
-	skb->protocol = eth_type_trans(skb, dev);
-
-	/* The packet was not an IPV4 packet so a complemented checksum was
-	   calculated. The value is found in the Internet Checksum field. */
-	if (cqe->status & EHEA_CQE_BLIND_CKSUM) {
-		skb->ip_summed = CHECKSUM_COMPLETE;
-		skb->csum = csum_unfold(~cqe->inet_checksum_value);
-	} else
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-
-	skb_record_rx_queue(skb, pr - &pr->port->port_res[0]);
-}
-
-static inline struct sk_buff *get_skb_by_index(struct sk_buff **skb_array,
-					       int arr_len,
-					       struct ehea_cqe *cqe)
-{
-	int skb_index = EHEA_BMASK_GET(EHEA_WR_ID_INDEX, cqe->wr_id);
-	struct sk_buff *skb;
-	void *pref;
-	int x;
-
-	x = skb_index + 1;
-	x &= (arr_len - 1);
-
-	pref = skb_array[x];
-	if (pref) {
-		prefetchw(pref);
-		prefetchw(pref + EHEA_CACHE_LINE);
-
-		pref = (skb_array[x]->data);
-		prefetch(pref);
-		prefetch(pref + EHEA_CACHE_LINE);
-		prefetch(pref + EHEA_CACHE_LINE * 2);
-		prefetch(pref + EHEA_CACHE_LINE * 3);
-	}
-
-	skb = skb_array[skb_index];
-	skb_array[skb_index] = NULL;
-	return skb;
-}
-
-static inline struct sk_buff *get_skb_by_index_ll(struct sk_buff **skb_array,
-						  int arr_len, int wqe_index)
-{
-	struct sk_buff *skb;
-	void *pref;
-	int x;
-
-	x = wqe_index + 1;
-	x &= (arr_len - 1);
-
-	pref = skb_array[x];
-	if (pref) {
-		prefetchw(pref);
-		prefetchw(pref + EHEA_CACHE_LINE);
-
-		pref = (skb_array[x]->data);
-		prefetchw(pref);
-		prefetchw(pref + EHEA_CACHE_LINE);
-	}
-
-	skb = skb_array[wqe_index];
-	skb_array[wqe_index] = NULL;
-	return skb;
-}
-
-static int ehea_treat_poll_error(struct ehea_port_res *pr, int rq,
-				 struct ehea_cqe *cqe, int *processed_rq2,
-				 int *processed_rq3)
-{
-	struct sk_buff *skb;
-
-	if (cqe->status & EHEA_CQE_STAT_ERR_TCP)
-		pr->p_stats.err_tcp_cksum++;
-	if (cqe->status & EHEA_CQE_STAT_ERR_IP)
-		pr->p_stats.err_ip_cksum++;
-	if (cqe->status & EHEA_CQE_STAT_ERR_CRC)
-		pr->p_stats.err_frame_crc++;
-
-	if (rq == 2) {
-		*processed_rq2 += 1;
-		skb = get_skb_by_index(pr->rq2_skba.arr, pr->rq2_skba.len, cqe);
-		dev_kfree_skb(skb);
-	} else if (rq == 3) {
-		*processed_rq3 += 1;
-		skb = get_skb_by_index(pr->rq3_skba.arr, pr->rq3_skba.len, cqe);
-		dev_kfree_skb(skb);
-	}
-
-	if (cqe->status & EHEA_CQE_STAT_FAT_ERR_MASK) {
-		if (netif_msg_rx_err(pr->port)) {
-			pr_err("Critical receive error for QP %d. Resetting port.\n",
-			       pr->qp->init_attr.qp_nr);
-			ehea_dump(cqe, sizeof(*cqe), "CQE");
-		}
-		ehea_schedule_port_reset(pr->port);
-		return 1;
-	}
-
-	return 0;
-}
-
-static int ehea_proc_rwqes(struct net_device *dev,
-			   struct ehea_port_res *pr,
-			   int budget)
-{
-	struct ehea_port *port = pr->port;
-	struct ehea_qp *qp = pr->qp;
-	struct ehea_cqe *cqe;
-	struct sk_buff *skb;
-	struct sk_buff **skb_arr_rq1 = pr->rq1_skba.arr;
-	struct sk_buff **skb_arr_rq2 = pr->rq2_skba.arr;
-	struct sk_buff **skb_arr_rq3 = pr->rq3_skba.arr;
-	int skb_arr_rq1_len = pr->rq1_skba.len;
-	int skb_arr_rq2_len = pr->rq2_skba.len;
-	int skb_arr_rq3_len = pr->rq3_skba.len;
-	int processed, processed_rq1, processed_rq2, processed_rq3;
-	u64 processed_bytes = 0;
-	int wqe_index, last_wqe_index, rq, port_reset;
-
-	processed = processed_rq1 = processed_rq2 = processed_rq3 = 0;
-	last_wqe_index = 0;
-
-	cqe = ehea_poll_rq1(qp, &wqe_index);
-	while ((processed < budget) && cqe) {
-		ehea_inc_rq1(qp);
-		processed_rq1++;
-		processed++;
-		if (netif_msg_rx_status(port))
-			ehea_dump(cqe, sizeof(*cqe), "CQE");
-
-		last_wqe_index = wqe_index;
-		rmb();
-		if (!ehea_check_cqe(cqe, &rq)) {
-			if (rq == 1) {
-				/* LL RQ1 */
-				skb = get_skb_by_index_ll(skb_arr_rq1,
-							  skb_arr_rq1_len,
-							  wqe_index);
-				if (unlikely(!skb)) {
-					netif_info(port, rx_err, dev,
-						  "LL rq1: skb=NULL\n");
-
-					skb = netdev_alloc_skb(dev,
-							       EHEA_L_PKT_SIZE);
-					if (!skb)
-						break;
-				}
-				skb_copy_to_linear_data(skb, ((char *)cqe) + 64,
-						 cqe->num_bytes_transfered - 4);
-				ehea_fill_skb(dev, skb, cqe, pr);
-			} else if (rq == 2) {
-				/* RQ2 */
-				skb = get_skb_by_index(skb_arr_rq2,
-						       skb_arr_rq2_len, cqe);
-				if (unlikely(!skb)) {
-					netif_err(port, rx_err, dev,
-						  "rq2: skb=NULL\n");
-					break;
-				}
-				ehea_fill_skb(dev, skb, cqe, pr);
-				processed_rq2++;
-			} else {
-				/* RQ3 */
-				skb = get_skb_by_index(skb_arr_rq3,
-						       skb_arr_rq3_len, cqe);
-				if (unlikely(!skb)) {
-					netif_err(port, rx_err, dev,
-						  "rq3: skb=NULL\n");
-					break;
-				}
-				ehea_fill_skb(dev, skb, cqe, pr);
-				processed_rq3++;
-			}
-
-			processed_bytes += skb->len;
-
-			if (cqe->status & EHEA_CQE_VLAN_TAG_XTRACT)
-				__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
-						       cqe->vlan_tag);
-
-			napi_gro_receive(&pr->napi, skb);
-		} else {
-			pr->p_stats.poll_receive_errors++;
-			port_reset = ehea_treat_poll_error(pr, rq, cqe,
-							   &processed_rq2,
-							   &processed_rq3);
-			if (port_reset)
-				break;
-		}
-		cqe = ehea_poll_rq1(qp, &wqe_index);
-	}
-
-	pr->rx_packets += processed;
-	pr->rx_bytes += processed_bytes;
-
-	ehea_refill_rq1(pr, last_wqe_index, processed_rq1);
-	ehea_refill_rq2(pr, processed_rq2);
-	ehea_refill_rq3(pr, processed_rq3);
-
-	return processed;
-}
-
-#define SWQE_RESTART_CHECK 0xdeadbeaff00d0000ull
-
-static void reset_sq_restart_flag(struct ehea_port *port)
-{
-	int i;
-
-	for (i = 0; i < port->num_def_qps; i++) {
-		struct ehea_port_res *pr = &port->port_res[i];
-		pr->sq_restart_flag = 0;
-	}
-	wake_up(&port->restart_wq);
-}
-
-static void check_sqs(struct ehea_port *port)
-{
-	struct ehea_swqe *swqe;
-	int swqe_index;
-	int i;
-
-	for (i = 0; i < port->num_def_qps; i++) {
-		struct ehea_port_res *pr = &port->port_res[i];
-		int ret;
-		swqe = ehea_get_swqe(pr->qp, &swqe_index);
-		memset(swqe, 0, SWQE_HEADER_SIZE);
-		atomic_dec(&pr->swqe_avail);
-
-		swqe->tx_control |= EHEA_SWQE_PURGE;
-		swqe->wr_id = SWQE_RESTART_CHECK;
-		swqe->tx_control |= EHEA_SWQE_SIGNALLED_COMPLETION;
-		swqe->tx_control |= EHEA_SWQE_IMM_DATA_PRESENT;
-		swqe->immediate_data_length = 80;
-
-		ehea_post_swqe(pr->qp, swqe);
-
-		ret = wait_event_timeout(port->restart_wq,
-					 pr->sq_restart_flag == 0,
-					 msecs_to_jiffies(100));
-
-		if (!ret) {
-			pr_err("HW/SW queues out of sync\n");
-			ehea_schedule_port_reset(pr->port);
-			return;
-		}
-	}
-}
-
-
-static struct ehea_cqe *ehea_proc_cqes(struct ehea_port_res *pr, int my_quota)
-{
-	struct sk_buff *skb;
-	struct ehea_cq *send_cq = pr->send_cq;
-	struct ehea_cqe *cqe;
-	int quota = my_quota;
-	int cqe_counter = 0;
-	int swqe_av = 0;
-	int index;
-	struct netdev_queue *txq = netdev_get_tx_queue(pr->port->netdev,
-						pr - &pr->port->port_res[0]);
-
-	cqe = ehea_poll_cq(send_cq);
-	while (cqe && (quota > 0)) {
-		ehea_inc_cq(send_cq);
-
-		cqe_counter++;
-		rmb();
-
-		if (cqe->wr_id == SWQE_RESTART_CHECK) {
-			pr->sq_restart_flag = 1;
-			swqe_av++;
-			break;
-		}
-
-		if (cqe->status & EHEA_CQE_STAT_ERR_MASK) {
-			pr_err("Bad send completion status=0x%04X\n",
-			       cqe->status);
-
-			if (netif_msg_tx_err(pr->port))
-				ehea_dump(cqe, sizeof(*cqe), "Send CQE");
-
-			if (cqe->status & EHEA_CQE_STAT_RESET_MASK) {
-				pr_err("Resetting port\n");
-				ehea_schedule_port_reset(pr->port);
-				break;
-			}
-		}
-
-		if (netif_msg_tx_done(pr->port))
-			ehea_dump(cqe, sizeof(*cqe), "CQE");
-
-		if (likely(EHEA_BMASK_GET(EHEA_WR_ID_TYPE, cqe->wr_id)
-			   == EHEA_SWQE2_TYPE)) {
-
-			index = EHEA_BMASK_GET(EHEA_WR_ID_INDEX, cqe->wr_id);
-			skb = pr->sq_skba.arr[index];
-			dev_consume_skb_any(skb);
-			pr->sq_skba.arr[index] = NULL;
-		}
-
-		swqe_av += EHEA_BMASK_GET(EHEA_WR_ID_REFILL, cqe->wr_id);
-		quota--;
-
-		cqe = ehea_poll_cq(send_cq);
-	}
-
-	ehea_update_feca(send_cq, cqe_counter);
-	atomic_add(swqe_av, &pr->swqe_avail);
-
-	if (unlikely(netif_tx_queue_stopped(txq) &&
-		     (atomic_read(&pr->swqe_avail) >= pr->swqe_refill_th))) {
-		__netif_tx_lock(txq, smp_processor_id());
-		if (netif_tx_queue_stopped(txq) &&
-		    (atomic_read(&pr->swqe_avail) >= pr->swqe_refill_th))
-			netif_tx_wake_queue(txq);
-		__netif_tx_unlock(txq);
-	}
-
-	wake_up(&pr->port->swqe_avail_wq);
-
-	return cqe;
-}
-
-#define EHEA_POLL_MAX_CQES 65535
-
-static int ehea_poll(struct napi_struct *napi, int budget)
-{
-	struct ehea_port_res *pr = container_of(napi, struct ehea_port_res,
-						napi);
-	struct net_device *dev = pr->port->netdev;
-	struct ehea_cqe *cqe;
-	struct ehea_cqe *cqe_skb = NULL;
-	int wqe_index;
-	int rx = 0;
-
-	cqe_skb = ehea_proc_cqes(pr, EHEA_POLL_MAX_CQES);
-	rx += ehea_proc_rwqes(dev, pr, budget - rx);
-
-	while (rx != budget) {
-		napi_complete(napi);
-		ehea_reset_cq_ep(pr->recv_cq);
-		ehea_reset_cq_ep(pr->send_cq);
-		ehea_reset_cq_n1(pr->recv_cq);
-		ehea_reset_cq_n1(pr->send_cq);
-		rmb();
-		cqe = ehea_poll_rq1(pr->qp, &wqe_index);
-		cqe_skb = ehea_poll_cq(pr->send_cq);
-
-		if (!cqe && !cqe_skb)
-			return rx;
-
-		if (!napi_schedule(napi))
-			return rx;
-
-		cqe_skb = ehea_proc_cqes(pr, EHEA_POLL_MAX_CQES);
-		rx += ehea_proc_rwqes(dev, pr, budget - rx);
-	}
-
-	return rx;
-}
-
-static irqreturn_t ehea_recv_irq_handler(int irq, void *param)
-{
-	struct ehea_port_res *pr = param;
-
-	napi_schedule(&pr->napi);
-
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t ehea_qp_aff_irq_handler(int irq, void *param)
-{
-	struct ehea_port *port = param;
-	struct ehea_eqe *eqe;
-	struct ehea_qp *qp;
-	u32 qp_token;
-	u64 resource_type, aer, aerr;
-	int reset_port = 0;
-
-	eqe = ehea_poll_eq(port->qp_eq);
-
-	while (eqe) {
-		qp_token = EHEA_BMASK_GET(EHEA_EQE_QP_TOKEN, eqe->entry);
-		pr_err("QP aff_err: entry=0x%llx, token=0x%x\n",
-		       eqe->entry, qp_token);
-
-		qp = port->port_res[qp_token].qp;
-
-		resource_type = ehea_error_data(port->adapter, qp->fw_handle,
-						&aer, &aerr);
-
-		if (resource_type == EHEA_AER_RESTYPE_QP) {
-			if ((aer & EHEA_AER_RESET_MASK) ||
-			    (aerr & EHEA_AERR_RESET_MASK))
-				 reset_port = 1;
-		} else
-			reset_port = 1;   /* Reset in case of CQ or EQ error */
-
-		eqe = ehea_poll_eq(port->qp_eq);
-	}
-
-	if (reset_port) {
-		pr_err("Resetting port\n");
-		ehea_schedule_port_reset(port);
-	}
-
-	return IRQ_HANDLED;
-}
-
-static struct ehea_port *ehea_get_port(struct ehea_adapter *adapter,
-				       int logical_port)
-{
-	int i;
-
-	for (i = 0; i < EHEA_MAX_PORTS; i++)
-		if (adapter->port[i])
-			if (adapter->port[i]->logical_port_id == logical_port)
-				return adapter->port[i];
-	return NULL;
-}
-
-int ehea_sense_port_attr(struct ehea_port *port)
-{
-	int ret;
-	u64 hret;
-	struct hcp_ehea_port_cb0 *cb0;
-
-	/* may be called via ehea_neq_tasklet() */
-	cb0 = (void *)get_zeroed_page(GFP_ATOMIC);
-	if (!cb0) {
-		pr_err("no mem for cb0\n");
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	hret = ehea_h_query_ehea_port(port->adapter->handle,
-				      port->logical_port_id, H_PORT_CB0,
-				      EHEA_BMASK_SET(H_PORT_CB0_ALL, 0xFFFF),
-				      cb0);
-	if (hret != H_SUCCESS) {
-		ret = -EIO;
-		goto out_free;
-	}
-
-	/* MAC address */
-	port->mac_addr = cb0->port_mac_addr << 16;
-
-	if (!is_valid_ether_addr((u8 *)&port->mac_addr)) {
-		ret = -EADDRNOTAVAIL;
-		goto out_free;
-	}
-
-	/* Port speed */
-	switch (cb0->port_speed) {
-	case H_SPEED_10M_H:
-		port->port_speed = EHEA_SPEED_10M;
-		port->full_duplex = 0;
-		break;
-	case H_SPEED_10M_F:
-		port->port_speed = EHEA_SPEED_10M;
-		port->full_duplex = 1;
-		break;
-	case H_SPEED_100M_H:
-		port->port_speed = EHEA_SPEED_100M;
-		port->full_duplex = 0;
-		break;
-	case H_SPEED_100M_F:
-		port->port_speed = EHEA_SPEED_100M;
-		port->full_duplex = 1;
-		break;
-	case H_SPEED_1G_F:
-		port->port_speed = EHEA_SPEED_1G;
-		port->full_duplex = 1;
-		break;
-	case H_SPEED_10G_F:
-		port->port_speed = EHEA_SPEED_10G;
-		port->full_duplex = 1;
-		break;
-	default:
-		port->port_speed = 0;
-		port->full_duplex = 0;
-		break;
-	}
-
-	port->autoneg = 1;
-	port->num_mcs = cb0->num_default_qps;
-
-	/* Number of default QPs */
-	if (use_mcs)
-		port->num_def_qps = cb0->num_default_qps;
-	else
-		port->num_def_qps = 1;
-
-	if (!port->num_def_qps) {
-		ret = -EINVAL;
-		goto out_free;
-	}
-
-	ret = 0;
-out_free:
-	if (ret || netif_msg_probe(port))
-		ehea_dump(cb0, sizeof(*cb0), "ehea_sense_port_attr");
-	free_page((unsigned long)cb0);
-out:
-	return ret;
-}
-
-int ehea_set_portspeed(struct ehea_port *port, u32 port_speed)
-{
-	struct hcp_ehea_port_cb4 *cb4;
-	u64 hret;
-	int ret = 0;
-
-	cb4 = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!cb4) {
-		pr_err("no mem for cb4\n");
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	cb4->port_speed = port_speed;
-
-	netif_carrier_off(port->netdev);
-
-	hret = ehea_h_modify_ehea_port(port->adapter->handle,
-				       port->logical_port_id,
-				       H_PORT_CB4, H_PORT_CB4_SPEED, cb4);
-	if (hret == H_SUCCESS) {
-		port->autoneg = port_speed == EHEA_SPEED_AUTONEG ? 1 : 0;
-
-		hret = ehea_h_query_ehea_port(port->adapter->handle,
-					      port->logical_port_id,
-					      H_PORT_CB4, H_PORT_CB4_SPEED,
-					      cb4);
-		if (hret == H_SUCCESS) {
-			switch (cb4->port_speed) {
-			case H_SPEED_10M_H:
-				port->port_speed = EHEA_SPEED_10M;
-				port->full_duplex = 0;
-				break;
-			case H_SPEED_10M_F:
-				port->port_speed = EHEA_SPEED_10M;
-				port->full_duplex = 1;
-				break;
-			case H_SPEED_100M_H:
-				port->port_speed = EHEA_SPEED_100M;
-				port->full_duplex = 0;
-				break;
-			case H_SPEED_100M_F:
-				port->port_speed = EHEA_SPEED_100M;
-				port->full_duplex = 1;
-				break;
-			case H_SPEED_1G_F:
-				port->port_speed = EHEA_SPEED_1G;
-				port->full_duplex = 1;
-				break;
-			case H_SPEED_10G_F:
-				port->port_speed = EHEA_SPEED_10G;
-				port->full_duplex = 1;
-				break;
-			default:
-				port->port_speed = 0;
-				port->full_duplex = 0;
-				break;
-			}
-		} else {
-			pr_err("Failed sensing port speed\n");
-			ret = -EIO;
-		}
-	} else {
-		if (hret == H_AUTHORITY) {
-			pr_info("Hypervisor denied setting port speed\n");
-			ret = -EPERM;
-		} else {
-			ret = -EIO;
-			pr_err("Failed setting port speed\n");
-		}
-	}
-	if (!prop_carrier_state || (port->phy_link == EHEA_PHY_LINK_UP))
-		netif_carrier_on(port->netdev);
-
-	free_page((unsigned long)cb4);
-out:
-	return ret;
-}
-
-static void ehea_parse_eqe(struct ehea_adapter *adapter, u64 eqe)
-{
-	int ret;
-	u8 ec;
-	u8 portnum;
-	struct ehea_port *port;
-	struct net_device *dev;
-
-	ec = EHEA_BMASK_GET(NEQE_EVENT_CODE, eqe);
-	portnum = EHEA_BMASK_GET(NEQE_PORTNUM, eqe);
-	port = ehea_get_port(adapter, portnum);
-	if (!port) {
-		netdev_err(NULL, "unknown portnum %x\n", portnum);
-		return;
-	}
-	dev = port->netdev;
-
-	switch (ec) {
-	case EHEA_EC_PORTSTATE_CHG:	/* port state change */
-
-		if (EHEA_BMASK_GET(NEQE_PORT_UP, eqe)) {
-			if (!netif_carrier_ok(dev)) {
-				ret = ehea_sense_port_attr(port);
-				if (ret) {
-					netdev_err(dev, "failed resensing port attributes\n");
-					break;
-				}
-
-				netif_info(port, link, dev,
-					   "Logical port up: %dMbps %s Duplex\n",
-					   port->port_speed,
-					   port->full_duplex == 1 ?
-					   "Full" : "Half");
-
-				netif_carrier_on(dev);
-				netif_wake_queue(dev);
-			}
-		} else
-			if (netif_carrier_ok(dev)) {
-				netif_info(port, link, dev,
-					   "Logical port down\n");
-				netif_carrier_off(dev);
-				netif_tx_disable(dev);
-			}
-
-		if (EHEA_BMASK_GET(NEQE_EXTSWITCH_PORT_UP, eqe)) {
-			port->phy_link = EHEA_PHY_LINK_UP;
-			netif_info(port, link, dev,
-				   "Physical port up\n");
-			if (prop_carrier_state)
-				netif_carrier_on(dev);
-		} else {
-			port->phy_link = EHEA_PHY_LINK_DOWN;
-			netif_info(port, link, dev,
-				   "Physical port down\n");
-			if (prop_carrier_state)
-				netif_carrier_off(dev);
-		}
-
-		if (EHEA_BMASK_GET(NEQE_EXTSWITCH_PRIMARY, eqe))
-			netdev_info(dev,
-				    "External switch port is primary port\n");
-		else
-			netdev_info(dev,
-				    "External switch port is backup port\n");
-
-		break;
-	case EHEA_EC_ADAPTER_MALFUNC:
-		netdev_err(dev, "Adapter malfunction\n");
-		break;
-	case EHEA_EC_PORT_MALFUNC:
-		netdev_info(dev, "Port malfunction\n");
-		netif_carrier_off(dev);
-		netif_tx_disable(dev);
-		break;
-	default:
-		netdev_err(dev, "unknown event code %x, eqe=0x%llX\n", ec, eqe);
-		break;
-	}
-}
-
-static void ehea_neq_tasklet(struct tasklet_struct *t)
-{
-	struct ehea_adapter *adapter = from_tasklet(adapter, t, neq_tasklet);
-	struct ehea_eqe *eqe;
-	u64 event_mask;
-
-	eqe = ehea_poll_eq(adapter->neq);
-	pr_debug("eqe=%p\n", eqe);
-
-	while (eqe) {
-		pr_debug("*eqe=%lx\n", (unsigned long) eqe->entry);
-		ehea_parse_eqe(adapter, eqe->entry);
-		eqe = ehea_poll_eq(adapter->neq);
-		pr_debug("next eqe=%p\n", eqe);
-	}
-
-	event_mask = EHEA_BMASK_SET(NELR_PORTSTATE_CHG, 1)
-		   | EHEA_BMASK_SET(NELR_ADAPTER_MALFUNC, 1)
-		   | EHEA_BMASK_SET(NELR_PORT_MALFUNC, 1);
-
-	ehea_h_reset_events(adapter->handle,
-			    adapter->neq->fw_handle, event_mask);
-}
-
-static irqreturn_t ehea_interrupt_neq(int irq, void *param)
-{
-	struct ehea_adapter *adapter = param;
-	tasklet_hi_schedule(&adapter->neq_tasklet);
-	return IRQ_HANDLED;
-}
-
-
-static int ehea_fill_port_res(struct ehea_port_res *pr)
-{
-	int ret;
-	struct ehea_qp_init_attr *init_attr = &pr->qp->init_attr;
-
-	ehea_init_fill_rq1(pr, pr->rq1_skba.len);
-
-	ret = ehea_refill_rq2(pr, init_attr->act_nr_rwqes_rq2 - 1);
-
-	ret |= ehea_refill_rq3(pr, init_attr->act_nr_rwqes_rq3 - 1);
-
-	return ret;
-}
-
-static int ehea_reg_interrupts(struct net_device *dev)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	struct ehea_port_res *pr;
-	int i, ret;
-
-
-	snprintf(port->int_aff_name, EHEA_IRQ_NAME_SIZE - 1, "%s-aff",
-		 dev->name);
-
-	ret = ibmebus_request_irq(port->qp_eq->attr.ist1,
-				  ehea_qp_aff_irq_handler,
-				  0, port->int_aff_name, port);
-	if (ret) {
-		netdev_err(dev, "failed registering irq for qp_aff_irq_handler:ist=%X\n",
-			   port->qp_eq->attr.ist1);
-		goto out_free_qpeq;
-	}
-
-	netif_info(port, ifup, dev,
-		   "irq_handle 0x%X for function qp_aff_irq_handler registered\n",
-		   port->qp_eq->attr.ist1);
-
-
-	for (i = 0; i < port->num_def_qps; i++) {
-		pr = &port->port_res[i];
-		snprintf(pr->int_send_name, EHEA_IRQ_NAME_SIZE - 1,
-			 "%s-queue%d", dev->name, i);
-		ret = ibmebus_request_irq(pr->eq->attr.ist1,
-					  ehea_recv_irq_handler,
-					  0, pr->int_send_name, pr);
-		if (ret) {
-			netdev_err(dev, "failed registering irq for ehea_queue port_res_nr:%d, ist=%X\n",
-				   i, pr->eq->attr.ist1);
-			goto out_free_req;
-		}
-		netif_info(port, ifup, dev,
-			   "irq_handle 0x%X for function ehea_queue_int %d registered\n",
-			   pr->eq->attr.ist1, i);
-	}
-out:
-	return ret;
-
-
-out_free_req:
-	while (--i >= 0) {
-		u32 ist = port->port_res[i].eq->attr.ist1;
-		ibmebus_free_irq(ist, &port->port_res[i]);
-	}
-
-out_free_qpeq:
-	ibmebus_free_irq(port->qp_eq->attr.ist1, port);
-	i = port->num_def_qps;
-
-	goto out;
-
-}
-
-static void ehea_free_interrupts(struct net_device *dev)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	struct ehea_port_res *pr;
-	int i;
-
-	/* send */
-
-	for (i = 0; i < port->num_def_qps; i++) {
-		pr = &port->port_res[i];
-		ibmebus_free_irq(pr->eq->attr.ist1, pr);
-		netif_info(port, intr, dev,
-			   "free send irq for res %d with handle 0x%X\n",
-			   i, pr->eq->attr.ist1);
-	}
-
-	/* associated events */
-	ibmebus_free_irq(port->qp_eq->attr.ist1, port);
-	netif_info(port, intr, dev,
-		   "associated event interrupt for handle 0x%X freed\n",
-		   port->qp_eq->attr.ist1);
-}
-
-static int ehea_configure_port(struct ehea_port *port)
-{
-	int ret, i;
-	u64 hret, mask;
-	struct hcp_ehea_port_cb0 *cb0;
-
-	ret = -ENOMEM;
-	cb0 = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!cb0)
-		goto out;
-
-	cb0->port_rc = EHEA_BMASK_SET(PXLY_RC_VALID, 1)
-		     | EHEA_BMASK_SET(PXLY_RC_IP_CHKSUM, 1)
-		     | EHEA_BMASK_SET(PXLY_RC_TCP_UDP_CHKSUM, 1)
-		     | EHEA_BMASK_SET(PXLY_RC_VLAN_XTRACT, 1)
-		     | EHEA_BMASK_SET(PXLY_RC_VLAN_TAG_FILTER,
-				      PXLY_RC_VLAN_FILTER)
-		     | EHEA_BMASK_SET(PXLY_RC_JUMBO_FRAME, 1);
-
-	for (i = 0; i < port->num_mcs; i++)
-		if (use_mcs)
-			cb0->default_qpn_arr[i] =
-				port->port_res[i].qp->init_attr.qp_nr;
-		else
-			cb0->default_qpn_arr[i] =
-				port->port_res[0].qp->init_attr.qp_nr;
-
-	if (netif_msg_ifup(port))
-		ehea_dump(cb0, sizeof(*cb0), "ehea_configure_port");
-
-	mask = EHEA_BMASK_SET(H_PORT_CB0_PRC, 1)
-	     | EHEA_BMASK_SET(H_PORT_CB0_DEFQPNARRAY, 1);
-
-	hret = ehea_h_modify_ehea_port(port->adapter->handle,
-				       port->logical_port_id,
-				       H_PORT_CB0, mask, cb0);
-	ret = -EIO;
-	if (hret != H_SUCCESS)
-		goto out_free;
-
-	ret = 0;
-
-out_free:
-	free_page((unsigned long)cb0);
-out:
-	return ret;
-}
-
-static int ehea_gen_smrs(struct ehea_port_res *pr)
-{
-	int ret;
-	struct ehea_adapter *adapter = pr->port->adapter;
-
-	ret = ehea_gen_smr(adapter, &adapter->mr, &pr->send_mr);
-	if (ret)
-		goto out;
-
-	ret = ehea_gen_smr(adapter, &adapter->mr, &pr->recv_mr);
-	if (ret)
-		goto out_free;
-
-	return 0;
-
-out_free:
-	ehea_rem_mr(&pr->send_mr);
-out:
-	pr_err("Generating SMRS failed\n");
-	return -EIO;
-}
-
-static int ehea_rem_smrs(struct ehea_port_res *pr)
-{
-	if ((ehea_rem_mr(&pr->send_mr)) ||
-	    (ehea_rem_mr(&pr->recv_mr)))
-		return -EIO;
-	else
-		return 0;
-}
-
-static int ehea_init_q_skba(struct ehea_q_skb_arr *q_skba, int max_q_entries)
-{
-	int arr_size = sizeof(void *) * max_q_entries;
-
-	q_skba->arr = vzalloc(arr_size);
-	if (!q_skba->arr)
-		return -ENOMEM;
-
-	q_skba->len = max_q_entries;
-	q_skba->index = 0;
-	q_skba->os_skbs = 0;
-
-	return 0;
-}
-
-static int ehea_init_port_res(struct ehea_port *port, struct ehea_port_res *pr,
-			      struct port_res_cfg *pr_cfg, int queue_token)
-{
-	struct ehea_adapter *adapter = port->adapter;
-	enum ehea_eq_type eq_type = EHEA_EQ;
-	struct ehea_qp_init_attr *init_attr = NULL;
-	int ret = -EIO;
-	u64 tx_bytes, rx_bytes, tx_packets, rx_packets;
-
-	tx_bytes = pr->tx_bytes;
-	tx_packets = pr->tx_packets;
-	rx_bytes = pr->rx_bytes;
-	rx_packets = pr->rx_packets;
-
-	memset(pr, 0, sizeof(struct ehea_port_res));
-
-	pr->tx_bytes = tx_bytes;
-	pr->tx_packets = tx_packets;
-	pr->rx_bytes = rx_bytes;
-	pr->rx_packets = rx_packets;
-
-	pr->port = port;
-
-	pr->eq = ehea_create_eq(adapter, eq_type, EHEA_MAX_ENTRIES_EQ, 0);
-	if (!pr->eq) {
-		pr_err("create_eq failed (eq)\n");
-		goto out_free;
-	}
-
-	pr->recv_cq = ehea_create_cq(adapter, pr_cfg->max_entries_rcq,
-				     pr->eq->fw_handle,
-				     port->logical_port_id);
-	if (!pr->recv_cq) {
-		pr_err("create_cq failed (cq_recv)\n");
-		goto out_free;
-	}
-
-	pr->send_cq = ehea_create_cq(adapter, pr_cfg->max_entries_scq,
-				     pr->eq->fw_handle,
-				     port->logical_port_id);
-	if (!pr->send_cq) {
-		pr_err("create_cq failed (cq_send)\n");
-		goto out_free;
-	}
-
-	if (netif_msg_ifup(port))
-		pr_info("Send CQ: act_nr_cqes=%d, Recv CQ: act_nr_cqes=%d\n",
-			pr->send_cq->attr.act_nr_of_cqes,
-			pr->recv_cq->attr.act_nr_of_cqes);
-
-	init_attr = kzalloc_obj(*init_attr);
-	if (!init_attr) {
-		ret = -ENOMEM;
-		pr_err("no mem for ehea_qp_init_attr\n");
-		goto out_free;
-	}
-
-	init_attr->low_lat_rq1 = 1;
-	init_attr->signalingtype = 1;	/* generate CQE if specified in WQE */
-	init_attr->rq_count = 3;
-	init_attr->qp_token = queue_token;
-	init_attr->max_nr_send_wqes = pr_cfg->max_entries_sq;
-	init_attr->max_nr_rwqes_rq1 = pr_cfg->max_entries_rq1;
-	init_attr->max_nr_rwqes_rq2 = pr_cfg->max_entries_rq2;
-	init_attr->max_nr_rwqes_rq3 = pr_cfg->max_entries_rq3;
-	init_attr->wqe_size_enc_sq = EHEA_SG_SQ;
-	init_attr->wqe_size_enc_rq1 = EHEA_SG_RQ1;
-	init_attr->wqe_size_enc_rq2 = EHEA_SG_RQ2;
-	init_attr->wqe_size_enc_rq3 = EHEA_SG_RQ3;
-	init_attr->rq2_threshold = EHEA_RQ2_THRESHOLD;
-	init_attr->rq3_threshold = EHEA_RQ3_THRESHOLD;
-	init_attr->port_nr = port->logical_port_id;
-	init_attr->send_cq_handle = pr->send_cq->fw_handle;
-	init_attr->recv_cq_handle = pr->recv_cq->fw_handle;
-	init_attr->aff_eq_handle = port->qp_eq->fw_handle;
-
-	pr->qp = ehea_create_qp(adapter, adapter->pd, init_attr);
-	if (!pr->qp) {
-		pr_err("create_qp failed\n");
-		ret = -EIO;
-		goto out_free;
-	}
-
-	if (netif_msg_ifup(port))
-		pr_info("QP: qp_nr=%d\n act_nr_snd_wqe=%d\n nr_rwqe_rq1=%d\n nr_rwqe_rq2=%d\n nr_rwqe_rq3=%d\n",
-			init_attr->qp_nr,
-			init_attr->act_nr_send_wqes,
-			init_attr->act_nr_rwqes_rq1,
-			init_attr->act_nr_rwqes_rq2,
-			init_attr->act_nr_rwqes_rq3);
-
-	pr->sq_skba_size = init_attr->act_nr_send_wqes + 1;
-
-	ret = ehea_init_q_skba(&pr->sq_skba, pr->sq_skba_size);
-	ret |= ehea_init_q_skba(&pr->rq1_skba, init_attr->act_nr_rwqes_rq1 + 1);
-	ret |= ehea_init_q_skba(&pr->rq2_skba, init_attr->act_nr_rwqes_rq2 + 1);
-	ret |= ehea_init_q_skba(&pr->rq3_skba, init_attr->act_nr_rwqes_rq3 + 1);
-	if (ret)
-		goto out_free;
-
-	pr->swqe_refill_th = init_attr->act_nr_send_wqes / 10;
-	if (ehea_gen_smrs(pr) != 0) {
-		ret = -EIO;
-		goto out_free;
-	}
-
-	atomic_set(&pr->swqe_avail, init_attr->act_nr_send_wqes - 1);
-
-	kfree(init_attr);
-
-	netif_napi_add(pr->port->netdev, &pr->napi, ehea_poll);
-
-	ret = 0;
-	goto out;
-
-out_free:
-	kfree(init_attr);
-	vfree(pr->sq_skba.arr);
-	vfree(pr->rq1_skba.arr);
-	vfree(pr->rq2_skba.arr);
-	vfree(pr->rq3_skba.arr);
-	ehea_destroy_qp(pr->qp);
-	ehea_destroy_cq(pr->send_cq);
-	ehea_destroy_cq(pr->recv_cq);
-	ehea_destroy_eq(pr->eq);
-out:
-	return ret;
-}
-
-static int ehea_clean_portres(struct ehea_port *port, struct ehea_port_res *pr)
-{
-	int ret, i;
-
-	if (pr->qp)
-		netif_napi_del(&pr->napi);
-
-	ret = ehea_destroy_qp(pr->qp);
-
-	if (!ret) {
-		ehea_destroy_cq(pr->send_cq);
-		ehea_destroy_cq(pr->recv_cq);
-		ehea_destroy_eq(pr->eq);
-
-		for (i = 0; i < pr->rq1_skba.len; i++)
-			dev_kfree_skb(pr->rq1_skba.arr[i]);
-
-		for (i = 0; i < pr->rq2_skba.len; i++)
-			dev_kfree_skb(pr->rq2_skba.arr[i]);
-
-		for (i = 0; i < pr->rq3_skba.len; i++)
-			dev_kfree_skb(pr->rq3_skba.arr[i]);
-
-		for (i = 0; i < pr->sq_skba.len; i++)
-			dev_kfree_skb(pr->sq_skba.arr[i]);
-
-		vfree(pr->rq1_skba.arr);
-		vfree(pr->rq2_skba.arr);
-		vfree(pr->rq3_skba.arr);
-		vfree(pr->sq_skba.arr);
-		ret = ehea_rem_smrs(pr);
-	}
-	return ret;
-}
-
-static void write_swqe2_immediate(struct sk_buff *skb, struct ehea_swqe *swqe,
-				  u32 lkey)
-{
-	int skb_data_size = skb_headlen(skb);
-	u8 *imm_data = &swqe->u.immdata_desc.immediate_data[0];
-	struct ehea_vsgentry *sg1entry = &swqe->u.immdata_desc.sg_entry;
-	unsigned int immediate_len = SWQE2_MAX_IMM;
-
-	swqe->descriptors = 0;
-
-	if (skb_is_gso(skb)) {
-		swqe->tx_control |= EHEA_SWQE_TSO;
-		swqe->mss = skb_shinfo(skb)->gso_size;
-		/*
-		 * For TSO packets we only copy the headers into the
-		 * immediate area.
-		 */
-		immediate_len = skb_tcp_all_headers(skb);
-	}
-
-	if (skb_is_gso(skb) || skb_data_size >= SWQE2_MAX_IMM) {
-		skb_copy_from_linear_data(skb, imm_data, immediate_len);
-		swqe->immediate_data_length = immediate_len;
-
-		if (skb_data_size > immediate_len) {
-			sg1entry->l_key = lkey;
-			sg1entry->len = skb_data_size - immediate_len;
-			sg1entry->vaddr =
-				ehea_map_vaddr(skb->data + immediate_len);
-			swqe->descriptors++;
-		}
-	} else {
-		skb_copy_from_linear_data(skb, imm_data, skb_data_size);
-		swqe->immediate_data_length = skb_data_size;
-	}
-}
-
-static inline void write_swqe2_data(struct sk_buff *skb, struct net_device *dev,
-				    struct ehea_swqe *swqe, u32 lkey)
-{
-	struct ehea_vsgentry *sg_list, *sg1entry, *sgentry;
-	skb_frag_t *frag;
-	int nfrags, sg1entry_contains_frag_data, i;
-
-	nfrags = skb_shinfo(skb)->nr_frags;
-	sg1entry = &swqe->u.immdata_desc.sg_entry;
-	sg_list = (struct ehea_vsgentry *)&swqe->u.immdata_desc.sg_list;
-	sg1entry_contains_frag_data = 0;
-
-	write_swqe2_immediate(skb, swqe, lkey);
-
-	/* write descriptors */
-	if (nfrags > 0) {
-		if (swqe->descriptors == 0) {
-			/* sg1entry not yet used */
-			frag = &skb_shinfo(skb)->frags[0];
-
-			/* copy sg1entry data */
-			sg1entry->l_key = lkey;
-			sg1entry->len = skb_frag_size(frag);
-			sg1entry->vaddr =
-				ehea_map_vaddr(skb_frag_address(frag));
-			swqe->descriptors++;
-			sg1entry_contains_frag_data = 1;
-		}
-
-		for (i = sg1entry_contains_frag_data; i < nfrags; i++) {
-
-			frag = &skb_shinfo(skb)->frags[i];
-			sgentry = &sg_list[i - sg1entry_contains_frag_data];
-
-			sgentry->l_key = lkey;
-			sgentry->len = skb_frag_size(frag);
-			sgentry->vaddr = ehea_map_vaddr(skb_frag_address(frag));
-			swqe->descriptors++;
-		}
-	}
-}
-
-static int ehea_broadcast_reg_helper(struct ehea_port *port, u32 hcallid)
-{
-	int ret = 0;
-	u64 hret;
-	u8 reg_type;
-
-	/* De/Register untagged packets */
-	reg_type = EHEA_BCMC_BROADCAST | EHEA_BCMC_UNTAGGED;
-	hret = ehea_h_reg_dereg_bcmc(port->adapter->handle,
-				     port->logical_port_id,
-				     reg_type, port->mac_addr, 0, hcallid);
-	if (hret != H_SUCCESS) {
-		pr_err("%sregistering bc address failed (tagged)\n",
-		       hcallid == H_REG_BCMC ? "" : "de");
-		ret = -EIO;
-		goto out_herr;
-	}
-
-	/* De/Register VLAN packets */
-	reg_type = EHEA_BCMC_BROADCAST | EHEA_BCMC_VLANID_ALL;
-	hret = ehea_h_reg_dereg_bcmc(port->adapter->handle,
-				     port->logical_port_id,
-				     reg_type, port->mac_addr, 0, hcallid);
-	if (hret != H_SUCCESS) {
-		pr_err("%sregistering bc address failed (vlan)\n",
-		       hcallid == H_REG_BCMC ? "" : "de");
-		ret = -EIO;
-	}
-out_herr:
-	return ret;
-}
-
-static int ehea_set_mac_addr(struct net_device *dev, void *sa)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	struct sockaddr *mac_addr = sa;
-	struct hcp_ehea_port_cb0 *cb0;
-	int ret;
-	u64 hret;
-
-	if (!is_valid_ether_addr(mac_addr->sa_data)) {
-		ret = -EADDRNOTAVAIL;
-		goto out;
-	}
-
-	cb0 = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!cb0) {
-		pr_err("no mem for cb0\n");
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	memcpy(&(cb0->port_mac_addr), &(mac_addr->sa_data[0]), ETH_ALEN);
-
-	cb0->port_mac_addr = cb0->port_mac_addr >> 16;
-
-	hret = ehea_h_modify_ehea_port(port->adapter->handle,
-				       port->logical_port_id, H_PORT_CB0,
-				       EHEA_BMASK_SET(H_PORT_CB0_MAC, 1), cb0);
-	if (hret != H_SUCCESS) {
-		ret = -EIO;
-		goto out_free;
-	}
-
-	eth_hw_addr_set(dev, mac_addr->sa_data);
-
-	/* Deregister old MAC in pHYP */
-	if (port->state == EHEA_PORT_UP) {
-		ret = ehea_broadcast_reg_helper(port, H_DEREG_BCMC);
-		if (ret)
-			goto out_upregs;
-	}
-
-	port->mac_addr = cb0->port_mac_addr << 16;
-
-	/* Register new MAC in pHYP */
-	if (port->state == EHEA_PORT_UP) {
-		ret = ehea_broadcast_reg_helper(port, H_REG_BCMC);
-		if (ret)
-			goto out_upregs;
-	}
-
-	ret = 0;
-
-out_upregs:
-	ehea_update_bcmc_registrations();
-out_free:
-	free_page((unsigned long)cb0);
-out:
-	return ret;
-}
-
-static void ehea_promiscuous_error(u64 hret, int enable)
-{
-	if (hret == H_AUTHORITY)
-		pr_info("Hypervisor denied %sabling promiscuous mode\n",
-			enable == 1 ? "en" : "dis");
-	else
-		pr_err("failed %sabling promiscuous mode\n",
-		       enable == 1 ? "en" : "dis");
-}
-
-static void ehea_promiscuous(struct net_device *dev, int enable)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	struct hcp_ehea_port_cb7 *cb7;
-	u64 hret;
-
-	if (enable == port->promisc)
-		return;
-
-	cb7 = (void *)get_zeroed_page(GFP_ATOMIC);
-	if (!cb7) {
-		pr_err("no mem for cb7\n");
-		goto out;
-	}
-
-	/* Modify Pxs_DUCQPN in CB7 */
-	cb7->def_uc_qpn = enable == 1 ? port->port_res[0].qp->fw_handle : 0;
-
-	hret = ehea_h_modify_ehea_port(port->adapter->handle,
-				       port->logical_port_id,
-				       H_PORT_CB7, H_PORT_CB7_DUCQPN, cb7);
-	if (hret) {
-		ehea_promiscuous_error(hret, enable);
-		goto out;
-	}
-
-	port->promisc = enable;
-out:
-	free_page((unsigned long)cb7);
-}
-
-static u64 ehea_multicast_reg_helper(struct ehea_port *port, u64 mc_mac_addr,
-				     u32 hcallid)
-{
-	u64 hret;
-	u8 reg_type;
-
-	reg_type = EHEA_BCMC_MULTICAST | EHEA_BCMC_UNTAGGED;
-	if (mc_mac_addr == 0)
-		reg_type |= EHEA_BCMC_SCOPE_ALL;
-
-	hret = ehea_h_reg_dereg_bcmc(port->adapter->handle,
-				     port->logical_port_id,
-				     reg_type, mc_mac_addr, 0, hcallid);
-	if (hret)
-		goto out;
-
-	reg_type = EHEA_BCMC_MULTICAST | EHEA_BCMC_VLANID_ALL;
-	if (mc_mac_addr == 0)
-		reg_type |= EHEA_BCMC_SCOPE_ALL;
-
-	hret = ehea_h_reg_dereg_bcmc(port->adapter->handle,
-				     port->logical_port_id,
-				     reg_type, mc_mac_addr, 0, hcallid);
-out:
-	return hret;
-}
-
-static int ehea_drop_multicast_list(struct net_device *dev)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	struct ehea_mc_list *mc_entry = port->mc_list;
-	struct list_head *pos;
-	struct list_head *temp;
-	int ret = 0;
-	u64 hret;
-
-	list_for_each_safe(pos, temp, &(port->mc_list->list)) {
-		mc_entry = list_entry(pos, struct ehea_mc_list, list);
-
-		hret = ehea_multicast_reg_helper(port, mc_entry->macaddr,
-						 H_DEREG_BCMC);
-		if (hret) {
-			pr_err("failed deregistering mcast MAC\n");
-			ret = -EIO;
-		}
-
-		list_del(pos);
-		kfree(mc_entry);
-	}
-	return ret;
-}
-
-static void ehea_allmulti(struct net_device *dev, int enable)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	u64 hret;
-
-	if (!port->allmulti) {
-		if (enable) {
-			/* Enable ALLMULTI */
-			ehea_drop_multicast_list(dev);
-			hret = ehea_multicast_reg_helper(port, 0, H_REG_BCMC);
-			if (!hret)
-				port->allmulti = 1;
-			else
-				netdev_err(dev,
-					   "failed enabling IFF_ALLMULTI\n");
-		}
-	} else {
-		if (!enable) {
-			/* Disable ALLMULTI */
-			hret = ehea_multicast_reg_helper(port, 0, H_DEREG_BCMC);
-			if (!hret)
-				port->allmulti = 0;
-			else
-				netdev_err(dev,
-					   "failed disabling IFF_ALLMULTI\n");
-		}
-	}
-}
-
-static void ehea_add_multicast_entry(struct ehea_port *port, u8 *mc_mac_addr)
-{
-	struct ehea_mc_list *ehea_mcl_entry;
-	u64 hret;
-
-	ehea_mcl_entry = kzalloc_obj(*ehea_mcl_entry, GFP_ATOMIC);
-	if (!ehea_mcl_entry)
-		return;
-
-	INIT_LIST_HEAD(&ehea_mcl_entry->list);
-
-	memcpy(&ehea_mcl_entry->macaddr, mc_mac_addr, ETH_ALEN);
-
-	hret = ehea_multicast_reg_helper(port, ehea_mcl_entry->macaddr,
-					 H_REG_BCMC);
-	if (!hret)
-		list_add(&ehea_mcl_entry->list, &port->mc_list->list);
-	else {
-		pr_err("failed registering mcast MAC\n");
-		kfree(ehea_mcl_entry);
-	}
-}
-
-static void ehea_set_multicast_list(struct net_device *dev)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	struct netdev_hw_addr *ha;
-	int ret;
-
-	ehea_promiscuous(dev, !!(dev->flags & IFF_PROMISC));
-
-	if (dev->flags & IFF_ALLMULTI) {
-		ehea_allmulti(dev, 1);
-		goto out;
-	}
-	ehea_allmulti(dev, 0);
-
-	if (!netdev_mc_empty(dev)) {
-		ret = ehea_drop_multicast_list(dev);
-		if (ret) {
-			/* Dropping the current multicast list failed.
-			 * Enabling ALL_MULTI is the best we can do.
-			 */
-			ehea_allmulti(dev, 1);
-		}
-
-		if (netdev_mc_count(dev) > port->adapter->max_mc_mac) {
-			pr_info("Mcast registration limit reached (0x%llx). Use ALLMULTI!\n",
-				port->adapter->max_mc_mac);
-			goto out;
-		}
-
-		netdev_for_each_mc_addr(ha, dev)
-			ehea_add_multicast_entry(port, ha->addr);
-
-	}
-out:
-	ehea_update_bcmc_registrations();
-}
-
-static void xmit_common(struct sk_buff *skb, struct ehea_swqe *swqe)
-{
-	swqe->tx_control |= EHEA_SWQE_IMM_DATA_PRESENT | EHEA_SWQE_CRC;
-
-	if (vlan_get_protocol(skb) != htons(ETH_P_IP))
-		return;
-
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
-		swqe->tx_control |= EHEA_SWQE_IP_CHECKSUM;
-
-	swqe->ip_start = skb_network_offset(skb);
-	swqe->ip_end = swqe->ip_start + ip_hdrlen(skb) - 1;
-
-	switch (ip_hdr(skb)->protocol) {
-	case IPPROTO_UDP:
-		if (skb->ip_summed == CHECKSUM_PARTIAL)
-			swqe->tx_control |= EHEA_SWQE_TCP_CHECKSUM;
-
-		swqe->tcp_offset = swqe->ip_end + 1 +
-				   offsetof(struct udphdr, check);
-		break;
-
-	case IPPROTO_TCP:
-		if (skb->ip_summed == CHECKSUM_PARTIAL)
-			swqe->tx_control |= EHEA_SWQE_TCP_CHECKSUM;
-
-		swqe->tcp_offset = swqe->ip_end + 1 +
-				   offsetof(struct tcphdr, check);
-		break;
-	}
-}
-
-static void ehea_xmit2(struct sk_buff *skb, struct net_device *dev,
-		       struct ehea_swqe *swqe, u32 lkey)
-{
-	swqe->tx_control |= EHEA_SWQE_DESCRIPTORS_PRESENT;
-
-	xmit_common(skb, swqe);
-
-	write_swqe2_data(skb, dev, swqe, lkey);
-}
-
-static void ehea_xmit3(struct sk_buff *skb, struct net_device *dev,
-		       struct ehea_swqe *swqe)
-{
-	u8 *imm_data = &swqe->u.immdata_nodesc.immediate_data[0];
-
-	xmit_common(skb, swqe);
-
-	if (!skb->data_len)
-		skb_copy_from_linear_data(skb, imm_data, skb->len);
-	else
-		skb_copy_bits(skb, 0, imm_data, skb->len);
-
-	swqe->immediate_data_length = skb->len;
-	dev_consume_skb_any(skb);
-}
-
-static netdev_tx_t ehea_start_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	struct ehea_swqe *swqe;
-	u32 lkey;
-	int swqe_index;
-	struct ehea_port_res *pr;
-	struct netdev_queue *txq;
-
-	pr = &port->port_res[skb_get_queue_mapping(skb)];
-	txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
-
-	swqe = ehea_get_swqe(pr->qp, &swqe_index);
-	memset(swqe, 0, SWQE_HEADER_SIZE);
-	atomic_dec(&pr->swqe_avail);
-
-	if (skb_vlan_tag_present(skb)) {
-		swqe->tx_control |= EHEA_SWQE_VLAN_INSERT;
-		swqe->vlan_tag = skb_vlan_tag_get(skb);
-	}
-
-	pr->tx_packets++;
-	pr->tx_bytes += skb->len;
-
-	if (skb->len <= SWQE3_MAX_IMM) {
-		u32 sig_iv = port->sig_comp_iv;
-		u32 swqe_num = pr->swqe_id_counter;
-		ehea_xmit3(skb, dev, swqe);
-		swqe->wr_id = EHEA_BMASK_SET(EHEA_WR_ID_TYPE, EHEA_SWQE3_TYPE)
-			| EHEA_BMASK_SET(EHEA_WR_ID_COUNT, swqe_num);
-		if (pr->swqe_ll_count >= (sig_iv - 1)) {
-			swqe->wr_id |= EHEA_BMASK_SET(EHEA_WR_ID_REFILL,
-						      sig_iv);
-			swqe->tx_control |= EHEA_SWQE_SIGNALLED_COMPLETION;
-			pr->swqe_ll_count = 0;
-		} else
-			pr->swqe_ll_count += 1;
-	} else {
-		swqe->wr_id =
-			EHEA_BMASK_SET(EHEA_WR_ID_TYPE, EHEA_SWQE2_TYPE)
-		      | EHEA_BMASK_SET(EHEA_WR_ID_COUNT, pr->swqe_id_counter)
-		      | EHEA_BMASK_SET(EHEA_WR_ID_REFILL, 1)
-		      | EHEA_BMASK_SET(EHEA_WR_ID_INDEX, pr->sq_skba.index);
-		pr->sq_skba.arr[pr->sq_skba.index] = skb;
-
-		pr->sq_skba.index++;
-		pr->sq_skba.index &= (pr->sq_skba.len - 1);
-
-		lkey = pr->send_mr.lkey;
-		ehea_xmit2(skb, dev, swqe, lkey);
-		swqe->tx_control |= EHEA_SWQE_SIGNALLED_COMPLETION;
-	}
-	pr->swqe_id_counter += 1;
-
-	netif_info(port, tx_queued, dev,
-		   "post swqe on QP %d\n", pr->qp->init_attr.qp_nr);
-	if (netif_msg_tx_queued(port))
-		ehea_dump(swqe, 512, "swqe");
-
-	if (unlikely(test_bit(__EHEA_STOP_XFER, &ehea_driver_flags))) {
-		netif_tx_stop_queue(txq);
-		swqe->tx_control |= EHEA_SWQE_PURGE;
-	}
-
-	ehea_post_swqe(pr->qp, swqe);
-
-	if (unlikely(atomic_read(&pr->swqe_avail) <= 1)) {
-		pr->p_stats.queue_stopped++;
-		netif_tx_stop_queue(txq);
-	}
-
-	return NETDEV_TX_OK;
-}
-
-static int ehea_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	struct ehea_adapter *adapter = port->adapter;
-	struct hcp_ehea_port_cb1 *cb1;
-	int index;
-	u64 hret;
-	int err = 0;
-
-	cb1 = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!cb1) {
-		pr_err("no mem for cb1\n");
-		err = -ENOMEM;
-		goto out;
-	}
-
-	hret = ehea_h_query_ehea_port(adapter->handle, port->logical_port_id,
-				      H_PORT_CB1, H_PORT_CB1_ALL, cb1);
-	if (hret != H_SUCCESS) {
-		pr_err("query_ehea_port failed\n");
-		err = -EINVAL;
-		goto out;
-	}
-
-	index = (vid / 64);
-	cb1->vlan_filter[index] |= ((u64)(0x8000000000000000 >> (vid & 0x3F)));
-
-	hret = ehea_h_modify_ehea_port(adapter->handle, port->logical_port_id,
-				       H_PORT_CB1, H_PORT_CB1_ALL, cb1);
-	if (hret != H_SUCCESS) {
-		pr_err("modify_ehea_port failed\n");
-		err = -EINVAL;
-	}
-out:
-	free_page((unsigned long)cb1);
-	return err;
-}
-
-static int ehea_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	struct ehea_adapter *adapter = port->adapter;
-	struct hcp_ehea_port_cb1 *cb1;
-	int index;
-	u64 hret;
-	int err = 0;
-
-	cb1 = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!cb1) {
-		pr_err("no mem for cb1\n");
-		err = -ENOMEM;
-		goto out;
-	}
-
-	hret = ehea_h_query_ehea_port(adapter->handle, port->logical_port_id,
-				      H_PORT_CB1, H_PORT_CB1_ALL, cb1);
-	if (hret != H_SUCCESS) {
-		pr_err("query_ehea_port failed\n");
-		err = -EINVAL;
-		goto out;
-	}
-
-	index = (vid / 64);
-	cb1->vlan_filter[index] &= ~((u64)(0x8000000000000000 >> (vid & 0x3F)));
-
-	hret = ehea_h_modify_ehea_port(adapter->handle, port->logical_port_id,
-				       H_PORT_CB1, H_PORT_CB1_ALL, cb1);
-	if (hret != H_SUCCESS) {
-		pr_err("modify_ehea_port failed\n");
-		err = -EINVAL;
-	}
-out:
-	free_page((unsigned long)cb1);
-	return err;
-}
-
-static int ehea_activate_qp(struct ehea_adapter *adapter, struct ehea_qp *qp)
-{
-	int ret = -EIO;
-	u64 hret;
-	u16 dummy16 = 0;
-	u64 dummy64 = 0;
-	struct hcp_modify_qp_cb0 *cb0;
-
-	cb0 = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!cb0) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle,
-				    EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF), cb0);
-	if (hret != H_SUCCESS) {
-		pr_err("query_ehea_qp failed (1)\n");
-		goto out;
-	}
-
-	cb0->qp_ctl_reg = H_QP_CR_STATE_INITIALIZED;
-	hret = ehea_h_modify_ehea_qp(adapter->handle, 0, qp->fw_handle,
-				     EHEA_BMASK_SET(H_QPCB0_QP_CTL_REG, 1), cb0,
-				     &dummy64, &dummy64, &dummy16, &dummy16);
-	if (hret != H_SUCCESS) {
-		pr_err("modify_ehea_qp failed (1)\n");
-		goto out;
-	}
-
-	hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle,
-				    EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF), cb0);
-	if (hret != H_SUCCESS) {
-		pr_err("query_ehea_qp failed (2)\n");
-		goto out;
-	}
-
-	cb0->qp_ctl_reg = H_QP_CR_ENABLED | H_QP_CR_STATE_INITIALIZED;
-	hret = ehea_h_modify_ehea_qp(adapter->handle, 0, qp->fw_handle,
-				     EHEA_BMASK_SET(H_QPCB0_QP_CTL_REG, 1), cb0,
-				     &dummy64, &dummy64, &dummy16, &dummy16);
-	if (hret != H_SUCCESS) {
-		pr_err("modify_ehea_qp failed (2)\n");
-		goto out;
-	}
-
-	hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle,
-				    EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF), cb0);
-	if (hret != H_SUCCESS) {
-		pr_err("query_ehea_qp failed (3)\n");
-		goto out;
-	}
-
-	cb0->qp_ctl_reg = H_QP_CR_ENABLED | H_QP_CR_STATE_RDY2SND;
-	hret = ehea_h_modify_ehea_qp(adapter->handle, 0, qp->fw_handle,
-				     EHEA_BMASK_SET(H_QPCB0_QP_CTL_REG, 1), cb0,
-				     &dummy64, &dummy64, &dummy16, &dummy16);
-	if (hret != H_SUCCESS) {
-		pr_err("modify_ehea_qp failed (3)\n");
-		goto out;
-	}
-
-	hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle,
-				    EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF), cb0);
-	if (hret != H_SUCCESS) {
-		pr_err("query_ehea_qp failed (4)\n");
-		goto out;
-	}
-
-	ret = 0;
-out:
-	free_page((unsigned long)cb0);
-	return ret;
-}
-
-static int ehea_port_res_setup(struct ehea_port *port, int def_qps)
-{
-	int ret, i;
-	struct port_res_cfg pr_cfg, pr_cfg_small_rx;
-	enum ehea_eq_type eq_type = EHEA_EQ;
-
-	port->qp_eq = ehea_create_eq(port->adapter, eq_type,
-				   EHEA_MAX_ENTRIES_EQ, 1);
-	if (!port->qp_eq) {
-		ret = -EINVAL;
-		pr_err("ehea_create_eq failed (qp_eq)\n");
-		goto out_kill_eq;
-	}
-
-	pr_cfg.max_entries_rcq = rq1_entries + rq2_entries + rq3_entries;
-	pr_cfg.max_entries_scq = sq_entries * 2;
-	pr_cfg.max_entries_sq = sq_entries;
-	pr_cfg.max_entries_rq1 = rq1_entries;
-	pr_cfg.max_entries_rq2 = rq2_entries;
-	pr_cfg.max_entries_rq3 = rq3_entries;
-
-	pr_cfg_small_rx.max_entries_rcq = 1;
-	pr_cfg_small_rx.max_entries_scq = sq_entries;
-	pr_cfg_small_rx.max_entries_sq = sq_entries;
-	pr_cfg_small_rx.max_entries_rq1 = 1;
-	pr_cfg_small_rx.max_entries_rq2 = 1;
-	pr_cfg_small_rx.max_entries_rq3 = 1;
-
-	for (i = 0; i < def_qps; i++) {
-		ret = ehea_init_port_res(port, &port->port_res[i], &pr_cfg, i);
-		if (ret)
-			goto out_clean_pr;
-	}
-	for (i = def_qps; i < def_qps; i++) {
-		ret = ehea_init_port_res(port, &port->port_res[i],
-					 &pr_cfg_small_rx, i);
-		if (ret)
-			goto out_clean_pr;
-	}
-
-	return 0;
-
-out_clean_pr:
-	while (--i >= 0)
-		ehea_clean_portres(port, &port->port_res[i]);
-
-out_kill_eq:
-	ehea_destroy_eq(port->qp_eq);
-	return ret;
-}
-
-static int ehea_clean_all_portres(struct ehea_port *port)
-{
-	int ret = 0;
-	int i;
-
-	for (i = 0; i < port->num_def_qps; i++)
-		ret |= ehea_clean_portres(port, &port->port_res[i]);
-
-	ret |= ehea_destroy_eq(port->qp_eq);
-
-	return ret;
-}
-
-static void ehea_remove_adapter_mr(struct ehea_adapter *adapter)
-{
-	if (adapter->active_ports)
-		return;
-
-	ehea_rem_mr(&adapter->mr);
-}
-
-static int ehea_add_adapter_mr(struct ehea_adapter *adapter)
-{
-	if (adapter->active_ports)
-		return 0;
-
-	return ehea_reg_kernel_mr(adapter, &adapter->mr);
-}
-
-static int ehea_up(struct net_device *dev)
-{
-	int ret, i;
-	struct ehea_port *port = netdev_priv(dev);
-
-	if (port->state == EHEA_PORT_UP)
-		return 0;
-
-	ret = ehea_port_res_setup(port, port->num_def_qps);
-	if (ret) {
-		netdev_err(dev, "port_res_failed\n");
-		goto out;
-	}
-
-	/* Set default QP for this port */
-	ret = ehea_configure_port(port);
-	if (ret) {
-		netdev_err(dev, "ehea_configure_port failed. ret:%d\n", ret);
-		goto out_clean_pr;
-	}
-
-	ret = ehea_reg_interrupts(dev);
-	if (ret) {
-		netdev_err(dev, "reg_interrupts failed. ret:%d\n", ret);
-		goto out_clean_pr;
-	}
-
-	for (i = 0; i < port->num_def_qps; i++) {
-		ret = ehea_activate_qp(port->adapter, port->port_res[i].qp);
-		if (ret) {
-			netdev_err(dev, "activate_qp failed\n");
-			goto out_free_irqs;
-		}
-	}
-
-	for (i = 0; i < port->num_def_qps; i++) {
-		ret = ehea_fill_port_res(&port->port_res[i]);
-		if (ret) {
-			netdev_err(dev, "out_free_irqs\n");
-			goto out_free_irqs;
-		}
-	}
-
-	ret = ehea_broadcast_reg_helper(port, H_REG_BCMC);
-	if (ret) {
-		ret = -EIO;
-		goto out_free_irqs;
-	}
-
-	port->state = EHEA_PORT_UP;
-
-	ret = 0;
-	goto out;
-
-out_free_irqs:
-	ehea_free_interrupts(dev);
-
-out_clean_pr:
-	ehea_clean_all_portres(port);
-out:
-	if (ret)
-		netdev_info(dev, "Failed starting. ret=%i\n", ret);
-
-	ehea_update_bcmc_registrations();
-	ehea_update_firmware_handles();
-
-	return ret;
-}
-
-static void port_napi_disable(struct ehea_port *port)
-{
-	int i;
-
-	for (i = 0; i < port->num_def_qps; i++)
-		napi_disable(&port->port_res[i].napi);
-}
-
-static void port_napi_enable(struct ehea_port *port)
-{
-	int i;
-
-	for (i = 0; i < port->num_def_qps; i++)
-		napi_enable(&port->port_res[i].napi);
-}
-
-static int ehea_open(struct net_device *dev)
-{
-	int ret;
-	struct ehea_port *port = netdev_priv(dev);
-
-	mutex_lock(&port->port_lock);
-
-	netif_info(port, ifup, dev, "enabling port\n");
-
-	netif_carrier_off(dev);
-
-	ret = ehea_up(dev);
-	if (!ret) {
-		port_napi_enable(port);
-		netif_tx_start_all_queues(dev);
-	}
-
-	mutex_unlock(&port->port_lock);
-	schedule_delayed_work(&port->stats_work,
-			      round_jiffies_relative(msecs_to_jiffies(1000)));
-
-	return ret;
-}
-
-static int ehea_down(struct net_device *dev)
-{
-	int ret;
-	struct ehea_port *port = netdev_priv(dev);
-
-	if (port->state == EHEA_PORT_DOWN)
-		return 0;
-
-	ehea_drop_multicast_list(dev);
-	ehea_allmulti(dev, 0);
-	ehea_broadcast_reg_helper(port, H_DEREG_BCMC);
-
-	ehea_free_interrupts(dev);
-
-	port->state = EHEA_PORT_DOWN;
-
-	ehea_update_bcmc_registrations();
-
-	ret = ehea_clean_all_portres(port);
-	if (ret)
-		netdev_info(dev, "Failed freeing resources. ret=%i\n", ret);
-
-	ehea_update_firmware_handles();
-
-	return ret;
-}
-
-static int ehea_stop(struct net_device *dev)
-{
-	int ret;
-	struct ehea_port *port = netdev_priv(dev);
-
-	netif_info(port, ifdown, dev, "disabling port\n");
-
-	set_bit(__EHEA_DISABLE_PORT_RESET, &port->flags);
-	cancel_work_sync(&port->reset_task);
-	cancel_delayed_work_sync(&port->stats_work);
-	mutex_lock(&port->port_lock);
-	netif_tx_stop_all_queues(dev);
-	port_napi_disable(port);
-	ret = ehea_down(dev);
-	mutex_unlock(&port->port_lock);
-	clear_bit(__EHEA_DISABLE_PORT_RESET, &port->flags);
-	return ret;
-}
-
-static void ehea_purge_sq(struct ehea_qp *orig_qp)
-{
-	struct ehea_qp qp = *orig_qp;
-	struct ehea_qp_init_attr *init_attr = &qp.init_attr;
-	struct ehea_swqe *swqe;
-	int wqe_index;
-	int i;
-
-	for (i = 0; i < init_attr->act_nr_send_wqes; i++) {
-		swqe = ehea_get_swqe(&qp, &wqe_index);
-		swqe->tx_control |= EHEA_SWQE_PURGE;
-	}
-}
-
-static void ehea_flush_sq(struct ehea_port *port)
-{
-	int i;
-
-	for (i = 0; i < port->num_def_qps; i++) {
-		struct ehea_port_res *pr = &port->port_res[i];
-		int swqe_max = pr->sq_skba_size - 2 - pr->swqe_ll_count;
-		int ret;
-
-		ret = wait_event_timeout(port->swqe_avail_wq,
-			 atomic_read(&pr->swqe_avail) >= swqe_max,
-			 msecs_to_jiffies(100));
-
-		if (!ret) {
-			pr_err("WARNING: sq not flushed completely\n");
-			break;
-		}
-	}
-}
-
-static int ehea_stop_qps(struct net_device *dev)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	struct ehea_adapter *adapter = port->adapter;
-	struct hcp_modify_qp_cb0 *cb0;
-	int ret = -EIO;
-	int dret;
-	int i;
-	u64 hret;
-	u64 dummy64 = 0;
-	u16 dummy16 = 0;
-
-	cb0 = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!cb0) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	for (i = 0; i < (port->num_def_qps); i++) {
-		struct ehea_port_res *pr =  &port->port_res[i];
-		struct ehea_qp *qp = pr->qp;
-
-		/* Purge send queue */
-		ehea_purge_sq(qp);
-
-		/* Disable queue pair */
-		hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle,
-					    EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF),
-					    cb0);
-		if (hret != H_SUCCESS) {
-			pr_err("query_ehea_qp failed (1)\n");
-			goto out;
-		}
-
-		cb0->qp_ctl_reg = (cb0->qp_ctl_reg & H_QP_CR_RES_STATE) << 8;
-		cb0->qp_ctl_reg &= ~H_QP_CR_ENABLED;
-
-		hret = ehea_h_modify_ehea_qp(adapter->handle, 0, qp->fw_handle,
-					     EHEA_BMASK_SET(H_QPCB0_QP_CTL_REG,
-							    1), cb0, &dummy64,
-					     &dummy64, &dummy16, &dummy16);
-		if (hret != H_SUCCESS) {
-			pr_err("modify_ehea_qp failed (1)\n");
-			goto out;
-		}
-
-		hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle,
-					    EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF),
-					    cb0);
-		if (hret != H_SUCCESS) {
-			pr_err("query_ehea_qp failed (2)\n");
-			goto out;
-		}
-
-		/* deregister shared memory regions */
-		dret = ehea_rem_smrs(pr);
-		if (dret) {
-			pr_err("unreg shared memory region failed\n");
-			goto out;
-		}
-	}
-
-	ret = 0;
-out:
-	free_page((unsigned long)cb0);
-
-	return ret;
-}
-
-static void ehea_update_rqs(struct ehea_qp *orig_qp, struct ehea_port_res *pr)
-{
-	struct ehea_qp qp = *orig_qp;
-	struct ehea_qp_init_attr *init_attr = &qp.init_attr;
-	struct ehea_rwqe *rwqe;
-	struct sk_buff **skba_rq2 = pr->rq2_skba.arr;
-	struct sk_buff **skba_rq3 = pr->rq3_skba.arr;
-	struct sk_buff *skb;
-	u32 lkey = pr->recv_mr.lkey;
-
-
-	int i;
-	int index;
-
-	for (i = 0; i < init_attr->act_nr_rwqes_rq2 + 1; i++) {
-		rwqe = ehea_get_next_rwqe(&qp, 2);
-		rwqe->sg_list[0].l_key = lkey;
-		index = EHEA_BMASK_GET(EHEA_WR_ID_INDEX, rwqe->wr_id);
-		skb = skba_rq2[index];
-		if (skb)
-			rwqe->sg_list[0].vaddr = ehea_map_vaddr(skb->data);
-	}
-
-	for (i = 0; i < init_attr->act_nr_rwqes_rq3 + 1; i++) {
-		rwqe = ehea_get_next_rwqe(&qp, 3);
-		rwqe->sg_list[0].l_key = lkey;
-		index = EHEA_BMASK_GET(EHEA_WR_ID_INDEX, rwqe->wr_id);
-		skb = skba_rq3[index];
-		if (skb)
-			rwqe->sg_list[0].vaddr = ehea_map_vaddr(skb->data);
-	}
-}
-
-static int ehea_restart_qps(struct net_device *dev)
-{
-	struct ehea_port *port = netdev_priv(dev);
-	struct ehea_adapter *adapter = port->adapter;
-	int ret = 0;
-	int i;
-
-	struct hcp_modify_qp_cb0 *cb0;
-	u64 hret;
-	u64 dummy64 = 0;
-	u16 dummy16 = 0;
-
-	cb0 = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!cb0)
-		return -ENOMEM;
-
-	for (i = 0; i < (port->num_def_qps); i++) {
-		struct ehea_port_res *pr =  &port->port_res[i];
-		struct ehea_qp *qp = pr->qp;
-
-		ret = ehea_gen_smrs(pr);
-		if (ret) {
-			netdev_err(dev, "creation of shared memory regions failed\n");
-			goto out;
-		}
-
-		ehea_update_rqs(qp, pr);
-
-		/* Enable queue pair */
-		hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle,
-					    EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF),
-					    cb0);
-		if (hret != H_SUCCESS) {
-			netdev_err(dev, "query_ehea_qp failed (1)\n");
-			ret = -EFAULT;
-			goto out;
-		}
-
-		cb0->qp_ctl_reg = (cb0->qp_ctl_reg & H_QP_CR_RES_STATE) << 8;
-		cb0->qp_ctl_reg |= H_QP_CR_ENABLED;
-
-		hret = ehea_h_modify_ehea_qp(adapter->handle, 0, qp->fw_handle,
-					     EHEA_BMASK_SET(H_QPCB0_QP_CTL_REG,
-							    1), cb0, &dummy64,
-					     &dummy64, &dummy16, &dummy16);
-		if (hret != H_SUCCESS) {
-			netdev_err(dev, "modify_ehea_qp failed (1)\n");
-			ret = -EFAULT;
-			goto out;
-		}
-
-		hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle,
-					    EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF),
-					    cb0);
-		if (hret != H_SUCCESS) {
-			netdev_err(dev, "query_ehea_qp failed (2)\n");
-			ret = -EFAULT;
-			goto out;
-		}
-
-		/* refill entire queue */
-		ehea_refill_rq1(pr, pr->rq1_skba.index, 0);
-		ehea_refill_rq2(pr, 0);
-		ehea_refill_rq3(pr, 0);
-	}
-out:
-	free_page((unsigned long)cb0);
-
-	return ret;
-}
-
-static void ehea_reset_port(struct work_struct *work)
-{
-	int ret;
-	struct ehea_port *port =
-		container_of(work, struct ehea_port, reset_task);
-	struct net_device *dev = port->netdev;
-
-	mutex_lock(&dlpar_mem_lock);
-	port->resets++;
-	mutex_lock(&port->port_lock);
-	netif_tx_disable(dev);
-
-	port_napi_disable(port);
-
-	ehea_down(dev);
-
-	ret = ehea_up(dev);
-	if (ret)
-		goto out;
-
-	ehea_set_multicast_list(dev);
-
-	netif_info(port, timer, dev, "reset successful\n");
-
-	port_napi_enable(port);
-
-	netif_tx_wake_all_queues(dev);
-out:
-	mutex_unlock(&port->port_lock);
-	mutex_unlock(&dlpar_mem_lock);
-}
-
-static void ehea_rereg_mrs(void)
-{
-	int ret, i;
-	struct ehea_adapter *adapter;
-
-	pr_info("LPAR memory changed - re-initializing driver\n");
-
-	list_for_each_entry(adapter, &adapter_list, list)
-		if (adapter->active_ports) {
-			/* Shutdown all ports */
-			for (i = 0; i < EHEA_MAX_PORTS; i++) {
-				struct ehea_port *port = adapter->port[i];
-				struct net_device *dev;
-
-				if (!port)
-					continue;
-
-				dev = port->netdev;
-
-				if (dev->flags & IFF_UP) {
-					mutex_lock(&port->port_lock);
-					netif_tx_disable(dev);
-					ehea_flush_sq(port);
-					ret = ehea_stop_qps(dev);
-					if (ret) {
-						mutex_unlock(&port->port_lock);
-						goto out;
-					}
-					port_napi_disable(port);
-					mutex_unlock(&port->port_lock);
-				}
-				reset_sq_restart_flag(port);
-			}
-
-			/* Unregister old memory region */
-			ret = ehea_rem_mr(&adapter->mr);
-			if (ret) {
-				pr_err("unregister MR failed - driver inoperable!\n");
-				goto out;
-			}
-		}
-
-	clear_bit(__EHEA_STOP_XFER, &ehea_driver_flags);
-
-	list_for_each_entry(adapter, &adapter_list, list)
-		if (adapter->active_ports) {
-			/* Register new memory region */
-			ret = ehea_reg_kernel_mr(adapter, &adapter->mr);
-			if (ret) {
-				pr_err("register MR failed - driver inoperable!\n");
-				goto out;
-			}
-
-			/* Restart all ports */
-			for (i = 0; i < EHEA_MAX_PORTS; i++) {
-				struct ehea_port *port = adapter->port[i];
-
-				if (port) {
-					struct net_device *dev = port->netdev;
-
-					if (dev->flags & IFF_UP) {
-						mutex_lock(&port->port_lock);
-						ret = ehea_restart_qps(dev);
-						if (!ret) {
-							check_sqs(port);
-							port_napi_enable(port);
-							netif_tx_wake_all_queues(dev);
-						} else {
-							netdev_err(dev, "Unable to restart QPS\n");
-						}
-						mutex_unlock(&port->port_lock);
-					}
-				}
-			}
-		}
-	pr_info("re-initializing driver complete\n");
-out:
-	return;
-}
-
-static void ehea_tx_watchdog(struct net_device *dev, unsigned int txqueue)
-{
-	struct ehea_port *port = netdev_priv(dev);
-
-	if (netif_carrier_ok(dev) &&
-	    !test_bit(__EHEA_STOP_XFER, &ehea_driver_flags))
-		ehea_schedule_port_reset(port);
-}
-
-static int ehea_sense_adapter_attr(struct ehea_adapter *adapter)
-{
-	struct hcp_query_ehea *cb;
-	u64 hret;
-	int ret;
-
-	cb = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!cb) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	hret = ehea_h_query_ehea(adapter->handle, cb);
-
-	if (hret != H_SUCCESS) {
-		ret = -EIO;
-		goto out_herr;
-	}
-
-	adapter->max_mc_mac = cb->max_mc_mac - 1;
-	ret = 0;
-
-out_herr:
-	free_page((unsigned long)cb);
-out:
-	return ret;
-}
-
-static int ehea_get_jumboframe_status(struct ehea_port *port, int *jumbo)
-{
-	struct hcp_ehea_port_cb4 *cb4;
-	u64 hret;
-	int ret = 0;
-
-	*jumbo = 0;
-
-	/* (Try to) enable *jumbo frames */
-	cb4 = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!cb4) {
-		pr_err("no mem for cb4\n");
-		ret = -ENOMEM;
-		goto out;
-	} else {
-		hret = ehea_h_query_ehea_port(port->adapter->handle,
-					      port->logical_port_id,
-					      H_PORT_CB4,
-					      H_PORT_CB4_JUMBO, cb4);
-		if (hret == H_SUCCESS) {
-			if (cb4->jumbo_frame)
-				*jumbo = 1;
-			else {
-				cb4->jumbo_frame = 1;
-				hret = ehea_h_modify_ehea_port(port->adapter->
-							       handle,
-							       port->
-							       logical_port_id,
-							       H_PORT_CB4,
-							       H_PORT_CB4_JUMBO,
-							       cb4);
-				if (hret == H_SUCCESS)
-					*jumbo = 1;
-			}
-		} else
-			ret = -EINVAL;
-
-		free_page((unsigned long)cb4);
-	}
-out:
-	return ret;
-}
-
-static ssize_t log_port_id_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	struct ehea_port *port = container_of(dev, struct ehea_port, ofdev.dev);
-	return sprintf(buf, "%d", port->logical_port_id);
-}
-
-static DEVICE_ATTR_RO(log_port_id);
-
-static void logical_port_release(struct device *dev)
-{
-	struct ehea_port *port = container_of(dev, struct ehea_port, ofdev.dev);
-	of_node_put(port->ofdev.dev.of_node);
-}
-
-static struct device *ehea_register_port(struct ehea_port *port,
-					 struct device_node *dn)
-{
-	int ret;
-
-	port->ofdev.dev.of_node = of_node_get(dn);
-	port->ofdev.dev.parent = &port->adapter->ofdev->dev;
-	port->ofdev.dev.bus = &ibmebus_bus_type;
-
-	dev_set_name(&port->ofdev.dev, "port%d", port_name_cnt++);
-	port->ofdev.dev.release = logical_port_release;
-
-	ret = of_device_register(&port->ofdev);
-	if (ret) {
-		pr_err("failed to register device. ret=%d\n", ret);
-		put_device(&port->ofdev.dev);
-		goto out;
-	}
-
-	ret = device_create_file(&port->ofdev.dev, &dev_attr_log_port_id);
-	if (ret) {
-		pr_err("failed to register attributes, ret=%d\n", ret);
-		goto out_unreg_of_dev;
-	}
-
-	return &port->ofdev.dev;
-
-out_unreg_of_dev:
-	of_device_unregister(&port->ofdev);
-out:
-	return NULL;
-}
-
-static void ehea_unregister_port(struct ehea_port *port)
-{
-	device_remove_file(&port->ofdev.dev, &dev_attr_log_port_id);
-	of_device_unregister(&port->ofdev);
-}
-
-static const struct net_device_ops ehea_netdev_ops = {
-	.ndo_open		= ehea_open,
-	.ndo_stop		= ehea_stop,
-	.ndo_start_xmit		= ehea_start_xmit,
-	.ndo_get_stats64	= ehea_get_stats64,
-	.ndo_set_mac_address	= ehea_set_mac_addr,
-	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_set_rx_mode	= ehea_set_multicast_list,
-	.ndo_vlan_rx_add_vid	= ehea_vlan_rx_add_vid,
-	.ndo_vlan_rx_kill_vid	= ehea_vlan_rx_kill_vid,
-	.ndo_tx_timeout		= ehea_tx_watchdog,
-};
-
-static struct ehea_port *ehea_setup_single_port(struct ehea_adapter *adapter,
-					 u32 logical_port_id,
-					 struct device_node *dn)
-{
-	int ret;
-	struct net_device *dev;
-	struct ehea_port *port;
-	struct device *port_dev;
-	int jumbo;
-
-	/* allocate memory for the port structures */
-	dev = alloc_etherdev_mq(sizeof(struct ehea_port), EHEA_MAX_PORT_RES);
-
-	if (!dev) {
-		ret = -ENOMEM;
-		goto out_err;
-	}
-
-	port = netdev_priv(dev);
-
-	mutex_init(&port->port_lock);
-	port->state = EHEA_PORT_DOWN;
-	port->sig_comp_iv = sq_entries / 10;
-
-	port->adapter = adapter;
-	port->netdev = dev;
-	port->logical_port_id = logical_port_id;
-
-	port->msg_enable = netif_msg_init(msg_level, EHEA_MSG_DEFAULT);
-
-	port->mc_list = kzalloc_obj(struct ehea_mc_list);
-	if (!port->mc_list) {
-		ret = -ENOMEM;
-		goto out_free_ethdev;
-	}
-
-	INIT_LIST_HEAD(&port->mc_list->list);
-
-	ret = ehea_sense_port_attr(port);
-	if (ret)
-		goto out_free_mc_list;
-
-	netif_set_real_num_rx_queues(dev, port->num_def_qps);
-	netif_set_real_num_tx_queues(dev, port->num_def_qps);
-
-	port_dev = ehea_register_port(port, dn);
-	if (!port_dev)
-		goto out_free_mc_list;
-
-	SET_NETDEV_DEV(dev, port_dev);
-
-	/* initialize net_device structure */
-	eth_hw_addr_set(dev, (u8 *)&port->mac_addr);
-
-	dev->netdev_ops = &ehea_netdev_ops;
-	ehea_set_ethtool_ops(dev);
-
-	dev->hw_features = NETIF_F_SG | NETIF_F_TSO |
-		      NETIF_F_IP_CSUM | NETIF_F_HW_VLAN_CTAG_TX;
-	dev->features = NETIF_F_SG | NETIF_F_TSO |
-		      NETIF_F_HIGHDMA | NETIF_F_IP_CSUM |
-		      NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
-		      NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_RXCSUM;
-	dev->vlan_features = NETIF_F_SG | NETIF_F_TSO | NETIF_F_HIGHDMA |
-			NETIF_F_IP_CSUM;
-	dev->watchdog_timeo = EHEA_WATCH_DOG_TIMEOUT;
-
-	/* MTU range: 68 - 9022 */
-	dev->min_mtu = ETH_MIN_MTU;
-	dev->max_mtu = EHEA_MAX_PACKET_SIZE;
-
-	INIT_WORK(&port->reset_task, ehea_reset_port);
-	INIT_DELAYED_WORK(&port->stats_work, ehea_update_stats);
-
-	init_waitqueue_head(&port->swqe_avail_wq);
-	init_waitqueue_head(&port->restart_wq);
-
-	ret = register_netdev(dev);
-	if (ret) {
-		pr_err("register_netdev failed. ret=%d\n", ret);
-		goto out_unreg_port;
-	}
-
-	ret = ehea_get_jumboframe_status(port, &jumbo);
-	if (ret)
-		netdev_err(dev, "failed determining jumbo frame status\n");
-
-	netdev_info(dev, "Jumbo frames are %sabled\n",
-		    jumbo == 1 ? "en" : "dis");
-
-	adapter->active_ports++;
-
-	return port;
-
-out_unreg_port:
-	ehea_unregister_port(port);
-
-out_free_mc_list:
-	kfree(port->mc_list);
-
-out_free_ethdev:
-	free_netdev(dev);
-
-out_err:
-	pr_err("setting up logical port with id=%d failed, ret=%d\n",
-	       logical_port_id, ret);
-	return NULL;
-}
-
-static void ehea_shutdown_single_port(struct ehea_port *port)
-{
-	struct ehea_adapter *adapter = port->adapter;
-
-	cancel_work_sync(&port->reset_task);
-	cancel_delayed_work_sync(&port->stats_work);
-	unregister_netdev(port->netdev);
-	ehea_unregister_port(port);
-	kfree(port->mc_list);
-	free_netdev(port->netdev);
-	adapter->active_ports--;
-}
-
-static int ehea_setup_ports(struct ehea_adapter *adapter)
-{
-	struct device_node *lhea_dn;
-	struct device_node *eth_dn;
-
-	const u32 *dn_log_port_id;
-	int i = 0;
-
-	lhea_dn = adapter->ofdev->dev.of_node;
-	for_each_child_of_node(lhea_dn, eth_dn) {
-		dn_log_port_id = of_get_property(eth_dn, "ibm,hea-port-no",
-						 NULL);
-		if (!dn_log_port_id) {
-			pr_err("bad device node: eth_dn name=%pOF\n", eth_dn);
-			continue;
-		}
-
-		if (ehea_add_adapter_mr(adapter)) {
-			pr_err("creating MR failed\n");
-			of_node_put(eth_dn);
-			return -EIO;
-		}
-
-		adapter->port[i] = ehea_setup_single_port(adapter,
-							  *dn_log_port_id,
-							  eth_dn);
-		if (adapter->port[i])
-			netdev_info(adapter->port[i]->netdev,
-				    "logical port id #%d\n", *dn_log_port_id);
-		else
-			ehea_remove_adapter_mr(adapter);
-
-		i++;
-	}
-	return 0;
-}
-
-static struct device_node *ehea_get_eth_dn(struct ehea_adapter *adapter,
-					   u32 logical_port_id)
-{
-	struct device_node *lhea_dn;
-	struct device_node *eth_dn;
-	const u32 *dn_log_port_id;
-
-	lhea_dn = adapter->ofdev->dev.of_node;
-	for_each_child_of_node(lhea_dn, eth_dn) {
-		dn_log_port_id = of_get_property(eth_dn, "ibm,hea-port-no",
-						 NULL);
-		if (dn_log_port_id)
-			if (*dn_log_port_id == logical_port_id)
-				return eth_dn;
-	}
-
-	return NULL;
-}
-
-static ssize_t probe_port_store(struct device *dev,
-			       struct device_attribute *attr,
-			       const char *buf, size_t count)
-{
-	struct ehea_adapter *adapter = dev_get_drvdata(dev);
-	struct ehea_port *port;
-	struct device_node *eth_dn = NULL;
-	int i;
-
-	u32 logical_port_id;
-
-	sscanf(buf, "%d", &logical_port_id);
-
-	port = ehea_get_port(adapter, logical_port_id);
-
-	if (port) {
-		netdev_info(port->netdev, "adding port with logical port id=%d failed: port already configured\n",
-			    logical_port_id);
-		return -EINVAL;
-	}
-
-	eth_dn = ehea_get_eth_dn(adapter, logical_port_id);
-
-	if (!eth_dn) {
-		pr_info("no logical port with id %d found\n", logical_port_id);
-		return -EINVAL;
-	}
-
-	if (ehea_add_adapter_mr(adapter)) {
-		pr_err("creating MR failed\n");
-		of_node_put(eth_dn);
-		return -EIO;
-	}
-
-	port = ehea_setup_single_port(adapter, logical_port_id, eth_dn);
-
-	of_node_put(eth_dn);
-
-	if (port) {
-		for (i = 0; i < EHEA_MAX_PORTS; i++)
-			if (!adapter->port[i]) {
-				adapter->port[i] = port;
-				break;
-			}
-
-		netdev_info(port->netdev, "added: (logical port id=%d)\n",
-			    logical_port_id);
-	} else {
-		ehea_remove_adapter_mr(adapter);
-		return -EIO;
-	}
-
-	return (ssize_t) count;
-}
-
-static ssize_t remove_port_store(struct device *dev,
-				 struct device_attribute *attr,
-				 const char *buf, size_t count)
-{
-	struct ehea_adapter *adapter = dev_get_drvdata(dev);
-	struct ehea_port *port;
-	int i;
-	u32 logical_port_id;
-
-	sscanf(buf, "%d", &logical_port_id);
-
-	port = ehea_get_port(adapter, logical_port_id);
-
-	if (port) {
-		netdev_info(port->netdev, "removed: (logical port id=%d)\n",
-			    logical_port_id);
-
-		ehea_shutdown_single_port(port);
-
-		for (i = 0; i < EHEA_MAX_PORTS; i++)
-			if (adapter->port[i] == port) {
-				adapter->port[i] = NULL;
-				break;
-			}
-	} else {
-		pr_err("removing port with logical port id=%d failed. port not configured.\n",
-		       logical_port_id);
-		return -EINVAL;
-	}
-
-	ehea_remove_adapter_mr(adapter);
-
-	return (ssize_t) count;
-}
-
-static DEVICE_ATTR_WO(probe_port);
-static DEVICE_ATTR_WO(remove_port);
-
-static int ehea_create_device_sysfs(struct platform_device *dev)
-{
-	int ret = device_create_file(&dev->dev, &dev_attr_probe_port);
-	if (ret)
-		goto out;
-
-	ret = device_create_file(&dev->dev, &dev_attr_remove_port);
-	if (ret)
-		device_remove_file(&dev->dev, &dev_attr_probe_port);
-out:
-	return ret;
-}
-
-static void ehea_remove_device_sysfs(struct platform_device *dev)
-{
-	device_remove_file(&dev->dev, &dev_attr_probe_port);
-	device_remove_file(&dev->dev, &dev_attr_remove_port);
-}
-
-static int ehea_reboot_notifier(struct notifier_block *nb,
-				unsigned long action, void *unused)
-{
-	if (action == SYS_RESTART) {
-		pr_info("Reboot: freeing all eHEA resources\n");
-		ibmebus_unregister_driver(&ehea_driver);
-	}
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block ehea_reboot_nb = {
-	.notifier_call = ehea_reboot_notifier,
-};
-
-static int ehea_mem_notifier(struct notifier_block *nb,
-			     unsigned long action, void *data)
-{
-	int ret = NOTIFY_BAD;
-	struct memory_notify *arg = data;
-
-	mutex_lock(&dlpar_mem_lock);
-
-	switch (action) {
-	case MEM_CANCEL_OFFLINE:
-		pr_info("memory offlining canceled");
-		fallthrough;	/* re-add canceled memory block */
-
-	case MEM_ONLINE:
-		pr_info("memory is going online");
-		set_bit(__EHEA_STOP_XFER, &ehea_driver_flags);
-		if (ehea_add_sect_bmap(arg->start_pfn, arg->nr_pages))
-			goto out_unlock;
-		ehea_rereg_mrs();
-		break;
-
-	case MEM_GOING_OFFLINE:
-		pr_info("memory is going offline");
-		set_bit(__EHEA_STOP_XFER, &ehea_driver_flags);
-		if (ehea_rem_sect_bmap(arg->start_pfn, arg->nr_pages))
-			goto out_unlock;
-		ehea_rereg_mrs();
-		break;
-
-	default:
-		break;
-	}
-
-	ehea_update_firmware_handles();
-	ret = NOTIFY_OK;
-
-out_unlock:
-	mutex_unlock(&dlpar_mem_lock);
-	return ret;
-}
-
-static struct notifier_block ehea_mem_nb = {
-	.notifier_call = ehea_mem_notifier,
-};
-
-static void ehea_crash_handler(void)
-{
-	int i;
-
-	if (ehea_fw_handles.arr)
-		for (i = 0; i < ehea_fw_handles.num_entries; i++)
-			ehea_h_free_resource(ehea_fw_handles.arr[i].adh,
-					     ehea_fw_handles.arr[i].fwh,
-					     FORCE_FREE);
-
-	if (ehea_bcmc_regs.arr)
-		for (i = 0; i < ehea_bcmc_regs.num_entries; i++)
-			ehea_h_reg_dereg_bcmc(ehea_bcmc_regs.arr[i].adh,
-					      ehea_bcmc_regs.arr[i].port_id,
-					      ehea_bcmc_regs.arr[i].reg_type,
-					      ehea_bcmc_regs.arr[i].macaddr,
-					      0, H_DEREG_BCMC);
-}
-
-static atomic_t ehea_memory_hooks_registered;
-
-/* Register memory hooks on probe of first adapter */
-static int ehea_register_memory_hooks(void)
-{
-	int ret = 0;
-
-	if (atomic_inc_return(&ehea_memory_hooks_registered) > 1)
-		return 0;
-
-	ret = ehea_create_busmap();
-	if (ret) {
-		pr_info("ehea_create_busmap failed\n");
-		goto out;
-	}
-
-	ret = register_reboot_notifier(&ehea_reboot_nb);
-	if (ret) {
-		pr_info("register_reboot_notifier failed\n");
-		goto out;
-	}
-
-	ret = register_memory_notifier(&ehea_mem_nb);
-	if (ret) {
-		pr_info("register_memory_notifier failed\n");
-		goto out2;
-	}
-
-	ret = crash_shutdown_register(ehea_crash_handler);
-	if (ret) {
-		pr_info("crash_shutdown_register failed\n");
-		goto out3;
-	}
-
-	return 0;
-
-out3:
-	unregister_memory_notifier(&ehea_mem_nb);
-out2:
-	unregister_reboot_notifier(&ehea_reboot_nb);
-out:
-	atomic_dec(&ehea_memory_hooks_registered);
-	return ret;
-}
-
-static void ehea_unregister_memory_hooks(void)
-{
-	/* Only remove the hooks if we've registered them */
-	if (atomic_read(&ehea_memory_hooks_registered) == 0)
-		return;
-
-	unregister_reboot_notifier(&ehea_reboot_nb);
-	if (crash_shutdown_unregister(ehea_crash_handler))
-		pr_info("failed unregistering crash handler\n");
-	unregister_memory_notifier(&ehea_mem_nb);
-}
-
-static int ehea_probe_adapter(struct platform_device *dev)
-{
-	struct ehea_adapter *adapter;
-	const u64 *adapter_handle;
-	int ret;
-	int i;
-
-	ret = ehea_register_memory_hooks();
-	if (ret)
-		return ret;
-
-	if (!dev || !dev->dev.of_node) {
-		pr_err("Invalid ibmebus device probed\n");
-		return -EINVAL;
-	}
-
-	adapter = devm_kzalloc(&dev->dev, sizeof(*adapter), GFP_KERNEL);
-	if (!adapter) {
-		ret = -ENOMEM;
-		dev_err(&dev->dev, "no mem for ehea_adapter\n");
-		goto out;
-	}
-
-	list_add(&adapter->list, &adapter_list);
-
-	adapter->ofdev = dev;
-
-	adapter_handle = of_get_property(dev->dev.of_node, "ibm,hea-handle",
-					 NULL);
-	if (adapter_handle)
-		adapter->handle = *adapter_handle;
-
-	if (!adapter->handle) {
-		dev_err(&dev->dev, "failed getting handle for adapter"
-			" '%pOF'\n", dev->dev.of_node);
-		ret = -ENODEV;
-		goto out_free_ad;
-	}
-
-	adapter->pd = EHEA_PD_ID;
-
-	platform_set_drvdata(dev, adapter);
-
-
-	/* initialize adapter and ports */
-	/* get adapter properties */
-	ret = ehea_sense_adapter_attr(adapter);
-	if (ret) {
-		dev_err(&dev->dev, "sense_adapter_attr failed: %d\n", ret);
-		goto out_free_ad;
-	}
-
-	adapter->neq = ehea_create_eq(adapter,
-				      EHEA_NEQ, EHEA_MAX_ENTRIES_EQ, 1);
-	if (!adapter->neq) {
-		ret = -EIO;
-		dev_err(&dev->dev, "NEQ creation failed\n");
-		goto out_free_ad;
-	}
-
-	tasklet_setup(&adapter->neq_tasklet, ehea_neq_tasklet);
-
-	ret = ehea_create_device_sysfs(dev);
-	if (ret)
-		goto out_kill_eq;
-
-	ret = ehea_setup_ports(adapter);
-	if (ret) {
-		dev_err(&dev->dev, "setup_ports failed\n");
-		goto out_rem_dev_sysfs;
-	}
-
-	ret = ibmebus_request_irq(adapter->neq->attr.ist1,
-				  ehea_interrupt_neq, 0,
-				  "ehea_neq", adapter);
-	if (ret) {
-		dev_err(&dev->dev, "requesting NEQ IRQ failed\n");
-		goto out_shutdown_ports;
-	}
-
-	/* Handle any events that might be pending. */
-	tasklet_hi_schedule(&adapter->neq_tasklet);
-
-	ret = 0;
-	goto out;
-
-out_shutdown_ports:
-	for (i = 0; i < EHEA_MAX_PORTS; i++)
-		if (adapter->port[i]) {
-			ehea_shutdown_single_port(adapter->port[i]);
-			adapter->port[i] = NULL;
-		}
-
-out_rem_dev_sysfs:
-	ehea_remove_device_sysfs(dev);
-
-out_kill_eq:
-	ehea_destroy_eq(adapter->neq);
-
-out_free_ad:
-	list_del(&adapter->list);
-
-out:
-	ehea_update_firmware_handles();
-
-	return ret;
-}
-
-static void ehea_remove(struct platform_device *dev)
-{
-	struct ehea_adapter *adapter = platform_get_drvdata(dev);
-	int i;
-
-	for (i = 0; i < EHEA_MAX_PORTS; i++)
-		if (adapter->port[i]) {
-			ehea_shutdown_single_port(adapter->port[i]);
-			adapter->port[i] = NULL;
-		}
-
-	ehea_remove_device_sysfs(dev);
-
-	ibmebus_free_irq(adapter->neq->attr.ist1, adapter);
-	tasklet_kill(&adapter->neq_tasklet);
-
-	ehea_destroy_eq(adapter->neq);
-	ehea_remove_adapter_mr(adapter);
-	list_del(&adapter->list);
-
-	ehea_update_firmware_handles();
-}
-
-static int check_module_parm(void)
-{
-	int ret = 0;
-
-	if ((rq1_entries < EHEA_MIN_ENTRIES_QP) ||
-	    (rq1_entries > EHEA_MAX_ENTRIES_RQ1)) {
-		pr_info("Bad parameter: rq1_entries\n");
-		ret = -EINVAL;
-	}
-	if ((rq2_entries < EHEA_MIN_ENTRIES_QP) ||
-	    (rq2_entries > EHEA_MAX_ENTRIES_RQ2)) {
-		pr_info("Bad parameter: rq2_entries\n");
-		ret = -EINVAL;
-	}
-	if ((rq3_entries < EHEA_MIN_ENTRIES_QP) ||
-	    (rq3_entries > EHEA_MAX_ENTRIES_RQ3)) {
-		pr_info("Bad parameter: rq3_entries\n");
-		ret = -EINVAL;
-	}
-	if ((sq_entries < EHEA_MIN_ENTRIES_QP) ||
-	    (sq_entries > EHEA_MAX_ENTRIES_SQ)) {
-		pr_info("Bad parameter: sq_entries\n");
-		ret = -EINVAL;
-	}
-
-	return ret;
-}
-
-static ssize_t capabilities_show(struct device_driver *drv, char *buf)
-{
-	return sprintf(buf, "%d", EHEA_CAPABILITIES);
-}
-
-static DRIVER_ATTR_RO(capabilities);
-
-static int __init ehea_module_init(void)
-{
-	int ret;
-
-	pr_info("IBM eHEA ethernet device driver (Release %s)\n", DRV_VERSION);
-
-	memset(&ehea_fw_handles, 0, sizeof(ehea_fw_handles));
-	memset(&ehea_bcmc_regs, 0, sizeof(ehea_bcmc_regs));
-
-	mutex_init(&ehea_fw_handles.lock);
-	spin_lock_init(&ehea_bcmc_regs.lock);
-
-	ret = check_module_parm();
-	if (ret)
-		goto out;
-
-	ret = ibmebus_register_driver(&ehea_driver);
-	if (ret) {
-		pr_err("failed registering eHEA device driver on ebus\n");
-		goto out;
-	}
-
-	ret = driver_create_file(&ehea_driver.driver,
-				 &driver_attr_capabilities);
-	if (ret) {
-		pr_err("failed to register capabilities attribute, ret=%d\n",
-		       ret);
-		goto out2;
-	}
-
-	return ret;
-
-out2:
-	ibmebus_unregister_driver(&ehea_driver);
-out:
-	return ret;
-}
-
-static void __exit ehea_module_exit(void)
-{
-	driver_remove_file(&ehea_driver.driver, &driver_attr_capabilities);
-	ibmebus_unregister_driver(&ehea_driver);
-	ehea_unregister_memory_hooks();
-	kfree(ehea_fw_handles.arr);
-	kfree(ehea_bcmc_regs.arr);
-	ehea_destroy_busmap();
-}
-
-module_init(ehea_module_init);
-module_exit(ehea_module_exit);
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_phyp.c b/drivers/net/ethernet/ibm/ehea/ehea_phyp.c
deleted file mode 100644
index e63716e139f5..000000000000
--- a/drivers/net/ethernet/ibm/ehea/ehea_phyp.c
+++ /dev/null
@@ -1,612 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  linux/drivers/net/ethernet/ibm/ehea/ehea_phyp.c
- *
- *  eHEA ethernet device driver for IBM eServer System p
- *
- *  (C) Copyright IBM Corp. 2006
- *
- *  Authors:
- *	 Christoph Raisch <raisch@de.ibm.com>
- *	 Jan-Bernd Themann <themann@de.ibm.com>
- *	 Thomas Klein <tklein@de.ibm.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include "ehea_phyp.h"
-
-
-static inline u16 get_order_of_qentries(u16 queue_entries)
-{
-	u8 ld = 1;		/*  logarithmus dualis */
-	while (((1U << ld) - 1) < queue_entries)
-		ld++;
-	return ld - 1;
-}
-
-/* Defines for H_CALL H_ALLOC_RESOURCE */
-#define H_ALL_RES_TYPE_QP	 1
-#define H_ALL_RES_TYPE_CQ	 2
-#define H_ALL_RES_TYPE_EQ	 3
-#define H_ALL_RES_TYPE_MR	 5
-#define H_ALL_RES_TYPE_MW	 6
-
-static long ehea_plpar_hcall_norets(unsigned long opcode,
-				    unsigned long arg1,
-				    unsigned long arg2,
-				    unsigned long arg3,
-				    unsigned long arg4,
-				    unsigned long arg5,
-				    unsigned long arg6,
-				    unsigned long arg7)
-{
-	long ret;
-	int i, sleep_msecs;
-
-	for (i = 0; i < 5; i++) {
-		ret = plpar_hcall_norets(opcode, arg1, arg2, arg3, arg4,
-					 arg5, arg6, arg7);
-
-		if (H_IS_LONG_BUSY(ret)) {
-			sleep_msecs = get_longbusy_msecs(ret);
-			msleep_interruptible(sleep_msecs);
-			continue;
-		}
-
-		if (ret < H_SUCCESS)
-			pr_err("opcode=%lx ret=%lx"
-			       " arg1=%lx arg2=%lx arg3=%lx arg4=%lx"
-			       " arg5=%lx arg6=%lx arg7=%lx\n",
-			       opcode, ret,
-			       arg1, arg2, arg3, arg4, arg5, arg6, arg7);
-
-		return ret;
-	}
-
-	return H_BUSY;
-}
-
-static long ehea_plpar_hcall9(unsigned long opcode,
-			      unsigned long *outs, /* array of 9 outputs */
-			      unsigned long arg1,
-			      unsigned long arg2,
-			      unsigned long arg3,
-			      unsigned long arg4,
-			      unsigned long arg5,
-			      unsigned long arg6,
-			      unsigned long arg7,
-			      unsigned long arg8,
-			      unsigned long arg9)
-{
-	long ret;
-	int i, sleep_msecs;
-	u8 cb_cat;
-
-	for (i = 0; i < 5; i++) {
-		ret = plpar_hcall9(opcode, outs,
-				   arg1, arg2, arg3, arg4, arg5,
-				   arg6, arg7, arg8, arg9);
-
-		if (H_IS_LONG_BUSY(ret)) {
-			sleep_msecs = get_longbusy_msecs(ret);
-			msleep_interruptible(sleep_msecs);
-			continue;
-		}
-
-		cb_cat = EHEA_BMASK_GET(H_MEHEAPORT_CAT, arg2);
-
-		if ((ret < H_SUCCESS) && !(((ret == H_AUTHORITY)
-		    && (opcode == H_MODIFY_HEA_PORT))
-		    && (((cb_cat == H_PORT_CB4) && ((arg3 == H_PORT_CB4_JUMBO)
-		    || (arg3 == H_PORT_CB4_SPEED))) || ((cb_cat == H_PORT_CB7)
-		    && (arg3 == H_PORT_CB7_DUCQPN)))))
-			pr_err("opcode=%lx ret=%lx"
-			       " arg1=%lx arg2=%lx arg3=%lx arg4=%lx"
-			       " arg5=%lx arg6=%lx arg7=%lx arg8=%lx"
-			       " arg9=%lx"
-			       " out1=%lx out2=%lx out3=%lx out4=%lx"
-			       " out5=%lx out6=%lx out7=%lx out8=%lx"
-			       " out9=%lx\n",
-			       opcode, ret,
-			       arg1, arg2, arg3, arg4, arg5,
-			       arg6, arg7, arg8, arg9,
-			       outs[0], outs[1], outs[2], outs[3], outs[4],
-			       outs[5], outs[6], outs[7], outs[8]);
-		return ret;
-	}
-
-	return H_BUSY;
-}
-
-u64 ehea_h_query_ehea_qp(const u64 adapter_handle, const u8 qp_category,
-			 const u64 qp_handle, const u64 sel_mask, void *cb_addr)
-{
-	return ehea_plpar_hcall_norets(H_QUERY_HEA_QP,
-				       adapter_handle,		/* R4 */
-				       qp_category,		/* R5 */
-				       qp_handle,		/* R6 */
-				       sel_mask,		/* R7 */
-				       __pa(cb_addr),		/* R8 */
-				       0, 0);
-}
-
-/* input param R5 */
-#define H_ALL_RES_QP_EQPO	  EHEA_BMASK_IBM(9, 11)
-#define H_ALL_RES_QP_QPP	  EHEA_BMASK_IBM(12, 12)
-#define H_ALL_RES_QP_RQR	  EHEA_BMASK_IBM(13, 15)
-#define H_ALL_RES_QP_EQEG	  EHEA_BMASK_IBM(16, 16)
-#define H_ALL_RES_QP_LL_QP	  EHEA_BMASK_IBM(17, 17)
-#define H_ALL_RES_QP_DMA128	  EHEA_BMASK_IBM(19, 19)
-#define H_ALL_RES_QP_HSM	  EHEA_BMASK_IBM(20, 21)
-#define H_ALL_RES_QP_SIGT	  EHEA_BMASK_IBM(22, 23)
-#define H_ALL_RES_QP_TENURE	  EHEA_BMASK_IBM(48, 55)
-#define H_ALL_RES_QP_RES_TYP	  EHEA_BMASK_IBM(56, 63)
-
-/* input param R9  */
-#define H_ALL_RES_QP_TOKEN	  EHEA_BMASK_IBM(0, 31)
-#define H_ALL_RES_QP_PD		  EHEA_BMASK_IBM(32, 63)
-
-/* input param R10 */
-#define H_ALL_RES_QP_MAX_SWQE	  EHEA_BMASK_IBM(4, 7)
-#define H_ALL_RES_QP_MAX_R1WQE	  EHEA_BMASK_IBM(12, 15)
-#define H_ALL_RES_QP_MAX_R2WQE	  EHEA_BMASK_IBM(20, 23)
-#define H_ALL_RES_QP_MAX_R3WQE	  EHEA_BMASK_IBM(28, 31)
-/* Max Send Scatter Gather Elements */
-#define H_ALL_RES_QP_MAX_SSGE	  EHEA_BMASK_IBM(37, 39)
-#define H_ALL_RES_QP_MAX_R1SGE	  EHEA_BMASK_IBM(45, 47)
-/* Max Receive SG Elements RQ1 */
-#define H_ALL_RES_QP_MAX_R2SGE	  EHEA_BMASK_IBM(53, 55)
-#define H_ALL_RES_QP_MAX_R3SGE	  EHEA_BMASK_IBM(61, 63)
-
-/* input param R11 */
-#define H_ALL_RES_QP_SWQE_IDL	  EHEA_BMASK_IBM(0, 7)
-/* max swqe immediate data length */
-#define H_ALL_RES_QP_PORT_NUM	  EHEA_BMASK_IBM(48, 63)
-
-/* input param R12 */
-#define H_ALL_RES_QP_TH_RQ2	  EHEA_BMASK_IBM(0, 15)
-/* Threshold RQ2 */
-#define H_ALL_RES_QP_TH_RQ3	  EHEA_BMASK_IBM(16, 31)
-/* Threshold RQ3 */
-
-/* output param R6 */
-#define H_ALL_RES_QP_ACT_SWQE	  EHEA_BMASK_IBM(0, 15)
-#define H_ALL_RES_QP_ACT_R1WQE	  EHEA_BMASK_IBM(16, 31)
-#define H_ALL_RES_QP_ACT_R2WQE	  EHEA_BMASK_IBM(32, 47)
-#define H_ALL_RES_QP_ACT_R3WQE	  EHEA_BMASK_IBM(48, 63)
-
-/* output param, R7 */
-#define H_ALL_RES_QP_ACT_SSGE	  EHEA_BMASK_IBM(0, 7)
-#define H_ALL_RES_QP_ACT_R1SGE	  EHEA_BMASK_IBM(8, 15)
-#define H_ALL_RES_QP_ACT_R2SGE	  EHEA_BMASK_IBM(16, 23)
-#define H_ALL_RES_QP_ACT_R3SGE	  EHEA_BMASK_IBM(24, 31)
-#define H_ALL_RES_QP_ACT_SWQE_IDL EHEA_BMASK_IBM(32, 39)
-
-/* output param R8,R9 */
-#define H_ALL_RES_QP_SIZE_SQ	  EHEA_BMASK_IBM(0, 31)
-#define H_ALL_RES_QP_SIZE_RQ1	  EHEA_BMASK_IBM(32, 63)
-#define H_ALL_RES_QP_SIZE_RQ2	  EHEA_BMASK_IBM(0, 31)
-#define H_ALL_RES_QP_SIZE_RQ3	  EHEA_BMASK_IBM(32, 63)
-
-/* output param R11,R12 */
-#define H_ALL_RES_QP_LIOBN_SQ	  EHEA_BMASK_IBM(0, 31)
-#define H_ALL_RES_QP_LIOBN_RQ1	  EHEA_BMASK_IBM(32, 63)
-#define H_ALL_RES_QP_LIOBN_RQ2	  EHEA_BMASK_IBM(0, 31)
-#define H_ALL_RES_QP_LIOBN_RQ3	  EHEA_BMASK_IBM(32, 63)
-
-u64 ehea_h_alloc_resource_qp(const u64 adapter_handle,
-			     struct ehea_qp_init_attr *init_attr, const u32 pd,
-			     u64 *qp_handle, struct h_epas *h_epas)
-{
-	u64 hret;
-	unsigned long outs[PLPAR_HCALL9_BUFSIZE];
-
-	u64 allocate_controls =
-	    EHEA_BMASK_SET(H_ALL_RES_QP_EQPO, init_attr->low_lat_rq1 ? 1 : 0)
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_QPP, 0)
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_RQR, 6)	/* rq1 & rq2 & rq3 */
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_EQEG, 0)	/* EQE gen. disabled */
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_LL_QP, init_attr->low_lat_rq1)
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_DMA128, 0)
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_HSM, 0)
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_SIGT, init_attr->signalingtype)
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_RES_TYP, H_ALL_RES_TYPE_QP);
-
-	u64 r9_reg = EHEA_BMASK_SET(H_ALL_RES_QP_PD, pd)
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_TOKEN, init_attr->qp_token);
-
-	u64 max_r10_reg =
-	    EHEA_BMASK_SET(H_ALL_RES_QP_MAX_SWQE,
-			   get_order_of_qentries(init_attr->max_nr_send_wqes))
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_R1WQE,
-			     get_order_of_qentries(init_attr->max_nr_rwqes_rq1))
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_R2WQE,
-			     get_order_of_qentries(init_attr->max_nr_rwqes_rq2))
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_R3WQE,
-			     get_order_of_qentries(init_attr->max_nr_rwqes_rq3))
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_SSGE, init_attr->wqe_size_enc_sq)
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_R1SGE,
-			     init_attr->wqe_size_enc_rq1)
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_R2SGE,
-			     init_attr->wqe_size_enc_rq2)
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_R3SGE,
-			     init_attr->wqe_size_enc_rq3);
-
-	u64 r11_in =
-	    EHEA_BMASK_SET(H_ALL_RES_QP_SWQE_IDL, init_attr->swqe_imm_data_len)
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_PORT_NUM, init_attr->port_nr);
-	u64 threshold =
-	    EHEA_BMASK_SET(H_ALL_RES_QP_TH_RQ2, init_attr->rq2_threshold)
-	    | EHEA_BMASK_SET(H_ALL_RES_QP_TH_RQ3, init_attr->rq3_threshold);
-
-	hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE,
-				 outs,
-				 adapter_handle,		/* R4 */
-				 allocate_controls,		/* R5 */
-				 init_attr->send_cq_handle,	/* R6 */
-				 init_attr->recv_cq_handle,	/* R7 */
-				 init_attr->aff_eq_handle,	/* R8 */
-				 r9_reg,			/* R9 */
-				 max_r10_reg,			/* R10 */
-				 r11_in,			/* R11 */
-				 threshold);			/* R12 */
-
-	*qp_handle = outs[0];
-	init_attr->qp_nr = (u32)outs[1];
-
-	init_attr->act_nr_send_wqes =
-	    (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_SWQE, outs[2]);
-	init_attr->act_nr_rwqes_rq1 =
-	    (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R1WQE, outs[2]);
-	init_attr->act_nr_rwqes_rq2 =
-	    (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R2WQE, outs[2]);
-	init_attr->act_nr_rwqes_rq3 =
-	    (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R3WQE, outs[2]);
-
-	init_attr->act_wqe_size_enc_sq = init_attr->wqe_size_enc_sq;
-	init_attr->act_wqe_size_enc_rq1 = init_attr->wqe_size_enc_rq1;
-	init_attr->act_wqe_size_enc_rq2 = init_attr->wqe_size_enc_rq2;
-	init_attr->act_wqe_size_enc_rq3 = init_attr->wqe_size_enc_rq3;
-
-	init_attr->nr_sq_pages =
-	    (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_SQ, outs[4]);
-	init_attr->nr_rq1_pages =
-	    (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ1, outs[4]);
-	init_attr->nr_rq2_pages =
-	    (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ2, outs[5]);
-	init_attr->nr_rq3_pages =
-	    (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ3, outs[5]);
-
-	init_attr->liobn_sq =
-	    (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_SQ, outs[7]);
-	init_attr->liobn_rq1 =
-	    (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ1, outs[7]);
-	init_attr->liobn_rq2 =
-	    (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ2, outs[8]);
-	init_attr->liobn_rq3 =
-	    (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ3, outs[8]);
-
-	if (!hret)
-		hcp_epas_ctor(h_epas, outs[6], outs[6]);
-
-	return hret;
-}
-
-u64 ehea_h_alloc_resource_cq(const u64 adapter_handle,
-			     struct ehea_cq_attr *cq_attr,
-			     u64 *cq_handle, struct h_epas *epas)
-{
-	u64 hret;
-	unsigned long outs[PLPAR_HCALL9_BUFSIZE];
-
-	hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE,
-				 outs,
-				 adapter_handle,		/* R4 */
-				 H_ALL_RES_TYPE_CQ,		/* R5 */
-				 cq_attr->eq_handle,		/* R6 */
-				 cq_attr->cq_token,		/* R7 */
-				 cq_attr->max_nr_of_cqes,	/* R8 */
-				 0, 0, 0, 0);			/* R9-R12 */
-
-	*cq_handle = outs[0];
-	cq_attr->act_nr_of_cqes = outs[3];
-	cq_attr->nr_pages = outs[4];
-
-	if (!hret)
-		hcp_epas_ctor(epas, outs[5], outs[6]);
-
-	return hret;
-}
-
-/* Defines for H_CALL H_ALLOC_RESOURCE */
-#define H_ALL_RES_TYPE_QP	 1
-#define H_ALL_RES_TYPE_CQ	 2
-#define H_ALL_RES_TYPE_EQ	 3
-#define H_ALL_RES_TYPE_MR	 5
-#define H_ALL_RES_TYPE_MW	 6
-
-/*  input param R5 */
-#define H_ALL_RES_EQ_NEQ	     EHEA_BMASK_IBM(0, 0)
-#define H_ALL_RES_EQ_NON_NEQ_ISN     EHEA_BMASK_IBM(6, 7)
-#define H_ALL_RES_EQ_INH_EQE_GEN     EHEA_BMASK_IBM(16, 16)
-#define H_ALL_RES_EQ_RES_TYPE	     EHEA_BMASK_IBM(56, 63)
-/*  input param R6 */
-#define H_ALL_RES_EQ_MAX_EQE	     EHEA_BMASK_IBM(32, 63)
-
-/*  output param R6 */
-#define H_ALL_RES_EQ_LIOBN	     EHEA_BMASK_IBM(32, 63)
-
-/*  output param R7 */
-#define H_ALL_RES_EQ_ACT_EQE	     EHEA_BMASK_IBM(32, 63)
-
-/*  output param R8 */
-#define H_ALL_RES_EQ_ACT_PS	     EHEA_BMASK_IBM(32, 63)
-
-/*  output param R9 */
-#define H_ALL_RES_EQ_ACT_EQ_IST_C    EHEA_BMASK_IBM(30, 31)
-#define H_ALL_RES_EQ_ACT_EQ_IST_1    EHEA_BMASK_IBM(40, 63)
-
-/*  output param R10 */
-#define H_ALL_RES_EQ_ACT_EQ_IST_2    EHEA_BMASK_IBM(40, 63)
-
-/*  output param R11 */
-#define H_ALL_RES_EQ_ACT_EQ_IST_3    EHEA_BMASK_IBM(40, 63)
-
-/*  output param R12 */
-#define H_ALL_RES_EQ_ACT_EQ_IST_4    EHEA_BMASK_IBM(40, 63)
-
-u64 ehea_h_alloc_resource_eq(const u64 adapter_handle,
-			     struct ehea_eq_attr *eq_attr, u64 *eq_handle)
-{
-	u64 hret, allocate_controls;
-	unsigned long outs[PLPAR_HCALL9_BUFSIZE];
-
-	/* resource type */
-	allocate_controls =
-	    EHEA_BMASK_SET(H_ALL_RES_EQ_RES_TYPE, H_ALL_RES_TYPE_EQ)
-	    | EHEA_BMASK_SET(H_ALL_RES_EQ_NEQ, eq_attr->type ? 1 : 0)
-	    | EHEA_BMASK_SET(H_ALL_RES_EQ_INH_EQE_GEN, !eq_attr->eqe_gen)
-	    | EHEA_BMASK_SET(H_ALL_RES_EQ_NON_NEQ_ISN, 1);
-
-	hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE,
-				 outs,
-				 adapter_handle,		/* R4 */
-				 allocate_controls,		/* R5 */
-				 eq_attr->max_nr_of_eqes,	/* R6 */
-				 0, 0, 0, 0, 0, 0);		/* R7-R10 */
-
-	*eq_handle = outs[0];
-	eq_attr->act_nr_of_eqes = outs[3];
-	eq_attr->nr_pages = outs[4];
-	eq_attr->ist1 = outs[5];
-	eq_attr->ist2 = outs[6];
-	eq_attr->ist3 = outs[7];
-	eq_attr->ist4 = outs[8];
-
-	return hret;
-}
-
-u64 ehea_h_modify_ehea_qp(const u64 adapter_handle, const u8 cat,
-			  const u64 qp_handle, const u64 sel_mask,
-			  void *cb_addr, u64 *inv_attr_id, u64 *proc_mask,
-			  u16 *out_swr, u16 *out_rwr)
-{
-	u64 hret;
-	unsigned long outs[PLPAR_HCALL9_BUFSIZE];
-
-	hret = ehea_plpar_hcall9(H_MODIFY_HEA_QP,
-				 outs,
-				 adapter_handle,		/* R4 */
-				 (u64) cat,			/* R5 */
-				 qp_handle,			/* R6 */
-				 sel_mask,			/* R7 */
-				 __pa(cb_addr),			/* R8 */
-				 0, 0, 0, 0);			/* R9-R12 */
-
-	*inv_attr_id = outs[0];
-	*out_swr = outs[3];
-	*out_rwr = outs[4];
-	*proc_mask = outs[5];
-
-	return hret;
-}
-
-u64 ehea_h_register_rpage(const u64 adapter_handle, const u8 pagesize,
-			  const u8 queue_type, const u64 resource_handle,
-			  const u64 log_pageaddr, u64 count)
-{
-	u64  reg_control;
-
-	reg_control = EHEA_BMASK_SET(H_REG_RPAGE_PAGE_SIZE, pagesize)
-		    | EHEA_BMASK_SET(H_REG_RPAGE_QT, queue_type);
-
-	return ehea_plpar_hcall_norets(H_REGISTER_HEA_RPAGES,
-				       adapter_handle,		/* R4 */
-				       reg_control,		/* R5 */
-				       resource_handle,		/* R6 */
-				       log_pageaddr,		/* R7 */
-				       count,			/* R8 */
-				       0, 0);			/* R9-R10 */
-}
-
-u64 ehea_h_register_smr(const u64 adapter_handle, const u64 orig_mr_handle,
-			const u64 vaddr_in, const u32 access_ctrl, const u32 pd,
-			struct ehea_mr *mr)
-{
-	u64 hret;
-	unsigned long outs[PLPAR_HCALL9_BUFSIZE];
-
-	hret = ehea_plpar_hcall9(H_REGISTER_SMR,
-				 outs,
-				 adapter_handle	      ,		 /* R4 */
-				 orig_mr_handle,		 /* R5 */
-				 vaddr_in,			 /* R6 */
-				 (((u64)access_ctrl) << 32ULL),	 /* R7 */
-				 pd,				 /* R8 */
-				 0, 0, 0, 0);			 /* R9-R12 */
-
-	mr->handle = outs[0];
-	mr->lkey = (u32)outs[2];
-
-	return hret;
-}
-
-u64 ehea_h_disable_and_get_hea(const u64 adapter_handle, const u64 qp_handle)
-{
-	unsigned long outs[PLPAR_HCALL9_BUFSIZE];
-
-	return ehea_plpar_hcall9(H_DISABLE_AND_GET_HEA,
-				 outs,
-				 adapter_handle,		/* R4 */
-				 H_DISABLE_GET_EHEA_WQE_P,	/* R5 */
-				 qp_handle,			/* R6 */
-				 0, 0, 0, 0, 0, 0);		/* R7-R12 */
-}
-
-u64 ehea_h_free_resource(const u64 adapter_handle, const u64 res_handle,
-			 u64 force_bit)
-{
-	return ehea_plpar_hcall_norets(H_FREE_RESOURCE,
-				       adapter_handle,	   /* R4 */
-				       res_handle,	   /* R5 */
-				       force_bit,
-				       0, 0, 0, 0);	   /* R7-R10 */
-}
-
-u64 ehea_h_alloc_resource_mr(const u64 adapter_handle, const u64 vaddr,
-			     const u64 length, const u32 access_ctrl,
-			     const u32 pd, u64 *mr_handle, u32 *lkey)
-{
-	u64 hret;
-	unsigned long outs[PLPAR_HCALL9_BUFSIZE];
-
-	hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE,
-				 outs,
-				 adapter_handle,		   /* R4 */
-				 5,				   /* R5 */
-				 vaddr,				   /* R6 */
-				 length,			   /* R7 */
-				 (((u64) access_ctrl) << 32ULL),   /* R8 */
-				 pd,				   /* R9 */
-				 0, 0, 0);			   /* R10-R12 */
-
-	*mr_handle = outs[0];
-	*lkey = (u32)outs[2];
-	return hret;
-}
-
-u64 ehea_h_register_rpage_mr(const u64 adapter_handle, const u64 mr_handle,
-			     const u8 pagesize, const u8 queue_type,
-			     const u64 log_pageaddr, const u64 count)
-{
-	if ((count > 1) && (log_pageaddr & ~PAGE_MASK)) {
-		pr_err("not on pageboundary\n");
-		return H_PARAMETER;
-	}
-
-	return ehea_h_register_rpage(adapter_handle, pagesize,
-				     queue_type, mr_handle,
-				     log_pageaddr, count);
-}
-
-u64 ehea_h_query_ehea(const u64 adapter_handle, void *cb_addr)
-{
-	u64 hret, cb_logaddr;
-
-	cb_logaddr = __pa(cb_addr);
-
-	hret = ehea_plpar_hcall_norets(H_QUERY_HEA,
-				       adapter_handle,		/* R4 */
-				       cb_logaddr,		/* R5 */
-				       0, 0, 0, 0, 0);		/* R6-R10 */
-#ifdef DEBUG
-	ehea_dump(cb_addr, sizeof(struct hcp_query_ehea), "hcp_query_ehea");
-#endif
-	return hret;
-}
-
-u64 ehea_h_query_ehea_port(const u64 adapter_handle, const u16 port_num,
-			   const u8 cb_cat, const u64 select_mask,
-			   void *cb_addr)
-{
-	u64 port_info;
-	u64 cb_logaddr = __pa(cb_addr);
-	u64 arr_index = 0;
-
-	port_info = EHEA_BMASK_SET(H_MEHEAPORT_CAT, cb_cat)
-		  | EHEA_BMASK_SET(H_MEHEAPORT_PN, port_num);
-
-	return ehea_plpar_hcall_norets(H_QUERY_HEA_PORT,
-				       adapter_handle,		/* R4 */
-				       port_info,		/* R5 */
-				       select_mask,		/* R6 */
-				       arr_index,		/* R7 */
-				       cb_logaddr,		/* R8 */
-				       0, 0);			/* R9-R10 */
-}
-
-u64 ehea_h_modify_ehea_port(const u64 adapter_handle, const u16 port_num,
-			    const u8 cb_cat, const u64 select_mask,
-			    void *cb_addr)
-{
-	unsigned long outs[PLPAR_HCALL9_BUFSIZE];
-	u64 port_info;
-	u64 arr_index = 0;
-	u64 cb_logaddr = __pa(cb_addr);
-
-	port_info = EHEA_BMASK_SET(H_MEHEAPORT_CAT, cb_cat)
-		  | EHEA_BMASK_SET(H_MEHEAPORT_PN, port_num);
-#ifdef DEBUG
-	ehea_dump(cb_addr, sizeof(struct hcp_ehea_port_cb0), "Before HCALL");
-#endif
-	return ehea_plpar_hcall9(H_MODIFY_HEA_PORT,
-				 outs,
-				 adapter_handle,		/* R4 */
-				 port_info,			/* R5 */
-				 select_mask,			/* R6 */
-				 arr_index,			/* R7 */
-				 cb_logaddr,			/* R8 */
-				 0, 0, 0, 0);			/* R9-R12 */
-}
-
-u64 ehea_h_reg_dereg_bcmc(const u64 adapter_handle, const u16 port_num,
-			  const u8 reg_type, const u64 mc_mac_addr,
-			  const u16 vlan_id, const u32 hcall_id)
-{
-	u64 r5_port_num, r6_reg_type, r7_mc_mac_addr, r8_vlan_id;
-	u64 mac_addr = mc_mac_addr >> 16;
-
-	r5_port_num = EHEA_BMASK_SET(H_REGBCMC_PN, port_num);
-	r6_reg_type = EHEA_BMASK_SET(H_REGBCMC_REGTYPE, reg_type);
-	r7_mc_mac_addr = EHEA_BMASK_SET(H_REGBCMC_MACADDR, mac_addr);
-	r8_vlan_id = EHEA_BMASK_SET(H_REGBCMC_VLANID, vlan_id);
-
-	return ehea_plpar_hcall_norets(hcall_id,
-				       adapter_handle,		/* R4 */
-				       r5_port_num,		/* R5 */
-				       r6_reg_type,		/* R6 */
-				       r7_mc_mac_addr,		/* R7 */
-				       r8_vlan_id,		/* R8 */
-				       0, 0);			/* R9-R12 */
-}
-
-u64 ehea_h_reset_events(const u64 adapter_handle, const u64 neq_handle,
-			const u64 event_mask)
-{
-	return ehea_plpar_hcall_norets(H_RESET_EVENTS,
-				       adapter_handle,		/* R4 */
-				       neq_handle,		/* R5 */
-				       event_mask,		/* R6 */
-				       0, 0, 0, 0);		/* R7-R12 */
-}
-
-u64 ehea_h_error_data(const u64 adapter_handle, const u64 ressource_handle,
-		      void *rblock)
-{
-	return ehea_plpar_hcall_norets(H_ERROR_DATA,
-				       adapter_handle,		/* R4 */
-				       ressource_handle,	/* R5 */
-				       __pa(rblock),		/* R6 */
-				       0, 0, 0, 0);		/* R7-R12 */
-}
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_phyp.h b/drivers/net/ethernet/ibm/ehea/ehea_phyp.h
deleted file mode 100644
index e8b56c103410..000000000000
--- a/drivers/net/ethernet/ibm/ehea/ehea_phyp.h
+++ /dev/null
@@ -1,433 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  linux/drivers/net/ethernet/ibm/ehea/ehea_phyp.h
- *
- *  eHEA ethernet device driver for IBM eServer System p
- *
- *  (C) Copyright IBM Corp. 2006
- *
- *  Authors:
- *       Christoph Raisch <raisch@de.ibm.com>
- *       Jan-Bernd Themann <themann@de.ibm.com>
- *       Thomas Klein <tklein@de.ibm.com>
- */
-
-#ifndef __EHEA_PHYP_H__
-#define __EHEA_PHYP_H__
-
-#include <linux/delay.h>
-#include <asm/hvcall.h>
-#include "ehea.h"
-#include "ehea_hw.h"
-
-/* Some abbreviations used here:
- *
- * hcp_*  - structures, variables and functions releated to Hypervisor Calls
- */
-
-/* Number of pages which can be registered at once by H_REGISTER_HEA_RPAGES */
-#define EHEA_MAX_RPAGE 512
-
-/* Notification Event Queue (NEQ) Entry bit masks */
-#define NEQE_EVENT_CODE		EHEA_BMASK_IBM(2, 7)
-#define NEQE_PORTNUM  		EHEA_BMASK_IBM(32, 47)
-#define NEQE_PORT_UP		EHEA_BMASK_IBM(16, 16)
-#define NEQE_EXTSWITCH_PORT_UP	EHEA_BMASK_IBM(17, 17)
-#define NEQE_EXTSWITCH_PRIMARY	EHEA_BMASK_IBM(18, 18)
-#define NEQE_PLID		EHEA_BMASK_IBM(16, 47)
-
-/* Notification Event Codes */
-#define EHEA_EC_PORTSTATE_CHG	0x30
-#define EHEA_EC_ADAPTER_MALFUNC	0x32
-#define EHEA_EC_PORT_MALFUNC	0x33
-
-/* Notification Event Log Register (NELR) bit masks */
-#define NELR_PORT_MALFUNC	EHEA_BMASK_IBM(61, 61)
-#define NELR_ADAPTER_MALFUNC	EHEA_BMASK_IBM(62, 62)
-#define NELR_PORTSTATE_CHG	EHEA_BMASK_IBM(63, 63)
-
-static inline void hcp_epas_ctor(struct h_epas *epas, u64 paddr_kernel,
-				 u64 paddr_user)
-{
-	/* To support 64k pages we must round to 64k page boundary */
-	epas->kernel.addr = ioremap((paddr_kernel & PAGE_MASK), PAGE_SIZE) +
-			    (paddr_kernel & ~PAGE_MASK);
-	epas->user.addr = paddr_user;
-}
-
-static inline void hcp_epas_dtor(struct h_epas *epas)
-{
-	if (epas->kernel.addr)
-		iounmap((void __iomem *)((u64)epas->kernel.addr & PAGE_MASK));
-
-	epas->user.addr = 0;
-	epas->kernel.addr = 0;
-}
-
-struct hcp_modify_qp_cb0 {
-	u64 qp_ctl_reg;		/* 00 */
-	u32 max_swqe;		/* 02 */
-	u32 max_rwqe;		/* 03 */
-	u32 port_nb;		/* 04 */
-	u32 reserved0;		/* 05 */
-	u64 qp_aer;		/* 06 */
-	u64 qp_tenure;		/* 08 */
-};
-
-/* Hcall Query/Modify Queue Pair Control Block 0 Selection Mask Bits */
-#define H_QPCB0_ALL             EHEA_BMASK_IBM(0, 5)
-#define H_QPCB0_QP_CTL_REG      EHEA_BMASK_IBM(0, 0)
-#define H_QPCB0_MAX_SWQE        EHEA_BMASK_IBM(1, 1)
-#define H_QPCB0_MAX_RWQE        EHEA_BMASK_IBM(2, 2)
-#define H_QPCB0_PORT_NB         EHEA_BMASK_IBM(3, 3)
-#define H_QPCB0_QP_AER          EHEA_BMASK_IBM(4, 4)
-#define H_QPCB0_QP_TENURE       EHEA_BMASK_IBM(5, 5)
-
-/* Queue Pair Control Register Status Bits */
-#define H_QP_CR_ENABLED		    0x8000000000000000ULL /* QP enabled */
-							  /* QP States: */
-#define H_QP_CR_STATE_RESET	    0x0000010000000000ULL /*  Reset */
-#define H_QP_CR_STATE_INITIALIZED   0x0000020000000000ULL /*  Initialized */
-#define H_QP_CR_STATE_RDY2RCV	    0x0000030000000000ULL /*  Ready to recv */
-#define H_QP_CR_STATE_RDY2SND	    0x0000050000000000ULL /*  Ready to send */
-#define H_QP_CR_STATE_ERROR	    0x0000800000000000ULL /*  Error */
-#define H_QP_CR_RES_STATE 	    0x0000007F00000000ULL /* Resultant state */
-
-struct hcp_modify_qp_cb1 {
-	u32 qpn;		/* 00 */
-	u32 qp_asyn_ev_eq_nb;	/* 01 */
-	u64 sq_cq_handle;	/* 02 */
-	u64 rq_cq_handle;	/* 04 */
-	/* sgel = scatter gather element */
-	u32 sgel_nb_sq;		/* 06 */
-	u32 sgel_nb_rq1;	/* 07 */
-	u32 sgel_nb_rq2;	/* 08 */
-	u32 sgel_nb_rq3;	/* 09 */
-};
-
-/* Hcall Query/Modify Queue Pair Control Block 1 Selection Mask Bits */
-#define H_QPCB1_ALL             EHEA_BMASK_IBM(0, 7)
-#define H_QPCB1_QPN             EHEA_BMASK_IBM(0, 0)
-#define H_QPCB1_ASYN_EV_EQ_NB   EHEA_BMASK_IBM(1, 1)
-#define H_QPCB1_SQ_CQ_HANDLE    EHEA_BMASK_IBM(2, 2)
-#define H_QPCB1_RQ_CQ_HANDLE    EHEA_BMASK_IBM(3, 3)
-#define H_QPCB1_SGEL_NB_SQ      EHEA_BMASK_IBM(4, 4)
-#define H_QPCB1_SGEL_NB_RQ1     EHEA_BMASK_IBM(5, 5)
-#define H_QPCB1_SGEL_NB_RQ2     EHEA_BMASK_IBM(6, 6)
-#define H_QPCB1_SGEL_NB_RQ3     EHEA_BMASK_IBM(7, 7)
-
-struct hcp_query_ehea {
-	u32 cur_num_qps;		/* 00 */
-	u32 cur_num_cqs;		/* 01 */
-	u32 cur_num_eqs;		/* 02 */
-	u32 cur_num_mrs;		/* 03 */
-	u32 auth_level;			/* 04 */
-	u32 max_num_qps;		/* 05 */
-	u32 max_num_cqs;		/* 06 */
-	u32 max_num_eqs;		/* 07 */
-	u32 max_num_mrs;		/* 08 */
-	u32 reserved0;			/* 09 */
-	u32 int_clock_freq;		/* 10 */
-	u32 max_num_pds;		/* 11 */
-	u32 max_num_addr_handles;	/* 12 */
-	u32 max_num_cqes;		/* 13 */
-	u32 max_num_wqes;		/* 14 */
-	u32 max_num_sgel_rq1wqe;	/* 15 */
-	u32 max_num_sgel_rq2wqe;	/* 16 */
-	u32 max_num_sgel_rq3wqe;	/* 17 */
-	u32 mr_page_size;		/* 18 */
-	u32 reserved1;			/* 19 */
-	u64 max_mr_size;		/* 20 */
-	u64 reserved2;			/* 22 */
-	u32 num_ports;			/* 24 */
-	u32 reserved3;			/* 25 */
-	u32 reserved4;			/* 26 */
-	u32 reserved5;			/* 27 */
-	u64 max_mc_mac;			/* 28 */
-	u64 ehea_cap;			/* 30 */
-	u32 max_isn_per_eq;		/* 32 */
-	u32 max_num_neq;		/* 33 */
-	u64 max_num_vlan_ids;		/* 34 */
-	u32 max_num_port_group;		/* 36 */
-	u32 max_num_phys_port;		/* 37 */
-
-};
-
-/* Hcall Query/Modify Port Control Block defines */
-#define H_PORT_CB0	 0
-#define H_PORT_CB1	 1
-#define H_PORT_CB2	 2
-#define H_PORT_CB3	 3
-#define H_PORT_CB4	 4
-#define H_PORT_CB5	 5
-#define H_PORT_CB6	 6
-#define H_PORT_CB7	 7
-
-struct hcp_ehea_port_cb0 {
-	u64 port_mac_addr;
-	u64 port_rc;
-	u64 reserved0;
-	u32 port_op_state;
-	u32 port_speed;
-	u32 ext_swport_op_state;
-	u32 neg_tpf_prpf;
-	u32 num_default_qps;
-	u32 reserved1;
-	u64 default_qpn_arr[16];
-};
-
-/* Hcall Query/Modify Port Control Block 0 Selection Mask Bits */
-#define H_PORT_CB0_ALL		EHEA_BMASK_IBM(0, 7)    /* Set all bits */
-#define H_PORT_CB0_MAC		EHEA_BMASK_IBM(0, 0)    /* MAC address */
-#define H_PORT_CB0_PRC		EHEA_BMASK_IBM(1, 1)    /* Port Recv Control */
-#define H_PORT_CB0_DEFQPNARRAY	EHEA_BMASK_IBM(7, 7)    /* Default QPN Array */
-
-/*  Hcall Query Port: Returned port speed values */
-#define H_SPEED_10M_H	1	/*  10 Mbps, Half Duplex */
-#define H_SPEED_10M_F	2	/*  10 Mbps, Full Duplex */
-#define H_SPEED_100M_H	3	/* 100 Mbps, Half Duplex */
-#define H_SPEED_100M_F	4	/* 100 Mbps, Full Duplex */
-#define H_SPEED_1G_F	6	/*   1 Gbps, Full Duplex */
-#define H_SPEED_10G_F	8	/*  10 Gbps, Full Duplex */
-
-/* Port Receive Control Status Bits */
-#define PXLY_RC_VALID           EHEA_BMASK_IBM(49, 49)
-#define PXLY_RC_VLAN_XTRACT     EHEA_BMASK_IBM(50, 50)
-#define PXLY_RC_TCP_6_TUPLE     EHEA_BMASK_IBM(51, 51)
-#define PXLY_RC_UDP_6_TUPLE     EHEA_BMASK_IBM(52, 52)
-#define PXLY_RC_TCP_3_TUPLE     EHEA_BMASK_IBM(53, 53)
-#define PXLY_RC_TCP_2_TUPLE     EHEA_BMASK_IBM(54, 54)
-#define PXLY_RC_LLC_SNAP        EHEA_BMASK_IBM(55, 55)
-#define PXLY_RC_JUMBO_FRAME     EHEA_BMASK_IBM(56, 56)
-#define PXLY_RC_FRAG_IP_PKT     EHEA_BMASK_IBM(57, 57)
-#define PXLY_RC_TCP_UDP_CHKSUM  EHEA_BMASK_IBM(58, 58)
-#define PXLY_RC_IP_CHKSUM       EHEA_BMASK_IBM(59, 59)
-#define PXLY_RC_MAC_FILTER      EHEA_BMASK_IBM(60, 60)
-#define PXLY_RC_UNTAG_FILTER    EHEA_BMASK_IBM(61, 61)
-#define PXLY_RC_VLAN_TAG_FILTER EHEA_BMASK_IBM(62, 63)
-
-#define PXLY_RC_VLAN_FILTER     2
-#define PXLY_RC_VLAN_PERM       0
-
-
-#define H_PORT_CB1_ALL          0x8000000000000000ULL
-
-struct hcp_ehea_port_cb1 {
-	u64 vlan_filter[64];
-};
-
-#define H_PORT_CB2_ALL          0xFFE0000000000000ULL
-
-struct hcp_ehea_port_cb2 {
-	u64 rxo;
-	u64 rxucp;
-	u64 rxufd;
-	u64 rxuerr;
-	u64 rxftl;
-	u64 rxmcp;
-	u64 rxbcp;
-	u64 txo;
-	u64 txucp;
-	u64 txmcp;
-	u64 txbcp;
-};
-
-struct hcp_ehea_port_cb3 {
-	u64 vlan_bc_filter[64];
-	u64 vlan_mc_filter[64];
-	u64 vlan_un_filter[64];
-	u64 port_mac_hash_array[64];
-};
-
-#define H_PORT_CB4_ALL          0xF000000000000000ULL
-#define H_PORT_CB4_JUMBO        0x1000000000000000ULL
-#define H_PORT_CB4_SPEED        0x8000000000000000ULL
-
-struct hcp_ehea_port_cb4 {
-	u32 port_speed;
-	u32 pause_frame;
-	u32 ens_port_op_state;
-	u32 jumbo_frame;
-	u32 ens_port_wrap;
-};
-
-/* Hcall Query/Modify Port Control Block 5 Selection Mask Bits */
-#define H_PORT_CB5_RCU		0x0001000000000000ULL
-#define PXS_RCU			EHEA_BMASK_IBM(61, 63)
-
-struct hcp_ehea_port_cb5 {
-	u64 prc;	        /* 00 */
-	u64 uaa;		/* 01 */
-	u64 macvc;		/* 02 */
-	u64 xpcsc;		/* 03 */
-	u64 xpcsp;		/* 04 */
-	u64 pcsid;		/* 05 */
-	u64 xpcsst;		/* 06 */
-	u64 pthlb;		/* 07 */
-	u64 pthrb;		/* 08 */
-	u64 pqu;		/* 09 */
-	u64 pqd;		/* 10 */
-	u64 prt;		/* 11 */
-	u64 wsth;		/* 12 */
-	u64 rcb;		/* 13 */
-	u64 rcm;		/* 14 */
-	u64 rcu;		/* 15 */
-	u64 macc;		/* 16 */
-	u64 pc;			/* 17 */
-	u64 pst;		/* 18 */
-	u64 ducqpn;		/* 19 */
-	u64 mcqpn;		/* 20 */
-	u64 mma;		/* 21 */
-	u64 pmc0h;		/* 22 */
-	u64 pmc0l;		/* 23 */
-	u64 lbc;		/* 24 */
-};
-
-#define H_PORT_CB6_ALL  0xFFFFFE7FFFFF8000ULL
-
-struct hcp_ehea_port_cb6 {
-	u64 rxo;		/* 00 */
-	u64 rx64;		/* 01 */
-	u64 rx65;		/* 02 */
-	u64 rx128;		/* 03 */
-	u64 rx256;		/* 04 */
-	u64 rx512;		/* 05 */
-	u64 rx1024;		/* 06 */
-	u64 rxbfcs;		/* 07 */
-	u64 rxime;		/* 08 */
-	u64 rxrle;		/* 09 */
-	u64 rxorle;		/* 10 */
-	u64 rxftl;		/* 11 */
-	u64 rxjab;		/* 12 */
-	u64 rxse;		/* 13 */
-	u64 rxce;		/* 14 */
-	u64 rxrf;		/* 15 */
-	u64 rxfrag;		/* 16 */
-	u64 rxuoc;		/* 17 */
-	u64 rxcpf;		/* 18 */
-	u64 rxsb;		/* 19 */
-	u64 rxfd;		/* 20 */
-	u64 rxoerr;		/* 21 */
-	u64 rxaln;		/* 22 */
-	u64 ducqpn;		/* 23 */
-	u64 reserved0;		/* 24 */
-	u64 rxmcp;		/* 25 */
-	u64 rxbcp;		/* 26 */
-	u64 txmcp;		/* 27 */
-	u64 txbcp;		/* 28 */
-	u64 txo;		/* 29 */
-	u64 tx64;		/* 30 */
-	u64 tx65;		/* 31 */
-	u64 tx128;		/* 32 */
-	u64 tx256;		/* 33 */
-	u64 tx512;		/* 34 */
-	u64 tx1024;		/* 35 */
-	u64 txbfcs;		/* 36 */
-	u64 txcpf;		/* 37 */
-	u64 txlf;		/* 38 */
-	u64 txrf;		/* 39 */
-	u64 txime;		/* 40 */
-	u64 txsc;		/* 41 */
-	u64 txmc;		/* 42 */
-	u64 txsqe;		/* 43 */
-	u64 txdef;		/* 44 */
-	u64 txlcol;		/* 45 */
-	u64 txexcol;		/* 46 */
-	u64 txcse;		/* 47 */
-	u64 txbor;		/* 48 */
-};
-
-#define H_PORT_CB7_DUCQPN 0x8000000000000000ULL
-
-struct hcp_ehea_port_cb7 {
-	u64 def_uc_qpn;
-};
-
-u64 ehea_h_query_ehea_qp(const u64 adapter_handle,
-			 const u8 qp_category,
-			 const u64 qp_handle, const u64 sel_mask,
-			 void *cb_addr);
-
-u64 ehea_h_modify_ehea_qp(const u64 adapter_handle,
-			  const u8 cat,
-			  const u64 qp_handle,
-			  const u64 sel_mask,
-			  void *cb_addr,
-			  u64 *inv_attr_id,
-			  u64 *proc_mask, u16 *out_swr, u16 *out_rwr);
-
-u64 ehea_h_alloc_resource_eq(const u64 adapter_handle,
-			     struct ehea_eq_attr *eq_attr, u64 *eq_handle);
-
-u64 ehea_h_alloc_resource_cq(const u64 adapter_handle,
-			     struct ehea_cq_attr *cq_attr,
-			     u64 *cq_handle, struct h_epas *epas);
-
-u64 ehea_h_alloc_resource_qp(const u64 adapter_handle,
-			     struct ehea_qp_init_attr *init_attr,
-			     const u32 pd,
-			     u64 *qp_handle, struct h_epas *h_epas);
-
-#define H_REG_RPAGE_PAGE_SIZE          EHEA_BMASK_IBM(48, 55)
-#define H_REG_RPAGE_QT                 EHEA_BMASK_IBM(62, 63)
-
-u64 ehea_h_register_rpage(const u64 adapter_handle,
-			  const u8 pagesize,
-			  const u8 queue_type,
-			  const u64 resource_handle,
-			  const u64 log_pageaddr, u64 count);
-
-#define H_DISABLE_GET_EHEA_WQE_P  1
-#define H_DISABLE_GET_SQ_WQE_P    2
-#define H_DISABLE_GET_RQC         3
-
-u64 ehea_h_disable_and_get_hea(const u64 adapter_handle, const u64 qp_handle);
-
-#define FORCE_FREE 1
-#define NORMAL_FREE 0
-
-u64 ehea_h_free_resource(const u64 adapter_handle, const u64 res_handle,
-			 u64 force_bit);
-
-u64 ehea_h_alloc_resource_mr(const u64 adapter_handle, const u64 vaddr,
-			     const u64 length, const u32 access_ctrl,
-			     const u32 pd, u64 *mr_handle, u32 *lkey);
-
-u64 ehea_h_register_rpage_mr(const u64 adapter_handle, const u64 mr_handle,
-			     const u8 pagesize, const u8 queue_type,
-			     const u64 log_pageaddr, const u64 count);
-
-u64 ehea_h_register_smr(const u64 adapter_handle, const u64 orig_mr_handle,
-			const u64 vaddr_in, const u32 access_ctrl, const u32 pd,
-			struct ehea_mr *mr);
-
-u64 ehea_h_query_ehea(const u64 adapter_handle, void *cb_addr);
-
-/* output param R5 */
-#define H_MEHEAPORT_CAT		EHEA_BMASK_IBM(40, 47)
-#define H_MEHEAPORT_PN		EHEA_BMASK_IBM(48, 63)
-
-u64 ehea_h_query_ehea_port(const u64 adapter_handle, const u16 port_num,
-			   const u8 cb_cat, const u64 select_mask,
-			   void *cb_addr);
-
-u64 ehea_h_modify_ehea_port(const u64 adapter_handle, const u16 port_num,
-			    const u8 cb_cat, const u64 select_mask,
-			    void *cb_addr);
-
-#define H_REGBCMC_PN            EHEA_BMASK_IBM(48, 63)
-#define H_REGBCMC_REGTYPE       EHEA_BMASK_IBM(60, 63)
-#define H_REGBCMC_MACADDR       EHEA_BMASK_IBM(16, 63)
-#define H_REGBCMC_VLANID        EHEA_BMASK_IBM(52, 63)
-
-u64 ehea_h_reg_dereg_bcmc(const u64 adapter_handle, const u16 port_num,
-			  const u8 reg_type, const u64 mc_mac_addr,
-			  const u16 vlan_id, const u32 hcall_id);
-
-u64 ehea_h_reset_events(const u64 adapter_handle, const u64 neq_handle,
-			const u64 event_mask);
-
-u64 ehea_h_error_data(const u64 adapter_handle, const u64 ressource_handle,
-		      void *rblock);
-
-#endif	/* __EHEA_PHYP_H__ */
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_qmr.c b/drivers/net/ethernet/ibm/ehea/ehea_qmr.c
deleted file mode 100644
index 60629a0032b2..000000000000
--- a/drivers/net/ethernet/ibm/ehea/ehea_qmr.c
+++ /dev/null
@@ -1,999 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  linux/drivers/net/ethernet/ibm/ehea/ehea_qmr.c
- *
- *  eHEA ethernet device driver for IBM eServer System p
- *
- *  (C) Copyright IBM Corp. 2006
- *
- *  Authors:
- *       Christoph Raisch <raisch@de.ibm.com>
- *       Jan-Bernd Themann <themann@de.ibm.com>
- *       Thomas Klein <tklein@de.ibm.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/mm.h>
-#include <linux/slab.h>
-#include "ehea.h"
-#include "ehea_phyp.h"
-#include "ehea_qmr.h"
-
-static struct ehea_bmap *ehea_bmap;
-
-static void *hw_qpageit_get_inc(struct hw_queue *queue)
-{
-	void *retvalue = hw_qeit_get(queue);
-
-	queue->current_q_offset += queue->pagesize;
-	if (queue->current_q_offset > queue->queue_length) {
-		queue->current_q_offset -= queue->pagesize;
-		retvalue = NULL;
-	} else if (((u64) retvalue) & (EHEA_PAGESIZE-1)) {
-		pr_err("not on pageboundary\n");
-		retvalue = NULL;
-	}
-	return retvalue;
-}
-
-static int hw_queue_ctor(struct hw_queue *queue, const u32 nr_of_pages,
-			  const u32 pagesize, const u32 qe_size)
-{
-	int pages_per_kpage = PAGE_SIZE / pagesize;
-	int i, k;
-
-	if ((pagesize > PAGE_SIZE) || (!pages_per_kpage)) {
-		pr_err("pagesize conflict! kernel pagesize=%d, ehea pagesize=%d\n",
-		       (int)PAGE_SIZE, (int)pagesize);
-		return -EINVAL;
-	}
-
-	queue->queue_length = nr_of_pages * pagesize;
-	queue->queue_pages = kmalloc_array(nr_of_pages, sizeof(void *),
-					   GFP_KERNEL);
-	if (!queue->queue_pages)
-		return -ENOMEM;
-
-	/*
-	 * allocate pages for queue:
-	 * outer loop allocates whole kernel pages (page aligned) and
-	 * inner loop divides a kernel page into smaller hea queue pages
-	 */
-	i = 0;
-	while (i < nr_of_pages) {
-		u8 *kpage = (u8 *)get_zeroed_page(GFP_KERNEL);
-		if (!kpage)
-			goto out_nomem;
-		for (k = 0; k < pages_per_kpage && i < nr_of_pages; k++) {
-			(queue->queue_pages)[i] = (struct ehea_page *)kpage;
-			kpage += pagesize;
-			i++;
-		}
-	}
-
-	queue->current_q_offset = 0;
-	queue->qe_size = qe_size;
-	queue->pagesize = pagesize;
-	queue->toggle_state = 1;
-
-	return 0;
-out_nomem:
-	for (i = 0; i < nr_of_pages; i += pages_per_kpage) {
-		if (!(queue->queue_pages)[i])
-			break;
-		free_page((unsigned long)(queue->queue_pages)[i]);
-	}
-	return -ENOMEM;
-}
-
-static void hw_queue_dtor(struct hw_queue *queue)
-{
-	int pages_per_kpage;
-	int i, nr_pages;
-
-	if (!queue || !queue->queue_pages)
-		return;
-
-	pages_per_kpage = PAGE_SIZE / queue->pagesize;
-
-	nr_pages = queue->queue_length / queue->pagesize;
-
-	for (i = 0; i < nr_pages; i += pages_per_kpage)
-		free_page((unsigned long)(queue->queue_pages)[i]);
-
-	kfree(queue->queue_pages);
-}
-
-struct ehea_cq *ehea_create_cq(struct ehea_adapter *adapter,
-			       int nr_of_cqe, u64 eq_handle, u32 cq_token)
-{
-	struct ehea_cq *cq;
-	u64 hret, rpage;
-	u32 counter;
-	int ret;
-	void *vpage;
-
-	cq = kzalloc_obj(*cq);
-	if (!cq)
-		goto out_nomem;
-
-	cq->attr.max_nr_of_cqes = nr_of_cqe;
-	cq->attr.cq_token = cq_token;
-	cq->attr.eq_handle = eq_handle;
-
-	cq->adapter = adapter;
-
-	hret = ehea_h_alloc_resource_cq(adapter->handle, &cq->attr,
-					&cq->fw_handle, &cq->epas);
-	if (hret != H_SUCCESS) {
-		pr_err("alloc_resource_cq failed\n");
-		goto out_freemem;
-	}
-
-	ret = hw_queue_ctor(&cq->hw_queue, cq->attr.nr_pages,
-			    EHEA_PAGESIZE, sizeof(struct ehea_cqe));
-	if (ret)
-		goto out_freeres;
-
-	for (counter = 0; counter < cq->attr.nr_pages; counter++) {
-		vpage = hw_qpageit_get_inc(&cq->hw_queue);
-		if (!vpage) {
-			pr_err("hw_qpageit_get_inc failed\n");
-			goto out_kill_hwq;
-		}
-
-		rpage = __pa(vpage);
-		hret = ehea_h_register_rpage(adapter->handle,
-					     0, EHEA_CQ_REGISTER_ORIG,
-					     cq->fw_handle, rpage, 1);
-		if (hret < H_SUCCESS) {
-			pr_err("register_rpage_cq failed ehea_cq=%p hret=%llx counter=%i act_pages=%i\n",
-			       cq, hret, counter, cq->attr.nr_pages);
-			goto out_kill_hwq;
-		}
-
-		if (counter == (cq->attr.nr_pages - 1)) {
-			vpage = hw_qpageit_get_inc(&cq->hw_queue);
-
-			if ((hret != H_SUCCESS) || (vpage)) {
-				pr_err("registration of pages not complete hret=%llx\n",
-				       hret);
-				goto out_kill_hwq;
-			}
-		} else {
-			if (hret != H_PAGE_REGISTERED) {
-				pr_err("CQ: registration of page failed hret=%llx\n",
-				       hret);
-				goto out_kill_hwq;
-			}
-		}
-	}
-
-	hw_qeit_reset(&cq->hw_queue);
-	ehea_reset_cq_ep(cq);
-	ehea_reset_cq_n1(cq);
-
-	return cq;
-
-out_kill_hwq:
-	hw_queue_dtor(&cq->hw_queue);
-
-out_freeres:
-	ehea_h_free_resource(adapter->handle, cq->fw_handle, FORCE_FREE);
-
-out_freemem:
-	kfree(cq);
-
-out_nomem:
-	return NULL;
-}
-
-static u64 ehea_destroy_cq_res(struct ehea_cq *cq, u64 force)
-{
-	u64 hret;
-	u64 adapter_handle = cq->adapter->handle;
-
-	/* deregister all previous registered pages */
-	hret = ehea_h_free_resource(adapter_handle, cq->fw_handle, force);
-	if (hret != H_SUCCESS)
-		return hret;
-
-	hw_queue_dtor(&cq->hw_queue);
-	kfree(cq);
-
-	return hret;
-}
-
-int ehea_destroy_cq(struct ehea_cq *cq)
-{
-	u64 hret, aer, aerr;
-	if (!cq)
-		return 0;
-
-	hcp_epas_dtor(&cq->epas);
-	hret = ehea_destroy_cq_res(cq, NORMAL_FREE);
-	if (hret == H_R_STATE) {
-		ehea_error_data(cq->adapter, cq->fw_handle, &aer, &aerr);
-		hret = ehea_destroy_cq_res(cq, FORCE_FREE);
-	}
-
-	if (hret != H_SUCCESS) {
-		pr_err("destroy CQ failed\n");
-		return -EIO;
-	}
-
-	return 0;
-}
-
-struct ehea_eq *ehea_create_eq(struct ehea_adapter *adapter,
-			       const enum ehea_eq_type type,
-			       const u32 max_nr_of_eqes, const u8 eqe_gen)
-{
-	int ret, i;
-	u64 hret, rpage;
-	void *vpage;
-	struct ehea_eq *eq;
-
-	eq = kzalloc_obj(*eq);
-	if (!eq)
-		return NULL;
-
-	eq->adapter = adapter;
-	eq->attr.type = type;
-	eq->attr.max_nr_of_eqes = max_nr_of_eqes;
-	eq->attr.eqe_gen = eqe_gen;
-	spin_lock_init(&eq->spinlock);
-
-	hret = ehea_h_alloc_resource_eq(adapter->handle,
-					&eq->attr, &eq->fw_handle);
-	if (hret != H_SUCCESS) {
-		pr_err("alloc_resource_eq failed\n");
-		goto out_freemem;
-	}
-
-	ret = hw_queue_ctor(&eq->hw_queue, eq->attr.nr_pages,
-			    EHEA_PAGESIZE, sizeof(struct ehea_eqe));
-	if (ret) {
-		pr_err("can't allocate eq pages\n");
-		goto out_freeres;
-	}
-
-	for (i = 0; i < eq->attr.nr_pages; i++) {
-		vpage = hw_qpageit_get_inc(&eq->hw_queue);
-		if (!vpage) {
-			pr_err("hw_qpageit_get_inc failed\n");
-			hret = H_RESOURCE;
-			goto out_kill_hwq;
-		}
-
-		rpage = __pa(vpage);
-
-		hret = ehea_h_register_rpage(adapter->handle, 0,
-					     EHEA_EQ_REGISTER_ORIG,
-					     eq->fw_handle, rpage, 1);
-
-		if (i == (eq->attr.nr_pages - 1)) {
-			/* last page */
-			vpage = hw_qpageit_get_inc(&eq->hw_queue);
-			if ((hret != H_SUCCESS) || (vpage))
-				goto out_kill_hwq;
-
-		} else {
-			if (hret != H_PAGE_REGISTERED)
-				goto out_kill_hwq;
-
-		}
-	}
-
-	hw_qeit_reset(&eq->hw_queue);
-	return eq;
-
-out_kill_hwq:
-	hw_queue_dtor(&eq->hw_queue);
-
-out_freeres:
-	ehea_h_free_resource(adapter->handle, eq->fw_handle, FORCE_FREE);
-
-out_freemem:
-	kfree(eq);
-	return NULL;
-}
-
-struct ehea_eqe *ehea_poll_eq(struct ehea_eq *eq)
-{
-	struct ehea_eqe *eqe;
-	unsigned long flags;
-
-	spin_lock_irqsave(&eq->spinlock, flags);
-	eqe = hw_eqit_eq_get_inc_valid(&eq->hw_queue);
-	spin_unlock_irqrestore(&eq->spinlock, flags);
-
-	return eqe;
-}
-
-static u64 ehea_destroy_eq_res(struct ehea_eq *eq, u64 force)
-{
-	u64 hret;
-	unsigned long flags;
-
-	spin_lock_irqsave(&eq->spinlock, flags);
-
-	hret = ehea_h_free_resource(eq->adapter->handle, eq->fw_handle, force);
-	spin_unlock_irqrestore(&eq->spinlock, flags);
-
-	if (hret != H_SUCCESS)
-		return hret;
-
-	hw_queue_dtor(&eq->hw_queue);
-	kfree(eq);
-
-	return hret;
-}
-
-int ehea_destroy_eq(struct ehea_eq *eq)
-{
-	u64 hret, aer, aerr;
-	if (!eq)
-		return 0;
-
-	hcp_epas_dtor(&eq->epas);
-
-	hret = ehea_destroy_eq_res(eq, NORMAL_FREE);
-	if (hret == H_R_STATE) {
-		ehea_error_data(eq->adapter, eq->fw_handle, &aer, &aerr);
-		hret = ehea_destroy_eq_res(eq, FORCE_FREE);
-	}
-
-	if (hret != H_SUCCESS) {
-		pr_err("destroy EQ failed\n");
-		return -EIO;
-	}
-
-	return 0;
-}
-
-/* allocates memory for a queue and registers pages in phyp */
-static int ehea_qp_alloc_register(struct ehea_qp *qp, struct hw_queue *hw_queue,
-			   int nr_pages, int wqe_size, int act_nr_sges,
-			   struct ehea_adapter *adapter, int h_call_q_selector)
-{
-	u64 hret, rpage;
-	int ret, cnt;
-	void *vpage;
-
-	ret = hw_queue_ctor(hw_queue, nr_pages, EHEA_PAGESIZE, wqe_size);
-	if (ret)
-		return ret;
-
-	for (cnt = 0; cnt < nr_pages; cnt++) {
-		vpage = hw_qpageit_get_inc(hw_queue);
-		if (!vpage) {
-			pr_err("hw_qpageit_get_inc failed\n");
-			goto out_kill_hwq;
-		}
-		rpage = __pa(vpage);
-		hret = ehea_h_register_rpage(adapter->handle,
-					     0, h_call_q_selector,
-					     qp->fw_handle, rpage, 1);
-		if (hret < H_SUCCESS) {
-			pr_err("register_rpage_qp failed\n");
-			goto out_kill_hwq;
-		}
-	}
-	hw_qeit_reset(hw_queue);
-	return 0;
-
-out_kill_hwq:
-	hw_queue_dtor(hw_queue);
-	return -EIO;
-}
-
-static inline u32 map_wqe_size(u8 wqe_enc_size)
-{
-	return 128 << wqe_enc_size;
-}
-
-struct ehea_qp *ehea_create_qp(struct ehea_adapter *adapter,
-			       u32 pd, struct ehea_qp_init_attr *init_attr)
-{
-	int ret;
-	u64 hret;
-	struct ehea_qp *qp;
-	u32 wqe_size_in_bytes_sq, wqe_size_in_bytes_rq1;
-	u32 wqe_size_in_bytes_rq2, wqe_size_in_bytes_rq3;
-
-
-	qp = kzalloc_obj(*qp);
-	if (!qp)
-		return NULL;
-
-	qp->adapter = adapter;
-
-	hret = ehea_h_alloc_resource_qp(adapter->handle, init_attr, pd,
-					&qp->fw_handle, &qp->epas);
-	if (hret != H_SUCCESS) {
-		pr_err("ehea_h_alloc_resource_qp failed\n");
-		goto out_freemem;
-	}
-
-	wqe_size_in_bytes_sq = map_wqe_size(init_attr->act_wqe_size_enc_sq);
-	wqe_size_in_bytes_rq1 = map_wqe_size(init_attr->act_wqe_size_enc_rq1);
-	wqe_size_in_bytes_rq2 = map_wqe_size(init_attr->act_wqe_size_enc_rq2);
-	wqe_size_in_bytes_rq3 = map_wqe_size(init_attr->act_wqe_size_enc_rq3);
-
-	ret = ehea_qp_alloc_register(qp, &qp->hw_squeue, init_attr->nr_sq_pages,
-				     wqe_size_in_bytes_sq,
-				     init_attr->act_wqe_size_enc_sq, adapter,
-				     0);
-	if (ret) {
-		pr_err("can't register for sq ret=%x\n", ret);
-		goto out_freeres;
-	}
-
-	ret = ehea_qp_alloc_register(qp, &qp->hw_rqueue1,
-				     init_attr->nr_rq1_pages,
-				     wqe_size_in_bytes_rq1,
-				     init_attr->act_wqe_size_enc_rq1,
-				     adapter, 1);
-	if (ret) {
-		pr_err("can't register for rq1 ret=%x\n", ret);
-		goto out_kill_hwsq;
-	}
-
-	if (init_attr->rq_count > 1) {
-		ret = ehea_qp_alloc_register(qp, &qp->hw_rqueue2,
-					     init_attr->nr_rq2_pages,
-					     wqe_size_in_bytes_rq2,
-					     init_attr->act_wqe_size_enc_rq2,
-					     adapter, 2);
-		if (ret) {
-			pr_err("can't register for rq2 ret=%x\n", ret);
-			goto out_kill_hwr1q;
-		}
-	}
-
-	if (init_attr->rq_count > 2) {
-		ret = ehea_qp_alloc_register(qp, &qp->hw_rqueue3,
-					     init_attr->nr_rq3_pages,
-					     wqe_size_in_bytes_rq3,
-					     init_attr->act_wqe_size_enc_rq3,
-					     adapter, 3);
-		if (ret) {
-			pr_err("can't register for rq3 ret=%x\n", ret);
-			goto out_kill_hwr2q;
-		}
-	}
-
-	qp->init_attr = *init_attr;
-
-	return qp;
-
-out_kill_hwr2q:
-	hw_queue_dtor(&qp->hw_rqueue2);
-
-out_kill_hwr1q:
-	hw_queue_dtor(&qp->hw_rqueue1);
-
-out_kill_hwsq:
-	hw_queue_dtor(&qp->hw_squeue);
-
-out_freeres:
-	ehea_h_disable_and_get_hea(adapter->handle, qp->fw_handle);
-	ehea_h_free_resource(adapter->handle, qp->fw_handle, FORCE_FREE);
-
-out_freemem:
-	kfree(qp);
-	return NULL;
-}
-
-static u64 ehea_destroy_qp_res(struct ehea_qp *qp, u64 force)
-{
-	u64 hret;
-	struct ehea_qp_init_attr *qp_attr = &qp->init_attr;
-
-
-	ehea_h_disable_and_get_hea(qp->adapter->handle, qp->fw_handle);
-	hret = ehea_h_free_resource(qp->adapter->handle, qp->fw_handle, force);
-	if (hret != H_SUCCESS)
-		return hret;
-
-	hw_queue_dtor(&qp->hw_squeue);
-	hw_queue_dtor(&qp->hw_rqueue1);
-
-	if (qp_attr->rq_count > 1)
-		hw_queue_dtor(&qp->hw_rqueue2);
-	if (qp_attr->rq_count > 2)
-		hw_queue_dtor(&qp->hw_rqueue3);
-	kfree(qp);
-
-	return hret;
-}
-
-int ehea_destroy_qp(struct ehea_qp *qp)
-{
-	u64 hret, aer, aerr;
-	if (!qp)
-		return 0;
-
-	hcp_epas_dtor(&qp->epas);
-
-	hret = ehea_destroy_qp_res(qp, NORMAL_FREE);
-	if (hret == H_R_STATE) {
-		ehea_error_data(qp->adapter, qp->fw_handle, &aer, &aerr);
-		hret = ehea_destroy_qp_res(qp, FORCE_FREE);
-	}
-
-	if (hret != H_SUCCESS) {
-		pr_err("destroy QP failed\n");
-		return -EIO;
-	}
-
-	return 0;
-}
-
-static inline int ehea_calc_index(unsigned long i, unsigned long s)
-{
-	return (i >> s) & EHEA_INDEX_MASK;
-}
-
-static inline int ehea_init_top_bmap(struct ehea_top_bmap *ehea_top_bmap,
-				     int dir)
-{
-	if (!ehea_top_bmap->dir[dir]) {
-		ehea_top_bmap->dir[dir] =
-			kzalloc_obj(struct ehea_dir_bmap);
-		if (!ehea_top_bmap->dir[dir])
-			return -ENOMEM;
-	}
-	return 0;
-}
-
-static inline int ehea_init_bmap(struct ehea_bmap *ehea_bmap, int top, int dir)
-{
-	if (!ehea_bmap->top[top]) {
-		ehea_bmap->top[top] =
-			kzalloc_obj(struct ehea_top_bmap);
-		if (!ehea_bmap->top[top])
-			return -ENOMEM;
-	}
-	return ehea_init_top_bmap(ehea_bmap->top[top], dir);
-}
-
-static DEFINE_MUTEX(ehea_busmap_mutex);
-static unsigned long ehea_mr_len;
-
-#define EHEA_BUSMAP_ADD_SECT 1
-#define EHEA_BUSMAP_REM_SECT 0
-
-static void ehea_rebuild_busmap(void)
-{
-	u64 vaddr = EHEA_BUSMAP_START;
-	int top, dir, idx;
-
-	for (top = 0; top < EHEA_MAP_ENTRIES; top++) {
-		struct ehea_top_bmap *ehea_top;
-		int valid_dir_entries = 0;
-
-		if (!ehea_bmap->top[top])
-			continue;
-		ehea_top = ehea_bmap->top[top];
-		for (dir = 0; dir < EHEA_MAP_ENTRIES; dir++) {
-			struct ehea_dir_bmap *ehea_dir;
-			int valid_entries = 0;
-
-			if (!ehea_top->dir[dir])
-				continue;
-			valid_dir_entries++;
-			ehea_dir = ehea_top->dir[dir];
-			for (idx = 0; idx < EHEA_MAP_ENTRIES; idx++) {
-				if (!ehea_dir->ent[idx])
-					continue;
-				valid_entries++;
-				ehea_dir->ent[idx] = vaddr;
-				vaddr += EHEA_SECTSIZE;
-			}
-			if (!valid_entries) {
-				ehea_top->dir[dir] = NULL;
-				kfree(ehea_dir);
-			}
-		}
-		if (!valid_dir_entries) {
-			ehea_bmap->top[top] = NULL;
-			kfree(ehea_top);
-		}
-	}
-}
-
-static int ehea_update_busmap(unsigned long pfn, unsigned long nr_pages, int add)
-{
-	unsigned long i, start_section, end_section;
-
-	if (!nr_pages)
-		return 0;
-
-	if (!ehea_bmap) {
-		ehea_bmap = kzalloc_obj(struct ehea_bmap);
-		if (!ehea_bmap)
-			return -ENOMEM;
-	}
-
-	start_section = (pfn * PAGE_SIZE) / EHEA_SECTSIZE;
-	end_section = start_section + ((nr_pages * PAGE_SIZE) / EHEA_SECTSIZE);
-	/* Mark entries as valid or invalid only; address is assigned later */
-	for (i = start_section; i < end_section; i++) {
-		u64 flag;
-		int top = ehea_calc_index(i, EHEA_TOP_INDEX_SHIFT);
-		int dir = ehea_calc_index(i, EHEA_DIR_INDEX_SHIFT);
-		int idx = i & EHEA_INDEX_MASK;
-
-		if (add) {
-			int ret = ehea_init_bmap(ehea_bmap, top, dir);
-			if (ret)
-				return ret;
-			flag = 1; /* valid */
-			ehea_mr_len += EHEA_SECTSIZE;
-		} else {
-			if (!ehea_bmap->top[top])
-				continue;
-			if (!ehea_bmap->top[top]->dir[dir])
-				continue;
-			flag = 0; /* invalid */
-			ehea_mr_len -= EHEA_SECTSIZE;
-		}
-
-		ehea_bmap->top[top]->dir[dir]->ent[idx] = flag;
-	}
-	ehea_rebuild_busmap(); /* Assign contiguous addresses for mr */
-	return 0;
-}
-
-int ehea_add_sect_bmap(unsigned long pfn, unsigned long nr_pages)
-{
-	int ret;
-
-	mutex_lock(&ehea_busmap_mutex);
-	ret = ehea_update_busmap(pfn, nr_pages, EHEA_BUSMAP_ADD_SECT);
-	mutex_unlock(&ehea_busmap_mutex);
-	return ret;
-}
-
-int ehea_rem_sect_bmap(unsigned long pfn, unsigned long nr_pages)
-{
-	int ret;
-
-	mutex_lock(&ehea_busmap_mutex);
-	ret = ehea_update_busmap(pfn, nr_pages, EHEA_BUSMAP_REM_SECT);
-	mutex_unlock(&ehea_busmap_mutex);
-	return ret;
-}
-
-static int ehea_is_hugepage(unsigned long pfn)
-{
-	if (pfn & EHEA_HUGEPAGE_PFN_MASK)
-		return 0;
-
-	if (page_shift(pfn_to_page(pfn)) != EHEA_HUGEPAGESHIFT)
-		return 0;
-
-	return 1;
-}
-
-static int ehea_create_busmap_callback(unsigned long initial_pfn,
-				       unsigned long total_nr_pages, void *arg)
-{
-	int ret;
-	unsigned long pfn, start_pfn, end_pfn, nr_pages;
-
-	if ((total_nr_pages * PAGE_SIZE) < EHEA_HUGEPAGE_SIZE)
-		return ehea_update_busmap(initial_pfn, total_nr_pages,
-					  EHEA_BUSMAP_ADD_SECT);
-
-	/* Given chunk is >= 16GB -> check for hugepages */
-	start_pfn = initial_pfn;
-	end_pfn = initial_pfn + total_nr_pages;
-	pfn = start_pfn;
-
-	while (pfn < end_pfn) {
-		if (ehea_is_hugepage(pfn)) {
-			/* Add mem found in front of the hugepage */
-			nr_pages = pfn - start_pfn;
-			ret = ehea_update_busmap(start_pfn, nr_pages,
-						 EHEA_BUSMAP_ADD_SECT);
-			if (ret)
-				return ret;
-
-			/* Skip the hugepage */
-			pfn += (EHEA_HUGEPAGE_SIZE / PAGE_SIZE);
-			start_pfn = pfn;
-		} else
-			pfn += (EHEA_SECTSIZE / PAGE_SIZE);
-	}
-
-	/* Add mem found behind the hugepage(s)  */
-	nr_pages = pfn - start_pfn;
-	return ehea_update_busmap(start_pfn, nr_pages, EHEA_BUSMAP_ADD_SECT);
-}
-
-int ehea_create_busmap(void)
-{
-	int ret;
-
-	mutex_lock(&ehea_busmap_mutex);
-	ehea_mr_len = 0;
-	ret = walk_system_ram_range(0, 1ULL << MAX_PHYSMEM_BITS, NULL,
-				   ehea_create_busmap_callback);
-	mutex_unlock(&ehea_busmap_mutex);
-	return ret;
-}
-
-void ehea_destroy_busmap(void)
-{
-	int top, dir;
-	mutex_lock(&ehea_busmap_mutex);
-	if (!ehea_bmap)
-		goto out_destroy;
-
-	for (top = 0; top < EHEA_MAP_ENTRIES; top++) {
-		if (!ehea_bmap->top[top])
-			continue;
-
-		for (dir = 0; dir < EHEA_MAP_ENTRIES; dir++) {
-			if (!ehea_bmap->top[top]->dir[dir])
-				continue;
-
-			kfree(ehea_bmap->top[top]->dir[dir]);
-		}
-
-		kfree(ehea_bmap->top[top]);
-	}
-
-	kfree(ehea_bmap);
-	ehea_bmap = NULL;
-out_destroy:
-	mutex_unlock(&ehea_busmap_mutex);
-}
-
-u64 ehea_map_vaddr(void *caddr)
-{
-	int top, dir, idx;
-	unsigned long index, offset;
-
-	if (!ehea_bmap)
-		return EHEA_INVAL_ADDR;
-
-	index = __pa(caddr) >> SECTION_SIZE_BITS;
-	top = (index >> EHEA_TOP_INDEX_SHIFT) & EHEA_INDEX_MASK;
-	if (!ehea_bmap->top[top])
-		return EHEA_INVAL_ADDR;
-
-	dir = (index >> EHEA_DIR_INDEX_SHIFT) & EHEA_INDEX_MASK;
-	if (!ehea_bmap->top[top]->dir[dir])
-		return EHEA_INVAL_ADDR;
-
-	idx = index & EHEA_INDEX_MASK;
-	if (!ehea_bmap->top[top]->dir[dir]->ent[idx])
-		return EHEA_INVAL_ADDR;
-
-	offset = (unsigned long)caddr & (EHEA_SECTSIZE - 1);
-	return ehea_bmap->top[top]->dir[dir]->ent[idx] | offset;
-}
-
-static inline void *ehea_calc_sectbase(int top, int dir, int idx)
-{
-	unsigned long ret = idx;
-	ret |= dir << EHEA_DIR_INDEX_SHIFT;
-	ret |= top << EHEA_TOP_INDEX_SHIFT;
-	return __va(ret << SECTION_SIZE_BITS);
-}
-
-static u64 ehea_reg_mr_section(int top, int dir, int idx, u64 *pt,
-			       struct ehea_adapter *adapter,
-			       struct ehea_mr *mr)
-{
-	void *pg;
-	u64 j, m, hret;
-	unsigned long k = 0;
-	u64 pt_abs = __pa(pt);
-
-	void *sectbase = ehea_calc_sectbase(top, dir, idx);
-
-	for (j = 0; j < (EHEA_PAGES_PER_SECTION / EHEA_MAX_RPAGE); j++) {
-
-		for (m = 0; m < EHEA_MAX_RPAGE; m++) {
-			pg = sectbase + ((k++) * EHEA_PAGESIZE);
-			pt[m] = __pa(pg);
-		}
-		hret = ehea_h_register_rpage_mr(adapter->handle, mr->handle, 0,
-						0, pt_abs, EHEA_MAX_RPAGE);
-
-		if ((hret != H_SUCCESS) &&
-		    (hret != H_PAGE_REGISTERED)) {
-			ehea_h_free_resource(adapter->handle, mr->handle,
-					     FORCE_FREE);
-			pr_err("register_rpage_mr failed\n");
-			return hret;
-		}
-	}
-	return hret;
-}
-
-static u64 ehea_reg_mr_sections(int top, int dir, u64 *pt,
-				struct ehea_adapter *adapter,
-				struct ehea_mr *mr)
-{
-	u64 hret = H_SUCCESS;
-	int idx;
-
-	for (idx = 0; idx < EHEA_MAP_ENTRIES; idx++) {
-		if (!ehea_bmap->top[top]->dir[dir]->ent[idx])
-			continue;
-
-		hret = ehea_reg_mr_section(top, dir, idx, pt, adapter, mr);
-		if ((hret != H_SUCCESS) && (hret != H_PAGE_REGISTERED))
-			return hret;
-	}
-	return hret;
-}
-
-static u64 ehea_reg_mr_dir_sections(int top, u64 *pt,
-				    struct ehea_adapter *adapter,
-				    struct ehea_mr *mr)
-{
-	u64 hret = H_SUCCESS;
-	int dir;
-
-	for (dir = 0; dir < EHEA_MAP_ENTRIES; dir++) {
-		if (!ehea_bmap->top[top]->dir[dir])
-			continue;
-
-		hret = ehea_reg_mr_sections(top, dir, pt, adapter, mr);
-		if ((hret != H_SUCCESS) && (hret != H_PAGE_REGISTERED))
-			return hret;
-	}
-	return hret;
-}
-
-int ehea_reg_kernel_mr(struct ehea_adapter *adapter, struct ehea_mr *mr)
-{
-	int ret;
-	u64 *pt;
-	u64 hret;
-	u32 acc_ctrl = EHEA_MR_ACC_CTRL;
-
-	unsigned long top;
-
-	pt = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!pt) {
-		pr_err("no mem\n");
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	hret = ehea_h_alloc_resource_mr(adapter->handle, EHEA_BUSMAP_START,
-					ehea_mr_len, acc_ctrl, adapter->pd,
-					&mr->handle, &mr->lkey);
-
-	if (hret != H_SUCCESS) {
-		pr_err("alloc_resource_mr failed\n");
-		ret = -EIO;
-		goto out;
-	}
-
-	if (!ehea_bmap) {
-		ehea_h_free_resource(adapter->handle, mr->handle, FORCE_FREE);
-		pr_err("no busmap available\n");
-		ret = -EIO;
-		goto out;
-	}
-
-	for (top = 0; top < EHEA_MAP_ENTRIES; top++) {
-		if (!ehea_bmap->top[top])
-			continue;
-
-		hret = ehea_reg_mr_dir_sections(top, pt, adapter, mr);
-		if((hret != H_PAGE_REGISTERED) && (hret != H_SUCCESS))
-			break;
-	}
-
-	if (hret != H_SUCCESS) {
-		ehea_h_free_resource(adapter->handle, mr->handle, FORCE_FREE);
-		pr_err("registering mr failed\n");
-		ret = -EIO;
-		goto out;
-	}
-
-	mr->vaddr = EHEA_BUSMAP_START;
-	mr->adapter = adapter;
-	ret = 0;
-out:
-	free_page((unsigned long)pt);
-	return ret;
-}
-
-int ehea_rem_mr(struct ehea_mr *mr)
-{
-	u64 hret;
-
-	if (!mr || !mr->adapter)
-		return -EINVAL;
-
-	hret = ehea_h_free_resource(mr->adapter->handle, mr->handle,
-				    FORCE_FREE);
-	if (hret != H_SUCCESS) {
-		pr_err("destroy MR failed\n");
-		return -EIO;
-	}
-
-	return 0;
-}
-
-int ehea_gen_smr(struct ehea_adapter *adapter, struct ehea_mr *old_mr,
-		 struct ehea_mr *shared_mr)
-{
-	u64 hret;
-
-	hret = ehea_h_register_smr(adapter->handle, old_mr->handle,
-				   old_mr->vaddr, EHEA_MR_ACC_CTRL,
-				   adapter->pd, shared_mr);
-	if (hret != H_SUCCESS)
-		return -EIO;
-
-	shared_mr->adapter = adapter;
-
-	return 0;
-}
-
-static void print_error_data(u64 *data)
-{
-	int length;
-	u64 type = EHEA_BMASK_GET(ERROR_DATA_TYPE, data[2]);
-	u64 resource = data[1];
-
-	length = EHEA_BMASK_GET(ERROR_DATA_LENGTH, data[0]);
-
-	if (length > EHEA_PAGESIZE)
-		length = EHEA_PAGESIZE;
-
-	if (type == EHEA_AER_RESTYPE_QP)
-		pr_err("QP (resource=%llX) state: AER=0x%llX, AERR=0x%llX, port=%llX\n",
-		       resource, data[6], data[12], data[22]);
-	else if (type == EHEA_AER_RESTYPE_CQ)
-		pr_err("CQ (resource=%llX) state: AER=0x%llX\n",
-		       resource, data[6]);
-	else if (type == EHEA_AER_RESTYPE_EQ)
-		pr_err("EQ (resource=%llX) state: AER=0x%llX\n",
-		       resource, data[6]);
-
-	ehea_dump(data, length, "error data");
-}
-
-u64 ehea_error_data(struct ehea_adapter *adapter, u64 res_handle,
-		    u64 *aer, u64 *aerr)
-{
-	unsigned long ret;
-	u64 *rblock;
-	u64 type = 0;
-
-	rblock = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!rblock) {
-		pr_err("Cannot allocate rblock memory\n");
-		goto out;
-	}
-
-	ret = ehea_h_error_data(adapter->handle, res_handle, rblock);
-
-	if (ret == H_SUCCESS) {
-		type = EHEA_BMASK_GET(ERROR_DATA_TYPE, rblock[2]);
-		*aer = rblock[6];
-		*aerr = rblock[12];
-		print_error_data(rblock);
-	} else if (ret == H_R_STATE) {
-		pr_err("No error data available: %llX\n", res_handle);
-	} else
-		pr_err("Error data could not be fetched: %llX\n", res_handle);
-
-	free_page((unsigned long)rblock);
-out:
-	return type;
-}
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_qmr.h b/drivers/net/ethernet/ibm/ehea/ehea_qmr.h
deleted file mode 100644
index 7c7cccd820f7..000000000000
--- a/drivers/net/ethernet/ibm/ehea/ehea_qmr.h
+++ /dev/null
@@ -1,390 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  linux/drivers/net/ethernet/ibm/ehea/ehea_qmr.h
- *
- *  eHEA ethernet device driver for IBM eServer System p
- *
- *  (C) Copyright IBM Corp. 2006
- *
- *  Authors:
- *       Christoph Raisch <raisch@de.ibm.com>
- *       Jan-Bernd Themann <themann@de.ibm.com>
- *       Thomas Klein <tklein@de.ibm.com>
- */
-
-#ifndef __EHEA_QMR_H__
-#define __EHEA_QMR_H__
-
-#include <linux/prefetch.h>
-#include "ehea.h"
-#include "ehea_hw.h"
-
-/*
- * page size of ehea hardware queues
- */
-
-#define EHEA_PAGESHIFT         12
-#define EHEA_PAGESIZE          (1UL << EHEA_PAGESHIFT)
-#define EHEA_SECTSIZE          (1UL << 24)
-#define EHEA_PAGES_PER_SECTION (EHEA_SECTSIZE >> EHEA_PAGESHIFT)
-#define EHEA_HUGEPAGESHIFT     34
-#define EHEA_HUGEPAGE_SIZE     (1UL << EHEA_HUGEPAGESHIFT)
-#define EHEA_HUGEPAGE_PFN_MASK ((EHEA_HUGEPAGE_SIZE - 1) >> PAGE_SHIFT)
-
-#if ((1UL << SECTION_SIZE_BITS) < EHEA_SECTSIZE)
-#error eHEA module cannot work if kernel sectionsize < ehea sectionsize
-#endif
-
-/* Some abbreviations used here:
- *
- * WQE  - Work Queue Entry
- * SWQE - Send Work Queue Entry
- * RWQE - Receive Work Queue Entry
- * CQE  - Completion Queue Entry
- * EQE  - Event Queue Entry
- * MR   - Memory Region
- */
-
-/* Use of WR_ID field for EHEA */
-#define EHEA_WR_ID_COUNT   EHEA_BMASK_IBM(0, 19)
-#define EHEA_WR_ID_TYPE    EHEA_BMASK_IBM(20, 23)
-#define EHEA_SWQE2_TYPE    0x1
-#define EHEA_SWQE3_TYPE    0x2
-#define EHEA_RWQE2_TYPE    0x3
-#define EHEA_RWQE3_TYPE    0x4
-#define EHEA_WR_ID_INDEX   EHEA_BMASK_IBM(24, 47)
-#define EHEA_WR_ID_REFILL  EHEA_BMASK_IBM(48, 63)
-
-struct ehea_vsgentry {
-	u64 vaddr;
-	u32 l_key;
-	u32 len;
-};
-
-/* maximum number of sg entries allowed in a WQE */
-#define EHEA_MAX_WQE_SG_ENTRIES  	252
-#define SWQE2_MAX_IMM            	(0xD0 - 0x30)
-#define SWQE3_MAX_IMM            	224
-
-/* tx control flags for swqe */
-#define EHEA_SWQE_CRC                   0x8000
-#define EHEA_SWQE_IP_CHECKSUM           0x4000
-#define EHEA_SWQE_TCP_CHECKSUM          0x2000
-#define EHEA_SWQE_TSO                   0x1000
-#define EHEA_SWQE_SIGNALLED_COMPLETION  0x0800
-#define EHEA_SWQE_VLAN_INSERT           0x0400
-#define EHEA_SWQE_IMM_DATA_PRESENT      0x0200
-#define EHEA_SWQE_DESCRIPTORS_PRESENT   0x0100
-#define EHEA_SWQE_WRAP_CTL_REC          0x0080
-#define EHEA_SWQE_WRAP_CTL_FORCE        0x0040
-#define EHEA_SWQE_BIND                  0x0020
-#define EHEA_SWQE_PURGE                 0x0010
-
-/* sizeof(struct ehea_swqe) less the union */
-#define SWQE_HEADER_SIZE		32
-
-struct ehea_swqe {
-	u64 wr_id;
-	u16 tx_control;
-	u16 vlan_tag;
-	u8 reserved1;
-	u8 ip_start;
-	u8 ip_end;
-	u8 immediate_data_length;
-	u8 tcp_offset;
-	u8 reserved2;
-	u16 reserved2b;
-	u8 wrap_tag;
-	u8 descriptors;		/* number of valid descriptors in WQE */
-	u16 reserved3;
-	u16 reserved4;
-	u16 mss;
-	u32 reserved5;
-	union {
-		/*  Send WQE Format 1 */
-		struct {
-			struct ehea_vsgentry sg_list[EHEA_MAX_WQE_SG_ENTRIES];
-		} no_immediate_data;
-
-		/*  Send WQE Format 2 */
-		struct {
-			struct ehea_vsgentry sg_entry;
-			/* 0x30 */
-			u8 immediate_data[SWQE2_MAX_IMM];
-			/* 0xd0 */
-			struct ehea_vsgentry sg_list[EHEA_MAX_WQE_SG_ENTRIES-1];
-		} immdata_desc __packed;
-
-		/*  Send WQE Format 3 */
-		struct {
-			u8 immediate_data[SWQE3_MAX_IMM];
-		} immdata_nodesc;
-	} u;
-};
-
-struct ehea_rwqe {
-	u64 wr_id;		/* work request ID */
-	u8 reserved1[5];
-	u8 data_segments;
-	u16 reserved2;
-	u64 reserved3;
-	u64 reserved4;
-	struct ehea_vsgentry sg_list[EHEA_MAX_WQE_SG_ENTRIES];
-};
-
-#define EHEA_CQE_VLAN_TAG_XTRACT   0x0400
-
-#define EHEA_CQE_TYPE_RQ           0x60
-#define EHEA_CQE_STAT_ERR_MASK     0x700F
-#define EHEA_CQE_STAT_FAT_ERR_MASK 0xF
-#define EHEA_CQE_BLIND_CKSUM       0x8000
-#define EHEA_CQE_STAT_ERR_TCP      0x4000
-#define EHEA_CQE_STAT_ERR_IP       0x2000
-#define EHEA_CQE_STAT_ERR_CRC      0x1000
-
-/* Defines which bad send cqe stati lead to a port reset */
-#define EHEA_CQE_STAT_RESET_MASK   0x0002
-
-struct ehea_cqe {
-	u64 wr_id;		/* work request ID from WQE */
-	u8 type;
-	u8 valid;
-	u16 status;
-	u16 reserved1;
-	u16 num_bytes_transfered;
-	u16 vlan_tag;
-	u16 inet_checksum_value;
-	u8 reserved2;
-	u8 header_length;
-	u16 reserved3;
-	u16 page_offset;
-	u16 wqe_count;
-	u32 qp_token;
-	u32 timestamp;
-	u32 reserved4;
-	u64 reserved5[3];
-};
-
-#define EHEA_EQE_VALID           EHEA_BMASK_IBM(0, 0)
-#define EHEA_EQE_IS_CQE          EHEA_BMASK_IBM(1, 1)
-#define EHEA_EQE_IDENTIFIER      EHEA_BMASK_IBM(2, 7)
-#define EHEA_EQE_QP_CQ_NUMBER    EHEA_BMASK_IBM(8, 31)
-#define EHEA_EQE_QP_TOKEN        EHEA_BMASK_IBM(32, 63)
-#define EHEA_EQE_CQ_TOKEN        EHEA_BMASK_IBM(32, 63)
-#define EHEA_EQE_KEY             EHEA_BMASK_IBM(32, 63)
-#define EHEA_EQE_PORT_NUMBER     EHEA_BMASK_IBM(56, 63)
-#define EHEA_EQE_EQ_NUMBER       EHEA_BMASK_IBM(48, 63)
-#define EHEA_EQE_SM_ID           EHEA_BMASK_IBM(48, 63)
-#define EHEA_EQE_SM_MECH_NUMBER  EHEA_BMASK_IBM(48, 55)
-#define EHEA_EQE_SM_PORT_NUMBER  EHEA_BMASK_IBM(56, 63)
-
-#define EHEA_AER_RESTYPE_QP  0x8
-#define EHEA_AER_RESTYPE_CQ  0x4
-#define EHEA_AER_RESTYPE_EQ  0x3
-
-/* Defines which affiliated errors lead to a port reset */
-#define EHEA_AER_RESET_MASK   0xFFFFFFFFFEFFFFFFULL
-#define EHEA_AERR_RESET_MASK  0xFFFFFFFFFFFFFFFFULL
-
-struct ehea_eqe {
-	u64 entry;
-};
-
-#define ERROR_DATA_LENGTH  EHEA_BMASK_IBM(52, 63)
-#define ERROR_DATA_TYPE    EHEA_BMASK_IBM(0, 7)
-
-static inline void *hw_qeit_calc(struct hw_queue *queue, u64 q_offset)
-{
-	struct ehea_page *current_page;
-
-	if (q_offset >= queue->queue_length)
-		q_offset -= queue->queue_length;
-	current_page = (queue->queue_pages)[q_offset >> EHEA_PAGESHIFT];
-	return &current_page->entries[q_offset & (EHEA_PAGESIZE - 1)];
-}
-
-static inline void *hw_qeit_get(struct hw_queue *queue)
-{
-	return hw_qeit_calc(queue, queue->current_q_offset);
-}
-
-static inline void hw_qeit_inc(struct hw_queue *queue)
-{
-	queue->current_q_offset += queue->qe_size;
-	if (queue->current_q_offset >= queue->queue_length) {
-		queue->current_q_offset = 0;
-		/* toggle the valid flag */
-		queue->toggle_state = (~queue->toggle_state) & 1;
-	}
-}
-
-static inline void *hw_qeit_get_inc(struct hw_queue *queue)
-{
-	void *retvalue = hw_qeit_get(queue);
-	hw_qeit_inc(queue);
-	return retvalue;
-}
-
-static inline void *hw_qeit_get_inc_valid(struct hw_queue *queue)
-{
-	struct ehea_cqe *retvalue = hw_qeit_get(queue);
-	u8 valid = retvalue->valid;
-	void *pref;
-
-	if ((valid >> 7) == (queue->toggle_state & 1)) {
-		/* this is a good one */
-		hw_qeit_inc(queue);
-		pref = hw_qeit_calc(queue, queue->current_q_offset);
-		prefetch(pref);
-		prefetch(pref + 128);
-	} else
-		retvalue = NULL;
-	return retvalue;
-}
-
-static inline void *hw_qeit_get_valid(struct hw_queue *queue)
-{
-	struct ehea_cqe *retvalue = hw_qeit_get(queue);
-	void *pref;
-	u8 valid;
-
-	pref = hw_qeit_calc(queue, queue->current_q_offset);
-	prefetch(pref);
-	prefetch(pref + 128);
-	prefetch(pref + 256);
-	valid = retvalue->valid;
-	if (!((valid >> 7) == (queue->toggle_state & 1)))
-		retvalue = NULL;
-	return retvalue;
-}
-
-static inline void *hw_qeit_reset(struct hw_queue *queue)
-{
-	queue->current_q_offset = 0;
-	return hw_qeit_get(queue);
-}
-
-static inline void *hw_qeit_eq_get_inc(struct hw_queue *queue)
-{
-	u64 last_entry_in_q = queue->queue_length - queue->qe_size;
-	void *retvalue;
-
-	retvalue = hw_qeit_get(queue);
-	queue->current_q_offset += queue->qe_size;
-	if (queue->current_q_offset > last_entry_in_q) {
-		queue->current_q_offset = 0;
-		queue->toggle_state = (~queue->toggle_state) & 1;
-	}
-	return retvalue;
-}
-
-static inline void *hw_eqit_eq_get_inc_valid(struct hw_queue *queue)
-{
-	void *retvalue = hw_qeit_get(queue);
-	u32 qe = *(u8 *)retvalue;
-	if ((qe >> 7) == (queue->toggle_state & 1))
-		hw_qeit_eq_get_inc(queue);
-	else
-		retvalue = NULL;
-	return retvalue;
-}
-
-static inline struct ehea_rwqe *ehea_get_next_rwqe(struct ehea_qp *qp,
-						   int rq_nr)
-{
-	struct hw_queue *queue;
-
-	if (rq_nr == 1)
-		queue = &qp->hw_rqueue1;
-	else if (rq_nr == 2)
-		queue = &qp->hw_rqueue2;
-	else
-		queue = &qp->hw_rqueue3;
-
-	return hw_qeit_get_inc(queue);
-}
-
-static inline struct ehea_swqe *ehea_get_swqe(struct ehea_qp *my_qp,
-					      int *wqe_index)
-{
-	struct hw_queue *queue = &my_qp->hw_squeue;
-	struct ehea_swqe *wqe_p;
-
-	*wqe_index = (queue->current_q_offset) >> (7 + EHEA_SG_SQ);
-	wqe_p = hw_qeit_get_inc(&my_qp->hw_squeue);
-
-	return wqe_p;
-}
-
-static inline void ehea_post_swqe(struct ehea_qp *my_qp, struct ehea_swqe *swqe)
-{
-	iosync();
-	ehea_update_sqa(my_qp, 1);
-}
-
-static inline struct ehea_cqe *ehea_poll_rq1(struct ehea_qp *qp, int *wqe_index)
-{
-	struct hw_queue *queue = &qp->hw_rqueue1;
-
-	*wqe_index = (queue->current_q_offset) >> (7 + EHEA_SG_RQ1);
-	return hw_qeit_get_valid(queue);
-}
-
-static inline void ehea_inc_cq(struct ehea_cq *cq)
-{
-	hw_qeit_inc(&cq->hw_queue);
-}
-
-static inline void ehea_inc_rq1(struct ehea_qp *qp)
-{
-	hw_qeit_inc(&qp->hw_rqueue1);
-}
-
-static inline struct ehea_cqe *ehea_poll_cq(struct ehea_cq *my_cq)
-{
-	return hw_qeit_get_valid(&my_cq->hw_queue);
-}
-
-#define EHEA_CQ_REGISTER_ORIG 0
-#define EHEA_EQ_REGISTER_ORIG 0
-
-enum ehea_eq_type {
-	EHEA_EQ = 0,		/* event queue              */
-	EHEA_NEQ		/* notification event queue */
-};
-
-struct ehea_eq *ehea_create_eq(struct ehea_adapter *adapter,
-			       enum ehea_eq_type type,
-			       const u32 length, const u8 eqe_gen);
-
-int ehea_destroy_eq(struct ehea_eq *eq);
-
-struct ehea_eqe *ehea_poll_eq(struct ehea_eq *eq);
-
-struct ehea_cq *ehea_create_cq(struct ehea_adapter *adapter, int cqe,
-			       u64 eq_handle, u32 cq_token);
-
-int ehea_destroy_cq(struct ehea_cq *cq);
-
-struct ehea_qp *ehea_create_qp(struct ehea_adapter *adapter, u32 pd,
-			       struct ehea_qp_init_attr *init_attr);
-
-int ehea_destroy_qp(struct ehea_qp *qp);
-
-int ehea_reg_kernel_mr(struct ehea_adapter *adapter, struct ehea_mr *mr);
-
-int ehea_gen_smr(struct ehea_adapter *adapter, struct ehea_mr *old_mr,
-		 struct ehea_mr *shared_mr);
-
-int ehea_rem_mr(struct ehea_mr *mr);
-
-u64 ehea_error_data(struct ehea_adapter *adapter, u64 res_handle,
-		    u64 *aer, u64 *aerr);
-
-int ehea_add_sect_bmap(unsigned long pfn, unsigned long nr_pages);
-int ehea_rem_sect_bmap(unsigned long pfn, unsigned long nr_pages);
-int ehea_create_busmap(void);
-void ehea_destroy_busmap(void);
-u64 ehea_map_vaddr(void *caddr);
-
-#endif	/* __EHEA_QMR_H__ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 894f2d06d39d..ef5e657816f0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3129,7 +3129,7 @@ static int i40e_tso(struct i40e_tx_buffer *first, u8 *hdr_len,
 					 SKB_GSO_UDP_TUNNEL_CSUM)) {
 		if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
 		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) {
-			l4.udp->len = 0;
+			udp_set_len_short(l4.udp, 0);
 
 			/* determine offset of outer transport header */
 			l4_offset = l4.hdr - skb->data;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 363c42bf3dcf..c30abf17cf5d 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -1774,7 +1774,7 @@ static int iavf_tso(struct iavf_tx_buffer *first, u8 *hdr_len,
 					 SKB_GSO_UDP_TUNNEL_CSUM)) {
 		if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
 		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) {
-			l4.udp->len = 0;
+			udp_set_len_short(l4.udp, 0);
 
 			/* determine offset of outer transport header */
 			l4_offset = l4.hdr - skb->data;
diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c
index 8fd954f1ebd6..7d21c3417b0b 100644
--- a/drivers/net/ethernet/intel/ice/ice_gnss.c
+++ b/drivers/net/ethernet/intel/ice/ice_gnss.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2021-2022, Intel Corporation. */
 
 #include "ice.h"
+#include <linux/slab.h>
 #include "ice_lib.h"
 
 /**
@@ -124,7 +125,7 @@ static void ice_gnss_read(struct kthread_work *work)
 
 	data_len = min_t(typeof(data_len), data_len, PAGE_SIZE);
 
-	buf = (char *)get_zeroed_page(GFP_KERNEL);
+	buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!buf) {
 		err = -ENOMEM;
 		goto requeue;
@@ -151,7 +152,7 @@ static void ice_gnss_read(struct kthread_work *work)
 			 count, i);
 	delay = ICE_GNSS_TIMER_DELAY_TIME;
 free_buf:
-	free_page((unsigned long)buf);
+	kfree(buf);
 requeue:
 	kthread_queue_delayed_work(gnss->kworker, &gnss->read_work, delay);
 	if (err)
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index c04c5856dad6..31303ab5be17 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1891,7 +1891,7 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 					 SKB_GSO_UDP_TUNNEL_CSUM)) {
 		if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
 		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) {
-			l4.udp->len = 0;
+			udp_set_len_short(l4.udp, 0);
 
 			/* determine offset of outer transport header */
 			l4_start = (u8)(l4.hdr - skb->data);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 7f9056404f64..566b08ca3a6c 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -2871,7 +2871,7 @@ int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off)
 				     (__force __wsum)htonl(paylen));
 		/* compute length of segmentation header */
 		off->tso_hdr_len = sizeof(struct udphdr) + l4_start;
-		l4.udp->len = htons(shinfo->gso_size + sizeof(struct udphdr));
+		udp_set_len_short(l4.udp, shinfo->gso_size + sizeof(struct udphdr));
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.h b/drivers/net/ethernet/intel/igb/e1000_82575.h
index 63ec253ac788..9e696d55e512 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.h
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.h
@@ -87,6 +87,27 @@ union e1000_adv_rx_desc {
 	} wb;  /* writeback */
 };
 
+#define E1000_RSS_TYPE_NO_HASH		 0
+#define E1000_RSS_TYPE_HASH_TCP_IPV4	 1
+#define E1000_RSS_TYPE_HASH_IPV4	 2
+#define E1000_RSS_TYPE_HASH_TCP_IPV6	 3
+#define E1000_RSS_TYPE_HASH_IPV6_EX	 4
+#define E1000_RSS_TYPE_HASH_IPV6	 5
+#define E1000_RSS_TYPE_HASH_TCP_IPV6_EX	 6
+#define E1000_RSS_TYPE_HASH_UDP_IPV4	 7
+#define E1000_RSS_TYPE_HASH_UDP_IPV6	 8
+#define E1000_RSS_TYPE_HASH_UDP_IPV6_EX	 9
+
+#define E1000_RSS_TYPE_MASK		GENMASK(3, 0)
+
+#define E1000_RSS_L4_TYPES_MASK	\
+	(BIT(E1000_RSS_TYPE_HASH_TCP_IPV4)	| \
+	 BIT(E1000_RSS_TYPE_HASH_TCP_IPV6)	| \
+	 BIT(E1000_RSS_TYPE_HASH_TCP_IPV6_EX)	| \
+	 BIT(E1000_RSS_TYPE_HASH_UDP_IPV4)	| \
+	 BIT(E1000_RSS_TYPE_HASH_UDP_IPV6)	| \
+	 BIT(E1000_RSS_TYPE_HASH_UDP_IPV6_EX))
+
 #define E1000_RXDADV_HDRBUFLEN_MASK      0x7FE0
 #define E1000_RXDADV_HDRBUFLEN_SHIFT     5
 #define E1000_RXDADV_STAT_TS             0x10000 /* Pkt was time stamped */
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 0fff1df81b7b..8c9b02058cec 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -495,6 +495,7 @@ struct hwmon_buff {
 #define IGB_N_PEROUT	2
 #define IGB_N_SDP	4
 #define IGB_RETA_SIZE	128
+#define IGB_RSS_KEY_SIZE	40
 
 enum igb_filter_match_flags {
 	IGB_FILTER_FLAG_ETHER_TYPE = 0x1,
@@ -655,6 +656,7 @@ struct igb_adapter {
 	struct i2c_client *i2c_client;
 	u32 rss_indir_tbl_init;
 	u8 rss_indir_tbl[IGB_RETA_SIZE];
+	u8 rss_key[IGB_RSS_KEY_SIZE];
 
 	unsigned long link_check_timeout;
 	int copper_tries;
@@ -735,6 +737,7 @@ void igb_down(struct igb_adapter *);
 void igb_reinit_locked(struct igb_adapter *);
 void igb_reset(struct igb_adapter *);
 int igb_reinit_queues(struct igb_adapter *);
+void igb_write_rss_key(struct igb_adapter *adapter);
 void igb_write_rss_indir_tbl(struct igb_adapter *);
 int igb_set_spd_dplx(struct igb_adapter *, u32, u8);
 int igb_setup_tx_resources(struct igb_ring *);
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index f7938c1da835..65014a54a6d1 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -3019,6 +3019,27 @@ static int igb_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	return ret;
 }
 
+/**
+ * igb_write_rss_key - Program the RSS key into device registers
+ * @adapter: board private structure
+ *
+ * Write the RSS key stored in adapter->rss_key to the E1000 hardware registers.
+ * Each 32-bit chunk of the key is read using get_unaligned_le32() and written
+ * to the appropriate register.
+ */
+void igb_write_rss_key(struct igb_adapter *adapter)
+{
+	struct e1000_hw *hw = &adapter->hw;
+
+	ASSERT_RTNL();
+
+	for (int i = 0; i < IGB_RSS_KEY_SIZE / 4; i++) {
+		u32 val = get_unaligned_le32(&adapter->rss_key[i * 4]);
+
+		wr32(E1000_RSSRK(i), val);
+	}
+}
+
 static int igb_get_eee(struct net_device *netdev, struct ethtool_keee *edata)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
@@ -3276,10 +3297,12 @@ static int igb_get_rxfh(struct net_device *netdev,
 	int i;
 
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
-	if (!rxfh->indir)
-		return 0;
-	for (i = 0; i < IGB_RETA_SIZE; i++)
-		rxfh->indir[i] = adapter->rss_indir_tbl[i];
+	if (rxfh->indir)
+		for (i = 0; i < IGB_RETA_SIZE; i++)
+			rxfh->indir[i] = adapter->rss_indir_tbl[i];
+
+	if (rxfh->key)
+		memcpy(rxfh->key, adapter->rss_key, sizeof(adapter->rss_key));
 
 	return 0;
 }
@@ -3319,6 +3342,11 @@ void igb_write_rss_indir_tbl(struct igb_adapter *adapter)
 	}
 }
 
+static u32 igb_get_rxfh_key_size(struct net_device *netdev)
+{
+	return IGB_RSS_KEY_SIZE;
+}
+
 static int igb_set_rxfh(struct net_device *netdev,
 			struct ethtool_rxfh_param *rxfh,
 			struct netlink_ext_ack *extack)
@@ -3329,35 +3357,39 @@ static int igb_set_rxfh(struct net_device *netdev,
 	u32 num_queues;
 
 	/* We do not allow change in unsupported parameters */
-	if (rxfh->key ||
-	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
-	     rxfh->hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
-	if (!rxfh->indir)
-		return 0;
 
-	num_queues = adapter->rss_queues;
+	if (rxfh->indir) {
+		num_queues = adapter->rss_queues;
 
-	switch (hw->mac.type) {
-	case e1000_82576:
-		/* 82576 supports 2 RSS queues for SR-IOV */
-		if (adapter->vfs_allocated_count)
-			num_queues = 2;
-		break;
-	default:
-		break;
-	}
+		switch (hw->mac.type) {
+		case e1000_82576:
+			/* 82576 supports 2 RSS queues for SR-IOV */
+			if (adapter->vfs_allocated_count)
+				num_queues = 2;
+			break;
+		default:
+			break;
+		}
+
+		/* Verify user input. */
+		for (i = 0; i < IGB_RETA_SIZE; i++)
+			if (rxfh->indir[i] >= num_queues)
+				return -EINVAL;
 
-	/* Verify user input. */
-	for (i = 0; i < IGB_RETA_SIZE; i++)
-		if (rxfh->indir[i] >= num_queues)
-			return -EINVAL;
 
+		for (i = 0; i < IGB_RETA_SIZE; i++)
+			adapter->rss_indir_tbl[i] = rxfh->indir[i];
 
-	for (i = 0; i < IGB_RETA_SIZE; i++)
-		adapter->rss_indir_tbl[i] = rxfh->indir[i];
+		igb_write_rss_indir_tbl(adapter);
+	}
 
-	igb_write_rss_indir_tbl(adapter);
+	if (rxfh->key) {
+		memcpy(adapter->rss_key, rxfh->key, sizeof(adapter->rss_key));
+		igb_write_rss_key(adapter);
+	}
 
 	return 0;
 }
@@ -3483,6 +3515,7 @@ static const struct ethtool_ops igb_ethtool_ops = {
 	.get_module_eeprom	= igb_get_module_eeprom,
 	.get_rxfh_indir_size	= igb_get_rxfh_indir_size,
 	.get_rxfh		= igb_get_rxfh,
+	.get_rxfh_key_size	= igb_get_rxfh_key_size,
 	.set_rxfh		= igb_set_rxfh,
 	.get_rxfh_fields	= igb_get_rxfh_fields,
 	.set_rxfh_fields	= igb_set_rxfh_fields,
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index a1e89a375744..d4a897a8c82c 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -4048,6 +4048,9 @@ static int igb_sw_init(struct igb_adapter *adapter)
 
 	pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word);
 
+	/* init RSS key */
+	netdev_rss_key_fill(adapter->rss_key, sizeof(adapter->rss_key));
+
 	/* set default ring sizes */
 	adapter->tx_ring_count = IGB_DEFAULT_TXD;
 	adapter->rx_ring_count = IGB_DEFAULT_RXD;
@@ -4522,11 +4525,8 @@ static void igb_setup_mrqc(struct igb_adapter *adapter)
 	struct e1000_hw *hw = &adapter->hw;
 	u32 mrqc, rxcsum;
 	u32 j, num_rx_queues;
-	u32 rss_key[10];
 
-	netdev_rss_key_fill(rss_key, sizeof(rss_key));
-	for (j = 0; j < 10; j++)
-		wr32(E1000_RSSRK(j), rss_key[j]);
+	igb_write_rss_key(adapter);
 
 	num_rx_queues = adapter->rss_queues;
 
@@ -8820,10 +8820,19 @@ static inline void igb_rx_hash(struct igb_ring *ring,
 			       union e1000_adv_rx_desc *rx_desc,
 			       struct sk_buff *skb)
 {
-	if (ring->netdev->features & NETIF_F_RXHASH)
-		skb_set_hash(skb,
-			     le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
-			     PKT_HASH_TYPE_L3);
+	u16 rss_type;
+
+	if (!(ring->netdev->features & NETIF_F_RXHASH))
+		return;
+
+	rss_type = le16_to_cpu(rx_desc->wb.lower.lo_dword.pkt_info) &
+		   E1000_RSS_TYPE_MASK;
+	if (!rss_type)
+		return;
+
+	skb_set_hash(skb, le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
+		     (E1000_RSS_L4_TYPES_MASK & BIT(rss_type)) ?
+		     PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 46d625b15f44..17f213cc93e4 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -30,6 +30,7 @@ void igc_ethtool_set_ops(struct net_device *);
 
 #define MAX_ETYPE_FILTER		8
 #define IGC_RETA_SIZE			128
+#define IGC_RSS_KEY_SIZE		40
 
 /* SDP support */
 #define IGC_N_EXTTS	2
@@ -302,6 +303,7 @@ struct igc_adapter {
 	unsigned int nfc_rule_count;
 
 	u8 rss_indir_tbl[IGC_RETA_SIZE];
+	u8 rss_key[IGC_RSS_KEY_SIZE];
 
 	unsigned long link_check_timeout;
 	struct igc_info ei;
@@ -361,6 +363,7 @@ unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter);
 void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
 			      const u32 max_rss_queues);
 int igc_reinit_queues(struct igc_adapter *adapter);
+void igc_write_rss_key(struct igc_adapter *adapter);
 void igc_write_rss_indir_tbl(struct igc_adapter *adapter);
 bool igc_has_link(struct igc_adapter *adapter);
 void igc_reset(struct igc_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
index 1613b562d17c..ab9120a3127f 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.c
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -114,11 +114,35 @@ static s32 igc_setup_copper_link_base(struct igc_hw *hw)
 	u32 ctrl;
 
 	ctrl = rd32(IGC_CTRL);
-	ctrl |= IGC_CTRL_SLU;
-	ctrl &= ~(IGC_CTRL_FRCSPD | IGC_CTRL_FRCDPX);
-	wr32(IGC_CTRL, ctrl);
-
-	ret_val = igc_setup_copper_link(hw);
+	ctrl &= ~(IGC_CTRL_FRCSPD | IGC_CTRL_FRCDPX |
+		  IGC_CTRL_SPEED_MASK | IGC_CTRL_FD);
+
+	if (hw->mac.autoneg_enabled) {
+		ctrl |= IGC_CTRL_SLU;
+		wr32(IGC_CTRL, ctrl);
+		ret_val = igc_setup_copper_link(hw);
+	} else {
+		ctrl |= IGC_CTRL_SLU | IGC_CTRL_FRCSPD | IGC_CTRL_FRCDPX;
+
+		switch (hw->mac.forced_speed_duplex) {
+		case IGC_FORCED_10H:
+			ctrl |= IGC_CTRL_SPEED_10;
+			break;
+		case IGC_FORCED_10F:
+			ctrl |= IGC_CTRL_SPEED_10 | IGC_CTRL_FD;
+			break;
+		case IGC_FORCED_100H:
+			ctrl |= IGC_CTRL_SPEED_100;
+			break;
+		case IGC_FORCED_100F:
+			ctrl |= IGC_CTRL_SPEED_100 | IGC_CTRL_FD;
+			break;
+		default:
+			return -IGC_ERR_CONFIG;
+		}
+		wr32(IGC_CTRL, ctrl);
+		ret_val = igc_setup_copper_link(hw);
+	}
 
 	return ret_val;
 }
@@ -443,6 +467,7 @@ static const struct igc_phy_operations igc_phy_ops_base = {
 	.reset			= igc_phy_hw_reset,
 	.read_reg		= igc_read_phy_reg_gpy,
 	.write_reg		= igc_write_phy_reg_gpy,
+	.force_speed_duplex	= igc_force_speed_duplex,
 };
 
 const struct igc_info igc_base_info = {
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 9482ab11f050..3f504751c2d9 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -129,10 +129,13 @@
 #define IGC_ERR_SWFW_SYNC		13
 
 /* Device Control */
+#define IGC_CTRL_FD		BIT(0)  /* Full Duplex */
 #define IGC_CTRL_RST		0x04000000  /* Global reset */
-
 #define IGC_CTRL_PHY_RST	0x80000000  /* PHY Reset */
 #define IGC_CTRL_SLU		0x00000040  /* Set link up (Force Link) */
+#define IGC_CTRL_SPEED_MASK	GENMASK(10, 8)
+#define IGC_CTRL_SPEED_10	FIELD_PREP(IGC_CTRL_SPEED_MASK, 0)
+#define IGC_CTRL_SPEED_100	FIELD_PREP(IGC_CTRL_SPEED_MASK, 1)
 #define IGC_CTRL_FRCSPD		0x00000800  /* Force Speed */
 #define IGC_CTRL_FRCDPX		0x00001000  /* Force Duplex */
 #define IGC_CTRL_VME		0x40000000  /* IEEE VLAN mode enable */
@@ -673,6 +676,10 @@
 #define IGC_GEN_POLL_TIMEOUT	1920
 
 /* PHY Control Register */
+#define MII_CR_SPEED_MASK	(BIT(6) | BIT(13))
+#define MII_CR_SPEED_10		0x0000	/* SSM=0, SSL=0: 10 Mb/s */
+#define MII_CR_SPEED_100	BIT(13)	/* SSM=0, SSL=1: 100 Mb/s */
+#define MII_CR_DUPLEX_EN	BIT(8)	/* 0 = Half Duplex, 1 = Full Duplex */
 #define MII_CR_RESTART_AUTO_NEG	0x0200  /* Restart auto negotiation */
 #define MII_CR_POWER_DOWN	0x0800  /* Power down */
 #define MII_CR_AUTO_NEG_EN	0x1000  /* Auto Neg Enable */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 0122009bedd0..89fe2788a565 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1460,6 +1460,26 @@ static int igc_ethtool_set_rxnfc(struct net_device *dev,
 	}
 }
 
+/**
+ * igc_write_rss_key - Program the RSS key into device registers
+ * @adapter: board private structure
+ *
+ * Write the RSS key stored in adapter->rss_key to the IGC_RSSRK registers.
+ * Each 32-bit chunk of the key is read using get_unaligned_le32() and written
+ * to the appropriate register.
+ */
+void igc_write_rss_key(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 val;
+	int i;
+
+	for (i = 0; i < IGC_RSS_KEY_SIZE / 4; i++) {
+		val = get_unaligned_le32(&adapter->rss_key[i * 4]);
+		wr32(IGC_RSSRK(i), val);
+	}
+}
+
 void igc_write_rss_indir_tbl(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
@@ -1482,6 +1502,11 @@ void igc_write_rss_indir_tbl(struct igc_adapter *adapter)
 	}
 }
 
+static u32 igc_ethtool_get_rxfh_key_size(struct net_device *netdev)
+{
+	return IGC_RSS_KEY_SIZE;
+}
+
 static u32 igc_ethtool_get_rxfh_indir_size(struct net_device *netdev)
 {
 	return IGC_RETA_SIZE;
@@ -1494,10 +1519,13 @@ static int igc_ethtool_get_rxfh(struct net_device *netdev,
 	int i;
 
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
-	if (!rxfh->indir)
-		return 0;
-	for (i = 0; i < IGC_RETA_SIZE; i++)
-		rxfh->indir[i] = adapter->rss_indir_tbl[i];
+
+	if (rxfh->indir)
+		for (i = 0; i < IGC_RETA_SIZE; i++)
+			rxfh->indir[i] = adapter->rss_indir_tbl[i];
+
+	if (rxfh->key)
+		memcpy(rxfh->key, adapter->rss_key, sizeof(adapter->rss_key));
 
 	return 0;
 }
@@ -1511,24 +1539,28 @@ static int igc_ethtool_set_rxfh(struct net_device *netdev,
 	int i;
 
 	/* We do not allow change in unsupported parameters */
-	if (rxfh->key ||
-	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
-	     rxfh->hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
-	if (!rxfh->indir)
-		return 0;
 
-	num_queues = adapter->rss_queues;
+	if (rxfh->indir) {
+		num_queues = adapter->rss_queues;
 
-	/* Verify user input. */
-	for (i = 0; i < IGC_RETA_SIZE; i++)
-		if (rxfh->indir[i] >= num_queues)
-			return -EINVAL;
+		/* Verify user input. */
+		for (i = 0; i < IGC_RETA_SIZE; i++)
+			if (rxfh->indir[i] >= num_queues)
+				return -EINVAL;
 
-	for (i = 0; i < IGC_RETA_SIZE; i++)
-		adapter->rss_indir_tbl[i] = rxfh->indir[i];
+		for (i = 0; i < IGC_RETA_SIZE; i++)
+			adapter->rss_indir_tbl[i] = rxfh->indir[i];
+
+		igc_write_rss_indir_tbl(adapter);
+	}
 
-	igc_write_rss_indir_tbl(adapter);
+	if (rxfh->key) {
+		memcpy(adapter->rss_key, rxfh->key, sizeof(adapter->rss_key));
+		igc_write_rss_key(adapter);
+	}
 
 	return 0;
 }
@@ -1914,44 +1946,58 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev,
 	ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
 	ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
 
-	/* advertising link modes */
-	if (hw->phy.autoneg_advertised & ADVERTISE_10_HALF)
-		ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half);
-	if (hw->phy.autoneg_advertised & ADVERTISE_10_FULL)
-		ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Full);
-	if (hw->phy.autoneg_advertised & ADVERTISE_100_HALF)
-		ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Half);
-	if (hw->phy.autoneg_advertised & ADVERTISE_100_FULL)
-		ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Full);
-	if (hw->phy.autoneg_advertised & ADVERTISE_1000_FULL)
-		ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full);
-	if (hw->phy.autoneg_advertised & ADVERTISE_2500_FULL)
-		ethtool_link_ksettings_add_link_mode(cmd, advertising, 2500baseT_Full);
-
 	/* set autoneg settings */
 	ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg);
-	ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg);
+	if (hw->mac.autoneg_enabled) {
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg);
+		cmd->base.autoneg = AUTONEG_ENABLE;
+
+		/* advertising link modes only apply when autoneg is on */
+		if (hw->phy.autoneg_advertised & ADVERTISE_10_HALF)
+			ethtool_link_ksettings_add_link_mode(cmd, advertising,
+							     10baseT_Half);
+		if (hw->phy.autoneg_advertised & ADVERTISE_10_FULL)
+			ethtool_link_ksettings_add_link_mode(cmd, advertising,
+							     10baseT_Full);
+		if (hw->phy.autoneg_advertised & ADVERTISE_100_HALF)
+			ethtool_link_ksettings_add_link_mode(cmd, advertising,
+							     100baseT_Half);
+		if (hw->phy.autoneg_advertised & ADVERTISE_100_FULL)
+			ethtool_link_ksettings_add_link_mode(cmd, advertising,
+							     100baseT_Full);
+		if (hw->phy.autoneg_advertised & ADVERTISE_1000_FULL)
+			ethtool_link_ksettings_add_link_mode(cmd, advertising,
+							     1000baseT_Full);
+		if (hw->phy.autoneg_advertised & ADVERTISE_2500_FULL)
+			ethtool_link_ksettings_add_link_mode(cmd, advertising,
+							     2500baseT_Full);
+
+		/* Set pause flow control advertising */
+		switch (hw->fc.requested_mode) {
+		case igc_fc_full:
+			ethtool_link_ksettings_add_link_mode(cmd, advertising,
+							     Pause);
+			break;
+		case igc_fc_rx_pause:
+			ethtool_link_ksettings_add_link_mode(cmd, advertising,
+							     Pause);
+			ethtool_link_ksettings_add_link_mode(cmd, advertising,
+							     Asym_Pause);
+			break;
+		case igc_fc_tx_pause:
+			ethtool_link_ksettings_add_link_mode(cmd, advertising,
+							     Asym_Pause);
+			break;
+		default:
+			break;
+		}
+	} else {
+		cmd->base.autoneg = AUTONEG_DISABLE;
+	}
 
-	/* Set pause flow control settings */
+	/* Pause is always supported */
 	ethtool_link_ksettings_add_link_mode(cmd, supported, Pause);
 
-	switch (hw->fc.requested_mode) {
-	case igc_fc_full:
-		ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
-		break;
-	case igc_fc_rx_pause:
-		ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
-		ethtool_link_ksettings_add_link_mode(cmd, advertising,
-						     Asym_Pause);
-		break;
-	case igc_fc_tx_pause:
-		ethtool_link_ksettings_add_link_mode(cmd, advertising,
-						     Asym_Pause);
-		break;
-	default:
-		break;
-	}
-
 	status = pm_runtime_suspended(&adapter->pdev->dev) ?
 		 0 : rd32(IGC_STATUS);
 
@@ -1983,7 +2029,6 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev,
 		cmd->base.duplex = DUPLEX_UNKNOWN;
 	}
 	cmd->base.speed = speed;
-	cmd->base.autoneg = AUTONEG_ENABLE;
 
 	/* MDI-X => 2; MDI =>1; Invalid =>0 */
 	if (hw->phy.media_type == igc_media_type_copper)
@@ -2000,37 +2045,50 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev,
 	return 0;
 }
 
-static int
-igc_ethtool_set_link_ksettings(struct net_device *netdev,
-			       const struct ethtool_link_ksettings *cmd)
+/**
+ * igc_handle_autoneg_disabled - Configure forced speed/duplex settings
+ * @adapter: private driver structure
+ * @speed: requested speed (must be SPEED_10 or SPEED_100)
+ * @duplex: requested duplex
+ *
+ * Records forced speed/duplex when autoneg is disabled.
+ * Caller must validate speed before calling this function.
+ */
+static void igc_handle_autoneg_disabled(struct igc_adapter *adapter, u32 speed,
+					u8 duplex)
 {
-	struct igc_adapter *adapter = netdev_priv(netdev);
-	struct net_device *dev = adapter->netdev;
-	struct igc_hw *hw = &adapter->hw;
-	u16 advertised = 0;
+	struct igc_mac_info *mac = &adapter->hw.mac;
 
-	/* When adapter in resetting mode, autoneg/speed/duplex
-	 * cannot be changed
-	 */
-	if (igc_check_reset_block(hw)) {
-		netdev_err(dev, "Cannot change link characteristics when reset is active\n");
-		return -EINVAL;
+	switch (speed) {
+	case SPEED_10:
+		mac->forced_speed_duplex = (duplex == DUPLEX_FULL) ?
+			IGC_FORCED_10F : IGC_FORCED_10H;
+		break;
+	case SPEED_100:
+		mac->forced_speed_duplex = (duplex == DUPLEX_FULL) ?
+			IGC_FORCED_100F : IGC_FORCED_100H;
+		break;
+	default:
+		WARN_ONCE(1, "Unsupported speed %u\n", speed);
+		return;
 	}
 
-	/* MDI setting is only allowed when autoneg enabled because
-	 * some hardware doesn't allow MDI setting when speed or
-	 * duplex is forced.
-	 */
-	if (cmd->base.eth_tp_mdix_ctrl) {
-		if (cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO &&
-		    cmd->base.autoneg != AUTONEG_ENABLE) {
-			netdev_err(dev, "Forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
-			return -EINVAL;
-		}
-	}
+	mac->autoneg_enabled = false;
+}
 
-	while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
-		usleep_range(1000, 2000);
+/**
+ * igc_handle_autoneg_enabled - Configure autonegotiation advertisement
+ * @adapter: private driver structure
+ * @cmd: ethtool link ksettings from user
+ *
+ * Records advertised speeds and flow control settings when autoneg
+ * is enabled.
+ */
+static void igc_handle_autoneg_enabled(struct igc_adapter *adapter,
+				       const struct ethtool_link_ksettings *cmd)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u16 advertised = 0;
 
 	if (ethtool_link_ksettings_test_link_mode(cmd, advertising,
 						  2500baseT_Full))
@@ -2056,14 +2114,66 @@ igc_ethtool_set_link_ksettings(struct net_device *netdev,
 						  10baseT_Half))
 		advertised |= ADVERTISE_10_HALF;
 
-	if (cmd->base.autoneg == AUTONEG_ENABLE) {
-		hw->phy.autoneg_advertised = advertised;
-		if (adapter->fc_autoneg)
-			hw->fc.requested_mode = igc_fc_default;
-	} else {
-		netdev_info(dev, "Force mode currently not supported\n");
+	hw->mac.autoneg_enabled = true;
+	hw->phy.autoneg_advertised = advertised;
+	if (adapter->fc_autoneg)
+		hw->fc.requested_mode = igc_fc_default;
+}
+
+static int
+igc_ethtool_set_link_ksettings(struct net_device *netdev,
+			       const struct ethtool_link_ksettings *cmd)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct net_device *dev = adapter->netdev;
+	struct igc_hw *hw = &adapter->hw;
+
+	/* When adapter in resetting mode, autoneg/speed/duplex
+	 * cannot be changed
+	 */
+	if (igc_check_reset_block(hw)) {
+		netdev_err(dev, "Cannot change link characteristics when reset is active\n");
+		return -EINVAL;
+	}
+
+	if (cmd->base.autoneg != AUTONEG_ENABLE &&
+	    cmd->base.autoneg != AUTONEG_DISABLE) {
+		netdev_info(dev, "Unsupported autoneg setting\n");
+		return -EINVAL;
+	}
+
+	/* MDI setting is only allowed when autoneg enabled because
+	 * some hardware doesn't allow MDI setting when speed or
+	 * duplex is forced.
+	 */
+	if (cmd->base.eth_tp_mdix_ctrl) {
+		if (cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO &&
+		    cmd->base.autoneg != AUTONEG_ENABLE) {
+			netdev_err(dev, "Forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
+			return -EINVAL;
+		}
 	}
 
+	if (cmd->base.autoneg == AUTONEG_DISABLE) {
+		if (cmd->base.speed != SPEED_10 && cmd->base.speed != SPEED_100) {
+			netdev_info(dev, "Unsupported speed for forced link\n");
+			return -EINVAL;
+		}
+		if (cmd->base.duplex != DUPLEX_HALF && cmd->base.duplex != DUPLEX_FULL) {
+			netdev_info(dev, "Duplex must be half or full for forced link\n");
+			return -EINVAL;
+		}
+	}
+
+	while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+		usleep_range(1000, 2000);
+
+	if (cmd->base.autoneg == AUTONEG_ENABLE)
+		igc_handle_autoneg_enabled(adapter, cmd);
+	else
+		igc_handle_autoneg_disabled(adapter, cmd->base.speed,
+					    cmd->base.duplex);
+
 	/* MDI-X => 2; MDI => 1; Auto => 3 */
 	if (cmd->base.eth_tp_mdix_ctrl) {
 		/* fix up the value for auto (3 => 0) as zero is mapped
@@ -2175,6 +2285,7 @@ static const struct ethtool_ops igc_ethtool_ops = {
 	.get_rxnfc		= igc_ethtool_get_rxnfc,
 	.set_rxnfc		= igc_ethtool_set_rxnfc,
 	.get_rx_ring_count	= igc_ethtool_get_rx_ring_count,
+	.get_rxfh_key_size	= igc_ethtool_get_rxfh_key_size,
 	.get_rxfh_indir_size	= igc_ethtool_get_rxfh_indir_size,
 	.get_rxfh		= igc_ethtool_get_rxfh,
 	.set_rxfh		= igc_ethtool_set_rxfh,
diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h
index be8a49a86d09..62aaee55668a 100644
--- a/drivers/net/ethernet/intel/igc/igc_hw.h
+++ b/drivers/net/ethernet/intel/igc/igc_hw.h
@@ -73,6 +73,13 @@ struct igc_info {
 
 extern const struct igc_info igc_base_info;
 
+enum igc_forced_speed_duplex {
+	IGC_FORCED_10H,
+	IGC_FORCED_10F,
+	IGC_FORCED_100H,
+	IGC_FORCED_100F,
+};
+
 struct igc_mac_info {
 	struct igc_mac_operations ops;
 
@@ -92,8 +99,9 @@ struct igc_mac_info {
 	bool asf_firmware_present;
 	bool arc_subsystem_valid;
 
-	bool autoneg_failed;
 	bool get_link_status;
+	bool autoneg_enabled;
+	enum igc_forced_speed_duplex forced_speed_duplex;
 };
 
 struct igc_nvm_operations {
diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c
index 7ac6637f8db7..d6f3f6618469 100644
--- a/drivers/net/ethernet/intel/igc/igc_mac.c
+++ b/drivers/net/ethernet/intel/igc/igc_mac.c
@@ -438,26 +438,23 @@ void igc_config_collision_dist(struct igc_hw *hw)
  * Checks the status of auto-negotiation after link up to ensure that the
  * speed and duplex were not forced.  If the link needed to be forced, then
  * flow control needs to be forced also.  If auto-negotiation is enabled
- * and did not fail, then we configure flow control based on our link
- * partner.
+ * then we configure flow control based on our link partner.
  */
 s32 igc_config_fc_after_link_up(struct igc_hw *hw)
 {
 	u16 mii_status_reg, mii_nway_adv_reg, mii_nway_lp_ability_reg;
-	struct igc_mac_info *mac = &hw->mac;
 	u16 speed, duplex;
 	s32 ret_val = 0;
 
-	/* Check for the case where we have fiber media and auto-neg failed
-	 * so we had to force link.  In this case, we need to force the
-	 * configuration of the MAC to match the "fc" parameter.
+	/* Without autoneg, flow control capability is not exchanged with the
+	 * link partner. IEEE 802.3 prohibits flow control in half-duplex mode.
 	 */
-	if (mac->autoneg_failed)
-		ret_val = igc_force_mac_fc(hw);
+	if (!hw->mac.autoneg_enabled) {
+		if (hw->mac.forced_speed_duplex == IGC_FORCED_10H ||
+		    hw->mac.forced_speed_duplex == IGC_FORCED_100H)
+			hw->fc.current_mode = igc_fc_none;
 
-	if (ret_val) {
-		hw_dbg("Error forcing flow control settings\n");
-		goto out;
+		goto force_fc;
 	}
 
 	/* In auto-neg, we need to check and see if Auto-Neg has completed,
@@ -472,15 +469,15 @@ s32 igc_config_fc_after_link_up(struct igc_hw *hw)
 	ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS,
 				       &mii_status_reg);
 	if (ret_val)
-		goto out;
+		return ret_val;
 	ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS,
 				       &mii_status_reg);
 	if (ret_val)
-		goto out;
+		return ret_val;
 
 	if (!(mii_status_reg & MII_SR_AUTONEG_COMPLETE)) {
 		hw_dbg("Copper PHY and Auto Neg has not completed.\n");
-		goto out;
+		return ret_val;
 	}
 
 	/* The AutoNeg process has completed, so we now need to
@@ -492,11 +489,11 @@ s32 igc_config_fc_after_link_up(struct igc_hw *hw)
 	ret_val = hw->phy.ops.read_reg(hw, PHY_AUTONEG_ADV,
 				       &mii_nway_adv_reg);
 	if (ret_val)
-		goto out;
+		return ret_val;
 	ret_val = hw->phy.ops.read_reg(hw, PHY_LP_ABILITY,
 				       &mii_nway_lp_ability_reg);
 	if (ret_val)
-		goto out;
+		return ret_val;
 	/* Two bits in the Auto Negotiation Advertisement Register
 	 * (Address 4) and two bits in the Auto Negotiation Base
 	 * Page Ability Register (Address 5) determine flow control
@@ -612,7 +609,7 @@ s32 igc_config_fc_after_link_up(struct igc_hw *hw)
 	ret_val = hw->mac.ops.get_speed_and_duplex(hw, &speed, &duplex);
 	if (ret_val) {
 		hw_dbg("Error getting link speed and duplex\n");
-		goto out;
+		return ret_val;
 	}
 
 	if (duplex == HALF_DUPLEX)
@@ -621,13 +618,13 @@ s32 igc_config_fc_after_link_up(struct igc_hw *hw)
 	/* Now we call a subroutine to actually force the MAC
 	 * controller to use the correct flow control settings.
 	 */
+force_fc:
 	ret_val = igc_force_mac_fc(hw);
 	if (ret_val) {
 		hw_dbg("Error forcing flow control settings\n");
-		goto out;
+		return ret_val;
 	}
 
-out:
 	return ret_val;
 }
 
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 2c9e2dfd8499..e6e9441fc3d4 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -785,11 +785,8 @@ static void igc_setup_mrqc(struct igc_adapter *adapter)
 	struct igc_hw *hw = &adapter->hw;
 	u32 j, num_rx_queues;
 	u32 mrqc, rxcsum;
-	u32 rss_key[10];
 
-	netdev_rss_key_fill(rss_key, sizeof(rss_key));
-	for (j = 0; j < 10; j++)
-		wr32(IGC_RSSRK(j), rss_key[j]);
+	igc_write_rss_key(adapter);
 
 	num_rx_queues = adapter->rss_queues;
 
@@ -5048,6 +5045,9 @@ static int igc_sw_init(struct igc_adapter *adapter)
 
 	pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word);
 
+	/* init RSS key */
+	netdev_rss_key_fill(adapter->rss_key, sizeof(adapter->rss_key));
+
 	/* set default ring sizes */
 	adapter->tx_ring_count = IGC_DEFAULT_TXD;
 	adapter->rx_ring_count = IGC_DEFAULT_RXD;
@@ -7298,7 +7298,7 @@ static int igc_probe(struct pci_dev *pdev,
 	/* Initialize link properties that are user-changeable */
 	adapter->fc_autoneg = true;
 	hw->phy.autoneg_advertised = 0xaf;
-
+	hw->mac.autoneg_enabled = true;
 	hw->fc.requested_mode = igc_fc_default;
 	hw->fc.current_mode = igc_fc_default;
 
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c
index 6c4d204aecfa..4cf737fb3b21 100644
--- a/drivers/net/ethernet/intel/igc/igc_phy.c
+++ b/drivers/net/ethernet/intel/igc/igc_phy.c
@@ -494,12 +494,20 @@ s32 igc_setup_copper_link(struct igc_hw *hw)
 	s32 ret_val = 0;
 	bool link;
 
-	/* Setup autoneg and flow control advertisement and perform
-	 * autonegotiation.
-	 */
-	ret_val = igc_copper_link_autoneg(hw);
-	if (ret_val)
-		goto out;
+	if (hw->mac.autoneg_enabled) {
+		/* Setup autoneg and flow control advertisement and perform
+		 * autonegotiation.
+		 */
+		ret_val = igc_copper_link_autoneg(hw);
+		if (ret_val)
+			goto out;
+	} else {
+		ret_val = hw->phy.ops.force_speed_duplex(hw);
+		if (ret_val) {
+			hw_dbg("Error Forcing Speed/Duplex\n");
+			goto out;
+		}
+	}
 
 	/* Check link status. Wait up to 100 microseconds for link to become
 	 * valid.
@@ -778,3 +786,48 @@ u16 igc_read_phy_fw_version(struct igc_hw *hw)
 
 	return gphy_version;
 }
+
+/**
+ * igc_force_speed_duplex - Force PHY speed and duplex settings
+ * @hw: pointer to the HW structure
+ *
+ * Programs the GPY PHY control register to disable autonegotiation
+ * and force the speed/duplex indicated by hw->mac.forced_speed_duplex.
+ */
+s32 igc_force_speed_duplex(struct igc_hw *hw)
+{
+	struct igc_phy_info *phy = &hw->phy;
+	u16 phy_ctrl;
+	s32 ret_val;
+
+	ret_val = phy->ops.read_reg(hw, PHY_CONTROL, &phy_ctrl);
+	if (ret_val)
+		return ret_val;
+
+	phy_ctrl &= ~(MII_CR_SPEED_MASK | MII_CR_DUPLEX_EN |
+		      MII_CR_AUTO_NEG_EN | MII_CR_RESTART_AUTO_NEG);
+
+	switch (hw->mac.forced_speed_duplex) {
+	case IGC_FORCED_10H:
+		phy_ctrl |= MII_CR_SPEED_10;
+		break;
+	case IGC_FORCED_10F:
+		phy_ctrl |= MII_CR_SPEED_10 | MII_CR_DUPLEX_EN;
+		break;
+	case IGC_FORCED_100H:
+		phy_ctrl |= MII_CR_SPEED_100;
+		break;
+	case IGC_FORCED_100F:
+		phy_ctrl |= MII_CR_SPEED_100 | MII_CR_DUPLEX_EN;
+		break;
+	default:
+		return -IGC_ERR_CONFIG;
+	}
+
+	ret_val = phy->ops.write_reg(hw, PHY_CONTROL, phy_ctrl);
+	if (ret_val)
+		return ret_val;
+
+	hw->mac.get_link_status = true;
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.h b/drivers/net/ethernet/intel/igc/igc_phy.h
index 832a7e359f18..d37a89174826 100644
--- a/drivers/net/ethernet/intel/igc/igc_phy.h
+++ b/drivers/net/ethernet/intel/igc/igc_phy.h
@@ -18,5 +18,6 @@ void igc_power_down_phy_copper(struct igc_hw *hw);
 s32 igc_write_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 data);
 s32 igc_read_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 *data);
 u16 igc_read_phy_fw_version(struct igc_hw *hw);
+s32 igc_force_speed_duplex(struct igc_hw *hw);
 
 #endif
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 744d6585a949..543e566425c1 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -5678,6 +5678,24 @@ static int mvneta_probe(struct platform_device *pdev)
 					 "use SW buffer management\n");
 				mvneta_bm_put(pp->bm_priv);
 				pp->bm_priv = NULL;
+			} else if (!device_link_add(&pdev->dev,
+						    &pp->bm_priv->pdev->dev,
+						    DL_FLAG_AUTOREMOVE_CONSUMER)) {
+				/*
+				 * Link guarantees BM resumes before mvneta.
+				 * Without it, BM may not be ready when
+				 * mvneta_bm_port_init() runs on resume,
+				 * causing stale buffer addresses and a crash.
+				 * Fall back to SW management to be safe.
+				 */
+				dev_warn(&pdev->dev,
+					 "failed to link to BM, use SW buffer management\n");
+				mvneta_bm_pool_destroy(pp->bm_priv,
+						       pp->pool_long, 1 << pp->id);
+				mvneta_bm_pool_destroy(pp->bm_priv,
+						       pp->pool_short, 1 << pp->id);
+				mvneta_bm_put(pp->bm_priv);
+				pp->bm_priv = NULL;
 			}
 		}
 		/* Set RX packet offset correction for platforms, whose
diff --git a/drivers/net/ethernet/marvell/mvneta_bm.c b/drivers/net/ethernet/marvell/mvneta_bm.c
index 6bb380494919..d6d76fbf27b6 100644
--- a/drivers/net/ethernet/marvell/mvneta_bm.c
+++ b/drivers/net/ethernet/marvell/mvneta_bm.c
@@ -129,6 +129,7 @@ static int mvneta_bm_pool_create(struct mvneta_bm *priv,
 	if (!IS_ALIGNED((u32)bm_pool->virt_addr, MVNETA_BM_POOL_PTR_ALIGN)) {
 		dma_free_coherent(&pdev->dev, size_bytes, bm_pool->virt_addr,
 				  bm_pool->phys_addr);
+		bm_pool->virt_addr = NULL;
 		dev_err(&pdev->dev, "BM pool %d is not %d bytes aligned\n",
 			bm_pool->id, MVNETA_BM_POOL_PTR_ALIGN);
 		return -ENOMEM;
@@ -139,6 +140,7 @@ static int mvneta_bm_pool_create(struct mvneta_bm *priv,
 	if (err < 0) {
 		dma_free_coherent(&pdev->dev, size_bytes, bm_pool->virt_addr,
 				  bm_pool->phys_addr);
+		bm_pool->virt_addr = NULL;
 		return err;
 	}
 
@@ -395,9 +397,20 @@ static void mvneta_bm_put_sram(struct mvneta_bm *priv)
 
 struct mvneta_bm *mvneta_bm_get(struct device_node *node)
 {
-	struct platform_device *pdev = of_find_device_by_node(node);
+	struct platform_device *pdev;
+	struct mvneta_bm *priv;
+
+	pdev = of_find_device_by_node(node);
+	if (!pdev)
+		return NULL;
+
+	priv = platform_get_drvdata(pdev);
+	if (!priv) {
+		platform_device_put(pdev);
+		return NULL;
+	}
 
-	return pdev ? platform_get_drvdata(pdev) : NULL;
+	return priv;
 }
 EXPORT_SYMBOL_GPL(mvneta_bm_get);
 
@@ -477,6 +490,75 @@ static void mvneta_bm_remove(struct platform_device *pdev)
 	clk_disable_unprepare(priv->clk);
 }
 
+static int mvneta_bm_suspend(struct device *dev)
+{
+	struct mvneta_bm *priv = dev_get_drvdata(dev);
+	int i;
+
+	/* Drain buffers and free pool resources while BM is still clocked */
+	for (i = 0; i < MVNETA_BM_POOLS_NUM; i++) {
+		struct mvneta_bm_pool *bm_pool = &priv->bm_pools[i];
+		int size_bytes;
+
+		if (bm_pool->type == MVNETA_BM_FREE)
+			continue;
+
+		mvneta_bm_bufs_free(priv, bm_pool, bm_pool->port_map);
+		if (bm_pool->hwbm_pool.buf_num)
+			dev_warn(&priv->pdev->dev,
+				 "pool %d: %d buffers not freed\n",
+				 bm_pool->id, bm_pool->hwbm_pool.buf_num);
+
+		mvneta_bm_pool_disable(priv, bm_pool->id);
+
+		if (bm_pool->virt_addr) {
+			size_bytes = sizeof(u32) * bm_pool->hwbm_pool.size;
+			dma_free_coherent(&priv->pdev->dev, size_bytes,
+					  bm_pool->virt_addr,
+					  bm_pool->phys_addr);
+			bm_pool->virt_addr = NULL;
+		}
+		/*
+		 * Safe to destroy: device_link guarantees all mvneta ports
+		 * have already suspended, so no hwbm_pool_add() can be in
+		 * progress holding buf_lock.  Pairs with mutex_init() in
+		 * mvneta_bm_pool_use() on resume.
+		 */
+		mutex_destroy(&bm_pool->hwbm_pool.buf_lock);
+		bm_pool->type = MVNETA_BM_FREE;
+	}
+
+	mvneta_bm_write(priv, MVNETA_BM_COMMAND_REG, MVNETA_BM_STOP_MASK);
+	clk_disable_unprepare(priv->clk);
+	return 0;
+}
+
+static int mvneta_bm_resume(struct device *dev)
+{
+	struct mvneta_bm *priv = dev_get_drvdata(dev);
+	int i, err;
+
+	err = clk_prepare_enable(priv->clk);
+	if (err)
+		return err;
+
+	/* Reinitialize BM hardware; pools are refilled by mvneta_resume() */
+	mvneta_bm_default_set(priv);
+
+	/* Restore pool registers lost during clock gating */
+	for (i = 0; i < MVNETA_BM_POOLS_NUM; i++) {
+		mvneta_bm_write(priv, MVNETA_BM_POOL_READ_PTR_REG(i), 0);
+		mvneta_bm_write(priv, MVNETA_BM_POOL_WRITE_PTR_REG(i), 0);
+		mvneta_bm_write(priv, MVNETA_BM_POOL_SIZE_REG(i),
+				priv->bm_pools[i].hwbm_pool.size);
+	}
+
+	mvneta_bm_write(priv, MVNETA_BM_COMMAND_REG, MVNETA_BM_START_MASK);
+	return 0;
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(mvneta_bm_pm_ops, mvneta_bm_suspend, mvneta_bm_resume);
+
 static const struct of_device_id mvneta_bm_match[] = {
 	{ .compatible = "marvell,armada-380-neta-bm" },
 	{ }
@@ -489,6 +571,7 @@ static struct platform_driver mvneta_bm_driver = {
 	.driver = {
 		.name = MVNETA_BM_DRIVER_NAME,
 		.of_match_table = mvneta_bm_match,
+		.pm = pm_sleep_ptr(&mvneta_bm_pm_ops),
 	},
 };
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 714e47f68d93..10552e9cf519 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -803,6 +803,7 @@ struct npc_set_pkind {
 			 */
 	u8 var_len_off_mask; /* Mask for length with in offset */
 	u8 shift_dir; /* shift direction to get length of the header at var_len_off */
+	u8 skip_size; /* l2 size to skip */
 };
 
 /* NPA mbox message formats */
@@ -1262,11 +1263,13 @@ struct nix_rss_flowkey_cfg {
 #define NIX_FLOW_KEY_TYPE_INNR_UDP      BIT(15)
 #define NIX_FLOW_KEY_TYPE_INNR_SCTP     BIT(16)
 #define NIX_FLOW_KEY_TYPE_INNR_ETH_DMAC BIT(17)
+#define NIX_FLOW_KEY_TYPE_CH_LEN_90B    BIT(18)
 #define NIX_FLOW_KEY_TYPE_CUSTOM0	BIT(19)
 #define NIX_FLOW_KEY_TYPE_VLAN		BIT(20)
 #define NIX_FLOW_KEY_TYPE_IPV4_PROTO	BIT(21)
 #define NIX_FLOW_KEY_TYPE_AH		BIT(22)
 #define NIX_FLOW_KEY_TYPE_ESP		BIT(23)
+#define NIX_FLOW_KEY_TYPE_ROCEV2	BIT(24)
 #define NIX_FLOW_KEY_TYPE_L4_DST_ONLY BIT(28)
 #define NIX_FLOW_KEY_TYPE_L4_SRC_ONLY BIT(29)
 #define NIX_FLOW_KEY_TYPE_L3_DST_ONLY BIT(30)
@@ -1461,7 +1464,7 @@ struct nix_inline_ipsec_lf_cfg {
 
 struct nix_hw_info {
 	struct mbox_msghdr hdr;
-	u16 rsvs16;
+	u16 vwqe_delay;
 	u16 max_mtu;
 	u16 min_mtu;
 	u32 rpm_dwrr_mtu;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
index eaed172f1606..719b3618eeb5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
@@ -161,10 +161,12 @@ enum npc_kpu_lh_ltype {
  * Software assigns pkind for each incoming port such as CGX
  * Ethernet interfaces, LBK interfaces, etc.
  */
-#define NPC_UNRESERVED_PKIND_COUNT NPC_RX_CPT_HDR_PTP_PKIND
+#define NPC_UNRESERVED_PKIND_COUNT NPC_RX_SKIP_SIZE_PKIND
 
 enum npc_pkind_type {
 	NPC_RX_LBK_PKIND = 0ULL,
+	NPC_RX_SKIP_SIZE_PKIND = 46ULL,
+	NPC_RX_CPT_SKIP_SIZE_PKIND = 50ULL,
 	NPC_RX_CPT_HDR_PTP_PKIND = 54ULL,
 	NPC_RX_CUSTOM_PRE_L2_PKIND = 55ULL,
 	NPC_RX_VLAN_EXDSA_PKIND = 56ULL,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 7f3505ae6860..c5610f242687 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -1181,7 +1181,7 @@ void rvu_switch_enable_lbk_link(struct rvu *rvu, u16 pcifunc, bool ena);
 
 int rvu_npc_set_parse_mode(struct rvu *rvu, u16 pcifunc, u64 mode, u8 dir,
 			   u64 pkind, u8 var_len_off, u8 var_len_off_mask,
-			   u8 shift_dir);
+			   u8 shift_dir, u8 skip_size);
 int rvu_get_hwvf(struct rvu *rvu, int pcifunc);
 
 /* CN10K MCS */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 6a0ce2665031..dade7bb6deb7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -3936,6 +3936,11 @@ int rvu_mbox_handler_nix_get_hw_info(struct rvu *rvu, struct msg_req *req,
 	if (blkaddr < 0)
 		return NIX_AF_ERR_AF_LF_INVALID;
 
+	rsp->vwqe_delay = 0;
+	if (!is_rvu_otx2(rvu))
+		rsp->vwqe_delay = rvu_read64(rvu, blkaddr, NIX_AF_VWQE_TIMER) &
+				  GENMASK_ULL(9, 0);
+
 	if (is_lbk_vf(rvu, pcifunc))
 		rvu_get_lbk_link_max_frs(rvu, &rsp->max_mtu);
 	else
@@ -4283,6 +4288,13 @@ static int set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
 			field->ltype_match = NPC_LT_LC_CUSTOM0;
 			field->ltype_mask = 0xF;
 			break;
+		case NIX_FLOW_KEY_TYPE_CH_LEN_90B:
+			field->lid = NPC_LID_LA;
+			field->hdr_offset = 24;
+			field->bytesm1 = 1; /* 2 Bytes*/
+			field->ltype_match = NPC_LT_LA_CUSTOM_L2_90B_ETHER;
+			field->ltype_mask = 0xF;
+			break;
 		case NIX_FLOW_KEY_TYPE_VLAN:
 			field->lid = NPC_LID_LB;
 			field->hdr_offset = 2; /* Skip TPID (2-bytes) */
@@ -4305,6 +4317,13 @@ static int set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
 				keyoff_marker = false;
 			}
 			break;
+		case NIX_FLOW_KEY_TYPE_ROCEV2:
+			field->hdr_offset = 5;
+			field->bytesm1 = 2; /* Destination QP */
+			field->ltype_mask = 0xF;
+			field->lid = NPC_LID_LE;
+			field->ltype_match = NPC_LT_LE_ROCEV2;
+			break;
 		}
 		field->ena = 1;
 
@@ -5392,7 +5411,7 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf)
 
 	/* reset HW config done for Switch headers */
 	rvu_npc_set_parse_mode(rvu, pcifunc, OTX2_PRIV_FLAGS_DEFAULT,
-			       (PKIND_TX | PKIND_RX), 0, 0, 0, 0);
+			       (PKIND_TX | PKIND_RX), 0, 0, 0, 0, 0);
 
 	/* Disabling CGX and NPC config done for PTP */
 	if (pfvf->hw_rx_tstamp_en) {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index c7bc0b3a29b9..08b83de9beb4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -4194,10 +4194,40 @@ npc_set_var_len_offset_pkind(struct rvu *rvu, u16 pcifunc, u64 pkind,
 	return 0;
 }
 
+static int npc_set_skip_size_pkind(struct rvu *rvu, u16 pcifunc, u64 pkind,
+				   u8 skip_size)
+{
+	struct npc_kpu_action0 *act0;
+	int blkaddr;
+	u64 val;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, pcifunc);
+	if (blkaddr < 0) {
+		dev_err(rvu->dev, "%s: NPC block not implemented\n", __func__);
+		return -EINVAL;
+	}
+
+	val = rvu_read64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind));
+	act0 = (struct npc_kpu_action0 *)&val;
+	act0->ptr_advance = skip_size;
+	rvu_write64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind), val);
+
+	/* Update CPT_HR new PKIND */
+	val = rvu_read64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind + 4));
+	act0 = (struct npc_kpu_action0 *)&val;
+	act0->ptr_advance = (skip_size + 40);
+	act0->next_state = NPC_S_KPU1_CPT_HDR;
+	act0->var_len_offset = (skip_size + 6);
+	act0->var_len_mask = 0xe0;
+	act0->var_len_shift = 0x5;
+	act0->var_len_right = 0x1;
+	rvu_write64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind + 4), val);
+	return 0;
+}
+
 int rvu_npc_set_parse_mode(struct rvu *rvu, u16 pcifunc, u64 mode, u8 dir,
 			   u64 pkind, u8 var_len_off, u8 var_len_off_mask,
-			   u8 shift_dir)
-
+			   u8 shift_dir, u8 skip_size)
 {
 	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	int blkaddr, nixlf, rc, intf_mode;
@@ -4218,6 +4248,12 @@ int rvu_npc_set_parse_mode(struct rvu *rvu, u16 pcifunc, u64 mode, u8 dir,
 							  shift_dir);
 			if (rc)
 				return rc;
+		} else if (pkind >= NPC_RX_SKIP_SIZE_PKIND &&
+			   pkind <= NPC_RX_SKIP_SIZE_PKIND + 3) {
+			rc = npc_set_skip_size_pkind(rvu, pcifunc, pkind,
+						     skip_size);
+			if (rc)
+				return rc;
 		}
 		rxpkind = pkind;
 		txpkind = pkind;
@@ -4254,7 +4290,8 @@ int rvu_mbox_handler_npc_set_pkind(struct rvu *rvu, struct npc_set_pkind *req,
 {
 	return rvu_npc_set_parse_mode(rvu, req->hdr.pcifunc, req->mode,
 				      req->dir, req->pkind, req->var_len_off,
-				      req->var_len_off_mask, req->shift_dir);
+				      req->var_len_off_mask, req->shift_dir,
+				      req->skip_size);
 }
 
 int rvu_mbox_handler_npc_read_base_steer_rule(struct rvu *rvu,
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c
index dbf173196608..8e41431c7f9c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c
@@ -656,6 +656,7 @@ static int cn20k_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id,
 	pp_params.nid = NUMA_NO_NODE;
 	pp_params.dev = pfvf->dev;
 	pp_params.dma_dir = DMA_FROM_DEVICE;
+	pp_params.netdev = pfvf->netdev;
 	pool->page_pool = page_pool_create(&pp_params);
 	if (IS_ERR(pool->page_pool)) {
 		netdev_err(pfvf->netdev, "Creation of page pool failed\n");
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 3d253132a17f..ca73a94db794 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1035,7 +1035,6 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 	if (qidx > pfvf->hw.xdp_queues)
 		otx2_attach_xsk_buff(pfvf, sq, (qidx - pfvf->hw.xdp_queues));
 
-
 	chan_offset = qidx % pfvf->hw.tx_chan_cnt;
 	err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, chan_offset, sqb_aura);
 	if (err) {
@@ -1517,6 +1516,7 @@ int otx2_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id,
 		pp_params.nid = NUMA_NO_NODE;
 		pp_params.dev = pfvf->dev;
 		pp_params.dma_dir = DMA_FROM_DEVICE;
+		pp_params.netdev = pfvf->netdev;
 		pool->page_pool = page_pool_create(&pp_params);
 		if (IS_ERR(pool->page_pool)) {
 			netdev_err(pfvf->netdev, "Creation of page pool failed\n");
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 625bb5a05344..8d2d607bc92f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -750,7 +750,7 @@ static void otx2_sqe_add_ext(struct otx2_nic *pfvf, struct otx2_snd_queue *sq,
 				ext->lso_format = pfvf->hw.lso_udpv6_idx;
 			}
 
-			udph->len = htons(sizeof(struct udphdr));
+			udp_set_len_short(udph, sizeof(struct udphdr));
 		}
 	} else if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
 		ext->tstmp = 1;
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_router.c b/drivers/net/ethernet/marvell/prestera/prestera_router.c
index b036b173a308..0c4f462baa6e 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_router.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_router.c
@@ -1302,10 +1302,8 @@ static int __prestera_inetaddr_port_event(struct net_device *port_dev,
 		dev_hold(port_dev);
 		break;
 	case NETDEV_DOWN:
-		if (!re) {
-			NL_SET_ERR_MSG_MOD(extack, "Can't find RIF");
-			return -EEXIST;
-		}
+		if (!re)
+			return 0;
 		prestera_rif_entry_destroy(port->sw, re);
 		dev_put(port_dev);
 		break;
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 5d291e50a47b..fe7610c42e5d 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -26,6 +26,7 @@
 #include <linux/bitfield.h>
 #include <net/dsa.h>
 #include <net/dst_metadata.h>
+#include <net/netdev_lock.h>
 #include <net/page_pool/helpers.h>
 #include <linux/genalloc.h>
 
@@ -5030,10 +5031,14 @@ void mtk_eth_set_dma_device(struct mtk_eth *eth, struct device *dma_dev)
 			continue;
 
 		list_add_tail(&dev->close_list, &dev_list);
+		netdev_lock_ops(dev);
 	}
 
 	netif_close_many(&dev_list, false);
 
+	list_for_each_entry(dev, &dev_list, close_list)
+		netdev_unlock_ops(dev);
+
 	eth->dma_dev = dma_dev;
 
 	list_for_each_entry_safe(dev, tmp, &dev_list, close_list) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index c31e05529fc4..b9026cc64383 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -383,6 +383,7 @@ static const struct devlink_ops mlx5_devlink_ops = {
 	.rate_node_del = mlx5_esw_devlink_rate_node_del,
 	.rate_leaf_parent_set = mlx5_esw_devlink_rate_leaf_parent_set,
 	.rate_node_parent_set = mlx5_esw_devlink_rate_node_parent_set,
+	.supported_cross_device_rate_nodes = true,
 #endif
 #ifdef CONFIG_MLX5_SF_MANAGER
 	.port_new = mlx5_devlink_sf_port_new,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index d507289096c2..45bda7b226e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1028,7 +1028,7 @@ struct mlx5e_profile {
 	void	(*cleanup_rx)(struct mlx5e_priv *priv);
 	int	(*init_tx)(struct mlx5e_priv *priv);
 	void	(*cleanup_tx)(struct mlx5e_priv *priv);
-	void	(*enable)(struct mlx5e_priv *priv);
+	int	(*enable)(struct mlx5e_priv *priv);
 	void	(*disable)(struct mlx5e_priv *priv);
 	int	(*update_rx)(struct mlx5e_priv *priv);
 	void	(*update_stats)(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 091b80a67189..4973fb473ff0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -88,13 +88,18 @@ enum {
 #ifdef CONFIG_MLX5_EN_ARFS
 	MLX5E_ARFS_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
 #endif
-#if defined(CONFIG_MLX5_EN_IPSEC) || defined(CONFIG_MLX5_EN_PSP)
+#if defined(CONFIG_MLX5_EN_IPSEC)
 	MLX5E_ACCEL_FS_ESP_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
 	MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL,
 	MLX5E_ACCEL_FS_POL_FT_LEVEL,
 	MLX5E_ACCEL_FS_POL_MISS_FT_LEVEL,
 	MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL,
 #endif
+#if defined(CONFIG_MLX5_EN_PSP)
+	MLX5E_ACCEL_FS_PSP_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
+	MLX5E_ACCEL_FS_PSP_ERR_FT_LEVEL,
+	MLX5E_ACCEL_FS_PSP_RX_FT_LEVEL,
+#endif
 };
 
 struct mlx5e_flow_steering;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index b526b3898c22..3f212e46fc2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -220,18 +220,7 @@ static inline void mlx5e_accel_tx_finish(struct mlx5e_txqsq *sq,
 
 static inline int mlx5e_accel_init_rx(struct mlx5e_priv *priv)
 {
-	int err;
-
-	err = mlx5_accel_psp_fs_init_rx_tables(priv);
-	if (err)
-		goto out;
-
-	err = mlx5e_ktls_init_rx(priv);
-	if (err)
-		mlx5_accel_psp_fs_cleanup_rx_tables(priv);
-
-out:
-	return err;
+	return mlx5e_ktls_init_rx(priv);
 }
 
 static inline void mlx5e_accel_cleanup_rx(struct mlx5e_priv *priv)
@@ -242,12 +231,6 @@ static inline void mlx5e_accel_cleanup_rx(struct mlx5e_priv *priv)
 
 static inline int mlx5e_accel_init_tx(struct mlx5e_priv *priv)
 {
-	int err;
-
-	err = mlx5_accel_psp_fs_init_tx_tables(priv);
-	if (err)
-		return err;
-
 	return mlx5e_ktls_init_tx(priv);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c
index d9adb993e64d..73b232379263 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c
@@ -21,51 +21,52 @@ enum accel_psp_syndrome {
 	PSP_BAD_TRAILER,
 };
 
-struct mlx5e_psp_tx {
+struct mlx5e_psp_tx_table {
 	struct mlx5_flow_namespace *ns;
 	struct mlx5_flow_table *ft;
 	struct mlx5_flow_group *fg;
 	struct mlx5_flow_handle *rule;
-	struct mutex mutex; /* Protect PSP TX steering */
-	u32 refcnt;
-	struct mlx5_fc *tx_counter;
 };
 
-struct mlx5e_psp_rx_err {
+struct mlx5e_psp_rx_check_table {
 	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *drop_group;
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_handle *auth_fail_rule;
 	struct mlx5_flow_handle *err_rule;
 	struct mlx5_flow_handle *bad_rule;
-	struct mlx5_modify_hdr *copy_modify_hdr;
 };
 
-struct mlx5e_accel_fs_psp_prot {
+struct mlx5e_psp_rx_decrypt_table {
 	struct mlx5_flow_table *ft;
 	struct mlx5_flow_group *miss_group;
 	struct mlx5_flow_handle *miss_rule;
 	struct mlx5_modify_hdr *rx_modify_hdr;
-	struct mlx5_flow_destination default_dest;
-	struct mlx5e_psp_rx_err rx_err;
-	u32 refcnt;
-	struct mutex prot_mutex; /* protect ESP4/ESP6 protocol */
-	struct mlx5_flow_handle *def_rule;
+	struct mlx5_flow_handle *rule;
 };
 
-struct mlx5e_accel_fs_psp {
-	struct mlx5e_accel_fs_psp_prot fs_prot[ACCEL_FS_PSP_NUM_TYPES];
-	struct mlx5_fc *rx_counter;
-	struct mlx5_fc *rx_auth_fail_counter;
-	struct mlx5_fc *rx_err_counter;
-	struct mlx5_fc *rx_bad_counter;
+struct mlx5e_psp_rx_table {
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *miss_group;
+	struct mlx5_flow_handle *miss_rule;
+	struct mlx5_flow_handle *udp_rules[ACCEL_FS_PSP_NUM_TYPES];
 };
 
 struct mlx5e_psp_fs {
 	struct mlx5_core_dev *mdev;
-	struct mlx5e_psp_tx *tx_fs;
-	/* Rx manage */
+	struct mlx5_fc *tx_counter;
+	struct mlx5e_psp_tx_table tx;
+
+	/* Rx */
 	struct mlx5e_flow_steering *fs;
-	struct mlx5e_accel_fs_psp *rx_fs;
+	struct mlx5_fc *rx_counter;
+	struct mlx5_fc *rx_auth_fail_counter;
+	struct mlx5_fc *rx_err_counter;
+	struct mlx5_fc *rx_bad_counter;
+
+	struct mlx5e_psp_rx_decrypt_table decrypt[ACCEL_FS_PSP_NUM_TYPES];
+	struct mlx5e_psp_rx_check_table check;
+	struct mlx5e_psp_rx_table rx;
 };
 
 /* PSP RX flow steering */
@@ -77,44 +78,200 @@ static enum mlx5_traffic_types fs_psp2tt(enum accel_fs_psp_type i)
 	return MLX5_TT_IPV6_UDP;
 }
 
-static void accel_psp_fs_rx_err_del_rules(struct mlx5e_psp_fs *fs,
-					  struct mlx5e_psp_rx_err *rx_err)
+static int accel_psp_fs_create_ft(struct mlx5e_psp_fs *fs,
+				  struct mlx5_flow_table_attr *ft_attr,
+				  struct mlx5_flow_table **ft)
+{
+	struct mlx5_flow_namespace *ns = mlx5e_fs_get_ns(fs->fs, false);
+	int err = 0;
+
+	*ft = mlx5_create_auto_grouped_flow_table(ns, ft_attr);
+	if (IS_ERR(*ft)) {
+		err = PTR_ERR(*ft);
+		*ft = NULL;
+	}
+
+	return err;
+}
+
+static void accel_psp_fs_destroy_ft(struct mlx5_flow_table **table)
 {
-	if (rx_err->bad_rule) {
-		mlx5_del_flow_rules(rx_err->bad_rule);
-		rx_err->bad_rule = NULL;
+	if (*table) {
+		mlx5_destroy_flow_table(*table);
+		*table = NULL;
 	}
+}
 
-	if (rx_err->err_rule) {
-		mlx5_del_flow_rules(rx_err->err_rule);
-		rx_err->err_rule = NULL;
+static void accel_psp_fs_del_flow_rule(struct mlx5_flow_handle **rule)
+{
+	if (*rule) {
+		mlx5_del_flow_rules(*rule);
+		*rule = NULL;
 	}
+}
+
+static int accel_psp_fs_create_miss_group(struct mlx5_flow_table *ft,
+					  struct mlx5_flow_group **group)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	u32 *in = kvzalloc(inlen, GFP_KERNEL);
+	int err = 0;
 
-	if (rx_err->auth_fail_rule) {
-		mlx5_del_flow_rules(rx_err->auth_fail_rule);
-		rx_err->auth_fail_rule = NULL;
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(create_flow_group_in, in, start_flow_index, ft->max_fte - 1);
+	MLX5_SET(create_flow_group_in, in, end_flow_index, ft->max_fte - 1);
+	*group = mlx5_create_flow_group(ft, in);
+	if (IS_ERR(*group)) {
+		err = PTR_ERR(*group);
+		*group = NULL;
 	}
+	kvfree(in);
 
-	if (rx_err->rule) {
-		mlx5_del_flow_rules(rx_err->rule);
-		rx_err->rule = NULL;
+	return err;
+}
+
+static void accel_psp_fs_destroy_flow_group(struct mlx5_flow_group **group)
+{
+	if (*group) {
+		mlx5_destroy_flow_group(*group);
+		*group = NULL;
 	}
+}
+
+static int accel_psp_fs_create_counter(struct mlx5_core_dev *dev,
+				       struct mlx5_fc **counter)
+{
+	*counter = mlx5_fc_create(dev, false);
+	if (IS_ERR(*counter)) {
+		int err = PTR_ERR(*counter);
+
+		*counter = NULL;
+		return err;
+	}
+
+	return 0;
+}
 
-	if (rx_err->copy_modify_hdr) {
-		mlx5_modify_header_dealloc(fs->mdev, rx_err->copy_modify_hdr);
-		rx_err->copy_modify_hdr = NULL;
+static void accel_psp_fs_destroy_counter(struct mlx5_core_dev *dev,
+					 struct mlx5_fc **counter)
+{
+	if (*counter) {
+		mlx5_fc_destroy(dev, *counter);
+		*counter = NULL;
 	}
 }
 
-static void accel_psp_fs_rx_err_destroy_ft(struct mlx5e_psp_fs *fs,
-					   struct mlx5e_psp_rx_err *rx_err)
+static void accel_psp_fs_rx_ft_destroy(struct mlx5e_psp_rx_table *rx)
+{
+	int i;
+
+	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++)
+		accel_psp_fs_del_flow_rule(&rx->udp_rules[i]);
+	accel_psp_fs_del_flow_rule(&rx->miss_rule);
+	accel_psp_fs_destroy_flow_group(&rx->miss_group);
+	accel_psp_fs_destroy_ft(&rx->ft);
+}
+
+static int accel_psp_fs_rx_ft_create(struct mlx5e_psp_fs *fs,
+				     struct mlx5e_psp_rx_table *rx)
 {
-	accel_psp_fs_rx_err_del_rules(fs, rx_err);
+	struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(fs->fs, false);
+	struct mlx5_flow_destination dest[2] = {};
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_core_dev *mdev = fs->mdev;
+	MLX5_DECLARE_FLOW_ACT(flow_act);
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int i, err = 0;
+
+	spec = kzalloc_obj(*spec);
+	if (!spec)
+		return -ENOMEM;
+
+	ft_attr.max_fte = 1 + ACCEL_FS_PSP_NUM_TYPES;
+	ft_attr.level = MLX5E_ACCEL_FS_PSP_RX_FT_LEVEL;
+	ft_attr.prio = MLX5E_NIC_PRIO;
+	ft_attr.autogroup.num_reserved_entries = 1;
+	err = accel_psp_fs_create_ft(fs, &ft_attr, &rx->ft);
+	if (err) {
+		mlx5_core_err(mdev, "fail to create psp rx ft err=%d\n", err);
+		goto out_err;
+	}
 
-	if (rx_err->ft) {
-		mlx5_destroy_flow_table(rx_err->ft);
-		rx_err->ft = NULL;
+	err = accel_psp_fs_create_miss_group(rx->ft, &rx->miss_group);
+	if (err) {
+		mlx5_core_err(mdev, "fail to create psp rx miss_group err=%d\n",
+			      err);
+		goto out_err;
 	}
+
+	/* Add miss rule */
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+		MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL;
+	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest[0].ft = mlx5_get_ttc_flow_table(ttc);
+	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest[1].counter = fs->rx_counter;
+	rule = mlx5_add_flow_rules(rx->ft, NULL, &flow_act, dest, 2);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev, "fail to create psp rx rule, err=%d\n",
+			      err);
+		goto out_err;
+	}
+	rx->miss_rule = rule;
+
+	/* Add UDP v4/v6 rules */
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 outer_headers.ip_version);
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, spec->match_criteria,
+			 ip_protocol);
+	MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, ip_protocol,
+		 IPPROTO_UDP);
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+		MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	flow_act.flags = 0;
+	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++) {
+		int version = i == ACCEL_FS_PSP4 ? 4 : 6;
+
+		MLX5_SET(fte_match_param, spec->match_value,
+			 outer_headers.ip_version, version);
+		dest[0] = mlx5_ttc_get_default_dest(ttc, fs_psp2tt(i));
+		dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+		dest[1].counter = fs->rx_counter;
+		rule = mlx5_add_flow_rules(rx->ft, spec, &flow_act, dest,
+					   2);
+		if (IS_ERR(rule)) {
+			err = PTR_ERR(rule);
+			mlx5_core_err(mdev,
+				      "fail to create psp rx UDP%d rule err=%d\n",
+				      version, err);
+			goto out_err;
+		}
+		rx->udp_rules[i] = rule;
+	}
+	goto out_spec;
+
+out_err:
+	accel_psp_fs_rx_ft_destroy(rx);
+out_spec:
+	kvfree(spec);
+	return err;
+}
+
+static
+void accel_psp_fs_rx_check_ft_destroy(struct mlx5e_psp_rx_check_table *check)
+{
+	accel_psp_fs_del_flow_rule(&check->bad_rule);
+	accel_psp_fs_del_flow_rule(&check->err_rule);
+	accel_psp_fs_del_flow_rule(&check->auth_fail_rule);
+	accel_psp_fs_del_flow_rule(&check->rule);
+	accel_psp_fs_destroy_flow_group(&check->drop_group);
+	accel_psp_fs_destroy_ft(&check->ft);
 }
 
 static void accel_psp_setup_syndrome_match(struct mlx5_flow_spec *spec,
@@ -129,15 +286,35 @@ static void accel_psp_setup_syndrome_match(struct mlx5_flow_spec *spec,
 	MLX5_SET(fte_match_set_misc2, misc_params_2, psp_syndrome, syndrome);
 }
 
-static int accel_psp_fs_rx_err_add_rule(struct mlx5e_psp_fs *fs,
-					struct mlx5e_accel_fs_psp_prot *fs_prot,
-					struct mlx5e_psp_rx_err *rx_err)
+static int accel_psp_add_drop_rule(struct mlx5_flow_table *ft,
+				   struct mlx5_flow_spec *spec,
+				   struct mlx5_fc *counter,
+				   struct mlx5_flow_handle **rule)
 {
-	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	int err = 0;
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP |
+			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter = counter;
+	*rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(*rule)) {
+		err = PTR_ERR(*rule);
+		*rule = NULL;
+	}
+	return err;
+}
+
+static
+int accel_psp_fs_rx_check_ft_create(struct mlx5e_psp_fs *fs,
+				    struct mlx5e_psp_rx_check_table *check)
+{
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_flow_destination dest = {};
 	struct mlx5_core_dev *mdev = fs->mdev;
-	struct mlx5_flow_destination dest[2];
 	struct mlx5_flow_act flow_act = {};
-	struct mlx5_modify_hdr *modify_hdr;
 	struct mlx5_flow_handle *fte;
 	struct mlx5_flow_spec *spec;
 	int err = 0;
@@ -146,174 +323,97 @@ static int accel_psp_fs_rx_err_add_rule(struct mlx5e_psp_fs *fs,
 	if (!spec)
 		return -ENOMEM;
 
-	/* Action to copy 7 bit psp_syndrome to regB[23:29] */
-	MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY);
-	MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_PSP_SYNDROME);
-	MLX5_SET(copy_action_in, action, src_offset, 0);
-	MLX5_SET(copy_action_in, action, length, 7);
-	MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
-	MLX5_SET(copy_action_in, action, dst_offset, 23);
+	ft_attr.max_fte = 4;
+	ft_attr.autogroup.num_reserved_entries = 1;
+	ft_attr.autogroup.max_num_groups = 2;
+	ft_attr.level = MLX5E_ACCEL_FS_PSP_ERR_FT_LEVEL;
+	ft_attr.prio = MLX5E_NIC_PRIO;
+	err = accel_psp_fs_create_ft(fs, &ft_attr, &check->ft);
+	if (err) {
+		mlx5_core_err(fs->mdev,
+			      "fail to create psp rx check ft err=%d\n", err);
+		goto out_err;
+	}
 
-	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL,
-					      1, action);
-	if (IS_ERR(modify_hdr)) {
-		err = PTR_ERR(modify_hdr);
-		mlx5_core_err(mdev,
-			      "fail to alloc psp copy modify_header_id err=%d\n", err);
-		goto out_spec;
+	err = accel_psp_fs_create_miss_group(check->ft, &check->drop_group);
+	if (err) {
+		mlx5_core_err(fs->mdev,
+			      "fail to create psp rx check drop group err=%d\n",
+			      err);
+		goto out_err;
 	}
 
 	accel_psp_setup_syndrome_match(spec, PSP_OK);
 	/* create fte */
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
-			  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
-			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	flow_act.modify_hdr = modify_hdr;
-	dest[0].type = fs_prot->default_dest.type;
-	dest[0].ft = fs_prot->default_dest.ft;
-	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest[1].counter = fs->rx_fs->rx_counter;
-	fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, dest, 2);
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest.ft = fs->rx.ft;
+	fte = mlx5_add_flow_rules(check->ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(fte)) {
 		err = PTR_ERR(fte);
-		mlx5_core_err(mdev, "fail to add psp rx err copy rule err=%d\n", err);
-		goto out;
+		mlx5_core_err(mdev, "fail to add psp rx check ok rule err=%d\n",
+			      err);
+		goto out_err;
 	}
-	rx_err->rule = fte;
+	check->rule = fte;
 
 	/* add auth fail drop rule */
 	memset(spec, 0, sizeof(*spec));
-	memset(&flow_act, 0, sizeof(flow_act));
 	accel_psp_setup_syndrome_match(spec, PSP_ICV_FAIL);
-	/* create fte */
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP |
-			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest[0].counter = fs->rx_fs->rx_auth_fail_counter;
-	fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, dest, 1);
-	if (IS_ERR(fte)) {
-		err = PTR_ERR(fte);
-		mlx5_core_err(mdev, "fail to add psp rx auth fail drop rule err=%d\n",
+	err = accel_psp_add_drop_rule(check->ft, spec,
+				      fs->rx_auth_fail_counter,
+				      &check->auth_fail_rule);
+	if (err) {
+		mlx5_core_err(mdev,
+			      "fail to add psp rx check auth fail drop rule err=%d\n",
 			      err);
-		goto out_drop_rule;
+		goto out_err;
 	}
-	rx_err->auth_fail_rule = fte;
 
 	/* add framing drop rule */
 	memset(spec, 0, sizeof(*spec));
-	memset(&flow_act, 0, sizeof(flow_act));
 	accel_psp_setup_syndrome_match(spec, PSP_BAD_TRAILER);
-	/* create fte */
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP |
-			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest[0].counter = fs->rx_fs->rx_err_counter;
-	fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, dest, 1);
-	if (IS_ERR(fte)) {
-		err = PTR_ERR(fte);
-		mlx5_core_err(mdev, "fail to add psp rx framing err drop rule err=%d\n",
+	err = accel_psp_add_drop_rule(check->ft, spec, fs->rx_err_counter,
+				      &check->err_rule);
+	if (err) {
+		mlx5_core_err(mdev,
+			      "fail to add psp rx check framing drop rule err=%d\n",
 			      err);
-		goto out_drop_auth_fail_rule;
+		goto out_err;
 	}
-	rx_err->err_rule = fte;
 
 	/* add misc. errors drop rule */
 	memset(spec, 0, sizeof(*spec));
-	memset(&flow_act, 0, sizeof(flow_act));
-	/* create fte */
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP |
-			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest[0].counter = fs->rx_fs->rx_bad_counter;
-	fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, dest, 1);
-	if (IS_ERR(fte)) {
-		err = PTR_ERR(fte);
-		mlx5_core_err(mdev, "fail to add psp rx misc. err drop rule err=%d\n",
+	err = accel_psp_add_drop_rule(check->ft, spec, fs->rx_bad_counter,
+				      &check->bad_rule);
+	if (err) {
+		mlx5_core_err(mdev,
+			      "fail to add psp rx check misc. err drop rule err=%d\n",
 			      err);
-		goto out_drop_error_rule;
+		goto out_err;
 	}
-	rx_err->bad_rule = fte;
-
-	rx_err->copy_modify_hdr = modify_hdr;
 
 	goto out_spec;
 
-out_drop_error_rule:
-	mlx5_del_flow_rules(rx_err->err_rule);
-	rx_err->err_rule = NULL;
-out_drop_auth_fail_rule:
-	mlx5_del_flow_rules(rx_err->auth_fail_rule);
-	rx_err->auth_fail_rule = NULL;
-out_drop_rule:
-	mlx5_del_flow_rules(rx_err->rule);
-	rx_err->rule = NULL;
-out:
-	mlx5_modify_header_dealloc(mdev, modify_hdr);
+out_err:
+	accel_psp_fs_rx_check_ft_destroy(check);
 out_spec:
 	kfree(spec);
 	return err;
 }
 
-static int accel_psp_fs_rx_err_create_ft(struct mlx5e_psp_fs *fs,
-					 struct mlx5e_accel_fs_psp_prot *fs_prot,
-					 struct mlx5e_psp_rx_err *rx_err)
+static void
+accel_psp_fs_rx_decrypt_ft_destroy(struct mlx5e_psp_fs *fs,
+				   struct mlx5e_psp_rx_decrypt_table *decrypt)
 {
-	struct mlx5_flow_namespace *ns = mlx5e_fs_get_ns(fs->fs, false);
-	struct mlx5_flow_table_attr ft_attr = {};
-	struct mlx5_flow_table *ft;
-	int err;
-
-	ft_attr.max_fte = 2;
-	ft_attr.autogroup.max_num_groups = 2;
-	ft_attr.level = MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL; // MLX5E_ACCEL_FS_TCP_FT_LEVEL
-	ft_attr.prio = MLX5E_NIC_PRIO;
-	ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
-	if (IS_ERR(ft)) {
-		err = PTR_ERR(ft);
-		mlx5_core_err(fs->mdev, "fail to create psp rx inline ft err=%d\n", err);
-		return err;
-	}
-
-	rx_err->ft = ft;
-	err = accel_psp_fs_rx_err_add_rule(fs, fs_prot, rx_err);
-	if (err)
-		goto out_err;
-
-	return 0;
-
-out_err:
-	mlx5_destroy_flow_table(ft);
-	rx_err->ft = NULL;
-	return err;
-}
-
-static void accel_psp_fs_rx_fs_destroy(struct mlx5e_psp_fs *fs,
-				       struct mlx5e_accel_fs_psp_prot *fs_prot)
-{
-	if (fs_prot->def_rule) {
-		mlx5_del_flow_rules(fs_prot->def_rule);
-		fs_prot->def_rule = NULL;
-	}
-
-	if (fs_prot->rx_modify_hdr) {
-		mlx5_modify_header_dealloc(fs->mdev, fs_prot->rx_modify_hdr);
-		fs_prot->rx_modify_hdr = NULL;
-	}
-
-	if (fs_prot->miss_rule) {
-		mlx5_del_flow_rules(fs_prot->miss_rule);
-		fs_prot->miss_rule = NULL;
-	}
-
-	if (fs_prot->miss_group) {
-		mlx5_destroy_flow_group(fs_prot->miss_group);
-		fs_prot->miss_group = NULL;
-	}
-
-	if (fs_prot->ft) {
-		mlx5_destroy_flow_table(fs_prot->ft);
-		fs_prot->ft = NULL;
+	accel_psp_fs_del_flow_rule(&decrypt->rule);
+	if (decrypt->rx_modify_hdr) {
+		mlx5_modify_header_dealloc(fs->mdev, decrypt->rx_modify_hdr);
+		decrypt->rx_modify_hdr = NULL;
 	}
+	accel_psp_fs_del_flow_rule(&decrypt->miss_rule);
+	accel_psp_fs_destroy_flow_group(&decrypt->miss_group);
+	accel_psp_fs_destroy_ft(&decrypt->ft);
 }
 
 static void setup_fte_udp_psp(struct mlx5_flow_spec *spec, u16 udp_port)
@@ -325,70 +425,64 @@ static void setup_fte_udp_psp(struct mlx5_flow_spec *spec, u16 udp_port)
 	MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, ip_protocol, IPPROTO_UDP);
 }
 
-static int accel_psp_fs_rx_create_ft(struct mlx5e_psp_fs *fs,
-				     struct mlx5e_accel_fs_psp_prot *fs_prot)
+static int
+accel_psp_fs_rx_decrypt_ft_create(struct mlx5e_psp_fs *fs,
+				  struct mlx5e_psp_rx_decrypt_table *decrypt,
+				  struct mlx5_flow_destination *default_dest)
 {
-	struct mlx5_flow_namespace *ns = mlx5e_fs_get_ns(fs->fs, false);
 	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_modify_hdr *modify_hdr = NULL;
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_destination dest = {};
 	struct mlx5_core_dev *mdev = fs->mdev;
-	struct mlx5_flow_group *miss_group;
 	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
-	struct mlx5_flow_table *ft;
-	u32 *flow_group_in;
 	int err = 0;
 
-	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
 	spec = kvzalloc_obj(*spec);
-	if (!flow_group_in || !spec) {
-		err = -ENOMEM;
-		goto out;
-	}
+	if (!spec)
+		return -ENOMEM;
 
 	/* Create FT */
 	ft_attr.max_fte = 2;
-	ft_attr.level = MLX5E_ACCEL_FS_ESP_FT_LEVEL;
-	ft_attr.prio = MLX5E_NIC_PRIO;
+	ft_attr.level = MLX5E_ACCEL_FS_PSP_FT_LEVEL;
 	ft_attr.autogroup.num_reserved_entries = 1;
 	ft_attr.autogroup.max_num_groups = 1;
-	ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
-	if (IS_ERR(ft)) {
-		err = PTR_ERR(ft);
-		mlx5_core_err(mdev, "fail to create psp rx ft err=%d\n", err);
+	ft_attr.prio = MLX5E_NIC_PRIO;
+	err = accel_psp_fs_create_ft(fs, &ft_attr, &decrypt->ft);
+	if (err) {
+		mlx5_core_err(mdev, "fail to create psp rx decrypt ft err=%d\n",
+			      err);
 		goto out_err;
 	}
-	fs_prot->ft = ft;
 
 	/* Create miss_group */
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1);
-	miss_group = mlx5_create_flow_group(ft, flow_group_in);
-	if (IS_ERR(miss_group)) {
-		err = PTR_ERR(miss_group);
-		mlx5_core_err(mdev, "fail to create psp rx miss_group err=%d\n", err);
+	err = accel_psp_fs_create_miss_group(decrypt->ft, &decrypt->miss_group);
+	if (err) {
+		mlx5_core_err(mdev,
+			      "fail to create psp rx decrypt miss_group err=%d\n",
+			      err);
 		goto out_err;
 	}
-	fs_prot->miss_group = miss_group;
 
 	/* Create miss rule */
-	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &fs_prot->default_dest, 1);
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	rule = mlx5_add_flow_rules(decrypt->ft, spec, &flow_act, default_dest,
+				   1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
-		mlx5_core_err(mdev, "fail to create psp rx miss_rule err=%d\n", err);
+		mlx5_core_err(mdev,
+			      "fail to create psp rx decrypt miss_rule err=%d\n",
+			      err);
 		goto out_err;
 	}
-	fs_prot->miss_rule = rule;
+	decrypt->miss_rule = rule;
 
-	/* Add default Rx psp rule */
+	/* Add PSP RX decrypt rule */
 	setup_fte_udp_psp(spec, PSP_DEFAULT_UDP_PORT);
 	flow_act.crypto.type = MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_PSP;
 	/* Set bit[31, 30] PSP marker */
-	/* Set bit[29-23] psp_syndrome is set in error FT */
 #define MLX5E_PSP_MARKER_BIT (BIT(30) | BIT(31))
 	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
 	MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
@@ -403,275 +497,159 @@ static int accel_psp_fs_rx_create_ft(struct mlx5e_psp_fs *fs,
 		modify_hdr = NULL;
 		goto out_err;
 	}
-	fs_prot->rx_modify_hdr = modify_hdr;
+	decrypt->rx_modify_hdr = modify_hdr;
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 			  MLX5_FLOW_CONTEXT_ACTION_CRYPTO_DECRYPT |
 			  MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 	flow_act.modify_hdr = modify_hdr;
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest.ft = fs_prot->rx_err.ft;
-	rule = mlx5_add_flow_rules(fs_prot->ft, spec, &flow_act, &dest, 1);
+	dest.ft = fs->check.ft;
+	rule = mlx5_add_flow_rules(decrypt->ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
-		mlx5_core_err(mdev,
-			      "fail to add psp rule Rx decryption, err=%d, flow_act.action = %#04X\n",
-			      err, flow_act.action);
+		mlx5_core_err(mdev, "fail to add psp rx decrypt rule, err=%d\n",
+			      err);
 		goto out_err;
 	}
 
-	fs_prot->def_rule = rule;
-	goto out;
+	decrypt->rule = rule;
+	goto out_spec;
 
 out_err:
-	accel_psp_fs_rx_fs_destroy(fs, fs_prot);
-out:
-	kvfree(flow_group_in);
+	accel_psp_fs_rx_decrypt_ft_destroy(fs, decrypt);
+out_spec:
 	kvfree(spec);
 	return err;
 }
 
-static int accel_psp_fs_rx_destroy(struct mlx5e_psp_fs *fs, enum accel_fs_psp_type type)
+static void accel_psp_fs_rx_destroy(struct mlx5e_psp_fs *fs)
 {
-	struct mlx5e_accel_fs_psp_prot *fs_prot;
-	struct mlx5e_accel_fs_psp *accel_psp;
-
-	accel_psp = fs->rx_fs;
-
-	/* The netdev unreg already happened, so all offloaded rule are already removed */
-	fs_prot = &accel_psp->fs_prot[type];
-
-	accel_psp_fs_rx_fs_destroy(fs, fs_prot);
-
-	accel_psp_fs_rx_err_destroy_ft(fs, &fs_prot->rx_err);
+	struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(fs->fs, false);
+	int i;
 
-	return 0;
+	/* disconnect */
+	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++) {
+		mlx5_ttc_fwd_default_dest(ttc, fs_psp2tt(i));
+		accel_psp_fs_rx_decrypt_ft_destroy(fs, &fs->decrypt[i]);
+	}
+	accel_psp_fs_rx_check_ft_destroy(&fs->check);
+	accel_psp_fs_rx_ft_destroy(&fs->rx);
 }
 
-static int accel_psp_fs_rx_create(struct mlx5e_psp_fs *fs, enum accel_fs_psp_type type)
+static int accel_psp_fs_rx_create(struct mlx5e_psp_fs *fs,
+				  struct netlink_ext_ack *extack)
 {
 	struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(fs->fs, false);
-	struct mlx5e_accel_fs_psp_prot *fs_prot;
-	struct mlx5e_accel_fs_psp *accel_psp;
-	int err;
-
-	accel_psp = fs->rx_fs;
-	fs_prot = &accel_psp->fs_prot[type];
+	int i, err;
 
-	fs_prot->default_dest = mlx5_ttc_get_default_dest(ttc, fs_psp2tt(type));
-
-	err = accel_psp_fs_rx_err_create_ft(fs, fs_prot, &fs_prot->rx_err);
-	if (err)
+	err = accel_psp_fs_rx_ft_create(fs, &fs->rx);
+	if (err) {
+		NL_SET_ERR_MSG(extack, "Failed creating RX steering table");
 		return err;
+	}
 
-	err = accel_psp_fs_rx_create_ft(fs, fs_prot);
-	if (err)
-		accel_psp_fs_rx_err_destroy_ft(fs, &fs_prot->rx_err);
-
-	return err;
-}
-
-static int accel_psp_fs_rx_ft_get(struct mlx5e_psp_fs *fs, enum accel_fs_psp_type type)
-{
-	struct mlx5e_accel_fs_psp_prot *fs_prot;
-	struct mlx5_flow_destination dest = {};
-	struct mlx5e_accel_fs_psp *accel_psp;
-	struct mlx5_ttc_table *ttc;
-	int err = 0;
-
-	if (!fs || !fs->rx_fs)
-		return -EINVAL;
-
-	ttc = mlx5e_fs_get_ttc(fs->fs, false);
-	accel_psp = fs->rx_fs;
-	fs_prot = &accel_psp->fs_prot[type];
-	mutex_lock(&fs_prot->prot_mutex);
-	if (fs_prot->refcnt++)
-		goto out;
-
-	/* create FT */
-	err = accel_psp_fs_rx_create(fs, type);
+	err = accel_psp_fs_rx_check_ft_create(fs, &fs->check);
 	if (err) {
-		fs_prot->refcnt--;
-		goto out;
+		NL_SET_ERR_MSG(extack,
+			       "Failed creating RX check steering table");
+		goto err_ft;
 	}
 
-	/* connect */
-	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest.ft = fs_prot->ft;
-	mlx5_ttc_fwd_dest(ttc, fs_psp2tt(type), &dest);
-
-out:
-	mutex_unlock(&fs_prot->prot_mutex);
-	return err;
-}
-
-static void accel_psp_fs_rx_ft_put(struct mlx5e_psp_fs *fs, enum accel_fs_psp_type type)
-{
-	struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(fs->fs, false);
-	struct mlx5e_accel_fs_psp_prot *fs_prot;
-	struct mlx5e_accel_fs_psp *accel_psp;
-
-	accel_psp = fs->rx_fs;
-	fs_prot = &accel_psp->fs_prot[type];
-	mutex_lock(&fs_prot->prot_mutex);
-	if (--fs_prot->refcnt)
-		goto out;
-
-	/* disconnect */
-	mlx5_ttc_fwd_default_dest(ttc, fs_psp2tt(type));
+	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++) {
+		struct mlx5_flow_destination dest;
+
+		dest = mlx5_ttc_get_default_dest(ttc, fs_psp2tt(i));
+		err = accel_psp_fs_rx_decrypt_ft_create(fs, &fs->decrypt[i],
+							&dest);
+		if (err) {
+			NL_SET_ERR_MSG(extack,
+				       "Failed creating RX decrypt steering table");
+			goto err_decrypt_ft;
+		}
+
+		dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+		dest.ft = fs->decrypt[i].ft;
+		mlx5_ttc_fwd_dest(ttc, fs_psp2tt(i), &dest);
+	}
 
-	/* remove FT */
-	accel_psp_fs_rx_destroy(fs, type);
+	return 0;
 
-out:
-	mutex_unlock(&fs_prot->prot_mutex);
+err_decrypt_ft:
+	while (--i >= 0) {
+		mlx5_ttc_fwd_default_dest(ttc, fs_psp2tt(i));
+		accel_psp_fs_rx_decrypt_ft_destroy(fs, &fs->decrypt[i]);
+	}
+	accel_psp_fs_rx_check_ft_destroy(&fs->check);
+err_ft:
+	accel_psp_fs_rx_ft_destroy(&fs->rx);
+	return err;
 }
 
-static void accel_psp_fs_cleanup_rx(struct mlx5e_psp_fs *fs)
+static void accel_psp_fs_rx_cleanup(struct mlx5e_psp_fs *fs)
 {
-	struct mlx5e_accel_fs_psp_prot *fs_prot;
-	struct mlx5e_accel_fs_psp *accel_psp;
-	enum accel_fs_psp_type i;
-
-	if (!fs->rx_fs)
-		return;
-
-	accel_psp = fs->rx_fs;
-	mlx5_fc_destroy(fs->mdev, accel_psp->rx_bad_counter);
-	mlx5_fc_destroy(fs->mdev, accel_psp->rx_err_counter);
-	mlx5_fc_destroy(fs->mdev, accel_psp->rx_auth_fail_counter);
-	mlx5_fc_destroy(fs->mdev, accel_psp->rx_counter);
-	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++) {
-		fs_prot = &accel_psp->fs_prot[i];
-		mutex_destroy(&fs_prot->prot_mutex);
-		WARN_ON(fs_prot->refcnt);
-	}
-	kfree(fs->rx_fs);
-	fs->rx_fs = NULL;
+	accel_psp_fs_destroy_counter(fs->mdev, &fs->rx_bad_counter);
+	accel_psp_fs_destroy_counter(fs->mdev, &fs->rx_err_counter);
+	accel_psp_fs_destroy_counter(fs->mdev, &fs->rx_auth_fail_counter);
+	accel_psp_fs_destroy_counter(fs->mdev, &fs->rx_counter);
 }
 
-static int accel_psp_fs_init_rx(struct mlx5e_psp_fs *fs)
+static int accel_psp_fs_rx_init(struct mlx5e_psp_fs *fs)
 {
-	struct mlx5e_accel_fs_psp_prot *fs_prot;
-	struct mlx5e_accel_fs_psp *accel_psp;
 	struct mlx5_core_dev *mdev = fs->mdev;
-	struct mlx5_fc *flow_counter;
-	enum accel_fs_psp_type i;
 	int err;
 
-	accel_psp = kzalloc_obj(*accel_psp);
-	if (!accel_psp)
-		return -ENOMEM;
-
-	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++) {
-		fs_prot = &accel_psp->fs_prot[i];
-		mutex_init(&fs_prot->prot_mutex);
-	}
-
-	flow_counter = mlx5_fc_create(mdev, false);
-	if (IS_ERR(flow_counter)) {
+	err = accel_psp_fs_create_counter(mdev, &fs->rx_counter);
+	if (err) {
 		mlx5_core_warn(mdev,
-			       "fail to create psp rx flow counter err=%pe\n",
-			       flow_counter);
-		err = PTR_ERR(flow_counter);
+			       "fail to create psp rx flow counter err=%d\n",
+			       err);
 		goto out_err;
 	}
-	accel_psp->rx_counter = flow_counter;
 
-	flow_counter = mlx5_fc_create(mdev, false);
-	if (IS_ERR(flow_counter)) {
+	err = accel_psp_fs_create_counter(mdev, &fs->rx_auth_fail_counter);
+	if (err) {
 		mlx5_core_warn(mdev,
-			       "fail to create psp rx auth fail flow counter err=%pe\n",
-			       flow_counter);
-		err = PTR_ERR(flow_counter);
-		goto out_counter_err;
+			       "fail to create psp rx auth fail flow counter err=%d\n",
+			       err);
+		goto out_err;
 	}
-	accel_psp->rx_auth_fail_counter = flow_counter;
 
-	flow_counter = mlx5_fc_create(mdev, false);
-	if (IS_ERR(flow_counter)) {
+	err = accel_psp_fs_create_counter(mdev, &fs->rx_err_counter);
+	if (err) {
 		mlx5_core_warn(mdev,
-			       "fail to create psp rx error flow counter err=%pe\n",
-			       flow_counter);
-		err = PTR_ERR(flow_counter);
-		goto out_auth_fail_counter_err;
+			       "fail to create psp rx error flow counter err=%d\n",
+			       err);
+		goto out_err;
 	}
-	accel_psp->rx_err_counter = flow_counter;
 
-	flow_counter = mlx5_fc_create(mdev, false);
-	if (IS_ERR(flow_counter)) {
+	err = accel_psp_fs_create_counter(mdev, &fs->rx_bad_counter);
+	if (err) {
 		mlx5_core_warn(mdev,
-			       "fail to create psp rx bad flow counter err=%pe\n",
-			       flow_counter);
-		err = PTR_ERR(flow_counter);
-		goto out_err_counter_err;
+			       "fail to create psp rx bad flow counter err=%d\n",
+			       err);
+		goto out_err;
 	}
-	accel_psp->rx_bad_counter = flow_counter;
-
-	fs->rx_fs = accel_psp;
 
 	return 0;
 
-out_err_counter_err:
-	mlx5_fc_destroy(mdev, accel_psp->rx_err_counter);
-	accel_psp->rx_err_counter = NULL;
-out_auth_fail_counter_err:
-	mlx5_fc_destroy(mdev, accel_psp->rx_auth_fail_counter);
-	accel_psp->rx_auth_fail_counter = NULL;
-out_counter_err:
-	mlx5_fc_destroy(mdev, accel_psp->rx_counter);
-	accel_psp->rx_counter = NULL;
 out_err:
-	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++) {
-		fs_prot = &accel_psp->fs_prot[i];
-		mutex_destroy(&fs_prot->prot_mutex);
-	}
-	kfree(accel_psp);
-	fs->rx_fs = NULL;
-
+	accel_psp_fs_rx_cleanup(fs);
 	return err;
 }
 
 void mlx5_accel_psp_fs_cleanup_rx_tables(struct mlx5e_priv *priv)
 {
-	int i;
-
 	if (!priv->psp)
 		return;
 
-	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++)
-		accel_psp_fs_rx_ft_put(priv->psp->fs, i);
-}
-
-int mlx5_accel_psp_fs_init_rx_tables(struct mlx5e_priv *priv)
-{
-	struct mlx5e_psp_fs *fs;
-	int err, i;
-
-	if (!priv->psp)
-		return 0;
-
-	fs = priv->psp->fs;
-	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++) {
-		err = accel_psp_fs_rx_ft_get(fs, i);
-		if (err)
-			goto out_err;
-	}
-
-	return 0;
-
-out_err:
-	i--;
-	while (i >= 0) {
-		accel_psp_fs_rx_ft_put(fs, i);
-		--i;
-	}
-
-	return err;
+	netdev_lock(priv->netdev);
+	accel_psp_fs_rx_destroy(priv->psp->fs);
+	netdev_unlock(priv->netdev);
 }
 
-static int accel_psp_fs_tx_create_ft_table(struct mlx5e_psp_fs *fs)
+static int accel_psp_fs_tx_ft_create(struct mlx5e_psp_fs *fs,
+				     struct mlx5e_psp_tx_table *tx)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_table_attr ft_attr = {};
@@ -681,7 +659,6 @@ static int accel_psp_fs_tx_create_ft_table(struct mlx5e_psp_fs *fs)
 	u32 *in, *mc, *outer_headers_c;
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
-	struct mlx5e_psp_tx *tx_fs;
 	struct mlx5_flow_table *ft;
 	struct mlx5_flow_group *fg;
 	int err = 0;
@@ -700,8 +677,7 @@ static int accel_psp_fs_tx_create_ft_table(struct mlx5e_psp_fs *fs)
 	ft_attr.level = MLX5E_PSP_LEVEL;
 	ft_attr.autogroup.max_num_groups = 1;
 
-	tx_fs = fs->tx_fs;
-	ft = mlx5_create_flow_table(tx_fs->ns, &ft_attr);
+	ft = mlx5_create_flow_table(tx->ns, &ft_attr);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		mlx5_core_err(mdev, "PSP: fail to add psp tx flow table, err = %d\n", err);
@@ -727,7 +703,7 @@ static int accel_psp_fs_tx_create_ft_table(struct mlx5e_psp_fs *fs)
 			  MLX5_FLOW_CONTEXT_ACTION_CRYPTO_ENCRYPT |
 			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest.counter = tx_fs->tx_counter;
+	dest.counter = fs->tx_counter;
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -735,9 +711,9 @@ static int accel_psp_fs_tx_create_ft_table(struct mlx5e_psp_fs *fs)
 		goto err_add_flow_rule;
 	}
 
-	tx_fs->ft = ft;
-	tx_fs->fg = fg;
-	tx_fs->rule = rule;
+	tx->ft = ft;
+	tx->fg = fg;
+	tx->rule = rule;
 	goto out;
 
 err_add_flow_rule:
@@ -750,87 +726,35 @@ out:
 	return err;
 }
 
-static void accel_psp_fs_tx_destroy(struct mlx5e_psp_tx *tx_fs)
+static void accel_psp_fs_tx_ft_destroy(struct mlx5e_psp_tx_table *tx)
 {
-	if (!tx_fs->ft)
-		return;
-
-	mlx5_del_flow_rules(tx_fs->rule);
-	mlx5_destroy_flow_group(tx_fs->fg);
-	mlx5_destroy_flow_table(tx_fs->ft);
+	accel_psp_fs_del_flow_rule(&tx->rule);
+	accel_psp_fs_destroy_flow_group(&tx->fg);
+	accel_psp_fs_destroy_ft(&tx->ft);
 }
 
-static int accel_psp_fs_tx_ft_get(struct mlx5e_psp_fs *fs)
+static void accel_psp_fs_tx_cleanup(struct mlx5e_psp_fs *fs)
 {
-	struct mlx5e_psp_tx *tx_fs = fs->tx_fs;
-	int err = 0;
-
-	mutex_lock(&tx_fs->mutex);
-	if (tx_fs->refcnt++)
-		goto out;
-
-	err = accel_psp_fs_tx_create_ft_table(fs);
-	if (err)
-		tx_fs->refcnt--;
-out:
-	mutex_unlock(&tx_fs->mutex);
-	return err;
+	accel_psp_fs_destroy_counter(fs->mdev, &fs->tx_counter);
 }
 
-static void accel_psp_fs_tx_ft_put(struct mlx5e_psp_fs *fs)
-{
-	struct mlx5e_psp_tx *tx_fs = fs->tx_fs;
-
-	mutex_lock(&tx_fs->mutex);
-	if (--tx_fs->refcnt)
-		goto out;
-
-	accel_psp_fs_tx_destroy(tx_fs);
-out:
-	mutex_unlock(&tx_fs->mutex);
-}
-
-static void accel_psp_fs_cleanup_tx(struct mlx5e_psp_fs *fs)
-{
-	struct mlx5e_psp_tx *tx_fs = fs->tx_fs;
-
-	if (!tx_fs)
-		return;
-
-	mlx5_fc_destroy(fs->mdev, tx_fs->tx_counter);
-	mutex_destroy(&tx_fs->mutex);
-	WARN_ON(tx_fs->refcnt);
-	kfree(tx_fs);
-	fs->tx_fs = NULL;
-}
-
-static int accel_psp_fs_init_tx(struct mlx5e_psp_fs *fs)
+static int accel_psp_fs_tx_init(struct mlx5e_psp_fs *fs)
 {
 	struct mlx5_core_dev *mdev = fs->mdev;
-	struct mlx5_flow_namespace *ns;
-	struct mlx5_fc *flow_counter;
-	struct mlx5e_psp_tx *tx_fs;
+	int err;
 
-	ns = mlx5_get_flow_namespace(mdev, MLX5_FLOW_NAMESPACE_EGRESS_IPSEC);
-	if (!ns)
+	fs->tx.ns = mlx5_get_flow_namespace(mdev,
+					    MLX5_FLOW_NAMESPACE_EGRESS_IPSEC);
+	if (!fs->tx.ns)
 		return -EOPNOTSUPP;
 
-	tx_fs = kzalloc_obj(*tx_fs);
-	if (!tx_fs)
-		return -ENOMEM;
-
-	flow_counter = mlx5_fc_create(mdev, false);
-	if (IS_ERR(flow_counter)) {
+	err = accel_psp_fs_create_counter(mdev, &fs->tx_counter);
+	if (err) {
 		mlx5_core_warn(mdev,
-			       "fail to create psp tx flow counter err=%pe\n",
-			       flow_counter);
-		kfree(tx_fs);
-		return PTR_ERR(flow_counter);
+			       "fail to create psp tx flow counter err=%d\n",
+			       err);
+		return err;
 	}
-	tx_fs->tx_counter = flow_counter;
-	mutex_init(&tx_fs->mutex);
-	tx_fs->ns = ns;
-	fs->tx_fs = tx_fs;
 	return 0;
 }
 
@@ -838,32 +762,29 @@ static void
 mlx5e_accel_psp_fs_get_stats_fill(struct mlx5e_priv *priv,
 				  struct mlx5e_psp_stats *stats)
 {
-	struct mlx5e_psp_tx *tx_fs = priv->psp->fs->tx_fs;
+	struct mlx5e_psp_fs *fs = priv->psp->fs;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5e_accel_fs_psp *accel_psp;
-
-	accel_psp = (struct mlx5e_accel_fs_psp *)priv->psp->fs->rx_fs;
 
-	if (tx_fs->tx_counter)
-		mlx5_fc_query(mdev, tx_fs->tx_counter, &stats->psp_tx_pkts,
+	if (fs->tx_counter)
+		mlx5_fc_query(mdev, fs->tx_counter, &stats->psp_tx_pkts,
 			      &stats->psp_tx_bytes);
 
-	if (accel_psp->rx_counter)
-		mlx5_fc_query(mdev, accel_psp->rx_counter, &stats->psp_rx_pkts,
+	if (fs->rx_counter)
+		mlx5_fc_query(mdev, fs->rx_counter, &stats->psp_rx_pkts,
 			      &stats->psp_rx_bytes);
 
-	if (accel_psp->rx_auth_fail_counter)
-		mlx5_fc_query(mdev, accel_psp->rx_auth_fail_counter,
+	if (fs->rx_auth_fail_counter)
+		mlx5_fc_query(mdev, fs->rx_auth_fail_counter,
 			      &stats->psp_rx_pkts_auth_fail,
 			      &stats->psp_rx_bytes_auth_fail);
 
-	if (accel_psp->rx_err_counter)
-		mlx5_fc_query(mdev, accel_psp->rx_err_counter,
+	if (fs->rx_err_counter)
+		mlx5_fc_query(mdev, fs->rx_err_counter,
 			      &stats->psp_rx_pkts_frame_err,
 			      &stats->psp_rx_bytes_frame_err);
 
-	if (accel_psp->rx_bad_counter)
-		mlx5_fc_query(mdev, accel_psp->rx_bad_counter,
+	if (fs->rx_bad_counter)
+		mlx5_fc_query(mdev, fs->rx_bad_counter,
 			      &stats->psp_rx_pkts_drop,
 			      &stats->psp_rx_bytes_drop);
 }
@@ -873,21 +794,15 @@ void mlx5_accel_psp_fs_cleanup_tx_tables(struct mlx5e_priv *priv)
 	if (!priv->psp)
 		return;
 
-	accel_psp_fs_tx_ft_put(priv->psp->fs);
-}
-
-int mlx5_accel_psp_fs_init_tx_tables(struct mlx5e_priv *priv)
-{
-	if (!priv->psp)
-		return 0;
-
-	return accel_psp_fs_tx_ft_get(priv->psp->fs);
+	netdev_lock(priv->netdev);
+	accel_psp_fs_tx_ft_destroy(&priv->psp->fs->tx);
+	netdev_unlock(priv->netdev);
 }
 
 static void mlx5e_accel_psp_fs_cleanup(struct mlx5e_psp_fs *fs)
 {
-	accel_psp_fs_cleanup_rx(fs);
-	accel_psp_fs_cleanup_tx(fs);
+	accel_psp_fs_rx_cleanup(fs);
+	accel_psp_fs_tx_cleanup(fs);
 	kfree(fs);
 }
 
@@ -901,29 +816,63 @@ static struct mlx5e_psp_fs *mlx5e_accel_psp_fs_init(struct mlx5e_priv *priv)
 		return ERR_PTR(-ENOMEM);
 
 	fs->mdev = priv->mdev;
-	err = accel_psp_fs_init_tx(fs);
+	err = accel_psp_fs_tx_init(fs);
 	if (err)
 		goto err_tx;
 
 	fs->fs = priv->fs;
-	err = accel_psp_fs_init_rx(fs);
+	err = accel_psp_fs_rx_init(fs);
 	if (err)
 		goto err_rx;
 
 	return fs;
 
 err_rx:
-	accel_psp_fs_cleanup_tx(fs);
+	accel_psp_fs_tx_cleanup(fs);
 err_tx:
 	kfree(fs);
 	return ERR_PTR(err);
 }
 
+static int accel_psp_fs_create(struct mlx5e_priv *priv,
+			       struct netlink_ext_ack *extack)
+{
+	int err;
+
+	err = accel_psp_fs_rx_create(priv->psp->fs, extack);
+	if (err)
+		return err;
+
+	err = accel_psp_fs_tx_ft_create(priv->psp->fs, &priv->psp->fs->tx);
+	if (err) {
+		NL_SET_ERR_MSG(extack, "Failed creating TX steering table");
+		accel_psp_fs_rx_destroy(priv->psp->fs);
+	}
+	return err;
+}
+
+static void accel_psp_fs_destroy(struct mlx5e_priv *priv)
+{
+	accel_psp_fs_tx_ft_destroy(&priv->psp->fs->tx);
+	accel_psp_fs_rx_destroy(priv->psp->fs);
+}
+
 static int
 mlx5e_psp_set_config(struct psp_dev *psd, struct psp_dev_config *conf,
 		     struct netlink_ext_ack *extack)
 {
-	return 0; /* TODO: this should actually do things to the device */
+	struct mlx5e_priv *priv = netdev_priv(psd->main_netdev);
+	bool psp_enabled = psd->config.versions;
+	bool enable_psp = conf->versions;
+	int err = 0;
+
+	netdev_lock(priv->netdev);
+	if (!psp_enabled && enable_psp)
+		err = accel_psp_fs_create(priv, extack);
+	else if (psp_enabled && !enable_psp)
+		accel_psp_fs_destroy(priv);
+	netdev_unlock(priv->netdev);
+	return err;
 }
 
 static int
@@ -1072,21 +1021,21 @@ void mlx5e_psp_unregister(struct mlx5e_priv *priv)
 {
 	struct mlx5e_psp *psp = priv->psp;
 
-	if (!psp || !psp->psp)
+	if (!psp || !psp->psd)
 		return;
 
-	psp_dev_unregister(psp->psp);
-	psp->psp = NULL;
+	psp_dev_unregister(psp->psd);
+	psp->psd = NULL;
 }
 
-void mlx5e_psp_register(struct mlx5e_priv *priv)
+int mlx5e_psp_register(struct mlx5e_priv *priv)
 {
 	struct mlx5e_psp *psp = priv->psp;
 	struct psp_dev *psd;
 
 	/* FW Caps missing */
 	if (!priv->psp)
-		return;
+		return 0;
 
 	psp->caps.assoc_drv_spc = sizeof(u32);
 	psp->caps.versions = 1 << PSP_VERSION_HDR0_AES_GCM_128;
@@ -1098,9 +1047,11 @@ void mlx5e_psp_register(struct mlx5e_priv *priv)
 	if (IS_ERR(psd)) {
 		mlx5_core_err(priv->mdev, "PSP failed to register due to %pe\n",
 			      psd);
-		return;
+		return PTR_ERR(psd);
 	}
-	psp->psp = psd;
+	psp->psd = psd;
+
+	return 0;
 }
 
 int mlx5e_psp_init(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h
index 6b62fef0d9a7..3f441e7dd55a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h
@@ -23,7 +23,7 @@ struct mlx5e_psp_stats {
 };
 
 struct mlx5e_psp {
-	struct psp_dev *psp;
+	struct psp_dev *psd;
 	struct psp_dev_caps caps;
 	struct mlx5e_psp_fs *fs;
 	atomic_t tx_key_cnt;
@@ -43,33 +43,21 @@ static inline bool mlx5_is_psp_device(struct mlx5_core_dev *mdev)
 	return true;
 }
 
-int mlx5_accel_psp_fs_init_rx_tables(struct mlx5e_priv *priv);
 void mlx5_accel_psp_fs_cleanup_rx_tables(struct mlx5e_priv *priv);
-int mlx5_accel_psp_fs_init_tx_tables(struct mlx5e_priv *priv);
 void mlx5_accel_psp_fs_cleanup_tx_tables(struct mlx5e_priv *priv);
-void mlx5e_psp_register(struct mlx5e_priv *priv);
+int mlx5e_psp_register(struct mlx5e_priv *priv);
 void mlx5e_psp_unregister(struct mlx5e_priv *priv);
 int mlx5e_psp_init(struct mlx5e_priv *priv);
 void mlx5e_psp_cleanup(struct mlx5e_priv *priv);
 #else
-static inline int mlx5_accel_psp_fs_init_rx_tables(struct mlx5e_priv *priv)
-{
-	return 0;
-}
-
 static inline void mlx5_accel_psp_fs_cleanup_rx_tables(struct mlx5e_priv *priv) { }
-static inline int mlx5_accel_psp_fs_init_tx_tables(struct mlx5e_priv *priv)
-{
-	return 0;
-}
-
 static inline void mlx5_accel_psp_fs_cleanup_tx_tables(struct mlx5e_priv *priv) { }
 static inline bool mlx5_is_psp_device(struct mlx5_core_dev *mdev)
 {
 	return false;
 }
 
-static inline void mlx5e_psp_register(struct mlx5e_priv *priv) { }
+static inline int mlx5e_psp_register(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_psp_unregister(struct mlx5e_priv *priv) { }
 static inline int mlx5e_psp_init(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_psp_cleanup(struct mlx5e_priv *priv) { }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c
index ef7f5338540f..348fd7a96261 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c
@@ -14,12 +14,6 @@
 #include "en_accel/psp_rxtx.h"
 #include "en_accel/psp.h"
 
-enum {
-	MLX5E_PSP_OFFLOAD_RX_SYNDROME_DECRYPTED,
-	MLX5E_PSP_OFFLOAD_RX_SYNDROME_AUTH_FAILED,
-	MLX5E_PSP_OFFLOAD_RX_SYNDROME_BAD_TRAILER,
-};
-
 static void mlx5e_psp_set_swp(struct sk_buff *skb,
 			      struct mlx5e_accel_tx_psp_state *psp_st,
 			      struct mlx5_wqe_eth_seg *eseg)
@@ -122,16 +116,11 @@ out:
 bool mlx5e_psp_offload_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
 				     struct mlx5_cqe64 *cqe)
 {
-	u32 psp_meta_data = be32_to_cpu(cqe->ft_metadata);
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	u16 dev_id = priv->psp->psp->id;
+	u16 dev_id = priv->psp->psd->id;
 	bool strip_icv = true;
 	u8 generation = 0;
 
-	/* TBD: report errors as SW counters to ethtool, any further handling ? */
-	if (MLX5_PSP_METADATA_SYNDROME(psp_meta_data) != MLX5E_PSP_OFFLOAD_RX_SYNDROME_DECRYPTED)
-		goto drop;
-
 	if (psp_dev_rcv(skb, dev_id, generation, strip_icv))
 		goto drop;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.h
index 70289c921bd6..2b080c39cc37 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.h
@@ -10,9 +10,8 @@
 #include "en.h"
 #include "en/txrx.h"
 
-/* Bit30: PSP marker, Bit29-23: PSP syndrome, Bit22-0: PSP obj id */
+/* Bit30: PSP marker, Bit22-0: PSP obj id */
 #define MLX5_PSP_METADATA_MARKER(metadata)  ((((metadata) >> 30) & 0x3) == 0x3)
-#define MLX5_PSP_METADATA_SYNDROME(metadata) (((metadata) >> 23) & GENMASK(6, 0))
 #define MLX5_PSP_METADATA_HANDLE(metadata)  ((metadata) & GENMASK(22, 0))
 
 struct mlx5e_accel_tx_psp_state {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c1acb9012d3f..0d8248f32fe5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -6193,7 +6193,7 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv)
 	return 0;
 }
 
-static void mlx5e_nic_enable(struct mlx5e_priv *priv)
+static int mlx5e_nic_enable(struct mlx5e_priv *priv)
 {
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -6201,7 +6201,9 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 
 	mlx5e_fs_init_l2_addr(priv->fs, netdev);
 	mlx5e_ipsec_init(priv);
-	mlx5e_psp_register(priv);
+	err = mlx5e_psp_register(priv);
+	if (err)
+		goto out_ipsec_cleanup;
 
 	err = mlx5e_macsec_init(priv);
 	if (err)
@@ -6224,7 +6226,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	mlx5e_pcie_cong_event_init(priv);
 	mlx5e_hv_vhca_stats_create(priv);
 	if (netdev->reg_state != NETREG_REGISTERED)
-		return;
+		return 0;
 	mlx5e_dcbnl_init_app(priv);
 
 	mlx5e_nic_set_rx_mode(priv);
@@ -6237,6 +6239,12 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	netdev_unlock(netdev);
 	netif_device_attach(netdev);
 	rtnl_unlock();
+
+	return 0;
+
+out_ipsec_cleanup:
+	mlx5e_ipsec_cleanup(priv);
+	return err;
 }
 
 static void mlx5e_nic_disable(struct mlx5e_priv *priv)
@@ -6618,13 +6626,18 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 	if (err)
 		goto err_cleanup_tx;
 
-	if (profile->enable)
-		profile->enable(priv);
+	if (profile->enable) {
+		err = profile->enable(priv);
+		if (err)
+			goto err_cleanup_rx;
+	}
 
 	mlx5e_update_features(priv->netdev);
 
 	return 0;
 
+err_cleanup_rx:
+	profile->cleanup_rx(priv);
 err_cleanup_tx:
 	profile->cleanup_tx(priv);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index c8b76d301c92..603051ab1eaa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1262,9 +1262,11 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv)
 	mlx5e_rep_neigh_cleanup(rpriv);
 }
 
-static void mlx5e_rep_enable(struct mlx5e_priv *priv)
+static int mlx5e_rep_enable(struct mlx5e_priv *priv)
 {
 	mlx5e_set_netdev_mtu_boundaries(priv);
+
+	return 0;
 }
 
 static void mlx5e_rep_disable(struct mlx5e_priv *priv)
@@ -1322,7 +1324,7 @@ static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event
 	return NOTIFY_DONE;
 }
 
-static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
+static int mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 {
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -1357,6 +1359,8 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 	netdev_unlock(netdev);
 	netif_device_attach(netdev);
 	rtnl_unlock();
+
+	return 0;
 }
 
 static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 6fbc0441c4b8..04af54b704d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1081,7 +1081,7 @@ static void mlx5e_shampo_update_ipv4_udp_hdr(struct mlx5e_rq *rq, struct iphdr *
 	struct udphdr *uh;
 
 	uh = (struct udphdr *)(skb->data + udp_off);
-	uh->len = htons(skb->len - udp_off);
+	udp_set_len_short(uh, skb->len - udp_off);
 
 	if (uh->check)
 		uh->check = ~udp_v4_check(skb->len - udp_off, ipv4->saddr,
@@ -1100,7 +1100,7 @@ static void mlx5e_shampo_update_ipv6_udp_hdr(struct mlx5e_rq *rq, struct ipv6hdr
 	struct udphdr *uh;
 
 	uh = (struct udphdr *)(skb->data + udp_off);
-	uh->len = htons(skb->len - udp_off);
+	udp_set_len_short(uh, skb->len - udp_off);
 
 	if (uh->check)
 		uh->check = ~udp_v6_check(skb->len - udp_off, &ipv6->saddr,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index accc26d1a872..1dcdb86690bb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -113,7 +113,7 @@ static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv)
 	/* Fill UDP header */
 	udph->source = htons(9);
 	udph->dest = htons(9); /* Discard Protocol */
-	udph->len = htons(sizeof(struct mlx5ehdr) + sizeof(struct udphdr));
+	udp_set_len_short(udph, sizeof(struct mlx5ehdr) + sizeof(struct udphdr));
 	udph->check = 0;
 
 	/* Fill IP header */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 6e50311faa27..36b00a856bc2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -74,7 +74,7 @@ static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *
 		memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len);
 		dl_port->attrs.switch_id.id_len = ppid.id_len;
 		devlink_port_attrs_pci_pf_set(dl_port, controller_num, pfnum,
-					      true);
+					      false);
 	}
 }
 
@@ -134,13 +134,16 @@ static void mlx5_esw_offloads_sf_devlink_port_attrs_set(struct mlx5_eswitch *esw
 {
 	struct mlx5_core_dev *dev = esw->dev;
 	struct netdev_phys_item_id ppid = {};
+	u32 hpf_ctrl;
 	u16 pfnum;
 
 	pfnum = mlx5_esw_sf_controller_to_pfnum(dev, controller);
+	hpf_ctrl = mlx5_esw_get_hpf_host_number(dev) + 1;
 	mlx5_esw_get_port_parent_id(dev, &ppid);
 	memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len);
 	dl_port->attrs.switch_id.id_len = ppid.id_len;
-	devlink_port_attrs_pci_sf_set(dl_port, controller, pfnum, sfnum, !!controller);
+	devlink_port_attrs_pci_sf_set(dl_port, controller, pfnum, sfnum,
+				      controller == hpf_ctrl);
 }
 
 int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
@@ -268,7 +271,6 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_vport *vport)
 	dl_port = vport->dl_port;
 	mlx5_esw_devlink_port_res_unregister(&dl_port->dl_port);
 
-	mlx5_esw_qos_vport_update_parent(vport, NULL, NULL);
 	devl_rate_leaf_destroy(&dl_port->dl_port);
 
 	devl_port_unregister(&dl_port->dl_port);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index faccc60fc93a..0d20f51b9702 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -11,57 +11,8 @@
 /* Minimum supported BW share value by the HW is 1 Mbit/sec */
 #define MLX5_MIN_BW_SHARE 1
 
-/* Holds rate nodes associated with an E-Switch. */
-struct mlx5_qos_domain {
-	/* Serializes access to all qos changes in the qos domain. */
-	struct mutex lock;
-	/* List of all mlx5_esw_sched_nodes. */
-	struct list_head nodes;
-};
-
-static void esw_qos_lock(struct mlx5_eswitch *esw)
-{
-	mutex_lock(&esw->qos.domain->lock);
-}
-
-static void esw_qos_unlock(struct mlx5_eswitch *esw)
-{
-	mutex_unlock(&esw->qos.domain->lock);
-}
-
-static void esw_assert_qos_lock_held(struct mlx5_eswitch *esw)
-{
-	lockdep_assert_held(&esw->qos.domain->lock);
-}
-
-static struct mlx5_qos_domain *esw_qos_domain_alloc(void)
-{
-	struct mlx5_qos_domain *qos_domain;
-
-	qos_domain = kzalloc_obj(*qos_domain);
-	if (!qos_domain)
-		return NULL;
-
-	mutex_init(&qos_domain->lock);
-	INIT_LIST_HEAD(&qos_domain->nodes);
-
-	return qos_domain;
-}
-
-static int esw_qos_domain_init(struct mlx5_eswitch *esw)
-{
-	esw->qos.domain = esw_qos_domain_alloc();
-
-	return esw->qos.domain ? 0 : -ENOMEM;
-}
-
-static void esw_qos_domain_release(struct mlx5_eswitch *esw)
-{
-	kfree(esw->qos.domain);
-	esw->qos.domain = NULL;
-}
-
 enum sched_node_type {
+	SCHED_NODE_TYPE_ROOT,
 	SCHED_NODE_TYPE_VPORTS_TSAR,
 	SCHED_NODE_TYPE_VPORT,
 	SCHED_NODE_TYPE_TC_ARBITER_TSAR,
@@ -94,7 +45,9 @@ struct mlx5_esw_sched_node {
 	enum sched_node_type type;
 	/* The eswitch this node belongs to. */
 	struct mlx5_eswitch *esw;
-	/* The children nodes of this node, empty list for leaf nodes. */
+	/* The children nodes of this node, empty list for leaf nodes.
+	 * Can be from multiple E-Switches.
+	 */
 	struct list_head children;
 	/* Valid only if this node is associated with a vport. */
 	struct mlx5_vport *vport;
@@ -106,16 +59,63 @@ struct mlx5_esw_sched_node {
 	u32 tc_bw[DEVLINK_RATE_TCS_MAX];
 };
 
-static void esw_qos_node_attach_to_parent(struct mlx5_esw_sched_node *node)
+/* Locking notes:
+ * QoS changes are normally protected by the shd lock. But on older HW shd
+ * might not be created at all, so there needs to be a fallback serialization
+ * mechanism. This is esw->state_lock.
+ * Callers into QoS hold a combination of RTNL, devlink instance lock and
+ * esw->state_lock. Devlink rate ops additionally hold the shd lock if it
+ * exists.
+ * - VF rate ops use esw_qos_lock/esw_qos_unlock.
+ * - callers with esw->state_lock held use esw_qos_shd_lock/esw_qos_shd_unlock.
+ * - devlink callers use esw_qos_devlink_lock/esw_qos_devlink_unlock.
+ */
+static void esw_assert_qos_lock_held(struct mlx5_core_dev *dev)
 {
-	if (!node->parent) {
-		/* Root children are assigned a depth level of 2. */
-		node->level = 2;
-		list_add_tail(&node->entry, &node->esw->qos.domain->nodes);
-	} else {
-		node->level = node->parent->level + 1;
-		list_add_tail(&node->entry, &node->parent->children);
-	}
+	if (dev->shd)
+		devl_assert_locked(dev->shd);
+	else
+		lockdep_assert_held(&dev->priv.eswitch->state_lock);
+}
+
+static void esw_qos_lock(struct mlx5_core_dev *dev)
+{
+	if (dev->shd)
+		devl_lock(dev->shd);
+	else
+		mutex_lock(&dev->priv.eswitch->state_lock);
+}
+
+static void esw_qos_unlock(struct mlx5_core_dev *dev)
+{
+	if (dev->shd)
+		devl_unlock(dev->shd);
+	else
+		mutex_unlock(&dev->priv.eswitch->state_lock);
+}
+
+static void esw_qos_shd_lock(struct mlx5_core_dev *dev)
+{
+	if (dev->shd)
+		devl_lock(dev->shd);
+}
+
+static void esw_qos_shd_unlock(struct mlx5_core_dev *dev)
+{
+	if (dev->shd)
+		devl_unlock(dev->shd);
+}
+
+static void esw_qos_devlink_lock(struct mlx5_core_dev *dev)
+{
+	if (!dev->shd)
+		mutex_lock(&dev->priv.eswitch->state_lock);
+}
+
+static void esw_qos_devlink_unlock(struct mlx5_core_dev *dev)
+{
+	if (!dev->shd)
+		mutex_unlock(&dev->priv.eswitch->state_lock);
 }
 
 static int esw_qos_num_tcs(struct mlx5_core_dev *dev)
@@ -125,14 +125,14 @@ static int esw_qos_num_tcs(struct mlx5_core_dev *dev)
 	return num_tcs < DEVLINK_RATE_TCS_MAX ? num_tcs : DEVLINK_RATE_TCS_MAX;
 }
 
-static void
-esw_qos_node_set_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_node *parent)
+static void esw_qos_node_set_parent(struct mlx5_esw_sched_node *node,
+				    struct mlx5_esw_sched_node *parent)
 {
-	list_del_init(&node->entry);
 	node->parent = parent;
-	if (parent)
-		node->esw = parent->esw;
-	esw_qos_node_attach_to_parent(node);
+	node->esw = parent->esw;
+	node->level = parent->level + 1;
+	list_del(&node->entry);
+	list_add_tail(&node->entry, &parent->children);
 }
 
 static void esw_qos_nodes_set_parent(struct list_head *nodes,
@@ -321,22 +321,19 @@ static int esw_qos_create_rate_limit_element(struct mlx5_esw_sched_node *node,
 	return esw_qos_node_create_sched_element(node, sched_ctx, extack);
 }
 
-static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw,
-					      struct mlx5_esw_sched_node *parent)
+static u32
+esw_qos_calculate_min_rate_divider(struct mlx5_esw_sched_node *parent)
 {
-	struct list_head *nodes = parent ? &parent->children : &esw->qos.domain->nodes;
-	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	u32 fw_max_bw_share = MLX5_CAP_QOS(parent->esw->dev, max_tsar_bw_share);
 	struct mlx5_esw_sched_node *node;
 	u32 max_guarantee = 0;
 
 	/* Find max min_rate across all nodes.
 	 * This will correspond to fw_max_bw_share in the final bw_share calculation.
 	 */
-	list_for_each_entry(node, nodes, entry) {
-		if (node->esw == esw && node->ix != esw->qos.root_tsar_ix &&
-		    node->min_rate > max_guarantee)
+	list_for_each_entry(node, &parent->children, entry)
+		if (node->min_rate > max_guarantee)
 			max_guarantee = node->min_rate;
-	}
 
 	if (max_guarantee)
 		return max_t(u32, max_guarantee / fw_max_bw_share, 1);
@@ -368,18 +365,13 @@ static void esw_qos_update_sched_node_bw_share(struct mlx5_esw_sched_node *node,
 	esw_qos_sched_elem_config(node, node->max_rate, bw_share, extack);
 }
 
-static void esw_qos_normalize_min_rate(struct mlx5_eswitch *esw,
-				       struct mlx5_esw_sched_node *parent,
+static void esw_qos_normalize_min_rate(struct mlx5_esw_sched_node *parent,
 				       struct netlink_ext_ack *extack)
 {
-	struct list_head *nodes = parent ? &parent->children : &esw->qos.domain->nodes;
-	u32 divider = esw_qos_calculate_min_rate_divider(esw, parent);
+	u32 divider = esw_qos_calculate_min_rate_divider(parent);
 	struct mlx5_esw_sched_node *node;
 
-	list_for_each_entry(node, nodes, entry) {
-		if (node->esw != esw || node->ix == esw->qos.root_tsar_ix)
-			continue;
-
+	list_for_each_entry(node, &parent->children, entry) {
 		/* Vports TC TSARs don't have a minimum rate configured,
 		 * so there's no need to update the bw_share on them.
 		 */
@@ -391,7 +383,7 @@ static void esw_qos_normalize_min_rate(struct mlx5_eswitch *esw,
 		if (list_empty(&node->children))
 			continue;
 
-		esw_qos_normalize_min_rate(node->esw, node, extack);
+		esw_qos_normalize_min_rate(node, extack);
 	}
 }
 
@@ -412,14 +404,11 @@ static u32 esw_qos_calculate_tc_bw_divider(u32 *tc_bw)
 static int esw_qos_set_node_min_rate(struct mlx5_esw_sched_node *node,
 				     u32 min_rate, struct netlink_ext_ack *extack)
 {
-	struct mlx5_eswitch *esw = node->esw;
-
 	if (min_rate == node->min_rate)
 		return 0;
 
 	node->min_rate = min_rate;
-	esw_qos_normalize_min_rate(esw, node->parent, extack);
-
+	esw_qos_normalize_min_rate(node->parent, extack);
 	return 0;
 }
 
@@ -460,6 +449,7 @@ esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node,
 	struct mlx5_esw_sched_node *parent = vport_node->parent;
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
 	struct mlx5_core_dev *dev = vport_node->esw->dev;
+	struct mlx5_vport *vport = vport_node->vport;
 	void *attr;
 
 	if (!mlx5_qos_element_type_supported(
@@ -471,11 +461,17 @@ esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node,
 	MLX5_SET(scheduling_context, sched_ctx, element_type,
 		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
 	attr = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes);
-	MLX5_SET(vport_element, attr, vport_number, vport_node->vport->vport);
-	MLX5_SET(scheduling_context, sched_ctx, parent_element_id,
-		 parent ? parent->ix : vport_node->esw->qos.root_tsar_ix);
+	MLX5_SET(vport_element, attr, vport_number, vport->vport);
+	MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent->ix);
 	MLX5_SET(scheduling_context, sched_ctx, max_average_bw,
 		 vport_node->max_rate);
+	if (vport->dev != dev) {
+		/* The port is assigned to a node on another eswitch. */
+		MLX5_SET(vport_element, attr, eswitch_owner_vhca_id_valid,
+			 true);
+		MLX5_SET(vport_element, attr, eswitch_owner_vhca_id,
+			 MLX5_CAP_GEN(vport->dev, vhca_id));
+	}
 
 	return esw_qos_node_create_sched_element(vport_node, sched_ctx, extack);
 }
@@ -487,6 +483,7 @@ esw_qos_vport_tc_create_sched_element(struct mlx5_esw_sched_node *vport_tc_node,
 {
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
 	struct mlx5_core_dev *dev = vport_tc_node->esw->dev;
+	struct mlx5_vport *vport = vport_tc_node->vport;
 	void *attr;
 
 	if (!mlx5_qos_element_type_supported(
@@ -498,8 +495,7 @@ esw_qos_vport_tc_create_sched_element(struct mlx5_esw_sched_node *vport_tc_node,
 	MLX5_SET(scheduling_context, sched_ctx, element_type,
 		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC);
 	attr = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes);
-	MLX5_SET(vport_tc_element, attr, vport_number,
-		 vport_tc_node->vport->vport);
+	MLX5_SET(vport_tc_element, attr, vport_number, vport->vport);
 	MLX5_SET(vport_tc_element, attr, traffic_class, vport_tc_node->tc);
 	MLX5_SET(scheduling_context, sched_ctx, max_bw_obj_id,
 		 rate_limit_elem_ix);
@@ -507,13 +503,20 @@ esw_qos_vport_tc_create_sched_element(struct mlx5_esw_sched_node *vport_tc_node,
 		 vport_tc_node->parent->ix);
 	MLX5_SET(scheduling_context, sched_ctx, bw_share,
 		 vport_tc_node->bw_share);
+	if (vport->dev != dev) {
+		/* The port is assigned to a node on another eswitch. */
+		MLX5_SET(vport_tc_element, attr, eswitch_owner_vhca_id_valid,
+			 true);
+		MLX5_SET(vport_tc_element, attr, eswitch_owner_vhca_id,
+			 MLX5_CAP_GEN(vport->dev, vhca_id));
+	}
 
 	return esw_qos_node_create_sched_element(vport_tc_node, sched_ctx,
 						 extack);
 }
 
 static struct mlx5_esw_sched_node *
-__esw_qos_alloc_node(struct mlx5_eswitch *esw, u32 tsar_ix, enum sched_node_type type,
+__esw_qos_alloc_node(u32 tsar_ix, enum sched_node_type type,
 		     struct mlx5_esw_sched_node *parent)
 {
 	struct mlx5_esw_sched_node *node;
@@ -522,20 +525,12 @@ __esw_qos_alloc_node(struct mlx5_eswitch *esw, u32 tsar_ix, enum sched_node_type
 	if (!node)
 		return NULL;
 
-	node->esw = esw;
 	node->ix = tsar_ix;
 	node->type = type;
-	node->parent = parent;
 	INIT_LIST_HEAD(&node->children);
-	esw_qos_node_attach_to_parent(node);
-	if (!parent) {
-		/* The caller is responsible for inserting the node into the
-		 * parent list if necessary. This function can also be used with
-		 * a NULL parent, which doesn't necessarily indicate that it
-		 * refers to the root scheduling element.
-		 */
-		list_del_init(&node->entry);
-	}
+	INIT_LIST_HEAD(&node->entry);
+	if (parent)
+		esw_qos_node_set_parent(node, parent);
 
 	return node;
 }
@@ -570,7 +565,7 @@ static int esw_qos_create_vports_tc_node(struct mlx5_esw_sched_node *parent,
 					  SCHEDULING_HIERARCHY_E_SWITCH))
 		return -EOPNOTSUPP;
 
-	vports_tc_node = __esw_qos_alloc_node(parent->esw, 0,
+	vports_tc_node = __esw_qos_alloc_node(0,
 					      SCHED_NODE_TYPE_VPORTS_TC_TSAR,
 					      parent);
 	if (!vports_tc_node) {
@@ -665,7 +660,6 @@ static int esw_qos_create_tc_arbiter_sched_elem(
 		struct netlink_ext_ack *extack)
 {
 	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
-	u32 tsar_parent_ix;
 	void *attr;
 
 	if (!mlx5_qos_tsar_type_supported(tc_arbiter_node->esw->dev,
@@ -678,10 +672,8 @@ static int esw_qos_create_tc_arbiter_sched_elem(
 
 	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
 	MLX5_SET(tsar_element, attr, tsar_type, TSAR_ELEMENT_TSAR_TYPE_TC_ARB);
-	tsar_parent_ix = tc_arbiter_node->parent ? tc_arbiter_node->parent->ix :
-			 tc_arbiter_node->esw->qos.root_tsar_ix;
 	MLX5_SET(scheduling_context, tsar_ctx, parent_element_id,
-		 tsar_parent_ix);
+		 tc_arbiter_node->parent->ix);
 	MLX5_SET(scheduling_context, tsar_ctx, element_type,
 		 SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
 	MLX5_SET(scheduling_context, tsar_ctx, max_average_bw,
@@ -694,37 +686,36 @@ static int esw_qos_create_tc_arbiter_sched_elem(
 }
 
 static struct mlx5_esw_sched_node *
-__esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct mlx5_esw_sched_node *parent,
+__esw_qos_create_vports_sched_node(struct mlx5_esw_sched_node *parent,
 				   struct netlink_ext_ack *extack)
 {
 	struct mlx5_esw_sched_node *node;
-	u32 tsar_ix;
 	int err;
+	u32 ix;
 
-	err = esw_qos_create_node_sched_elem(esw->dev, esw->qos.root_tsar_ix, 0,
-					     0, &tsar_ix);
+	err = esw_qos_create_node_sched_elem(parent->esw->dev, parent->ix, 0, 0,
+					     &ix);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "E-Switch create TSAR for node failed");
 		return ERR_PTR(err);
 	}
 
-	node = __esw_qos_alloc_node(esw, tsar_ix, SCHED_NODE_TYPE_VPORTS_TSAR, parent);
+	node = __esw_qos_alloc_node(ix, SCHED_NODE_TYPE_VPORTS_TSAR, parent);
 	if (!node) {
 		NL_SET_ERR_MSG_MOD(extack, "E-Switch alloc node failed");
 		err = -ENOMEM;
 		goto err_alloc_node;
 	}
 
-	list_add_tail(&node->entry, &esw->qos.domain->nodes);
-	esw_qos_normalize_min_rate(esw, NULL, extack);
-	trace_mlx5_esw_node_qos_create(esw->dev, node, node->ix);
+	esw_qos_normalize_min_rate(parent, extack);
+	trace_mlx5_esw_node_qos_create(parent->esw->dev, node, node->ix);
 
 	return node;
 
 err_alloc_node:
-	if (mlx5_destroy_scheduling_element_cmd(esw->dev,
+	if (mlx5_destroy_scheduling_element_cmd(parent->esw->dev,
 						SCHEDULING_HIERARCHY_E_SWITCH,
-						tsar_ix))
+						ix))
 		NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR for node failed");
 	return ERR_PTR(err);
 }
@@ -738,7 +729,7 @@ esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct netlink_ext_ac
 	struct mlx5_esw_sched_node *node;
 	int err;
 
-	esw_assert_qos_lock_held(esw);
+	esw_assert_qos_lock_held(esw->dev);
 	if (!MLX5_CAP_QOS(esw->dev, log_esw_max_sched_depth))
 		return ERR_PTR(-EOPNOTSUPP);
 
@@ -746,7 +737,7 @@ esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct netlink_ext_ac
 	if (err)
 		return ERR_PTR(err);
 
-	node = __esw_qos_create_vports_sched_node(esw, NULL, extack);
+	node = __esw_qos_create_vports_sched_node(esw->qos.root, extack);
 	if (IS_ERR(node))
 		esw_qos_put(esw);
 
@@ -762,45 +753,54 @@ static void __esw_qos_destroy_node(struct mlx5_esw_sched_node *node, struct netl
 
 	trace_mlx5_esw_node_qos_destroy(esw->dev, node, node->ix);
 	esw_qos_destroy_node(node, extack);
-	esw_qos_normalize_min_rate(esw, NULL, extack);
+	esw_qos_normalize_min_rate(esw->qos.root, extack);
 }
 
 static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_esw_sched_node *root;
+	u32 root_ix;
 	int err;
 
 	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
 		return -EOPNOTSUPP;
 
-	err = esw_qos_create_node_sched_elem(esw->dev, 0, 0, 0,
-					     &esw->qos.root_tsar_ix);
+	err = esw_qos_create_node_sched_elem(esw->dev, 0, 0, 0, &root_ix);
 	if (err) {
 		esw_warn(dev, "E-Switch create root TSAR failed (%d)\n", err);
 		return err;
 	}
 
+	root = __esw_qos_alloc_node(root_ix, SCHED_NODE_TYPE_ROOT, NULL);
+	if (!root) {
+		esw_warn(dev, "E-Switch create root node failed\n");
+		err = -ENOMEM;
+		goto out_err;
+	}
+	root->esw = esw;
+	root->level = 1;
+	esw->qos.root = root;
 	refcount_set(&esw->qos.refcnt, 1);
 
 	return 0;
+out_err:
+	mlx5_destroy_scheduling_element_cmd(dev, SCHEDULING_HIERARCHY_E_SWITCH,
+					    root_ix);
+	return err;
 }
 
 static void esw_qos_destroy(struct mlx5_eswitch *esw)
 {
-	int err;
-
-	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
-						  SCHEDULING_HIERARCHY_E_SWITCH,
-						  esw->qos.root_tsar_ix);
-	if (err)
-		esw_warn(esw->dev, "E-Switch destroy root TSAR failed (%d)\n", err);
+	esw_qos_destroy_node(esw->qos.root, NULL);
+	esw->qos.root = NULL;
 }
 
 static int esw_qos_get(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack)
 {
 	int err = 0;
 
-	esw_assert_qos_lock_held(esw);
+	esw_assert_qos_lock_held(esw->dev);
 	if (!refcount_inc_not_zero(&esw->qos.refcnt)) {
 		/* esw_qos_create() set refcount to 1 only on success.
 		 * No need to decrement on failure.
@@ -813,7 +813,7 @@ static int esw_qos_get(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack)
 
 static void esw_qos_put(struct mlx5_eswitch *esw)
 {
-	esw_assert_qos_lock_held(esw);
+	esw_assert_qos_lock_held(esw->dev);
 	if (refcount_dec_and_test(&esw->qos.refcnt))
 		esw_qos_destroy(esw);
 }
@@ -866,8 +866,7 @@ esw_qos_create_vport_tc_sched_node(struct mlx5_vport *vport,
 	u8 tc = vports_tc_node->tc;
 	int err;
 
-	vport_tc_node = __esw_qos_alloc_node(vport_node->esw, 0,
-					     SCHED_NODE_TYPE_VPORT_TC,
+	vport_tc_node = __esw_qos_alloc_node(0, SCHED_NODE_TYPE_VPORT_TC,
 					     vports_tc_node);
 	if (!vport_tc_node)
 		return -ENOMEM;
@@ -959,7 +958,7 @@ esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type,
 		/* Increase the parent's level by 2 to account for both the
 		 * TC arbiter and the vports TC scheduling element.
 		 */
-		new_level = (parent ? parent->level : 2) + 2;
+		new_level = parent->level + 2;
 		max_level = 1 << MLX5_CAP_QOS(vport_node->esw->dev,
 					      log_esw_max_sched_depth);
 		if (new_level > max_level) {
@@ -970,7 +969,7 @@ esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type,
 		}
 	}
 
-	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
+	esw_assert_qos_lock_held(vport->dev);
 
 	if (type == SCHED_NODE_TYPE_RATE_LIMITER)
 		err = esw_qos_create_rate_limit_element(vport_node, extack);
@@ -997,7 +996,7 @@ esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type,
 err_sched_nodes:
 	if (type == SCHED_NODE_TYPE_RATE_LIMITER) {
 		esw_qos_node_destroy_sched_element(vport_node, NULL);
-		esw_qos_node_attach_to_parent(vport_node);
+		esw_qos_node_set_parent(vport_node, vport_node->parent);
 	} else {
 		esw_qos_tc_arbiter_scheduling_teardown(vport_node, NULL);
 	}
@@ -1055,7 +1054,7 @@ static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_a
 	vport_node->bw_share = 0;
 	memset(vport_node->tc_bw, 0, sizeof(vport_node->tc_bw));
 	list_del_init(&vport_node->entry);
-	esw_qos_normalize_min_rate(vport_node->esw, vport_node->parent, extack);
+	esw_qos_normalize_min_rate(vport_node->parent, extack);
 
 	trace_mlx5_esw_vport_qos_destroy(vport_node->esw->dev, vport);
 }
@@ -1068,7 +1067,7 @@ static int esw_qos_vport_enable(struct mlx5_vport *vport,
 	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
 	int err;
 
-	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
+	esw_assert_qos_lock_held(vport->dev);
 
 	esw_qos_node_set_parent(vport_node, parent);
 	if (type == SCHED_NODE_TYPE_VPORT)
@@ -1079,9 +1078,10 @@ static int esw_qos_vport_enable(struct mlx5_vport *vport,
 		return err;
 
 	vport_node->type = type;
-	esw_qos_normalize_min_rate(vport_node->esw, parent, extack);
-	trace_mlx5_esw_vport_qos_create(vport->dev, vport, vport_node->max_rate,
-					vport_node->bw_share);
+	esw_qos_normalize_min_rate(parent, extack);
+	trace_mlx5_esw_vport_qos_create(vport_node->esw->dev, vport,
+					vport_node->bw_share,
+					vport_node->max_rate);
 
 	return 0;
 }
@@ -1092,22 +1092,20 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 {
 	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
 	struct mlx5_esw_sched_node *sched_node;
-	struct mlx5_eswitch *parent_esw;
 	int err;
 
-	esw_assert_qos_lock_held(esw);
+	esw_assert_qos_lock_held(vport->dev);
 	err = esw_qos_get(esw, extack);
 	if (err)
 		return err;
 
-	parent_esw = parent ? parent->esw : esw;
-	sched_node = __esw_qos_alloc_node(parent_esw, 0, type, parent);
+	if (!parent)
+		parent = esw->qos.root;
+	sched_node = __esw_qos_alloc_node(0, type, parent);
 	if (!sched_node) {
 		esw_qos_put(esw);
 		return -ENOMEM;
 	}
-	if (!parent)
-		list_add_tail(&sched_node->entry, &esw->qos.domain->nodes);
 
 	sched_node->max_rate = max_rate;
 	sched_node->min_rate = min_rate;
@@ -1125,33 +1123,23 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 
 static void mlx5_esw_qos_vport_disable_locked(struct mlx5_vport *vport)
 {
-	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
-
-	esw_assert_qos_lock_held(esw);
+	esw_assert_qos_lock_held(vport->dev);
 	if (!vport->qos.sched_node)
 		return;
 
 	esw_qos_vport_disable(vport, NULL);
 	mlx5_esw_qos_vport_qos_free(vport);
-	esw_qos_put(esw);
+	esw_qos_put(vport->dev->priv.eswitch);
 }
 
 void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport)
 {
 	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
-	struct mlx5_esw_sched_node *parent;
 
 	lockdep_assert_held(&esw->state_lock);
-	esw_qos_lock(esw);
-	if (!vport->qos.sched_node)
-		goto unlock;
-
-	parent = vport->qos.sched_node->parent;
-	WARN(parent, "Disabling QoS on port before detaching it from node");
-
+	esw_qos_shd_lock(vport->dev);
 	mlx5_esw_qos_vport_disable_locked(vport);
-unlock:
-	esw_qos_unlock(esw);
+	esw_qos_shd_unlock(vport->dev);
 }
 
 static int mlx5_esw_qos_set_vport_max_rate(struct mlx5_vport *vport, u32 max_rate,
@@ -1159,7 +1147,7 @@ static int mlx5_esw_qos_set_vport_max_rate(struct mlx5_vport *vport, u32 max_rat
 {
 	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
 
-	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
+	esw_assert_qos_lock_held(vport->dev);
 
 	if (!vport_node)
 		return mlx5_esw_qos_vport_enable(vport, SCHED_NODE_TYPE_VPORT, NULL, max_rate, 0,
@@ -1174,7 +1162,7 @@ static int mlx5_esw_qos_set_vport_min_rate(struct mlx5_vport *vport, u32 min_rat
 {
 	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
 
-	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
+	esw_assert_qos_lock_held(vport->dev);
 
 	if (!vport_node)
 		return mlx5_esw_qos_vport_enable(vport, SCHED_NODE_TYPE_VPORT, NULL, 0, min_rate,
@@ -1187,29 +1175,27 @@ static int mlx5_esw_qos_set_vport_min_rate(struct mlx5_vport *vport, u32 min_rat
 
 int mlx5_esw_qos_set_vport_rate(struct mlx5_vport *vport, u32 max_rate, u32 min_rate)
 {
-	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
 	int err;
 
-	esw_qos_lock(esw);
+	esw_qos_lock(vport->dev);
 	err = mlx5_esw_qos_set_vport_min_rate(vport, min_rate, NULL);
 	if (!err)
 		err = mlx5_esw_qos_set_vport_max_rate(vport, max_rate, NULL);
-	esw_qos_unlock(esw);
+	esw_qos_unlock(vport->dev);
 	return err;
 }
 
 bool mlx5_esw_qos_get_vport_rate(struct mlx5_vport *vport, u32 *max_rate, u32 *min_rate)
 {
-	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
 	bool enabled;
 
-	esw_qos_lock(esw);
+	esw_qos_shd_lock(vport->dev);
 	enabled = !!vport->qos.sched_node;
 	if (enabled) {
 		*max_rate = vport->qos.sched_node->max_rate;
 		*min_rate = vport->qos.sched_node->min_rate;
 	}
-	esw_qos_unlock(esw);
+	esw_qos_shd_unlock(vport->dev);
 	return enabled;
 }
 
@@ -1234,6 +1220,28 @@ static int esw_qos_vport_tc_check_type(enum sched_node_type curr_type,
 	return 0;
 }
 
+static bool esw_qos_validate_unsupported_tc_bw(struct mlx5_eswitch *esw,
+					       u32 *tc_bw)
+{
+	int i, num_tcs = esw_qos_num_tcs(esw->dev);
+
+	for (i = num_tcs; i < DEVLINK_RATE_TCS_MAX; i++)
+		if (tc_bw[i])
+			return false;
+
+	return true;
+}
+
+static bool esw_qos_vport_validate_unsupported_tc_bw(struct mlx5_vport *vport,
+						     u32 *tc_bw)
+{
+	struct mlx5_esw_sched_node *node = vport->qos.sched_node;
+	struct mlx5_eswitch *esw = node ?
+		node->parent->esw : vport->dev->priv.eswitch;
+
+	return esw_qos_validate_unsupported_tc_bw(esw, tc_bw);
+}
+
 static int esw_qos_vport_update(struct mlx5_vport *vport,
 				enum sched_node_type type,
 				struct mlx5_esw_sched_node *parent,
@@ -1245,7 +1253,7 @@ static int esw_qos_vport_update(struct mlx5_vport *vport,
 	u32 curr_tc_bw[DEVLINK_RATE_TCS_MAX] = {0};
 	int err;
 
-	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
+	esw_assert_qos_lock_held(vport->dev);
 	if (curr_type == type && curr_parent == parent)
 		return 0;
 
@@ -1253,8 +1261,15 @@ static int esw_qos_vport_update(struct mlx5_vport *vport,
 	if (err)
 		return err;
 
-	if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type)
+	if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) {
 		esw_qos_tc_arbiter_get_bw_shares(vport_node, curr_tc_bw);
+		if (!esw_qos_validate_unsupported_tc_bw(parent->esw,
+							curr_tc_bw)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Unsupported traffic classes on the new device");
+			return -EOPNOTSUPP;
+		}
+	}
 
 	esw_qos_vport_disable(vport, extack);
 
@@ -1275,11 +1290,10 @@ static int esw_qos_vport_update(struct mlx5_vport *vport,
 static int esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw_sched_node *parent,
 				       struct netlink_ext_ack *extack)
 {
-	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
 	struct mlx5_esw_sched_node *curr_parent;
 	enum sched_node_type type;
 
-	esw_assert_qos_lock_held(esw);
+	esw_assert_qos_lock_held(vport->dev);
 	curr_parent = vport->qos.sched_node->parent;
 	if (curr_parent == parent)
 		return 0;
@@ -1287,10 +1301,9 @@ static int esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw
 	/* Set vport QoS type based on parent node type if different from
 	 * default QoS; otherwise, use the vport's current QoS type.
 	 */
-	if (parent && parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+	if (parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
 		type = SCHED_NODE_TYPE_RATE_LIMITER;
-	else if (curr_parent &&
-		 curr_parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+	else if (curr_parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
 		type = SCHED_NODE_TYPE_VPORT;
 	else
 		type = vport->qos.sched_node->type;
@@ -1319,11 +1332,9 @@ static int esw_qos_switch_tc_arbiter_node_to_vports(
 	struct mlx5_esw_sched_node *node,
 	struct netlink_ext_ack *extack)
 {
-	u32 parent_tsar_ix = node->parent ?
-			     node->parent->ix : node->esw->qos.root_tsar_ix;
 	int err;
 
-	err = esw_qos_create_node_sched_elem(node->esw->dev, parent_tsar_ix,
+	err = esw_qos_create_node_sched_elem(node->esw->dev, node->parent->ix,
 					     node->max_rate, node->bw_share,
 					     &node->ix);
 	if (err) {
@@ -1378,8 +1389,8 @@ esw_qos_move_node(struct mlx5_esw_sched_node *curr_node)
 {
 	struct mlx5_esw_sched_node *new_node;
 
-	new_node = __esw_qos_alloc_node(curr_node->esw, curr_node->ix,
-					curr_node->type, NULL);
+	new_node = __esw_qos_alloc_node(curr_node->ix, curr_node->type,
+					curr_node->parent);
 	if (!new_node)
 		return ERR_PTR(-ENOMEM);
 
@@ -1489,41 +1500,16 @@ out:
 	return err;
 }
 
-static u32 mlx5_esw_qos_lag_link_speed_get(struct mlx5_core_dev *mdev,
-					   bool take_rtnl)
-{
-	struct ethtool_link_ksettings lksettings;
-	struct net_device *slave, *master;
-	u32 speed = SPEED_UNKNOWN;
-
-	slave = mlx5_uplink_netdev_get(mdev);
-	if (!slave)
-		goto out;
-
-	if (take_rtnl)
-		rtnl_lock();
-	master = netdev_master_upper_dev_get(slave);
-	if (master && !__ethtool_get_link_ksettings(master, &lksettings))
-		speed = lksettings.base.speed;
-	if (take_rtnl)
-		rtnl_unlock();
-
-out:
-	mlx5_uplink_netdev_put(mdev, slave);
-	return speed;
-}
-
 static int mlx5_esw_qos_max_link_speed_get(struct mlx5_core_dev *mdev, u32 *link_speed_max,
-					   bool take_rtnl,
 					   struct netlink_ext_ack *extack)
 {
 	int err;
 
-	if (!mlx5_lag_is_active(mdev))
+	if (!mlx5_lag_is_active(mdev) ||
+	    mlx5_lag_query_bond_speed(mdev, link_speed_max) < 0 ||
+	    *link_speed_max == 0)
 		goto skip_lag;
 
-	*link_speed_max = mlx5_esw_qos_lag_link_speed_get(mdev, take_rtnl);
-
 	if (*link_speed_max != (u32)SPEED_UNKNOWN)
 		return 0;
 
@@ -1560,7 +1546,8 @@ int mlx5_esw_qos_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32
 		return PTR_ERR(vport);
 
 	if (rate_mbps) {
-		err = mlx5_esw_qos_max_link_speed_get(esw->dev, &link_speed_max, false, NULL);
+		err = mlx5_esw_qos_max_link_speed_get(esw->dev, &link_speed_max,
+						      NULL);
 		if (err)
 			return err;
 
@@ -1570,9 +1557,9 @@ int mlx5_esw_qos_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32
 			return err;
 	}
 
-	esw_qos_lock(esw);
+	esw_qos_lock(vport->dev);
 	err = mlx5_esw_qos_set_vport_max_rate(vport, rate_mbps, NULL);
-	esw_qos_unlock(esw);
+	esw_qos_unlock(vport->dev);
 
 	return err;
 }
@@ -1598,7 +1585,7 @@ static int esw_qos_devlink_rate_to_mbps(struct mlx5_core_dev *mdev, const char *
 		return -EINVAL;
 	}
 
-	err = mlx5_esw_qos_max_link_speed_get(mdev, &link_speed_max, true, extack);
+	err = mlx5_esw_qos_max_link_speed_get(mdev, &link_speed_max, extack);
 	if (err)
 		return err;
 
@@ -1610,30 +1597,6 @@ static int esw_qos_devlink_rate_to_mbps(struct mlx5_core_dev *mdev, const char *
 	return 0;
 }
 
-static bool esw_qos_validate_unsupported_tc_bw(struct mlx5_eswitch *esw,
-					       u32 *tc_bw)
-{
-	int i, num_tcs = esw_qos_num_tcs(esw->dev);
-
-	for (i = num_tcs; i < DEVLINK_RATE_TCS_MAX; i++) {
-		if (tc_bw[i])
-			return false;
-	}
-
-	return true;
-}
-
-static bool esw_qos_vport_validate_unsupported_tc_bw(struct mlx5_vport *vport,
-						     u32 *tc_bw)
-{
-	struct mlx5_esw_sched_node *node = vport->qos.sched_node;
-	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
-
-	esw = (node && node->parent) ? node->parent->esw : esw;
-
-	return esw_qos_validate_unsupported_tc_bw(esw, tc_bw);
-}
-
 static bool esw_qos_tc_bw_disabled(u32 *tc_bw)
 {
 	int i;
@@ -1650,55 +1613,38 @@ static void esw_vport_qos_prune_empty(struct mlx5_vport *vport)
 {
 	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
 
-	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
+	esw_assert_qos_lock_held(vport->dev);
 	if (!vport_node)
 		return;
 
-	if (vport_node->parent || vport_node->max_rate ||
-	    vport_node->min_rate || !esw_qos_tc_bw_disabled(vport_node->tc_bw))
+	if (vport_node->parent != vport_node->esw->qos.root ||
+	    vport_node->max_rate || vport_node->min_rate ||
+	    !esw_qos_tc_bw_disabled(vport_node->tc_bw))
 		return;
 
 	mlx5_esw_qos_vport_disable_locked(vport);
 }
 
-int mlx5_esw_qos_init(struct mlx5_eswitch *esw)
-{
-	if (esw->qos.domain)
-		return 0;  /* Nothing to change. */
-
-	return esw_qos_domain_init(esw);
-}
-
-void mlx5_esw_qos_cleanup(struct mlx5_eswitch *esw)
-{
-	if (esw->qos.domain)
-		esw_qos_domain_release(esw);
-}
-
 /* Eswitch devlink rate API */
 
 int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void *priv,
 					    u64 tx_share, struct netlink_ext_ack *extack)
 {
 	struct mlx5_vport *vport = priv;
-	struct mlx5_eswitch *esw;
 	int err;
 
-	esw = vport->dev->priv.eswitch;
-	if (!mlx5_esw_allowed(esw))
+	if (!mlx5_esw_allowed(vport->dev->priv.eswitch))
 		return -EPERM;
 
 	err = esw_qos_devlink_rate_to_mbps(vport->dev, "tx_share", &tx_share, extack);
 	if (err)
 		return err;
 
-	esw_qos_lock(esw);
+	esw_qos_devlink_lock(vport->dev);
 	err = mlx5_esw_qos_set_vport_min_rate(vport, tx_share, extack);
-	if (err)
-		goto out;
-	esw_vport_qos_prune_empty(vport);
-out:
-	esw_qos_unlock(esw);
+	if (!err)
+		esw_vport_qos_prune_empty(vport);
+	esw_qos_devlink_unlock(vport->dev);
 	return err;
 }
 
@@ -1706,24 +1652,20 @@ int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *
 					  u64 tx_max, struct netlink_ext_ack *extack)
 {
 	struct mlx5_vport *vport = priv;
-	struct mlx5_eswitch *esw;
 	int err;
 
-	esw = vport->dev->priv.eswitch;
-	if (!mlx5_esw_allowed(esw))
+	if (!mlx5_esw_allowed(vport->dev->priv.eswitch))
 		return -EPERM;
 
 	err = esw_qos_devlink_rate_to_mbps(vport->dev, "tx_max", &tx_max, extack);
 	if (err)
 		return err;
 
-	esw_qos_lock(esw);
+	esw_qos_devlink_lock(vport->dev);
 	err = mlx5_esw_qos_set_vport_max_rate(vport, tx_max, extack);
-	if (err)
-		goto out;
-	esw_vport_qos_prune_empty(vport);
-out:
-	esw_qos_unlock(esw);
+	if (!err)
+		esw_vport_qos_prune_empty(vport);
+	esw_qos_devlink_unlock(vport->dev);
 	return err;
 }
 
@@ -1734,16 +1676,14 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf,
 {
 	struct mlx5_esw_sched_node *vport_node;
 	struct mlx5_vport *vport = priv;
-	struct mlx5_eswitch *esw;
 	bool disable;
 	int err = 0;
 
-	esw = vport->dev->priv.eswitch;
-	if (!mlx5_esw_allowed(esw))
+	if (!mlx5_esw_allowed(vport->dev->priv.eswitch))
 		return -EPERM;
 
 	disable = esw_qos_tc_bw_disabled(tc_bw);
-	esw_qos_lock(esw);
+	esw_qos_devlink_lock(vport->dev);
 
 	if (!esw_qos_vport_validate_unsupported_tc_bw(vport, tc_bw)) {
 		NL_SET_ERR_MSG_MOD(extack,
@@ -1777,7 +1717,7 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf,
 	if (!err)
 		esw_qos_set_tc_arbiter_bw_shares(vport_node, tc_bw, extack);
 unlock:
-	esw_qos_unlock(esw);
+	esw_qos_devlink_unlock(vport->dev);
 	return err;
 }
 
@@ -1787,18 +1727,17 @@ int mlx5_esw_devlink_rate_node_tc_bw_set(struct devlink_rate *rate_node,
 					 struct netlink_ext_ack *extack)
 {
 	struct mlx5_esw_sched_node *node = priv;
-	struct mlx5_eswitch *esw = node->esw;
 	bool disable;
 	int err;
 
-	if (!esw_qos_validate_unsupported_tc_bw(esw, tc_bw)) {
+	if (!esw_qos_validate_unsupported_tc_bw(node->esw, tc_bw)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "E-Switch traffic classes number is not supported");
 		return -EOPNOTSUPP;
 	}
 
 	disable = esw_qos_tc_bw_disabled(tc_bw);
-	esw_qos_lock(esw);
+	esw_qos_devlink_lock(node->esw->dev);
 	if (disable) {
 		err = esw_qos_node_disable_tc_arbitration(node, extack);
 		goto unlock;
@@ -1808,7 +1747,7 @@ int mlx5_esw_devlink_rate_node_tc_bw_set(struct devlink_rate *rate_node,
 	if (!err)
 		esw_qos_set_tc_arbiter_bw_shares(node, tc_bw, extack);
 unlock:
-	esw_qos_unlock(esw);
+	esw_qos_devlink_unlock(node->esw->dev);
 	return err;
 }
 
@@ -1823,9 +1762,9 @@ int mlx5_esw_devlink_rate_node_tx_share_set(struct devlink_rate *rate_node, void
 	if (err)
 		return err;
 
-	esw_qos_lock(esw);
+	esw_qos_devlink_lock(esw->dev);
 	err = esw_qos_set_node_min_rate(node, tx_share, extack);
-	esw_qos_unlock(esw);
+	esw_qos_devlink_unlock(esw->dev);
 	return err;
 }
 
@@ -1840,9 +1779,9 @@ int mlx5_esw_devlink_rate_node_tx_max_set(struct devlink_rate *rate_node, void *
 	if (err)
 		return err;
 
-	esw_qos_lock(esw);
+	esw_qos_devlink_lock(esw->dev);
 	err = esw_qos_sched_elem_config(node, tx_max, node->bw_share, extack);
-	esw_qos_unlock(esw);
+	esw_qos_devlink_unlock(esw->dev);
 	return err;
 }
 
@@ -1857,7 +1796,7 @@ int mlx5_esw_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv,
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	esw_qos_lock(esw);
+	esw_qos_devlink_lock(esw->dev);
 	if (esw->mode != MLX5_ESWITCH_OFFLOADS) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Rate node creation supported only in switchdev mode");
@@ -1870,10 +1809,9 @@ int mlx5_esw_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv,
 		err = PTR_ERR(node);
 		goto unlock;
 	}
-
 	*priv = node;
 unlock:
-	esw_qos_unlock(esw);
+	esw_qos_devlink_unlock(esw->dev);
 	return err;
 }
 
@@ -1883,25 +1821,53 @@ int mlx5_esw_devlink_rate_node_del(struct devlink_rate *rate_node, void *priv,
 	struct mlx5_esw_sched_node *node = priv;
 	struct mlx5_eswitch *esw = node->esw;
 
-	esw_qos_lock(esw);
+	esw_qos_devlink_lock(esw->dev);
 	__esw_qos_destroy_node(node, extack);
 	esw_qos_put(esw);
-	esw_qos_unlock(esw);
+	esw_qos_devlink_unlock(esw->dev);
+
 	return 0;
 }
 
-int mlx5_esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw_sched_node *parent,
-				     struct netlink_ext_ack *extack)
+static int
+mlx5_esw_validate_cross_esw_scheduling(struct mlx5_eswitch *esw,
+				       struct mlx5_esw_sched_node *parent,
+				       struct netlink_ext_ack *extack)
 {
-	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
-	int err = 0;
+	if (!parent || esw == parent->esw)
+		return 0;
 
-	if (parent && parent->esw != esw) {
-		NL_SET_ERR_MSG_MOD(extack, "Cross E-Switch scheduling is not supported");
+	if (!MLX5_CAP_QOS(esw->dev, esw_cross_esw_sched)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cross E-Switch scheduling is not supported");
+		return -EOPNOTSUPP;
+	}
+	if (!esw->dev->shd || esw->dev->shd != parent->esw->dev->shd) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot add vport to a parent belonging to a different device");
 		return -EOPNOTSUPP;
 	}
+	if (!mlx5_lag_is_active(esw->dev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cross E-Switch scheduling requires LAG to be activated");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+mlx5_esw_qos_vport_update_parent(struct mlx5_vport *vport,
+				 struct mlx5_esw_sched_node *parent,
+				 struct netlink_ext_ack *extack)
+{
+	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
+	int err;
+
+	err = mlx5_esw_validate_cross_esw_scheduling(esw, parent, extack);
+	if (err)
+		return err;
 
-	esw_qos_lock(esw);
 	if (!vport->qos.sched_node && parent) {
 		enum sched_node_type type;
 
@@ -1910,9 +1876,11 @@ int mlx5_esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw_s
 		err = mlx5_esw_qos_vport_enable(vport, type, parent, 0, 0,
 						extack);
 	} else if (vport->qos.sched_node) {
-		err = esw_qos_vport_update_parent(vport, parent, extack);
+		err = esw_qos_vport_update_parent(vport,
+						  parent ? : esw->qos.root,
+						  extack);
 	}
-	esw_qos_unlock(esw);
+
 	return err;
 }
 
@@ -1925,14 +1893,11 @@ int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate,
 	struct mlx5_vport *vport = priv;
 	int err;
 
+	esw_qos_devlink_lock(vport->dev);
 	err = mlx5_esw_qos_vport_update_parent(vport, node, extack);
-	if (!err) {
-		struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
-
-		esw_qos_lock(esw);
+	if (!err)
 		esw_vport_qos_prune_empty(vport);
-		esw_qos_unlock(esw);
-	}
+	esw_qos_devlink_unlock(vport->dev);
 
 	return err;
 }
@@ -1958,7 +1923,7 @@ mlx5_esw_qos_node_validate_set_parent(struct mlx5_esw_sched_node *node,
 {
 	u8 new_level, max_level;
 
-	if (parent && parent->esw != node->esw) {
+	if (parent->esw != node->esw) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Cannot assign node to another E-Switch");
 		return -EOPNOTSUPP;
@@ -1970,13 +1935,13 @@ mlx5_esw_qos_node_validate_set_parent(struct mlx5_esw_sched_node *node,
 		return -EOPNOTSUPP;
 	}
 
-	if (parent && parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) {
+	if (parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Cannot attach a node to a parent with TC bandwidth configured");
 		return -EOPNOTSUPP;
 	}
 
-	new_level = parent ? parent->level + 1 : 2;
+	new_level = parent->level + 1;
 	if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) {
 		/* Increase by one to account for the vports TC scheduling
 		 * element.
@@ -2027,14 +1992,12 @@ static int esw_qos_vports_node_update_parent(struct mlx5_esw_sched_node *node,
 {
 	struct mlx5_esw_sched_node *curr_parent = node->parent;
 	struct mlx5_eswitch *esw = node->esw;
-	u32 parent_ix;
 	int err;
 
-	parent_ix = parent ? parent->ix : node->esw->qos.root_tsar_ix;
 	mlx5_destroy_scheduling_element_cmd(esw->dev,
 					    SCHEDULING_HIERARCHY_E_SWITCH,
 					    node->ix);
-	err = esw_qos_create_node_sched_elem(esw->dev, parent_ix,
+	err = esw_qos_create_node_sched_elem(esw->dev, parent->ix,
 					     node->max_rate, 0, &node->ix);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack,
@@ -2061,12 +2024,15 @@ static int mlx5_esw_qos_node_update_parent(struct mlx5_esw_sched_node *node,
 	struct mlx5_eswitch *esw = node->esw;
 	int err;
 
+	esw_qos_devlink_lock(esw->dev);
+	curr_parent = node->parent;
+	if (!parent)
+		parent = esw->qos.root;
+
 	err = mlx5_esw_qos_node_validate_set_parent(node, parent, extack);
 	if (err)
-		return err;
+		goto out;
 
-	esw_qos_lock(esw);
-	curr_parent = node->parent;
 	if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) {
 		err = esw_qos_tc_arbiter_node_update_parent(node, parent,
 							    extack);
@@ -2077,12 +2043,11 @@ static int mlx5_esw_qos_node_update_parent(struct mlx5_esw_sched_node *node,
 	if (err)
 		goto out;
 
-	esw_qos_normalize_min_rate(esw, curr_parent, extack);
-	esw_qos_normalize_min_rate(esw, parent, extack);
+	esw_qos_normalize_min_rate(curr_parent, extack);
+	esw_qos_normalize_min_rate(parent, extack);
 
 out:
-	esw_qos_unlock(esw);
-
+	esw_qos_devlink_unlock(esw->dev);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
index 0a50982b0e27..f275e850d2c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
@@ -6,9 +6,6 @@
 
 #ifdef CONFIG_MLX5_ESWITCH
 
-int mlx5_esw_qos_init(struct mlx5_eswitch *esw);
-void mlx5_esw_qos_cleanup(struct mlx5_eswitch *esw);
-
 int mlx5_esw_qos_set_vport_rate(struct mlx5_vport *evport, u32 max_rate, u32 min_rate);
 bool mlx5_esw_qos_get_vport_rate(struct mlx5_vport *vport, u32 *max_rate, u32 *min_rate);
 void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index a0e2ca87b8d8..b6e2c153b4f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1885,10 +1885,6 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs)
 	MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
 	mlx5_eq_notifier_register(esw->dev, &esw->nb);
 
-	err = mlx5_esw_qos_init(esw);
-	if (err)
-		goto err_esw_init;
-
 	if (esw->mode == MLX5_ESWITCH_LEGACY) {
 		err = esw_legacy_enable(esw);
 	} else {
@@ -1990,6 +1986,13 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf)
 		 esw->esw_funcs.num_vfs, esw->esw_funcs.num_ec_vfs, esw->enabled_vports);
 
 	mlx5_eswitch_invalidate_wq(esw);
+
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS) {
+		struct devlink *devlink = priv_to_devlink(esw->dev);
+
+		devl_rate_nodes_destroy(devlink);
+	}
+
 	mlx5_esw_reps_block(esw);
 
 	if (!mlx5_core_is_ecpf(esw->dev)) {
@@ -2003,12 +2006,6 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf)
 	}
 
 	mlx5_esw_reps_unblock(esw);
-
-	if (esw->mode == MLX5_ESWITCH_OFFLOADS) {
-		struct devlink *devlink = priv_to_devlink(esw->dev);
-
-		devl_rate_nodes_destroy(devlink);
-	}
 	/* Destroy legacy fdb when disabling sriov in legacy mode. */
 	if (esw->mode == MLX5_ESWITCH_LEGACY)
 		mlx5_eswitch_disable_locked(esw);
@@ -2039,6 +2036,9 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw)
 		 esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
 		 esw->esw_funcs.num_vfs, esw->esw_funcs.num_ec_vfs, esw->enabled_vports);
 
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS)
+		devl_rate_nodes_destroy(devlink);
+
 	if (esw->fdb_table.flags & MLX5_ESW_FDB_CREATED) {
 		esw->fdb_table.flags &= ~MLX5_ESW_FDB_CREATED;
 		if (esw->mode == MLX5_ESWITCH_OFFLOADS)
@@ -2047,9 +2047,6 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw)
 			esw_legacy_disable(esw);
 		mlx5_esw_acls_ns_cleanup(esw);
 	}
-
-	if (esw->mode == MLX5_ESWITCH_OFFLOADS)
-		devl_rate_nodes_destroy(devlink);
 }
 
 void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
@@ -2554,9 +2551,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		goto reps_err;
 
 	esw->mode = MLX5_ESWITCH_LEGACY;
-	err = mlx5_esw_qos_init(esw);
-	if (err)
-		goto reps_err;
 
 	mutex_init(&esw->offloads.encap_tbl_lock);
 	hash_init(esw->offloads.encap_tbl);
@@ -2611,7 +2605,6 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 
 	mlx5_eswitch_invalidate_wq(esw);
 	destroy_workqueue(esw->work_queue);
-	mlx5_esw_qos_cleanup(esw);
 	WARN_ON(refcount_read(&esw->qos.refcnt));
 	mutex_destroy(&esw->state_lock);
 	WARN_ON(!xa_empty(&esw->offloads.vhca_map));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index fea72b1dedab..c655f6e8da1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -234,8 +234,10 @@ struct mlx5_vport {
 
 	struct mlx5_vport_info  info;
 
-	/* Protected with the E-Switch qos domain lock. The Vport QoS can
-	 * either be disabled (sched_node is NULL) or in one of three states:
+	/* Protected by either the shared devlink (dev->shd) lock or by
+	 * esw->state_lock. See esw_assert_qos_lock_held() for more details.
+	 * The Vport QoS can either be disabled (sched_node is NULL) or in one
+	 * of three states:
 	 * 1. Regular QoS (sched_node is a vport node).
 	 * 2. TC QoS enabled on the vport (sched_node is a TC arbiter).
 	 * 3. TC QoS enabled on the vport's parent node
@@ -382,7 +384,6 @@ enum {
 };
 
 struct dentry;
-struct mlx5_qos_domain;
 
 struct mlx5_eswitch {
 	struct mlx5_core_dev    *dev;
@@ -411,12 +412,15 @@ struct mlx5_eswitch {
 	atomic64_t user_count;
 	wait_queue_head_t work_queue_wait;
 
-	/* Protected with the E-Switch qos domain lock. */
+	/* QoS changes are serialized by either the shared devlink (dev->shd)
+	 * lock or by esw->state_lock. See esw_assert_qos_lock_held() for more
+	 * details.
+	 */
 	struct {
 		/* Initially 0, meaning no QoS users and QoS is disabled. */
 		refcount_t refcnt;
-		u32 root_tsar_ix;
-		struct mlx5_qos_domain *domain;
+		/* The root node of the hierarchy. */
+		struct mlx5_esw_sched_node *root;
 	} qos;
 
 	struct mlx5_esw_bridge_offloads *br_offloads;
@@ -482,8 +486,6 @@ int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
 				 u16 vport_num, bool setting);
 int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport,
 				u32 max_rate, u32 min_rate);
-int mlx5_esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw_sched_node *node,
-				     struct netlink_ext_ack *extack);
 int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting);
 int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting);
 int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index dbaf33b537f7..906584345a02 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -214,17 +214,7 @@ struct mlx5_ft_underlay_qp {
 	u32 qpn;
 };
 
-#define MLX5_FTE_MATCH_PARAM_RESERVED	reserved_at_e00
-/* Calculate the fte_match_param length and without the reserved length.
- * Make sure the reserved field is the last.
- */
-#define MLX5_ST_SZ_DW_MATCH_PARAM					    \
-	((MLX5_BYTE_OFF(fte_match_param, MLX5_FTE_MATCH_PARAM_RESERVED) / sizeof(u32)) + \
-	 BUILD_BUG_ON_ZERO(MLX5_ST_SZ_BYTES(fte_match_param) !=		     \
-			   MLX5_FLD_SZ_BYTES(fte_match_param,		     \
-					     MLX5_FTE_MATCH_PARAM_RESERVED) +\
-			   MLX5_BYTE_OFF(fte_match_param,		     \
-					 MLX5_FTE_MATCH_PARAM_RESERVED)))
+#define MLX5_ST_SZ_DW_MATCH_PARAM MLX5_ST_SZ_DW(fte_match_param)
 
 struct fs_fte_action {
 	int				modify_mask;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
index e624f5da96c8..8fae90101653 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
@@ -1172,13 +1172,13 @@ int mlx5hws_cmd_query_caps(struct mlx5_core_dev *mdev,
 		}
 
 		if (MLX5_GET(query_hca_cap_out, out,
-			     capability.esw_cap.esw_manager_vport_number_valid))
+			     capability.e_switch_cap.esw_manager_vport_number_valid))
 			caps->eswitch_manager_vport_number =
 				MLX5_GET(query_hca_cap_out, out,
-					 capability.esw_cap.esw_manager_vport_number);
+					 capability.e_switch_cap.esw_manager_vport_number);
 
 		caps->merged_eswitch = MLX5_GET(query_hca_cap_out, out,
-						capability.esw_cap.merged_eswitch);
+						capability.e_switch_cap.merged_eswitch);
 	}
 
 	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, out_size);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 82569162d2e5..815e8d8e3185 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -663,8 +663,11 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
-static void mlxsw_sp_set_rx_mode(struct net_device *dev)
+static int mlxsw_sp_set_rx_mode_async(struct net_device *dev,
+				      struct netdev_hw_addr_list *uc,
+				      struct netdev_hw_addr_list *mc)
 {
+	return 0;
 }
 
 static int mlxsw_sp_port_set_mac_address(struct net_device *dev, void *p)
@@ -1191,7 +1194,7 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
 	.ndo_stop		= mlxsw_sp_port_stop,
 	.ndo_start_xmit		= mlxsw_sp_port_xmit,
 	.ndo_setup_tc           = mlxsw_sp_setup_tc,
-	.ndo_set_rx_mode	= mlxsw_sp_set_rx_mode,
+	.ndo_set_rx_mode_async	= mlxsw_sp_set_rx_mode_async,
 	.ndo_set_mac_address	= mlxsw_sp_port_set_mac_address,
 	.ndo_change_mtu		= mlxsw_sp_port_change_mtu,
 	.ndo_get_stats64	= mlxsw_sp_port_get_stats64,
@@ -1549,6 +1552,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port,
 	dev->vlan_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	dev->lltx = true;
 	dev->netns_immutable = true;
+	dev->request_ops_lock = true;
 
 	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = MLXSW_PORT_MAX_MTU - MLXSW_PORT_ETH_FRAME_HDR;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index cbb272a96359..0d0cd093b3c6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -1118,7 +1118,7 @@ u8 mlxsw_sp_acl_erp_delta_value(const struct mlxsw_sp_acl_erp_delta *delta,
 }
 
 void mlxsw_sp_acl_erp_delta_clear(const struct mlxsw_sp_acl_erp_delta *delta,
-				  const char *enc_key)
+				  char *enc_key)
 {
 	u16 start = delta->start;
 	u8 mask = delta->mask;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 010204f73ea4..67cc7a5737dd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -245,7 +245,7 @@ u8 mlxsw_sp_acl_erp_delta_mask(const struct mlxsw_sp_acl_erp_delta *delta);
 u8 mlxsw_sp_acl_erp_delta_value(const struct mlxsw_sp_acl_erp_delta *delta,
 				const char *enc_key);
 void mlxsw_sp_acl_erp_delta_clear(const struct mlxsw_sp_acl_erp_delta *delta,
-				  const char *enc_key);
+				  char *enc_key);
 
 struct mlxsw_sp_acl_erp_mask;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
index 7f78b1ef61cc..3bdb532d833b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
@@ -1262,6 +1262,8 @@ mlxsw_sp_set_module_power_mode(struct net_device *dev,
 
 const struct ethtool_ops mlxsw_sp_port_ethtool_ops = {
 	.cap_link_lanes_supported	= true,
+	.op_needs_rtnl			= ETHTOOL_OP_NEEDS_RTNL_SPAUSEPARAM |
+					  ETHTOOL_OP_NEEDS_RTNL_GLINK,
 	.get_drvinfo			= mlxsw_sp_port_get_drvinfo,
 	.get_link			= ethtool_op_get_link,
 	.get_link_ext_state		= mlxsw_sp_port_get_link_ext_state,
diff --git a/drivers/net/ethernet/microchip/lan865x/lan865x.c b/drivers/net/ethernet/microchip/lan865x/lan865x.c
index 0277d9737369..26a2761332a5 100644
--- a/drivers/net/ethernet/microchip/lan865x/lan865x.c
+++ b/drivers/net/ethernet/microchip/lan865x/lan865x.c
@@ -346,7 +346,7 @@ static int lan865x_probe(struct spi_device *spi)
 	spi_set_drvdata(spi, priv);
 	INIT_WORK(&priv->multicast_work, lan865x_multicast_work_handler);
 
-	priv->tc6 = oa_tc6_init(spi, netdev);
+	priv->tc6 = oa_tc6_init(spi, netdev, NULL);
 	if (!priv->tc6) {
 		ret = -ENODEV;
 		goto free_netdev;
diff --git a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_regs.c b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_regs.c
index ace4ba21eec4..3fc2c006ba12 100644
--- a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_regs.c
+++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_regs.c
@@ -95,6 +95,7 @@ const unsigned int lan969x_gaddr[GADDR_LAST] = {
 	[GA_HSCH_SYSTEM] = 37384,
 	[GA_HSCH_MMGT] = 36260,
 	[GA_HSCH_TAS_CONFIG] = 37696,
+	[GA_HSCH_TAS_PROFILE_CFG] = 37712,
 	[GA_PTP_PTP_CFG] = 512,
 	[GA_PTP_PTP_TOD_DOMAINS] = 528,
 	[GA_PTP_PHASE_DETECTOR_CTRL] = 628,
@@ -129,6 +130,7 @@ const unsigned int lan969x_gcnt[GCNT_LAST] = {
 	[GC_GCB_SIO_CTRL] = 1,
 	[GC_HSCH_HSCH_CFG] = 1120,
 	[GC_HSCH_HSCH_DWRR] = 32,
+	[GC_HSCH_TAS_PROFILE_CFG] = 30,
 	[GC_PTP_PTP_PINS] = 8,
 	[GC_PTP_PHASE_DETECTOR_CTRL] = 8,
 	[GC_REW_PORT] = 35,
@@ -144,6 +146,7 @@ const unsigned int lan969x_gsize[GSIZE_LAST] = {
 	[GW_FDMA_FDMA] = 448,
 	[GW_GCB_CHIP_REGS] = 180,
 	[GW_HSCH_TAS_CONFIG] = 16,
+	[GW_HSCH_TAS_PROFILE_CFG] = 68,
 	[GW_PTP_PHASE_DETECTOR_CTRL] = 12,
 	[GW_QSYS_PAUSE_CFG] = 988,
 };
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h
index d9ef4ef137b8..d34467513648 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h
@@ -5369,6 +5369,18 @@ extern const struct sparx5_regs *regs;
 #define HSCH_TAS_STATEMACHINE_CFG_REVISIT_DLY_GET(x)\
 	FIELD_GET(HSCH_TAS_STATEMACHINE_CFG_REVISIT_DLY, x)
 
+/* HSCH:TAS_PROFILE_CFG:TAS_PROFILE_CONFIG */
+#define HSCH_TAS_PROFILE_CONFIG(g)                                             \
+	__REG(TARGET_HSCH, 0, 1, regs->gaddr[GA_HSCH_TAS_PROFILE_CFG], g,       \
+	      regs->gcnt[GC_HSCH_TAS_PROFILE_CFG],                              \
+	      regs->gsize[GW_HSCH_TAS_PROFILE_CFG], 32, 0, 1, 4)
+
+#define HSCH_TAS_PROFILE_CONFIG_LINK_SPEED       GENMASK(10, 8)
+#define HSCH_TAS_PROFILE_CONFIG_LINK_SPEED_SET(x)\
+	FIELD_PREP(HSCH_TAS_PROFILE_CONFIG_LINK_SPEED, x)
+#define HSCH_TAS_PROFILE_CONFIG_LINK_SPEED_GET(x)\
+	FIELD_GET(HSCH_TAS_PROFILE_CONFIG_LINK_SPEED, x)
+
 /* LAN969X ONLY */
 /* HSIOWRAP:XMII_CFG:XMII_CFG */
 #define HSIO_WRAP_XMII_CFG(g)                                                  \
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
index 62c49893de3c..ef06bed3a9cc 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
@@ -11,6 +11,7 @@
 #include "sparx5_main_regs.h"
 #include "sparx5_main.h"
 #include "sparx5_port.h"
+#include "sparx5_qos.h"
 
 #define SPX5_ETYPE_TAG_C     0x8100
 #define SPX5_ETYPE_TAG_S     0x88a8
@@ -1050,6 +1051,9 @@ int sparx5_port_config(struct sparx5 *sparx5,
 		 sparx5,
 		 QFWD_SWITCH_PORT_MODE(port->portno));
 
+	/* Notify TAS about the speed. */
+	sparx5_tas_speed(port, conf->speed);
+
 	/* Save the new values */
 	port->conf = *conf;
 
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c
index e580670f3992..972da8a71f5a 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c
@@ -9,6 +9,17 @@
 #include "sparx5_main.h"
 #include "sparx5_qos.h"
 
+enum sparx5_tas_link_speed {
+	TAS_SPEED_NO_GB,
+	TAS_SPEED_10,
+	TAS_SPEED_100,
+	TAS_SPEED_1000,
+	TAS_SPEED_2500,
+	TAS_SPEED_5000,
+	TAS_SPEED_10000,
+	TAS_SPEED_25000,
+};
+
 /* Calculate new base_time based on cycle_time.
  *
  * The hardware requires a base_time that is always in the future.
@@ -581,3 +592,41 @@ int sparx5_tc_ets_del(struct sparx5_port *port)
 
 	return sparx5_dwrr_conf_set(port, &dwrr);
 }
+
+void sparx5_tas_speed(struct sparx5_port *port, int speed)
+{
+	struct sparx5 *sparx5 = port->sparx5;
+	u8 spd;
+
+	switch (speed) {
+	case SPEED_10:
+		spd = TAS_SPEED_10;
+		break;
+	case SPEED_100:
+		spd = TAS_SPEED_100;
+		break;
+	case SPEED_1000:
+		spd = TAS_SPEED_1000;
+		break;
+	case SPEED_2500:
+		spd = TAS_SPEED_2500;
+		break;
+	case SPEED_5000:
+		spd = TAS_SPEED_5000;
+		break;
+	case SPEED_10000:
+		spd = TAS_SPEED_10000;
+		break;
+	case SPEED_25000:
+		spd = TAS_SPEED_25000;
+		break;
+	default:
+		netdev_err(port->ndev, "TAS: Unsupported speed: %d\n", speed);
+		return;
+	}
+
+	spx5_rmw(HSCH_TAS_PROFILE_CONFIG_LINK_SPEED_SET(spd),
+		 HSCH_TAS_PROFILE_CONFIG_LINK_SPEED,
+		 sparx5,
+		 HSCH_TAS_PROFILE_CONFIG(port->portno));
+}
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.h b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.h
index 04f76f1e23f6..a92a699c551f 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.h
@@ -60,6 +60,7 @@ struct sparx5_dwrr {
 };
 
 int sparx5_qos_init(struct sparx5 *sparx5);
+void sparx5_tas_speed(struct sparx5_port *port, int speed);
 
 /* Multi-Queue Priority */
 int sparx5_tc_mqprio_add(struct net_device *ndev, u8 num_tc);
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_regs.c b/drivers/net/ethernet/microchip/sparx5/sparx5_regs.c
index 220e81b714d4..3863f954bd83 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_regs.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_regs.c
@@ -95,6 +95,7 @@ const unsigned int sparx5_gaddr[GADDR_LAST] = {
 	[GA_HSCH_SYSTEM] = 184000,
 	[GA_HSCH_MMGT] = 162368,
 	[GA_HSCH_TAS_CONFIG] = 162384,
+	[GA_HSCH_TAS_PROFILE_CFG] = 188416,
 	[GA_PTP_PTP_CFG] = 320,
 	[GA_PTP_PTP_TOD_DOMAINS] = 336,
 	[GA_PTP_PHASE_DETECTOR_CTRL] = 420,
@@ -129,6 +130,7 @@ const unsigned int sparx5_gcnt[GCNT_LAST] = {
 	[GC_GCB_SIO_CTRL] = 3,
 	[GC_HSCH_HSCH_CFG] = 5040,
 	[GC_HSCH_HSCH_DWRR] = 72,
+	[GC_HSCH_TAS_PROFILE_CFG] = 100,
 	[GC_PTP_PTP_PINS] = 5,
 	[GC_PTP_PHASE_DETECTOR_CTRL] = 5,
 	[GC_REW_PORT] = 70,
@@ -144,6 +146,7 @@ const unsigned int sparx5_gsize[GSIZE_LAST] = {
 	[GW_FDMA_FDMA] = 428,
 	[GW_GCB_CHIP_REGS] = 424,
 	[GW_HSCH_TAS_CONFIG] = 12,
+	[GW_HSCH_TAS_PROFILE_CFG] = 64,
 	[GW_PTP_PHASE_DETECTOR_CTRL] = 8,
 	[GW_QSYS_PAUSE_CFG] = 1128,
 };
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_regs.h b/drivers/net/ethernet/microchip/sparx5/sparx5_regs.h
index ea28130c2341..585589a31e90 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_regs.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_regs.h
@@ -104,6 +104,7 @@ enum sparx5_gaddr_enum {
 	GA_HSCH_SYSTEM,
 	GA_HSCH_MMGT,
 	GA_HSCH_TAS_CONFIG,
+	GA_HSCH_TAS_PROFILE_CFG,
 	GA_PTP_PTP_CFG,
 	GA_PTP_PTP_TOD_DOMAINS,
 	GA_PTP_PHASE_DETECTOR_CTRL,
@@ -139,6 +140,7 @@ enum sparx5_gcnt_enum {
 	GC_GCB_SIO_CTRL,
 	GC_HSCH_HSCH_CFG,
 	GC_HSCH_HSCH_DWRR,
+	GC_HSCH_TAS_PROFILE_CFG,
 	GC_PTP_PTP_PINS,
 	GC_PTP_PHASE_DETECTOR_CTRL,
 	GC_REW_PORT,
@@ -155,6 +157,7 @@ enum sparx5_gsize_enum {
 	GW_FDMA_FDMA,
 	GW_GCB_CHIP_REGS,
 	GW_HSCH_TAS_CONFIG,
+	GW_HSCH_TAS_PROFILE_CFG,
 	GW_PTP_PHASE_DETECTOR_CTRL,
 	GW_QSYS_PAUSE_CFG,
 	GSIZE_LAST,
diff --git a/drivers/net/ethernet/microsoft/Kconfig b/drivers/net/ethernet/microsoft/Kconfig
index 3f36ee6a8ece..e9be18c92ca5 100644
--- a/drivers/net/ethernet/microsoft/Kconfig
+++ b/drivers/net/ethernet/microsoft/Kconfig
@@ -21,6 +21,7 @@ config MICROSOFT_MANA
 	depends on X86_64 || (ARM64 && !CPU_BIG_ENDIAN)
 	depends on PCI_HYPERV
 	select AUXILIARY_BUS
+	select DIMLIB
 	select PAGE_POOL
 	select NET_SHAPER
 	help
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index e8b7ffb47eb9..a38d4bb74621 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /* Copyright (c) 2021, Microsoft Corporation. */
 
+#include <linux/bitfield.h>
 #include <linux/debugfs.h>
 #include <linux/module.h>
 #include <linux/pci.h>
@@ -466,6 +467,7 @@ static int mana_gd_disable_queue(struct gdma_queue *queue)
 #define DOORBELL_OFFSET_RQ	0x400
 #define DOORBELL_OFFSET_CQ	0x800
 #define DOORBELL_OFFSET_EQ	0xFF8
+#define DOORBELL_OFFSET_DIM	0x820
 
 static void mana_gd_ring_doorbell(struct gdma_context *gc, u32 db_index,
 				  enum gdma_queue_type q_type, u32 qid,
@@ -506,6 +508,16 @@ static void mana_gd_ring_doorbell(struct gdma_context *gc, u32 db_index,
 		addr += DOORBELL_OFFSET_SQ;
 		break;
 
+	case GDMA_DIM:
+		e.dim.id = qid;
+		e.dim.mod_usec = FIELD_GET(MANA_INTR_MODR_USEC_MAX, tail_ptr);
+		e.dim.mod_usec_vld = !!(tail_ptr & MANA_INTR_MODR_USEC_VLD);
+		e.dim.mod_comps = FIELD_GET(MANA_INTR_MODR_COMP_MASK, tail_ptr);
+		e.dim.mod_comps_vld = num_req;
+
+		addr += DOORBELL_OFFSET_DIM;
+		break;
+
 	default:
 		WARN_ON(1);
 		return;
@@ -540,6 +552,23 @@ void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit)
 }
 EXPORT_SYMBOL_NS(mana_gd_ring_cq, "NET_MANA");
 
+void mana_gd_ring_dim(struct gdma_queue *cq, u32 mod_usec, bool mod_usec_vld,
+		      u32 mod_comps, bool mod_comps_vld)
+{
+	struct gdma_context *gc = cq->gdma_dev->gdma_context;
+	u32 dim_val;
+
+	/* Convert the DIM values to doorbell parameters */
+	dim_val = FIELD_PREP(MANA_INTR_MODR_USEC_MAX, mod_usec) |
+		  FIELD_PREP(MANA_INTR_MODR_COMP_MASK, mod_comps);
+	if (mod_usec_vld)
+		dim_val |= MANA_INTR_MODR_USEC_VLD;
+
+	mana_gd_ring_doorbell(gc, cq->gdma_dev->doorbell, GDMA_DIM, cq->id,
+			      dim_val, mod_comps_vld);
+}
+EXPORT_SYMBOL_NS(mana_gd_ring_dim, "NET_MANA");
+
 #define MANA_SERVICE_PERIOD 10
 
 static void mana_serv_rescan(struct pci_dev *pdev)
@@ -2427,6 +2456,8 @@ static void mana_gd_remove(struct pci_dev *pdev)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
 
+	pci_disable_sriov(pdev);
+
 	mana_rdma_remove(&gc->mana_ib);
 	mana_remove(&gc->mana, false);
 
@@ -2496,6 +2527,27 @@ static void mana_gd_shutdown(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
+static int mana_sriov_configure(struct pci_dev *pdev, int numvfs)
+{
+	int err = 0;
+
+	dev_info(&pdev->dev, "Requested num VFs: %d\n", numvfs);
+
+	if (numvfs > 0) {
+		err = pci_enable_sriov(pdev, numvfs);
+	} else {
+		if (pci_vfs_assigned(pdev)) {
+			dev_warn(&pdev->dev,
+				 "Cannot disable SR-IOV while VFs are assigned\n");
+			return -EPERM;
+		}
+
+		pci_disable_sriov(pdev);
+	}
+
+	return err ? err : numvfs;
+}
+
 static const struct pci_device_id mana_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_MICROSOFT, MANA_PF_DEVICE_ID) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MICROSOFT, MANA_PF2_DEVICE_ID) },
@@ -2511,6 +2563,7 @@ static struct pci_driver mana_driver = {
 	.suspend	= mana_gd_suspend,
 	.resume		= mana_gd_resume,
 	.shutdown	= mana_gd_shutdown,
+	.sriov_configure = mana_sriov_configure,
 };
 
 static int __init mana_driver_init(void)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 9d9bfd116dab..a8c329bdbacf 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -892,6 +892,17 @@ static void mana_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	struct mana_context *ac = apc->ac;
 	struct gdma_context *gc = ac->gdma_dev->gdma_context;
 
+	/* Debug knob for bringup/qualification: when set, log the timeout and
+	 * skip the reset so the failing state is preserved for telemetry.
+	 * Disabled by default; production behaviour is unchanged.
+	 */
+	if (READ_ONCE(apc->tx_timeout_skip_reset)) {
+		netdev_warn(netdev,
+			    "TX timeout on queue %u: reset skipped (tx_timeout_skip_reset enabled)\n",
+			    txqueue);
+		return;
+	}
+
 	/* Already in service, hence tx queue reset is not required.*/
 	if (test_bit(GC_IN_SERVICE, &gc->flags))
 		return;
@@ -1591,6 +1602,15 @@ int mana_create_wq_obj(struct mana_port_context *apc,
 
 	mana_gd_init_req_hdr(&req.hdr, MANA_CREATE_WQ_OBJ,
 			     sizeof(req), sizeof(resp));
+
+	/* Our driver uses different message versions for request and
+	 * response in this case.
+	 * Our firmware is forward compatible with newer message versions, so
+	 * the old firmware still properly handles this message, just the new
+	 * feature fields are ignored, and queue creation will be successful.
+	 */
+	req.hdr.req.msg_version = GDMA_MESSAGE_V3;
+	req.hdr.resp.msg_version = GDMA_MESSAGE_V2;
 	req.vport = vport;
 	req.wq_type = wq_type;
 	req.wq_gdma_region = wq_spec->gdma_region;
@@ -1599,6 +1619,9 @@ int mana_create_wq_obj(struct mana_port_context *apc,
 	req.cq_size = cq_spec->queue_size;
 	req.cq_moderation_ctx_id = cq_spec->modr_ctx_id;
 	req.cq_parent_qid = cq_spec->attached_eq;
+	req.req_cq_moderation = cq_spec->req_cq_moderation;
+	req.cq_moderation_comp = cq_spec->cq_moderation_comp;
+	req.cq_moderation_usec = cq_spec->cq_moderation_usec;
 
 	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
 				sizeof(resp));
@@ -1856,6 +1879,7 @@ static void mana_poll_tx_cq(struct mana_cq *cq)
 	struct gdma_posted_wqe_info *wqe_info;
 	unsigned int pkt_transmitted = 0;
 	unsigned int wqe_unit_cnt = 0;
+	unsigned int tx_bytes = 0;
 	struct mana_txq *txq = cq->txq;
 	struct mana_port_context *apc;
 	struct netdev_queue *net_txq;
@@ -1937,6 +1961,8 @@ static void mana_poll_tx_cq(struct mana_cq *cq)
 
 		mana_unmap_skb(skb, apc);
 
+		tx_bytes += skb->len;
+
 		napi_consume_skb(skb, cq->budget);
 
 		pkt_transmitted++;
@@ -1967,6 +1993,10 @@ static void mana_poll_tx_cq(struct mana_cq *cq)
 	if (atomic_sub_return(pkt_transmitted, &txq->pending_sends) < 0)
 		WARN_ON_ONCE(1);
 
+	/* Feed DIM with the completion rate observed here, in NAPI context. */
+	cq->tx_dim_pkts += pkt_transmitted;
+	cq->tx_dim_bytes += tx_bytes;
+
 	cq->work_done = pkt_transmitted;
 }
 
@@ -2352,6 +2382,117 @@ static void mana_poll_rx_cq(struct mana_cq *cq)
 		xdp_do_flush();
 }
 
+static void mana_rx_dim_work(struct work_struct *work)
+{
+	struct dim *dim = container_of(work, struct dim, work);
+	struct dim_cq_moder cur_moder;
+	struct mana_cq *cq;
+
+	cur_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
+	cq = container_of(dim, struct mana_cq, dim);
+
+	cur_moder.usec = min_t(u16, cur_moder.usec, MANA_INTR_MODR_USEC_MAX);
+	cur_moder.pkts = min_t(u16, cur_moder.pkts, MANA_INTR_MODR_COMP_MAX);
+
+	mana_gd_ring_dim(cq->gdma_cq, cur_moder.usec, true,
+			 cur_moder.pkts, true);
+
+	dim->state = DIM_START_MEASURE;
+}
+
+static void mana_tx_dim_work(struct work_struct *work)
+{
+	struct dim *dim = container_of(work, struct dim, work);
+	struct dim_cq_moder cur_moder;
+	struct mana_cq *cq;
+
+	cur_moder = net_dim_get_tx_moderation(dim->mode, dim->profile_ix);
+	cq = container_of(dim, struct mana_cq, dim);
+
+	cur_moder.usec = min_t(u16, cur_moder.usec, MANA_INTR_MODR_USEC_MAX);
+	cur_moder.pkts = min_t(u16, cur_moder.pkts, MANA_INTR_MODR_COMP_MAX);
+
+	mana_gd_ring_dim(cq->gdma_cq, cur_moder.usec, true,
+			 cur_moder.pkts, true);
+
+	dim->state = DIM_START_MEASURE;
+}
+
+/* The caller must update apc->rx/tx_dim_enabled before disabling and
+ * after enabling. And synchronize_net() before draining the DIM work,
+ * so that NAPI cannot observe a stale flag.
+ */
+void mana_dim_change(struct mana_cq *cq, bool enable)
+{
+	bool is_rx = cq->type == MANA_CQ_TYPE_RX;
+	struct mana_port_context *apc;
+	work_func_t work_func;
+	u32 usec, comp;
+
+	if (is_rx) {
+		apc = netdev_priv(cq->rxq->ndev);
+		usec = apc->intr_modr_rx_usec;
+		comp = apc->intr_modr_rx_comp;
+		work_func = mana_rx_dim_work;
+	} else {
+		apc = netdev_priv(cq->txq->ndev);
+		usec = apc->intr_modr_tx_usec;
+		comp = apc->intr_modr_tx_comp;
+		work_func = mana_tx_dim_work;
+	}
+
+	/* On enable, zero the DIM state so net_dim() starts measuring from
+	 * scratch.
+	 * On disable, drain any pending DIM work and restore the static
+	 * moderation values.
+	 */
+	if (enable) {
+		memset(&cq->dim, 0, sizeof(cq->dim));
+		cq->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+		INIT_WORK(&cq->dim.work, work_func);
+	} else {
+		cancel_work_sync(&cq->dim.work);
+		mana_gd_ring_dim(cq->gdma_cq, usec, true, comp, true);
+	}
+}
+
+static void mana_update_rx_dim(struct mana_cq *cq)
+{
+	struct mana_port_context *apc = netdev_priv(cq->rxq->ndev);
+	struct dim_sample dim_sample = {};
+	struct mana_rxq *rxq = cq->rxq;
+
+	/* Pairs with smp_store_release() in mana_set_coalesce(): observing the
+	 * enable flag set guarantees the DIM (re)initialization is visible.
+	 */
+	if (!smp_load_acquire(&apc->rx_dim_enabled))
+		return;
+
+	dim_update_sample(READ_ONCE(cq->dim_event_ctr), rxq->stats.packets,
+			  rxq->stats.bytes, &dim_sample);
+	net_dim(&cq->dim, &dim_sample);
+}
+
+static void mana_update_tx_dim(struct mana_cq *cq)
+{
+	struct mana_port_context *apc = netdev_priv(cq->txq->ndev);
+	struct dim_sample dim_sample = {};
+
+	/* Pairs with smp_store_release() in mana_set_coalesce(): observing the
+	 * enable flag set guarantees the DIM (re)initialization is visible.
+	 */
+	if (!smp_load_acquire(&apc->tx_dim_enabled))
+		return;
+
+	/* cq->tx_dim_pkts/bytes are accumulated in mana_poll_tx_cq(), in the
+	 * same NAPI context as this read, so they track the hardware
+	 * completion rate and need no u64_stats_sync protection.
+	 */
+	dim_update_sample(READ_ONCE(cq->dim_event_ctr), cq->tx_dim_pkts,
+			  cq->tx_dim_bytes, &dim_sample);
+	net_dim(&cq->dim, &dim_sample);
+}
+
 static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
 {
 	struct mana_cq *cq = context;
@@ -2370,6 +2511,15 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
 	if (w < cq->budget) {
 		mana_gd_ring_cq(gdma_queue, SET_ARM_BIT);
 		cq->work_done_since_doorbell = 0;
+
+		/* Update DIM before napi_complete_done() to prevent running
+		 * net_dim() concurrently.
+		 */
+		if (cq->type == MANA_CQ_TYPE_RX)
+			mana_update_rx_dim(cq);
+		else
+			mana_update_tx_dim(cq);
+
 		napi_complete_done(&cq->napi, w);
 	} else if (cq->work_done_since_doorbell >=
 		   (cq->gdma_cq->queue_size / COMP_ENTRY_SIZE) * 4) {
@@ -2402,6 +2552,7 @@ static void mana_schedule_napi(void *context, struct gdma_queue *gdma_queue)
 {
 	struct mana_cq *cq = context;
 
+	WRITE_ONCE(cq->dim_event_ctr, cq->dim_event_ctr + 1);
 	napi_schedule_irqoff(&cq->napi);
 }
 
@@ -2444,6 +2595,7 @@ static void mana_destroy_txq(struct mana_port_context *apc)
 		if (apc->tx_qp[i]->txq.napi_initialized) {
 			napi_synchronize(napi);
 			napi_disable_locked(napi);
+			cancel_work_sync(&apc->tx_qp[i]->tx_cq.dim.work);
 			netif_napi_del_locked(napi);
 			apc->tx_qp[i]->txq.napi_initialized = false;
 		}
@@ -2577,6 +2729,11 @@ static int mana_create_txq(struct mana_port_context *apc,
 		cq_spec.modr_ctx_id = 0;
 		cq_spec.attached_eq = cq->gdma_cq->cq.parent->id;
 
+		/* DIM setting can be changed at runtime */
+		cq_spec.req_cq_moderation = true;
+		cq_spec.cq_moderation_usec = apc->intr_modr_tx_usec;
+		cq_spec.cq_moderation_comp = apc->intr_modr_tx_comp;
+
 		err = mana_create_wq_obj(apc, apc->port_handle, GDMA_SQ,
 					 &wq_spec, &cq_spec,
 					 &apc->tx_qp[i]->tx_object);
@@ -2607,6 +2764,13 @@ static int mana_create_txq(struct mana_port_context *apc,
 
 		set_bit(NAPI_STATE_NO_BUSY_POLL, &cq->napi.state);
 		netif_napi_add_locked(net, &cq->napi, mana_poll);
+
+		/* Initialize the DIM work before enabling NAPI, so that a poll
+		 * cannot reach net_dim() with an uninitialized cq->dim.work.
+		 */
+		INIT_WORK(&cq->dim.work, mana_tx_dim_work);
+		cq->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+
 		napi_enable_locked(&cq->napi);
 		txq->napi_initialized = true;
 
@@ -2644,6 +2808,7 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
 		napi_synchronize(napi);
 
 		napi_disable_locked(napi);
+		cancel_work_sync(&rxq->rx_cq.dim.work);
 		netif_napi_del_locked(napi);
 	}
 
@@ -2887,6 +3052,11 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 	cq_spec.modr_ctx_id = 0;
 	cq_spec.attached_eq = cq->gdma_cq->cq.parent->id;
 
+	/* DIM setting can be changed at runtime */
+	cq_spec.req_cq_moderation = true;
+	cq_spec.cq_moderation_usec = apc->intr_modr_rx_usec;
+	cq_spec.cq_moderation_comp = apc->intr_modr_rx_comp;
+
 	err = mana_create_wq_obj(apc, apc->port_handle, GDMA_RQ,
 				 &wq_spec, &cq_spec, &rxq->rxobj);
 	if (err)
@@ -2919,6 +3089,12 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 	WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq, MEM_TYPE_PAGE_POOL,
 					   rxq->page_pool));
 
+	/* Initialize the DIM work before enabling NAPI, so that a poll
+	 * cannot reach net_dim() with an uninitialized cq->dim.work.
+	 */
+	INIT_WORK(&cq->dim.work, mana_rx_dim_work);
+	cq->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+
 	napi_enable_locked(&cq->napi);
 
 	mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
@@ -3321,6 +3497,9 @@ static int mana_init_port(struct net_device *ndev)
 			   &apc->steer_cqe_coalescing);
 	debugfs_create_u32("current_speed", 0400, apc->mana_port_debugfs,
 			   &apc->speed);
+	debugfs_create_bool("tx_timeout_skip_reset", 0600,
+			    apc->mana_port_debugfs,
+			    &apc->tx_timeout_skip_reset);
 	return 0;
 
 reset_apc:
@@ -3585,6 +3764,16 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	apc->link_cfg_error = 1;
 	apc->cqe_coalescing_enable = 0;
 
+	/* Initialize interrupt moderation settings if supported by HW */
+	if (gc->pf_cap_flags1 & GDMA_PF_CAP_FLAG_1_DYN_INTERRUPT_MODERATION) {
+		apc->intr_modr_rx_usec = MANA_INTR_MODR_USEC_DEF;
+		apc->intr_modr_rx_comp = MANA_INTR_MODR_COMP_DEF;
+		apc->intr_modr_tx_usec = MANA_INTR_MODR_USEC_DEF;
+		apc->intr_modr_tx_comp = MANA_INTR_MODR_COMP_DEF;
+		apc->rx_dim_enabled = MANA_ADAPTIVE_RX_DEF;
+		apc->tx_dim_enabled = MANA_ADAPTIVE_TX_DEF;
+	}
+
 	mutex_init(&apc->vport_mutex);
 	apc->vport_use_count = 0;
 
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index 881df597d7f9..9e31e2595ae3 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -419,6 +419,15 @@ static int mana_get_coalesce(struct net_device *ndev,
 	    !kernel_coal->rx_cqe_nsecs)
 		kernel_coal->rx_cqe_nsecs = MANA_RX_CQE_NSEC_DEF;
 
+	ec->rx_coalesce_usecs = apc->intr_modr_rx_usec;
+	ec->rx_max_coalesced_frames = apc->intr_modr_rx_comp;
+
+	ec->tx_coalesce_usecs = apc->intr_modr_tx_usec;
+	ec->tx_max_coalesced_frames = apc->intr_modr_tx_comp;
+
+	ec->use_adaptive_rx_coalesce = apc->rx_dim_enabled;
+	ec->use_adaptive_tx_coalesce = apc->tx_dim_enabled;
+
 	return 0;
 }
 
@@ -428,9 +437,34 @@ static int mana_set_coalesce(struct net_device *ndev,
 			     struct netlink_ext_ack *extack)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
-	u8 saved_cqe_coalescing_enable;
+	struct {
+		u16 intr_modr_rx_usec;
+		u16 intr_modr_rx_comp;
+		u16 intr_modr_tx_usec;
+		u16 intr_modr_tx_comp;
+		u8 cqe_coalescing_enable;
+		bool rx_dim_enabled;
+		bool tx_dim_enabled;
+	} saved;
+	bool modr_changed = false;
+	bool dim_changed = false;
+	struct gdma_context *gc;
 	int err;
 
+	gc = apc->ac->gdma_dev->gdma_context;
+
+	/* Both static and dynamic interrupt moderation (DIM) rely on the
+	 * same HW capability advertised by the PF.
+	 */
+	if ((ec->use_adaptive_rx_coalesce || ec->use_adaptive_tx_coalesce ||
+	     ec->rx_coalesce_usecs || ec->tx_coalesce_usecs ||
+	     ec->rx_max_coalesced_frames || ec->tx_max_coalesced_frames) &&
+	    !(gc->pf_cap_flags1 & GDMA_PF_CAP_FLAG_1_DYN_INTERRUPT_MODERATION)) {
+		NL_SET_ERR_MSG(extack,
+			       "Interrupt Moderation is not supported by HW");
+		return -EOPNOTSUPP;
+	}
+
 	if (kernel_coal->rx_cqe_frames != 1 &&
 	    kernel_coal->rx_cqe_frames != MANA_RXCOMP_OOB_NUM_PPI) {
 		NL_SET_ERR_MSG_FMT(extack,
@@ -440,18 +474,129 @@ static int mana_set_coalesce(struct net_device *ndev,
 		return -EINVAL;
 	}
 
-	saved_cqe_coalescing_enable = apc->cqe_coalescing_enable;
+	if (ec->rx_coalesce_usecs > MANA_INTR_MODR_USEC_MAX ||
+	    ec->tx_coalesce_usecs > MANA_INTR_MODR_USEC_MAX) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "coalesce usecs must be <= %lu",
+				   MANA_INTR_MODR_USEC_MAX);
+		return -EINVAL;
+	}
+
+	if (ec->rx_max_coalesced_frames > MANA_INTR_MODR_COMP_MAX ||
+	    ec->tx_max_coalesced_frames > MANA_INTR_MODR_COMP_MAX) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "coalesce frames must be <= %lu",
+				   MANA_INTR_MODR_COMP_MAX);
+		return -EINVAL;
+	}
+
+	if (ec->rx_coalesce_usecs != apc->intr_modr_rx_usec ||
+	    ec->rx_max_coalesced_frames != apc->intr_modr_rx_comp ||
+	    ec->tx_coalesce_usecs != apc->intr_modr_tx_usec ||
+	    ec->tx_max_coalesced_frames != apc->intr_modr_tx_comp)
+		modr_changed = true;
+
+	saved.intr_modr_rx_usec = apc->intr_modr_rx_usec;
+	saved.intr_modr_rx_comp = apc->intr_modr_rx_comp;
+	saved.intr_modr_tx_usec = apc->intr_modr_tx_usec;
+	saved.intr_modr_tx_comp = apc->intr_modr_tx_comp;
+
+	apc->intr_modr_rx_usec = ec->rx_coalesce_usecs;
+	apc->intr_modr_rx_comp = ec->rx_max_coalesced_frames;
+	apc->intr_modr_tx_usec = ec->tx_coalesce_usecs;
+	apc->intr_modr_tx_comp = ec->tx_max_coalesced_frames;
+
+	if (!!ec->use_adaptive_rx_coalesce != apc->rx_dim_enabled ||
+	    !!ec->use_adaptive_tx_coalesce != apc->tx_dim_enabled)
+		dim_changed = true;
+
+	saved.rx_dim_enabled = apc->rx_dim_enabled;
+	saved.tx_dim_enabled = apc->tx_dim_enabled;
+
+	saved.cqe_coalescing_enable = apc->cqe_coalescing_enable;
 	apc->cqe_coalescing_enable =
 		kernel_coal->rx_cqe_frames == MANA_RXCOMP_OOB_NUM_PPI;
 
-	if (!apc->port_is_up)
+	if (!apc->port_is_up) {
+		WRITE_ONCE(apc->rx_dim_enabled, !!ec->use_adaptive_rx_coalesce);
+		WRITE_ONCE(apc->tx_dim_enabled, !!ec->use_adaptive_tx_coalesce);
 		return 0;
+	}
 
-	err = mana_config_rss(apc, TRI_STATE_TRUE, false, false);
-	if (err)
-		apc->cqe_coalescing_enable = saved_cqe_coalescing_enable;
+	if (apc->cqe_coalescing_enable != saved.cqe_coalescing_enable) {
+		/* CQE coalescing setting is applied via RSS configuration. */
+		err = mana_config_rss(apc, TRI_STATE_TRUE, false, false);
+		if (err) {
+			netdev_err(ndev, "Change CQE coalescing failed: %d\n",
+				   err);
+			apc->cqe_coalescing_enable =
+				saved.cqe_coalescing_enable;
+			apc->intr_modr_rx_usec = saved.intr_modr_rx_usec;
+			apc->intr_modr_rx_comp = saved.intr_modr_rx_comp;
+			apc->intr_modr_tx_usec = saved.intr_modr_tx_usec;
+			apc->intr_modr_tx_comp = saved.intr_modr_tx_comp;
+			return err;
+		}
+	}
 
-	return err;
+	if (modr_changed || dim_changed) {
+		bool new_rx_dim = !!ec->use_adaptive_rx_coalesce;
+		bool new_tx_dim = !!ec->use_adaptive_tx_coalesce;
+		bool disable_rx_dim = saved.rx_dim_enabled && !new_rx_dim;
+		bool disable_tx_dim = saved.tx_dim_enabled && !new_tx_dim;
+		bool enable_rx_dim = !saved.rx_dim_enabled && new_rx_dim;
+		bool enable_tx_dim = !saved.tx_dim_enabled && new_tx_dim;
+		int q;
+
+		/* On disable: clear the per-port flag first and
+		 * synchronize_net() so any in-flight NAPI poll observes
+		 * the new value and will not schedule further DIM work;
+		 * then drain pending work and restore the static
+		 * moderation values.
+		 */
+		if (disable_rx_dim)
+			WRITE_ONCE(apc->rx_dim_enabled, false);
+		if (disable_tx_dim)
+			WRITE_ONCE(apc->tx_dim_enabled, false);
+		if (disable_rx_dim || disable_tx_dim)
+			synchronize_net();
+
+		for (q = 0; q < apc->num_queues; q++) {
+			struct mana_cq *rx_cq = &apc->rxqs[q]->rx_cq;
+			struct mana_cq *tx_cq = &apc->tx_qp[q]->tx_cq;
+
+			if (disable_rx_dim)
+				mana_dim_change(rx_cq, false);
+			else if (enable_rx_dim)
+				mana_dim_change(rx_cq, true);
+			else if (!new_rx_dim && modr_changed)
+				mana_gd_ring_dim(rx_cq->gdma_cq,
+						 apc->intr_modr_rx_usec, true,
+						 apc->intr_modr_rx_comp, true);
+
+			if (disable_tx_dim)
+				mana_dim_change(tx_cq, false);
+			else if (enable_tx_dim)
+				mana_dim_change(tx_cq, true);
+			else if (!new_tx_dim && modr_changed)
+				mana_gd_ring_dim(tx_cq->gdma_cq,
+						 apc->intr_modr_tx_usec, true,
+						 apc->intr_modr_tx_comp, true);
+		}
+
+		/* Publish the enable flag with release semantics so a
+		 * concurrent NAPI poll that observes it set also sees the DIM
+		 * (re)init done by mana_dim_change() above.
+		 */
+		if (enable_rx_dim)
+			/* pairs with smp_load_acquire() in mana_update_rx_dim() */
+			smp_store_release(&apc->rx_dim_enabled, true);
+		if (enable_tx_dim)
+			/* pairs with smp_load_acquire() in mana_update_tx_dim() */
+			smp_store_release(&apc->tx_dim_enabled, true);
+	}
+
+	return 0;
 }
 
 /* mana_set_channels - change the number of queues on a port
@@ -595,7 +740,13 @@ static int mana_get_link_ksettings(struct net_device *ndev,
 }
 
 const struct ethtool_ops mana_ethtool_ops = {
-	.supported_coalesce_params = ETHTOOL_COALESCE_RX_CQE_FRAMES,
+	.supported_coalesce_params = ETHTOOL_COALESCE_RX_CQE_FRAMES |
+				     ETHTOOL_COALESCE_RX_USECS |
+				     ETHTOOL_COALESCE_RX_MAX_FRAMES |
+				     ETHTOOL_COALESCE_TX_USECS |
+				     ETHTOOL_COALESCE_TX_MAX_FRAMES |
+				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX |
+				     ETHTOOL_COALESCE_USE_ADAPTIVE_TX,
 	.op_needs_rtnl		= ETHTOOL_OP_NEEDS_RTNL_SCHANNELS |
 				  ETHTOOL_OP_NEEDS_RTNL_SRINGPARAM |
 				  ETHTOOL_OP_NEEDS_RTNL_GLINK,
diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
index 0727d53345a3..417c15d1ff42 100644
--- a/drivers/net/ethernet/oa_tc6.c
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -12,46 +12,6 @@
 #include <linux/phy.h>
 #include <linux/oa_tc6.h>
 
-/* OPEN Alliance TC6 registers */
-/* Standard Capabilities Register */
-#define OA_TC6_REG_STDCAP			0x0002
-#define STDCAP_DIRECT_PHY_REG_ACCESS		BIT(8)
-
-/* Reset Control and Status Register */
-#define OA_TC6_REG_RESET			0x0003
-#define RESET_SWRESET				BIT(0)	/* Software Reset */
-
-/* Configuration Register #0 */
-#define OA_TC6_REG_CONFIG0			0x0004
-#define CONFIG0_SYNC				BIT(15)
-#define CONFIG0_ZARFE_ENABLE			BIT(12)
-
-/* Status Register #0 */
-#define OA_TC6_REG_STATUS0			0x0008
-#define STATUS0_RESETC				BIT(6)	/* Reset Complete */
-#define STATUS0_HEADER_ERROR			BIT(5)
-#define STATUS0_LOSS_OF_FRAME_ERROR		BIT(4)
-#define STATUS0_RX_BUFFER_OVERFLOW_ERROR	BIT(3)
-#define STATUS0_TX_PROTOCOL_ERROR		BIT(0)
-
-/* Buffer Status Register */
-#define OA_TC6_REG_BUFFER_STATUS		0x000B
-#define BUFFER_STATUS_TX_CREDITS_AVAILABLE	GENMASK(15, 8)
-#define BUFFER_STATUS_RX_CHUNKS_AVAILABLE	GENMASK(7, 0)
-
-/* Interrupt Mask Register #0 */
-#define OA_TC6_REG_INT_MASK0			0x000C
-#define INT_MASK0_HEADER_ERR_MASK		BIT(5)
-#define INT_MASK0_LOSS_OF_FRAME_ERR_MASK	BIT(4)
-#define INT_MASK0_RX_BUFFER_OVERFLOW_ERR_MASK	BIT(3)
-#define INT_MASK0_TX_PROTOCOL_ERR_MASK		BIT(0)
-#define INT_MASK0_ALL_INTERRUPTS                (GENMASK(5, 0) | \
-						 GENMASK(12, 7))
-
-/* PHY Clause 22 registers base address and mask */
-#define OA_TC6_PHY_STD_REG_ADDR_BASE		0xFF00
-#define OA_TC6_PHY_STD_REG_ADDR_MASK		0x1F
-
 /* Control command header */
 #define OA_TC6_CTRL_HEADER_DATA_NOT_CTRL	BIT(31)
 #define OA_TC6_CTRL_HEADER_WRITE_NOT_READ	BIT(29)
@@ -81,23 +41,17 @@
 #define OA_TC6_DATA_FOOTER_END_BYTE_OFFSET	GENMASK(13, 8)
 #define OA_TC6_DATA_FOOTER_TX_CREDITS		GENMASK(5, 1)
 
-/* PHY – Clause 45 registers memory map selector (MMS) as per table 6 in the
- * OPEN Alliance specification.
- */
-#define OA_TC6_PHY_C45_PCS_MMS2			2	/* MMD 3 */
-#define OA_TC6_PHY_C45_PMA_PMD_MMS3		3	/* MMD 1 */
-#define OA_TC6_PHY_C45_VS_PLCA_MMS4		4	/* MMD 31 */
-#define OA_TC6_PHY_C45_AUTO_NEG_MMS5		5	/* MMD 7 */
-#define OA_TC6_PHY_C45_POWER_UNIT_MMS6		6	/* MMD 13 */
-
+#define OA_TC6_CTRL_PROT_REPLY_SIZE		4
 #define OA_TC6_CTRL_HEADER_SIZE			4
 #define OA_TC6_CTRL_REG_VALUE_SIZE		4
 #define OA_TC6_CTRL_IGNORED_SIZE		4
 #define OA_TC6_CTRL_MAX_REGISTERS		128
-#define OA_TC6_CTRL_SPI_BUF_SIZE		(OA_TC6_CTRL_HEADER_SIZE +\
-						(OA_TC6_CTRL_MAX_REGISTERS *\
-						OA_TC6_CTRL_REG_VALUE_SIZE) +\
-						OA_TC6_CTRL_IGNORED_SIZE)
+#define OA_TC6_CTRL_SPI_BUF_SIZE	(OA_TC6_CTRL_HEADER_SIZE +\
+					(OA_TC6_CTRL_MAX_REGISTERS *\
+					(OA_TC6_CTRL_REG_VALUE_SIZE +\
+					OA_TC6_CTRL_PROT_REPLY_SIZE)) +\
+					OA_TC6_CTRL_IGNORED_SIZE)
+
 #define OA_TC6_CHUNK_PAYLOAD_SIZE		64
 #define OA_TC6_DATA_HEADER_SIZE			4
 #define OA_TC6_CHUNK_SIZE			(OA_TC6_DATA_HEADER_SIZE +\
@@ -108,6 +62,8 @@
 #define STATUS0_RESETC_POLL_DELAY		1000
 #define STATUS0_RESETC_POLL_TIMEOUT		1000000
 
+#define OA_TC6_REG_MMS_MASK		GENMASK(19, 16)
+
 /* Internal structure for MAC-PHY drivers */
 struct oa_tc6 {
 	struct net_device *netdev;
@@ -130,6 +86,8 @@ struct oa_tc6 {
 	bool rx_buf_overflow;
 	bool int_flag;
 	bool disable_traffic;
+	bool prot_ctrl;
+	enum oa_tc6_quirk_flag quirk_flags;
 };
 
 enum oa_tc6_header_type {
@@ -213,25 +171,36 @@ static void oa_tc6_update_ctrl_write_data(struct oa_tc6 *tc6, u32 value[],
 {
 	__be32 *tx_buf = tc6->spi_ctrl_tx_buf + OA_TC6_CTRL_HEADER_SIZE;
 
-	for (int i = 0; i < length; i++)
+	for (int i = 0; i < length; i++) {
 		*tx_buf++ = cpu_to_be32(value[i]);
+		if (tc6->prot_ctrl)
+			*tx_buf++ = cpu_to_be32(~value[i]);
+	}
 }
 
-static u16 oa_tc6_calculate_ctrl_buf_size(u8 length)
+static u16 oa_tc6_calculate_ctrl_buf_size(u8 length, bool ctrl_prot)
 {
+	u32 reply_size = OA_TC6_CTRL_REG_VALUE_SIZE;
+
+	if (ctrl_prot)
+		reply_size += OA_TC6_CTRL_PROT_REPLY_SIZE;
+
 	/* Control command consists 4 bytes header + 4 bytes register value for
-	 * each register + 4 bytes ignored value.
+	 * each register (+ 4 bytes for the register value complement in case
+	 * protected mode is used) + 4 bytes ignored value.
 	 */
-	return OA_TC6_CTRL_HEADER_SIZE + OA_TC6_CTRL_REG_VALUE_SIZE * length +
+	return OA_TC6_CTRL_HEADER_SIZE + reply_size * length +
 	       OA_TC6_CTRL_IGNORED_SIZE;
 }
 
 static void oa_tc6_prepare_ctrl_spi_buf(struct oa_tc6 *tc6, u32 address,
 					u32 value[], u8 length,
-					enum oa_tc6_register_op reg_op)
+					enum oa_tc6_register_op reg_op,
+					u16 buf_size)
 {
 	__be32 *tx_buf = tc6->spi_ctrl_tx_buf;
 
+	memset(tx_buf, 0, buf_size);
 	*tx_buf = oa_tc6_prepare_ctrl_header(address, length, reg_op);
 
 	if (reg_op == OA_TC6_CTRL_REG_WRITE)
@@ -254,10 +223,12 @@ static int oa_tc6_check_ctrl_write_reply(struct oa_tc6 *tc6, u8 size)
 	return 0;
 }
 
-static int oa_tc6_check_ctrl_read_reply(struct oa_tc6 *tc6, u8 size)
+static int oa_tc6_check_ctrl_read_reply(struct oa_tc6 *tc6, u8 length)
 {
-	u32 *rx_buf = tc6->spi_ctrl_rx_buf + OA_TC6_CTRL_IGNORED_SIZE;
-	u32 *tx_buf = tc6->spi_ctrl_tx_buf;
+	__be32 *rx_buf = tc6->spi_ctrl_rx_buf + OA_TC6_CTRL_IGNORED_SIZE;
+	__be32 *tx_buf = tc6->spi_ctrl_tx_buf;
+	u32 complement;
+	u32 reply;
 
 	/* The echoed control read header must match with the one that was
 	 * transmitted.
@@ -265,6 +236,20 @@ static int oa_tc6_check_ctrl_read_reply(struct oa_tc6 *tc6, u8 size)
 	if (*tx_buf != *rx_buf)
 		return -EPROTO;
 
+	if (tc6->prot_ctrl) {
+		/* Skip past the echoed header to the value/complement pairs */
+		rx_buf += 1;
+		for (int i = 0; i < length; i++) {
+			reply = be32_to_cpu(rx_buf[0]);
+			complement = be32_to_cpu(rx_buf[1]);
+
+			if (complement != ~reply)
+				return -EPROTO;
+
+			rx_buf += 2;
+		}
+	}
+
 	return 0;
 }
 
@@ -274,8 +259,13 @@ static void oa_tc6_copy_ctrl_read_data(struct oa_tc6 *tc6, u32 value[],
 	__be32 *rx_buf = tc6->spi_ctrl_rx_buf + OA_TC6_CTRL_IGNORED_SIZE +
 			 OA_TC6_CTRL_HEADER_SIZE;
 
-	for (int i = 0; i < length; i++)
+	for (int i = 0; i < length; i++) {
 		value[i] = be32_to_cpu(*rx_buf++);
+
+		/* skip complement word */
+		if (tc6->prot_ctrl)
+			rx_buf++;
+	}
 }
 
 static int oa_tc6_perform_ctrl(struct oa_tc6 *tc6, u32 address, u32 value[],
@@ -284,10 +274,10 @@ static int oa_tc6_perform_ctrl(struct oa_tc6 *tc6, u32 address, u32 value[],
 	u16 size;
 	int ret;
 
-	/* Prepare control command and copy to SPI control buffer */
-	oa_tc6_prepare_ctrl_spi_buf(tc6, address, value, length, reg_op);
+	size = oa_tc6_calculate_ctrl_buf_size(length, tc6->prot_ctrl);
 
-	size = oa_tc6_calculate_ctrl_buf_size(length);
+	/* Prepare control command and copy to SPI control buffer */
+	oa_tc6_prepare_ctrl_spi_buf(tc6, address, value, length, reg_op, size);
 
 	/* Perform SPI transfer */
 	ret = oa_tc6_spi_transfer(tc6, OA_TC6_CTRL_HEADER, size);
@@ -302,7 +292,7 @@ static int oa_tc6_perform_ctrl(struct oa_tc6 *tc6, u32 address, u32 value[],
 		return oa_tc6_check_ctrl_write_reply(tc6, size);
 
 	/* Check echoed/received control read command reply for errors */
-	ret = oa_tc6_check_ctrl_read_reply(tc6, size);
+	ret = oa_tc6_check_ctrl_read_reply(tc6, length);
 	if (ret)
 		return ret;
 
@@ -356,6 +346,27 @@ int oa_tc6_read_register(struct oa_tc6 *tc6, u32 address, u32 *value)
 EXPORT_SYMBOL_GPL(oa_tc6_read_register);
 
 /**
+ * oa_tc6_read_register_mms - function for reading a MAC-PHY register in a
+ * specified memory map.
+ * @tc6: oa_tc6 struct.
+ * @mms: Memory map selector for the register.
+ * @address: register address of the MAC-PHY to be read.
+ * @value: value read from the @address register address of the MAC-PHY.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int oa_tc6_read_register_mms(struct oa_tc6 *tc6, u8 mms, u16 address,
+			     u32 *value)
+{
+	u32 mms_reg;
+
+	mms_reg = FIELD_PREP(OA_TC6_REG_MMS_MASK, mms) | address;
+
+	return oa_tc6_read_registers(tc6, mms_reg, value, 1);
+}
+EXPORT_SYMBOL_GPL(oa_tc6_read_register_mms);
+
+/**
  * oa_tc6_write_registers - function for writing multiple consecutive registers.
  * @tc6: oa_tc6 struct.
  * @address: address of the first register to be written in the MAC-PHY.
@@ -399,6 +410,27 @@ int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value)
 }
 EXPORT_SYMBOL_GPL(oa_tc6_write_register);
 
+/**
+ * oa_tc6_write_register_mms - function for writing a MAC-PHY register in a
+ * specified memory map.
+ * @tc6: oa_tc6 struct.
+ * @mms: Memory map selector for the register.
+ * @address: register address of the MAC-PHY to be written.
+ * @value: value to be written in the @address register address of the MAC-PHY.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int oa_tc6_write_register_mms(struct oa_tc6 *tc6, u8 mms, u16 address,
+			      u32 value)
+{
+	u32 mms_reg;
+
+	mms_reg = FIELD_PREP(OA_TC6_REG_MMS_MASK, mms) | address;
+
+	return oa_tc6_write_registers(tc6, mms_reg, &value, 1);
+}
+EXPORT_SYMBOL_GPL(oa_tc6_write_register_mms);
+
 static int oa_tc6_check_phy_reg_direct_access_capability(struct oa_tc6 *tc6)
 {
 	u32 regval;
@@ -408,7 +440,7 @@ static int oa_tc6_check_phy_reg_direct_access_capability(struct oa_tc6 *tc6)
 	if (ret)
 		return ret;
 
-	if (!(regval & STDCAP_DIRECT_PHY_REG_ACCESS))
+	if (!(regval & OA_TC6_STDCAP_DIRECT_PHY_REG_ACCESS))
 		return -ENODEV;
 
 	return 0;
@@ -462,36 +494,39 @@ static int oa_tc6_get_phy_c45_mms(int devnum)
 	}
 }
 
-static int oa_tc6_mdiobus_read_c45(struct mii_bus *bus, int addr, int devnum,
-				   int regnum)
+int oa_tc6_mdiobus_read_c45(struct mii_bus *bus, int addr, int devnum,
+			    int regnum)
 {
 	struct oa_tc6 *tc6 = bus->priv;
 	u32 regval;
+	int mms;
 	int ret;
 
-	ret = oa_tc6_get_phy_c45_mms(devnum);
-	if (ret < 0)
-		return ret;
+	mms = oa_tc6_get_phy_c45_mms(devnum);
+	if (mms < 0)
+		return mms;
 
-	ret = oa_tc6_read_register(tc6, (ret << 16) | regnum, &regval);
+	ret = oa_tc6_read_register_mms(tc6, mms, regnum, &regval);
 	if (ret)
 		return ret;
 
 	return regval;
 }
+EXPORT_SYMBOL_GPL(oa_tc6_mdiobus_read_c45);
 
-static int oa_tc6_mdiobus_write_c45(struct mii_bus *bus, int addr, int devnum,
-				    int regnum, u16 val)
+int oa_tc6_mdiobus_write_c45(struct mii_bus *bus, int addr, int devnum,
+			     int regnum, u16 val)
 {
 	struct oa_tc6 *tc6 = bus->priv;
-	int ret;
+	int mms;
 
-	ret = oa_tc6_get_phy_c45_mms(devnum);
-	if (ret < 0)
-		return ret;
+	mms = oa_tc6_get_phy_c45_mms(devnum);
+	if (mms < 0)
+		return mms;
 
-	return oa_tc6_write_register(tc6, (ret << 16) | regnum, val);
+	return oa_tc6_write_register_mms(tc6, mms, regnum, val);
 }
+EXPORT_SYMBOL_GPL(oa_tc6_mdiobus_write_c45);
 
 static int oa_tc6_mdiobus_register(struct oa_tc6 *tc6)
 {
@@ -544,6 +579,9 @@ static int oa_tc6_phy_init(struct oa_tc6 *tc6)
 {
 	int ret;
 
+	if (tc6->quirk_flags & OA_TC6_BROKEN_PHY)
+		return 0;
+
 	ret = oa_tc6_check_phy_reg_direct_access_capability(tc6);
 	if (ret) {
 		netdev_err(tc6->netdev,
@@ -580,6 +618,9 @@ static int oa_tc6_phy_init(struct oa_tc6 *tc6)
 
 static void oa_tc6_phy_exit(struct oa_tc6 *tc6)
 {
+	if (tc6->quirk_flags & OA_TC6_BROKEN_PHY)
+		return;
+
 	phy_disconnect(tc6->phydev);
 	oa_tc6_mdiobus_unregister(tc6);
 }
@@ -601,7 +642,7 @@ static int oa_tc6_read_status0(struct oa_tc6 *tc6)
 
 static int oa_tc6_sw_reset_macphy(struct oa_tc6 *tc6)
 {
-	u32 regval = RESET_SWRESET;
+	u32 regval = OA_TC6_RESET_SWRESET;
 	int ret;
 
 	ret = oa_tc6_write_register(tc6, OA_TC6_REG_RESET, regval);
@@ -610,7 +651,7 @@ static int oa_tc6_sw_reset_macphy(struct oa_tc6 *tc6)
 
 	/* Poll for soft reset complete for every 1ms until 1s timeout */
 	ret = readx_poll_timeout(oa_tc6_read_status0, tc6, regval,
-				 regval & STATUS0_RESETC,
+				 regval & OA_TC6_STATUS0_RESETC,
 				 STATUS0_RESETC_POLL_DELAY,
 				 STATUS0_RESETC_POLL_TIMEOUT);
 	if (ret)
@@ -629,10 +670,10 @@ static int oa_tc6_unmask_macphy_error_interrupts(struct oa_tc6 *tc6)
 	if (ret)
 		return ret;
 
-	regval &= ~(INT_MASK0_TX_PROTOCOL_ERR_MASK |
-		    INT_MASK0_RX_BUFFER_OVERFLOW_ERR_MASK |
-		    INT_MASK0_LOSS_OF_FRAME_ERR_MASK |
-		    INT_MASK0_HEADER_ERR_MASK);
+	regval &= ~(OA_TC6_INT_MASK0_TX_PROTOCOL_ERR_MASK |
+		    OA_TC6_INT_MASK0_RX_BUFFER_OVERFLOW_ERR_MASK |
+		    OA_TC6_INT_MASK0_LOSS_OF_FRAME_ERR_MASK |
+		    OA_TC6_INT_MASK0_HEADER_ERR_MASK);
 
 	return oa_tc6_write_register(tc6, OA_TC6_REG_INT_MASK0, regval);
 }
@@ -647,7 +688,7 @@ static int oa_tc6_enable_data_transfer(struct oa_tc6 *tc6)
 		return ret;
 
 	/* Enable configuration synchronization for data transfer */
-	value |= CONFIG0_SYNC;
+	value |= OA_TC6_CONFIG0_SYNC;
 
 	return oa_tc6_write_register(tc6, OA_TC6_REG_CONFIG0, value);
 }
@@ -692,7 +733,7 @@ static void oa_tc6_free_pending_skbs(struct oa_tc6 *tc6)
  */
 static void oa_tc6_disable_traffic(struct oa_tc6 *tc6)
 {
-	u32 regval = INT_MASK0_ALL_INTERRUPTS;
+	u32 regval = OA_TC6_INT_MASK0_ALL_INTERRUPTS;
 
 	tc6->disable_traffic = true;
 	oa_tc6_free_pending_skbs(tc6);
@@ -722,25 +763,25 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6)
 		return ret;
 	}
 
-	if (FIELD_GET(STATUS0_RX_BUFFER_OVERFLOW_ERROR, value)) {
+	if (FIELD_GET(OA_TC6_STATUS0_RX_BUFFER_OVERFLOW_ERROR, value)) {
 		tc6->rx_buf_overflow = true;
 		oa_tc6_cleanup_ongoing_rx_skb(tc6);
 		net_err_ratelimited("%s: Receive buffer overflow error\n",
 				    tc6->netdev->name);
 		return -EAGAIN;
 	}
-	if (FIELD_GET(STATUS0_TX_PROTOCOL_ERROR, value)) {
+	if (FIELD_GET(OA_TC6_STATUS0_TX_PROTOCOL_ERROR, value)) {
 		netdev_err(tc6->netdev, "Transmit protocol error\n");
 		return -ENODEV;
 	}
 	/* TODO: Currently loss of frame and header errors are treated as
 	 * non-recoverable errors. They will be handled in the next version.
 	 */
-	if (FIELD_GET(STATUS0_LOSS_OF_FRAME_ERROR, value)) {
+	if (FIELD_GET(OA_TC6_STATUS0_LOSS_OF_FRAME_ERROR, value)) {
 		netdev_err(tc6->netdev, "Loss of frame error\n");
 		return -ENODEV;
 	}
-	if (FIELD_GET(STATUS0_HEADER_ERROR, value)) {
+	if (FIELD_GET(OA_TC6_STATUS0_HEADER_ERROR, value)) {
 		netdev_err(tc6->netdev, "Header error\n");
 		return -ENODEV;
 	}
@@ -1187,9 +1228,10 @@ static int oa_tc6_update_buffer_status_from_register(struct oa_tc6 *tc6)
 	if (ret)
 		return ret;
 
-	tc6->tx_credits = FIELD_GET(BUFFER_STATUS_TX_CREDITS_AVAILABLE, value);
-	tc6->rx_chunks_available = FIELD_GET(BUFFER_STATUS_RX_CHUNKS_AVAILABLE,
-					     value);
+	tc6->tx_credits = FIELD_GET(OA_TC6_BUFFER_STATUS_TX_CREDITS_AVAILABLE,
+				    value);
+	tc6->rx_chunks_available =
+		FIELD_GET(OA_TC6_BUFFER_STATUS_RX_CHUNKS_AVAILABLE, value);
 
 	return 0;
 }
@@ -1233,7 +1275,7 @@ int oa_tc6_zero_align_receive_frame_enable(struct oa_tc6 *tc6)
 		return ret;
 
 	/* Set Zero-Align Receive Frame Enable */
-	regval |= CONFIG0_ZARFE_ENABLE;
+	regval |= OA_TC6_CONFIG0_ZARFE_ENABLE;
 
 	return oa_tc6_write_register(tc6, OA_TC6_REG_CONFIG0, regval);
 }
@@ -1272,15 +1314,31 @@ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(oa_tc6_start_xmit);
 
+static int oa_tc6_check_ctrl_protection(struct oa_tc6 *tc6)
+{
+	u32 regval;
+	int ret;
+
+	ret = oa_tc6_read_register(tc6, OA_TC6_REG_CONFIG0, &regval);
+	if (ret)
+		return ret;
+
+	tc6->prot_ctrl = FIELD_GET(OA_TC6_CONFIG0_PROTE, regval);
+
+	return 0;
+}
+
 /**
  * oa_tc6_init - allocates and initializes oa_tc6 structure.
  * @spi: device with which data will be exchanged.
  * @netdev: network device interface structure.
+ * @quirks: device specific modifiers for the OA TC6 protocol.
  *
  * Return: pointer reference to the oa_tc6 structure if the MAC-PHY
  * initialization is successful otherwise NULL.
  */
-struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev)
+struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev,
+			   struct oa_tc6_quirks *quirks)
 {
 	struct oa_tc6 *tc6;
 	int ret;
@@ -1295,6 +1353,9 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev)
 	mutex_init(&tc6->spi_ctrl_lock);
 	spin_lock_init(&tc6->tx_skb_lock);
 
+	if (quirks)
+		tc6->quirk_flags = quirks->quirk_flags;
+
 	/* Set the SPI controller to pump at realtime priority */
 	tc6->spi->rt = true;
 	if (spi_setup(tc6->spi) < 0)
@@ -1324,6 +1385,14 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev)
 	if (!tc6->spi_data_rx_buf)
 		return NULL;
 
+	/* Check the PROTE bit status so that we can reset the device */
+	ret = oa_tc6_check_ctrl_protection(tc6);
+	if (ret) {
+		dev_err(&tc6->spi->dev,
+			"Failed to check the protection mode: %d\n", ret);
+		return NULL;
+	}
+
 	ret = oa_tc6_sw_reset_macphy(tc6);
 	if (ret) {
 		dev_err(&tc6->spi->dev,
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 48b94ce77490..88c5c52e0e38 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -16,7 +16,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/ptp_classify.h>
 #include <linux/ptp_pch.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
 #define PCH_GBE_MAR_ENTRIES		16
 #define PCH_GBE_SHORT_PKT		64
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c
index 528114877677..c999754afb5f 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c
@@ -558,18 +558,15 @@ struct sync_item {
 void ionic_rx_filter_sync(struct ionic_lif *lif)
 {
 	struct device *dev = lif->ionic->dev;
-	struct list_head sync_add_list;
-	struct list_head sync_del_list;
 	struct sync_item *sync_item;
 	struct ionic_rx_filter *f;
+	LIST_HEAD(sync_add_list);
+	LIST_HEAD(sync_del_list);
 	struct hlist_head *head;
 	struct hlist_node *tmp;
 	struct sync_item *spos;
 	unsigned int i;
 
-	INIT_LIST_HEAD(&sync_add_list);
-	INIT_LIST_HEAD(&sync_del_list);
-
 	clear_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state);
 
 	/* Copy the filters to be added and deleted
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 3a5c25026858..19c2b870feed 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -639,7 +639,7 @@ qed_dcbx_get_operational_params(struct qed_hwfn *p_hwfn,
 	flags = p_hwfn->p_dcbx_info->operational.flags;
 
 	/* If DCBx version is non zero, then negotiation
-	 * was successfuly performed
+	 * was successfully performed
 	 */
 	p_operational = &params->operational;
 	enabled = !!(QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION) !=
diff --git a/drivers/net/ethernet/qualcomm/ppe/ppe.c b/drivers/net/ethernet/qualcomm/ppe/ppe.c
index be747510d947..3c301e609d3e 100644
--- a/drivers/net/ethernet/qualcomm/ppe/ppe.c
+++ b/drivers/net/ethernet/qualcomm/ppe/ppe.c
@@ -106,7 +106,6 @@ static const struct regmap_config regmap_config_ipq9574 = {
 	.rd_table = &ppe_reg_table,
 	.wr_table = &ppe_reg_table,
 	.max_register = 0xbef800,
-	.fast_io = true,
 };
 
 static int ppe_clock_init_and_reset(struct ppe_device *ppe_dev)
diff --git a/drivers/net/ethernet/qualcomm/ppe/ppe_config.c b/drivers/net/ethernet/qualcomm/ppe/ppe_config.c
index e9a0e22907a6..125b73be92b1 100644
--- a/drivers/net/ethernet/qualcomm/ppe/ppe_config.c
+++ b/drivers/net/ethernet/qualcomm/ppe/ppe_config.c
@@ -1367,7 +1367,8 @@ int ppe_rss_hash_config_set(struct ppe_device *ppe_dev, int mode,
  *
  * Return: 0 on success, negative error code on failure.
  */
-int ppe_ring_queue_map_set(struct ppe_device *ppe_dev, int ring_id, u32 *queue_map)
+int ppe_ring_queue_map_set(struct ppe_device *ppe_dev, int ring_id,
+			   const u32 *queue_map)
 {
 	u32 reg, queue_bitmap_val[PPE_RING_TO_QUEUE_BITMAP_WORD_CNT];
 
@@ -1380,7 +1381,7 @@ int ppe_ring_queue_map_set(struct ppe_device *ppe_dev, int ring_id, u32 *queue_m
 }
 
 static int ppe_config_bm_threshold(struct ppe_device *ppe_dev, int bm_port_id,
-				   const struct ppe_bm_port_config port_cfg)
+				   struct ppe_bm_port_config port_cfg)
 {
 	u32 reg, val, bm_fc_val[2];
 	int ret;
@@ -1586,7 +1587,7 @@ qm_config_fail:
 }
 
 static int ppe_node_scheduler_config(struct ppe_device *ppe_dev,
-				     const struct ppe_scheduler_port_config config)
+				     struct ppe_scheduler_port_config config)
 {
 	struct ppe_scheduler_cfg sch_cfg;
 	int ret, i;
diff --git a/drivers/net/ethernet/qualcomm/ppe/ppe_config.h b/drivers/net/ethernet/qualcomm/ppe/ppe_config.h
index 4bb45ca40144..60493e51e0a4 100644
--- a/drivers/net/ethernet/qualcomm/ppe/ppe_config.h
+++ b/drivers/net/ethernet/qualcomm/ppe/ppe_config.h
@@ -313,5 +313,5 @@ int ppe_rss_hash_config_set(struct ppe_device *ppe_dev, int mode,
 			    struct ppe_rss_hash_cfg hash_cfg);
 int ppe_ring_queue_map_set(struct ppe_device *ppe_dev,
 			   int ring_id,
-			   u32 *queue_map);
+			   const u32 *queue_map);
 #endif
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 78d4df55740a..bed6f63facf2 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -423,7 +423,8 @@ struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id)
 {
 	struct rmnet_endpoint *ep;
 
-	hlist_for_each_entry_rcu(ep, &port->muxed_ep[mux_id], hlnode) {
+	hlist_for_each_entry_rcu(ep, &port->muxed_ep[mux_id], hlnode,
+				 lockdep_rtnl_is_held()) {
 		if (ep->mux_id == mux_id)
 			return ep;
 	}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c
index 2eccc7617507..e4701b29e1a0 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c
@@ -82,7 +82,6 @@ static int sxgbe_platform_probe(struct platform_device *pdev)
 	void __iomem *addr;
 	struct sxgbe_priv_data *priv = NULL;
 	struct sxgbe_plat_data *plat_dat = NULL;
-	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct device_node *node = dev->of_node;
 
 	/* Get memory resource */
@@ -158,7 +157,7 @@ err_tx_irq_unmap:
 		irq_dispose_mapping(priv->txq[i]->irq_no);
 	irq_dispose_mapping(priv->irq);
 err_drv_remove:
-	sxgbe_drv_remove(ndev);
+	sxgbe_drv_remove(priv->dev);
 err_out:
 	return -ENODEV;
 }
diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
index c4c43434f314..979f2801e2a8 100644
--- a/drivers/net/ethernet/sfc/Kconfig
+++ b/drivers/net/ethernet/sfc/Kconfig
@@ -66,6 +66,15 @@ config SFC_MCDI_LOGGING
 	  Driver-Interface) commands and responses, allowing debugging of
 	  driver/firmware interaction.  The tracing is actually enabled by
 	  a sysfs file 'mcdi_logging' under the PCI device.
+config SFC_CXL
+	bool "Solarflare SFC9100-family CXL support"
+	depends on SFC && CXL_BUS >= SFC
+	default SFC
+	help
+	  This enables SFC CXL support if the kernel is configuring CXL for
+	  using CTPIO with CXL.mem. The SFC device with CXL support and
+	  with a CXL-aware firmware can be used for minimizing latencies
+	  when sending through CTPIO.
 
 source "drivers/net/ethernet/sfc/falcon/Kconfig"
 source "drivers/net/ethernet/sfc/siena/Kconfig"
diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index d99039ec468d..bb0f1891cde6 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -13,6 +13,7 @@ sfc-$(CONFIG_SFC_SRIOV)	+= sriov.o ef10_sriov.o ef100_sriov.o ef100_rep.o \
                            mae.o tc.o tc_bindings.o tc_counters.o \
                            tc_encap_actions.o tc_conntrack.o
 
+sfc-$(CONFIG_SFC_CXL)	+= efx_cxl.o
 obj-$(CONFIG_SFC)	+= sfc.o
 
 obj-$(CONFIG_SFC_FALCON) += falcon/
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 7e04f115bbaa..73bc064929f6 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -24,6 +24,7 @@
 #include <linux/wait.h>
 #include <linux/workqueue.h>
 #include <net/udp_tunnel.h>
+#include "efx_cxl.h"
 
 /* Hardware control for EF10 architecture including 'Huntington'. */
 
@@ -106,7 +107,7 @@ static int efx_ef10_get_vf_index(struct efx_nic *efx)
 
 static int efx_ef10_init_datapath_caps(struct efx_nic *efx)
 {
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_CAPABILITIES_V4_OUT_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_CAPABILITIES_V7_OUT_LEN);
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	size_t outlen;
 	int rc;
@@ -177,6 +178,12 @@ static int efx_ef10_init_datapath_caps(struct efx_nic *efx)
 			  efx->num_mac_stats);
 	}
 
+	if (outlen < MC_CMD_GET_CAPABILITIES_V7_OUT_LEN)
+		nic_data->datapath_caps3 = 0;
+	else
+		nic_data->datapath_caps3 = MCDI_DWORD(outbuf,
+						      GET_CAPABILITIES_V7_OUT_FLAGS3);
+
 	return 0;
 }
 
@@ -1140,6 +1147,9 @@ static int efx_ef10_dimension_resources(struct efx_nic *efx)
 	unsigned int channel_vis, pio_write_vi_base, max_vis;
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	unsigned int uc_mem_map_size, wc_mem_map_size;
+#ifdef CONFIG_SFC_CXL
+	struct efx_probe_data *probe_data;
+#endif
 	void __iomem *membase;
 	int rc;
 
@@ -1263,8 +1273,23 @@ static int efx_ef10_dimension_resources(struct efx_nic *efx)
 	iounmap(efx->membase);
 	efx->membase = membase;
 
-	/* Set up the WC mapping if needed */
-	if (wc_mem_map_size) {
+	if (!wc_mem_map_size)
+		goto skip_pio;
+
+	/* Set up the WC mapping */
+
+#ifdef CONFIG_SFC_CXL
+	probe_data = container_of(efx, struct efx_probe_data, efx);
+	if ((nic_data->datapath_caps3 &
+	    (1 << MC_CMD_GET_CAPABILITIES_V7_OUT_CXL_CONFIG_ENABLE_LBN)) &&
+	    probe_data->cxl_pio_initialised) {
+		/* Using PIO through CXL mapping */
+		nic_data->pio_write_base = probe_data->cxl->ctpio_cxl;
+		nic_data->pio_write_vi_base = pio_write_vi_base;
+	} else
+#endif
+	{
+		/* Using legacy PIO BAR mapping */
 		nic_data->wc_membase = ioremap_wc(efx->membase_phys +
 						  uc_mem_map_size,
 						  wc_mem_map_size);
@@ -1279,12 +1304,14 @@ static int efx_ef10_dimension_resources(struct efx_nic *efx)
 			nic_data->wc_membase +
 			(pio_write_vi_base * efx->vi_stride + ER_DZ_TX_PIOBUF -
 			 uc_mem_map_size);
-
-		rc = efx_ef10_link_piobufs(efx);
-		if (rc)
-			efx_ef10_free_piobufs(efx);
 	}
 
+	rc = efx_ef10_link_piobufs(efx);
+	if (rc)
+		efx_ef10_free_piobufs(efx);
+
+skip_pio:
+
 	netif_dbg(efx, probe, efx->net_dev,
 		  "memory BAR at %pa (virtual %p+%x UC, %p+%x WC)\n",
 		  &efx->membase_phys, efx->membase, uc_mem_map_size,
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 8f136a11d396..3806cd3dd7f4 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -34,6 +34,7 @@
 #include "selftest.h"
 #include "sriov.h"
 #include "efx_devlink.h"
+#include "efx_cxl.h"
 
 #include "mcdi_port_common.h"
 #include "mcdi_pcol.h"
@@ -981,12 +982,15 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
 	efx_pci_remove_main(efx);
 
 	efx_fini_io(efx);
+
+	probe_data = container_of(efx, struct efx_probe_data, efx);
+	efx_cxl_exit(probe_data);
+
 	pci_dbg(efx->pci_dev, "shutdown successful\n");
 
 	efx_fini_devlink_and_unlock(efx);
 	efx_fini_struct(efx);
 	free_netdev(efx->net_dev);
-	probe_data = container_of(efx, struct efx_probe_data, efx);
 	kfree(probe_data);
 };
 
@@ -1190,6 +1194,17 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 	if (rc)
 		goto fail2;
 
+	/* A successful cxl initialization implies a CXL region created to be
+	 * used for PIO buffers. If there is no CXL support legacy PIO buffers
+	 * defined at specific PCI BAR regions will be used. If there is CXL
+	 * support and the cxl initialization fails, the driver probe fails.
+	 */
+	rc = efx_cxl_init(probe_data);
+	if (rc) {
+		pci_err(pci_dev, "CXL initialization failed with error %d\n", rc);
+		goto fail3;
+	}
+
 	rc = efx_pci_probe_post_io(efx);
 	if (rc) {
 		/* On failure, retry once immediately.
@@ -1228,6 +1243,7 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 	return 0;
 
  fail3:
+	efx_cxl_exit(probe_data);
 	efx_fini_io(efx);
  fail2:
 	efx_fini_struct(efx);
diff --git a/drivers/net/ethernet/sfc/efx_cxl.c b/drivers/net/ethernet/sfc/efx_cxl.c
new file mode 100644
index 000000000000..348d7404cd7a
--- /dev/null
+++ b/drivers/net/ethernet/sfc/efx_cxl.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/****************************************************************************
+ *
+ * Driver for AMD network controllers and boards
+ * Copyright (C) 2025, Advanced Micro Devices, Inc.
+ */
+
+#include <linux/pci.h>
+
+#include <cxl/cxl.h>
+#include <cxl/pci.h>
+#include "net_driver.h"
+#include "efx_cxl.h"
+
+#define EFX_CTPIO_BUFFER_SIZE	SZ_256M
+
+int efx_cxl_init(struct efx_probe_data *probe_data)
+{
+	struct efx_nic *efx = &probe_data->efx;
+	struct pci_dev *pci_dev = efx->pci_dev;
+	struct range cxl_pio_range;
+	struct efx_cxl *cxl;
+	u16 dvsec;
+	int rc;
+
+	/* Is the device configured with and using CXL? */
+	if (!pcie_is_cxl(pci_dev))
+		return 0;
+
+	dvsec = pci_find_dvsec_capability(pci_dev, PCI_VENDOR_ID_CXL,
+					  PCI_DVSEC_CXL_DEVICE);
+	if (!dvsec) {
+		pci_info(pci_dev, "CXL_DVSEC_PCIE_DEVICE capability not found\n");
+		return 0;
+	}
+
+	pci_dbg(pci_dev, "CXL_DVSEC_PCIE_DEVICE capability found\n");
+
+	/* Create a cxl_dev_state embedded in the cxl struct using cxl core api
+	 * specifying no mbox available.
+	 */
+	cxl = devm_cxl_dev_state_create(&pci_dev->dev, CXL_DEVTYPE_DEVMEM,
+					pci_get_dsn(pci_dev), dvsec,
+					struct efx_cxl, cxlds, false);
+
+	if (!cxl)
+		return -ENOMEM;
+
+	rc = cxl_pci_setup_regs(pci_dev, CXL_REGLOC_RBI_COMPONENT,
+				&cxl->cxlds.reg_map);
+	if (rc) {
+		pci_err(pci_dev, "No component registers\n");
+		return rc;
+	}
+
+	if (!cxl->cxlds.reg_map.component_map.hdm_decoder.valid) {
+		pci_err(pci_dev, "Expected HDM component register not found\n");
+		return -ENODEV;
+	}
+
+	if (!cxl->cxlds.reg_map.component_map.ras.valid) {
+		pci_err(pci_dev, "Expected RAS component register not found\n");
+		return -ENODEV;
+	}
+
+	/* Set media ready explicitly as there are neither mailbox for checking
+	 * this state nor the CXL register involved, both not mandatory for
+	 * type2.
+	 */
+	cxl->cxlds.media_ready = true;
+
+	if (cxl_set_capacity(&cxl->cxlds, EFX_CTPIO_BUFFER_SIZE)) {
+		pci_err(pci_dev, "dpa capacity setup failed\n");
+		return -ENODEV;
+	}
+
+	cxl->cxlmd = devm_cxl_probe_mem(&cxl->cxlds, &cxl_pio_range);
+	if (IS_ERR(cxl->cxlmd)) {
+		pci_err(pci_dev, "CXL accel memdev creation failed\n");
+		return PTR_ERR(cxl->cxlmd);
+	}
+
+	cxl->ctpio_cxl = ioremap_wc(cxl_pio_range.start,
+				    range_len(&cxl_pio_range));
+	if (!cxl->ctpio_cxl) {
+		pci_err(pci_dev, "CXL ioremap region (%pra) failed\n",
+			&cxl_pio_range);
+		return -ENOMEM;
+	}
+
+	probe_data->cxl_pio_initialised = true;
+	probe_data->cxl = cxl;
+
+	return 0;
+}
+
+void efx_cxl_exit(struct efx_probe_data *probe_data)
+{
+	if (!probe_data->cxl)
+		return;
+
+	iounmap(probe_data->cxl->ctpio_cxl);
+}
+
+MODULE_IMPORT_NS("CXL");
diff --git a/drivers/net/ethernet/sfc/efx_cxl.h b/drivers/net/ethernet/sfc/efx_cxl.h
new file mode 100644
index 000000000000..3e2705cb063f
--- /dev/null
+++ b/drivers/net/ethernet/sfc/efx_cxl.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/****************************************************************************
+ * Driver for AMD network controllers and boards
+ * Copyright (C) 2025, Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef EFX_CXL_H
+#define EFX_CXL_H
+
+#ifdef CONFIG_SFC_CXL
+
+#include <cxl/cxl.h>
+
+struct efx_probe_data;
+
+struct efx_cxl {
+	struct cxl_dev_state cxlds;
+	struct cxl_memdev *cxlmd;
+	void __iomem *ctpio_cxl;
+};
+
+int efx_cxl_init(struct efx_probe_data *probe_data);
+void efx_cxl_exit(struct efx_probe_data *probe_data);
+#else
+static inline int efx_cxl_init(struct efx_probe_data *probe_data) { return 0; }
+static inline void efx_cxl_exit(struct efx_probe_data *probe_data) {}
+#endif
+#endif
diff --git a/drivers/net/ethernet/sfc/falcon/selftest.c b/drivers/net/ethernet/sfc/falcon/selftest.c
index db4dd7fb77f5..4d29e0baf2eb 100644
--- a/drivers/net/ethernet/sfc/falcon/selftest.c
+++ b/drivers/net/ethernet/sfc/falcon/selftest.c
@@ -401,8 +401,8 @@ static void ef4_iterate_state(struct ef4_nic *efx)
 
 	/* Initialise udp header */
 	payload->udp.source = 0;
-	payload->udp.len = htons(sizeof(*payload) -
-				 offsetof(struct ef4_loopback_payload, udp));
+	udp_set_len_short(&payload->udp, sizeof(*payload) -
+			  offsetof(struct ef4_loopback_payload, udp));
 	payload->udp.check = 0;	/* checksum ignored */
 
 	/* Fill out payload */
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index e65db9b70724..b806d3d90c42 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -7,6 +7,7 @@
 #include <linux/delay.h>
 #include <linux/moduleparam.h>
 #include <linux/atomic.h>
+#include <linux/slab.h>
 #include "net_driver.h"
 #include "nic.h"
 #include "io.h"
@@ -71,7 +72,7 @@ int efx_mcdi_init(struct efx_nic *efx)
 	mcdi->efx = efx;
 #ifdef CONFIG_SFC_MCDI_LOGGING
 	/* consuming code assumes buffer is page-sized */
-	mcdi->logging_buffer = (char *)__get_free_page(GFP_KERNEL);
+	mcdi->logging_buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!mcdi->logging_buffer)
 		goto fail1;
 	mcdi->logging_enabled = mcdi_logging_default;
@@ -112,7 +113,7 @@ int efx_mcdi_init(struct efx_nic *efx)
 	return 0;
 fail2:
 #ifdef CONFIG_SFC_MCDI_LOGGING
-	free_page((unsigned long)mcdi->logging_buffer);
+	kfree(mcdi->logging_buffer);
 fail1:
 #endif
 	kfree(efx->mcdi);
@@ -138,7 +139,7 @@ void efx_mcdi_fini(struct efx_nic *efx)
 		return;
 
 #ifdef CONFIG_SFC_MCDI_LOGGING
-	free_page((unsigned long)efx->mcdi->iface.logging_buffer);
+	kfree(efx->mcdi->iface.logging_buffer);
 #endif
 
 	kfree(efx->mcdi);
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index b98c259f672d..3964b2c56609 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -1197,14 +1197,24 @@ struct efx_nic {
 	atomic_t n_rx_noskb_drops;
 };
 
+#ifdef CONFIG_SFC_CXL
+struct efx_cxl;
+#endif
+
 /**
  * struct efx_probe_data - State after hardware probe
  * @pci_dev: The PCI device
  * @efx: Efx NIC details
+ * @cxl: details of related cxl objects
+ * @cxl_pio_initialised: cxl initialization outcome.
  */
 struct efx_probe_data {
 	struct pci_dev *pci_dev;
 	struct efx_nic efx;
+#ifdef CONFIG_SFC_CXL
+	struct efx_cxl *cxl;
+	bool cxl_pio_initialised;
+#endif
 };
 
 static inline struct efx_nic *efx_netdev_priv(struct net_device *dev)
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index ec3b2df43b68..7480f9995dfb 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -152,6 +152,8 @@ enum {
  *	%MC_CMD_GET_CAPABILITIES response)
  * @datapath_caps2: Further Capabilities of datapath firmware (FLAGS2 field of
  * %MC_CMD_GET_CAPABILITIES response)
+ * @datapath_caps3: Further Capabilities of datapath firmware (FLAGS3 field of
+ * %MC_CMD_GET_CAPABILITIES response)
  * @rx_dpcpu_fw_id: Firmware ID of the RxDPCPU
  * @tx_dpcpu_fw_id: Firmware ID of the TxDPCPU
  * @must_probe_vswitching: Flag: vswitching has yet to be setup after MC reboot
@@ -187,6 +189,7 @@ struct efx_ef10_nic_data {
 	bool must_check_datapath_caps;
 	u32 datapath_caps;
 	u32 datapath_caps2;
+	u32 datapath_caps3;
 	unsigned int rx_dpcpu_fw_id;
 	unsigned int tx_dpcpu_fw_id;
 	bool must_probe_vswitching;
diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c
index 8ec76329237a..dc716feb79cb 100644
--- a/drivers/net/ethernet/sfc/selftest.c
+++ b/drivers/net/ethernet/sfc/selftest.c
@@ -398,8 +398,8 @@ static void efx_iterate_state(struct efx_nic *efx)
 
 	/* Initialise udp header */
 	payload->udp.source = 0;
-	payload->udp.len = htons(sizeof(*payload) -
-				 offsetof(struct efx_loopback_payload, udp));
+	udp_set_len_short(&payload->udp, sizeof(*payload) -
+			  offsetof(struct efx_loopback_payload, udp));
 	payload->udp.check = 0;	/* checksum ignored */
 
 	/* Fill out payload */
diff --git a/drivers/net/ethernet/sfc/siena/mcdi.c b/drivers/net/ethernet/sfc/siena/mcdi.c
index 4d0d6bd5d3d1..048c1e6017c0 100644
--- a/drivers/net/ethernet/sfc/siena/mcdi.c
+++ b/drivers/net/ethernet/sfc/siena/mcdi.c
@@ -7,6 +7,7 @@
 #include <linux/delay.h>
 #include <linux/moduleparam.h>
 #include <linux/atomic.h>
+#include <linux/slab.h>
 #include "net_driver.h"
 #include "nic.h"
 #include "io.h"
@@ -73,7 +74,7 @@ int efx_siena_mcdi_init(struct efx_nic *efx)
 	mcdi->efx = efx;
 #ifdef CONFIG_SFC_SIENA_MCDI_LOGGING
 	/* consuming code assumes buffer is page-sized */
-	mcdi->logging_buffer = (char *)__get_free_page(GFP_KERNEL);
+	mcdi->logging_buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!mcdi->logging_buffer)
 		goto fail1;
 	mcdi->logging_enabled = efx_siena_mcdi_logging_default;
@@ -116,7 +117,7 @@ int efx_siena_mcdi_init(struct efx_nic *efx)
 	return 0;
 fail2:
 #ifdef CONFIG_SFC_SIENA_MCDI_LOGGING
-	free_page((unsigned long)mcdi->logging_buffer);
+	kfree(mcdi->logging_buffer);
 fail1:
 #endif
 	kfree(efx->mcdi);
@@ -142,7 +143,7 @@ void efx_siena_mcdi_fini(struct efx_nic *efx)
 		return;
 
 #ifdef CONFIG_SFC_SIENA_MCDI_LOGGING
-	free_page((unsigned long)efx->mcdi->iface.logging_buffer);
+	kfree(efx->mcdi->iface.logging_buffer);
 #endif
 
 	kfree(efx->mcdi);
diff --git a/drivers/net/ethernet/sfc/siena/selftest.c b/drivers/net/ethernet/sfc/siena/selftest.c
index 930643612df5..c74cf5131364 100644
--- a/drivers/net/ethernet/sfc/siena/selftest.c
+++ b/drivers/net/ethernet/sfc/siena/selftest.c
@@ -399,8 +399,8 @@ static void efx_iterate_state(struct efx_nic *efx)
 
 	/* Initialise udp header */
 	payload->udp.source = 0;
-	payload->udp.len = htons(sizeof(*payload) -
-				 offsetof(struct efx_loopback_payload, udp));
+	udp_set_len_short(&payload->udp, sizeof(*payload) -
+			  offsetof(struct efx_loopback_payload, udp));
 	payload->udp.check = 0;	/* checksum ignored */
 
 	/* Fill out payload */
diff --git a/drivers/net/ethernet/sfc/tc_encap_actions.c b/drivers/net/ethernet/sfc/tc_encap_actions.c
index db222abef53b..c2ad3a358d20 100644
--- a/drivers/net/ethernet/sfc/tc_encap_actions.c
+++ b/drivers/net/ethernet/sfc/tc_encap_actions.c
@@ -311,7 +311,7 @@ static void efx_gen_tun_header_udp(struct efx_tc_encap_action *encap, u8 len)
 	encap->encap_hdr_len += sizeof(*udp);
 
 	udp->dest = key->tp_dst;
-	udp->len = cpu_to_be16(sizeof(*udp) + len);
+	udp_set_len_short(udp, sizeof(*udp) + len);
 }
 
 static void efx_gen_tun_header_vxlan(struct efx_tc_encap_action *encap)
diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c
index 39731069d99e..009f37105eaf 100644
--- a/drivers/net/ethernet/sgi/ioc3-eth.c
+++ b/drivers/net/ethernet/sgi/ioc3-eth.c
@@ -967,11 +967,12 @@ static void ioc3eth_remove(struct platform_device *pdev)
 	struct net_device *dev = platform_get_drvdata(pdev);
 	struct ioc3_private *ip = netdev_priv(dev);
 
+	unregister_netdev(dev);
+	timer_delete_sync(&ip->ioc3_timer);
+
 	dma_free_coherent(ip->dma_dev, RX_RING_SIZE, ip->rxr, ip->rxr_dma);
 	dma_free_coherent(ip->dma_dev, TX_RING_SIZE + SZ_16K - 1, ip->tx_ring, ip->txr_dma);
 
-	unregister_netdev(dev);
-	timer_delete_sync(&ip->ioc3_timer);
 	free_netdev(dev);
 }
 
@@ -1061,9 +1062,9 @@ static netdev_tx_t ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		d1 = dma_map_single(ip->dma_dev, skb->data, s1, DMA_TO_DEVICE);
 		if (dma_mapping_error(ip->dma_dev, d1))
 			goto drop_packet;
-		d2 = dma_map_single(ip->dma_dev, (void *)b2, s1, DMA_TO_DEVICE);
+		d2 = dma_map_single(ip->dma_dev, (void *)b2, s2, DMA_TO_DEVICE);
 		if (dma_mapping_error(ip->dma_dev, d2)) {
-			dma_unmap_single(ip->dma_dev, d1, len, DMA_TO_DEVICE);
+			dma_unmap_single(ip->dma_dev, d1, s1, DMA_TO_DEVICE);
 			goto drop_packet;
 		}
 		desc->p1     = cpu_to_be64(ioc3_map(d1, PCI64_ATTR_PREF));
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c
index 4ac979d874d6..eab8c13fbdcc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c
@@ -28,11 +28,15 @@
 
 /*
  * TX/RX Clock Delay Bit Masks:
- * - TX Delay: bits [14:8] — TX_CLK delay (unit: 0.02ns per bit)
- * - RX Delay: bits [30:24] — RX_CLK delay (unit: 0.02ns per bit)
+ * - TX Delay: bits [14:8] - TX_CLK delay (unit: 0.02ns per bit)
+ * - TX Invert : bit  [15]
+ * - RX Delay: bits [30:24] - RX_CLK delay (unit: 0.02ns per bit)
+ * - RX Invert : bit  [31]
  */
 #define EIC7700_ETH_TX_ADJ_DELAY	GENMASK(14, 8)
 #define EIC7700_ETH_RX_ADJ_DELAY	GENMASK(30, 24)
+#define EIC7700_ETH_TX_INV_DELAY	BIT(15)
+#define EIC7700_ETH_RX_INV_DELAY	BIT(31)
 
 #define EIC7700_MAX_DELAY_STEPS		0x7F
 #define EIC7700_DELAY_STEP_PS		20
@@ -43,7 +47,14 @@ static const char * const eic7700_clk_names[] = {
 	"tx", "axi", "cfg",
 };
 
+struct eic7700_dwmac_data {
+	bool rgmii_rx_clk_invert;
+	bool has_internal_tx_delay;
+	u32 tx_clk_inherent_skew_ps;
+};
+
 struct eic7700_qos_priv {
+	struct device *dev;
 	struct plat_stmmacenet_data *plat_dat;
 	struct regmap *eic7700_hsp_regmap;
 	u32 eth_axi_lp_ctrl_offset;
@@ -54,6 +65,7 @@ struct eic7700_qos_priv {
 	u32 eth_clk_dly_param;
 	bool has_txd_offset;
 	bool has_rxd_offset;
+	bool eth_rx_clk_inv;
 };
 
 static int eic7700_clks_config(void *priv, bool enabled)
@@ -97,9 +109,6 @@ static int eic7700_dwmac_init(struct device *dev, void *priv)
 	if (dwc->has_rxd_offset)
 		regmap_write(dwc->eic7700_hsp_regmap, dwc->eth_rxd_offset, 0);
 
-	regmap_write(dwc->eic7700_hsp_regmap, dwc->eth_clk_offset,
-		     dwc->eth_clk_dly_param);
-
 	return 0;
 }
 
@@ -126,8 +135,38 @@ static int eic7700_dwmac_resume(struct device *dev, void *priv)
 	return ret;
 }
 
+/*
+ * eth1 requires RX clock inversion at 1000Mbps due to silicon-inherent
+ * RX sampling skew at MAC input.
+ *
+ * The configuration is updated in fix_mac_speed() because the required
+ * sampling behavior depends on the negotiated link speed.
+ */
+static void eic7700_dwmac_fix_speed(void *priv, phy_interface_t interface,
+				    int speed, unsigned int mode)
+{
+	struct eic7700_qos_priv *dwc = (struct eic7700_qos_priv *)priv;
+	u32 dly_param = dwc->eth_clk_dly_param;
+
+	switch (speed) {
+	case SPEED_1000:
+		if (dwc->eth_rx_clk_inv)
+			dly_param |= EIC7700_ETH_RX_INV_DELAY;
+		break;
+	case SPEED_100:
+	case SPEED_10:
+		break;
+	default:
+		dev_warn(dwc->dev, "unsupported speed %u\n", speed);
+		return;
+	}
+
+	regmap_write(dwc->eic7700_hsp_regmap, dwc->eth_clk_offset, dly_param);
+}
+
 static int eic7700_dwmac_probe(struct platform_device *pdev)
 {
+	const struct eic7700_dwmac_data *data;
 	struct plat_stmmacenet_data *plat_dat;
 	struct stmmac_resources stmmac_res;
 	struct eic7700_qos_priv *dwc_priv;
@@ -148,6 +187,30 @@ static int eic7700_dwmac_probe(struct platform_device *pdev)
 	if (!dwc_priv)
 		return -ENOMEM;
 
+	dwc_priv->dev = &pdev->dev;
+
+	data = device_get_match_data(&pdev->dev);
+	if (!data)
+		return dev_err_probe(&pdev->dev,
+				     -EINVAL, "no match data found\n");
+
+	dwc_priv->eth_rx_clk_inv = data->rgmii_rx_clk_invert;
+	/*
+	 * The MAC silicon unconditionally adds ~2 ns TX delay; prevent
+	 * the PHY from also adding TX delay to avoid doubling it.
+	 *
+	 * DT specifies rgmii-id (TX from MAC silicon, RX from PHY);
+	 * override to rgmii-rxid so the PHY only adds its RX delay.
+	 */
+	if (data->has_internal_tx_delay) {
+		plat_dat->phy_interface =
+				 phy_fix_phy_mode_for_mac_delays(plat_dat->phy_interface,
+								 true, false);
+		if (plat_dat->phy_interface == PHY_INTERFACE_MODE_NA)
+			return dev_err_probe(&pdev->dev, -EINVAL,
+				"phy interface mode is NA\n");
+	}
+
 	/* Read rx-internal-delay-ps and update rx_clk delay */
 	if (!of_property_read_u32(pdev->dev.of_node,
 				  "rx-internal-delay-ps", &delay_ps)) {
@@ -165,12 +228,15 @@ static int eic7700_dwmac_probe(struct platform_device *pdev)
 		dwc_priv->eth_clk_dly_param &= ~EIC7700_ETH_RX_ADJ_DELAY;
 		dwc_priv->eth_clk_dly_param |=
 				 FIELD_PREP(EIC7700_ETH_RX_ADJ_DELAY, val);
-	} else {
-		return dev_err_probe(&pdev->dev, -EINVAL,
-			"missing required property rx-internal-delay-ps\n");
 	}
 
-	/* Read tx-internal-delay-ps and update tx_clk delay */
+	/* Read tx-internal-delay-ps and update tx_clk delay.
+	 *
+	 * For eswin,eic7700-qos-eth-clk-inversion, the DT property describes
+	 * the effective TX delay at the MAC output, including the inherent
+	 * silicon delay. Subtract the fixed component to obtain the
+	 * programmable delay value.
+	 */
 	if (!of_property_read_u32(pdev->dev.of_node,
 				  "tx-internal-delay-ps", &delay_ps)) {
 		if (delay_ps % EIC7700_DELAY_STEP_PS)
@@ -178,18 +244,22 @@ static int eic7700_dwmac_probe(struct platform_device *pdev)
 				"tx delay must be multiple of %dps\n",
 				EIC7700_DELAY_STEP_PS);
 
+		if (delay_ps < data->tx_clk_inherent_skew_ps)
+			return dev_err_probe(&pdev->dev, -EINVAL,
+				"tx delay %ups below inherent skew %ups\n",
+				delay_ps, data->tx_clk_inherent_skew_ps);
+
+		delay_ps -= data->tx_clk_inherent_skew_ps;
+
 		if (delay_ps > EIC7700_MAX_DELAY_PS)
 			return dev_err_probe(&pdev->dev, -EINVAL,
-				"tx delay out of range\n");
+				"tx delay out of programmable range\n");
 
 		val = delay_ps / EIC7700_DELAY_STEP_PS;
 
 		dwc_priv->eth_clk_dly_param &= ~EIC7700_ETH_TX_ADJ_DELAY;
 		dwc_priv->eth_clk_dly_param |=
 				 FIELD_PREP(EIC7700_ETH_TX_ADJ_DELAY, val);
-	} else {
-		return dev_err_probe(&pdev->dev, -EINVAL,
-			"missing required property tx-internal-delay-ps\n");
 	}
 
 	dwc_priv->eic7700_hsp_regmap =
@@ -260,12 +330,31 @@ static int eic7700_dwmac_probe(struct platform_device *pdev)
 	plat_dat->exit = eic7700_dwmac_exit;
 	plat_dat->suspend = eic7700_dwmac_suspend;
 	plat_dat->resume = eic7700_dwmac_resume;
+	plat_dat->fix_mac_speed = eic7700_dwmac_fix_speed;
 
 	return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 }
 
+static const struct eic7700_dwmac_data eic7700_dwmac_data = {
+	.rgmii_rx_clk_invert = false,
+	.has_internal_tx_delay = false,
+	.tx_clk_inherent_skew_ps = 0,
+};
+
+static const struct eic7700_dwmac_data eic7700_dwmac_data_clk_inversion = {
+	.rgmii_rx_clk_invert = true,
+	.has_internal_tx_delay = true,
+	.tx_clk_inherent_skew_ps = 2000,
+};
+
 static const struct of_device_id eic7700_dwmac_match[] = {
-	{ .compatible = "eswin,eic7700-qos-eth" },
+	{	.compatible = "eswin,eic7700-qos-eth",
+		.data = &eic7700_dwmac_data,
+	},
+	{
+		.compatible = "eswin,eic7700-qos-eth-clk-inversion",
+		.data = &eic7700_dwmac_data_clk_inversion,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, eic7700_dwmac_match);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 151c77713025..0de4bc949913 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6357,28 +6357,17 @@ static irqreturn_t stmmac_msi_intr_rx(int irq, void *data)
  *  @rq: An IOCTL specific structure, that can contain a pointer to
  *  a proprietary structure used to pass information to the driver.
  *  @cmd: IOCTL command
- *  Description:
- *  Currently it supports the phy_mii_ioctl(...) and HW time stamping.
+ *  Description: Forward the PHY ioctls to phylink
+ *  Return: Zero on success or negative error code.
  */
 static int stmmac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
 	struct stmmac_priv *priv = netdev_priv (dev);
-	int ret = -EOPNOTSUPP;
 
 	if (!netif_running(dev))
 		return -EINVAL;
 
-	switch (cmd) {
-	case SIOCGMIIPHY:
-	case SIOCGMIIREG:
-	case SIOCSMIIREG:
-		ret = phylink_mii_ioctl(priv->phylink, rq, cmd);
-		break;
-	default:
-		break;
-	}
-
-	return ret;
+	return phylink_mii_ioctl(priv->phylink, rq, cmd);
 }
 
 static int stmmac_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
index a0c75886587c..29e824bd90ca 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
@@ -154,9 +154,9 @@ static struct sk_buff *stmmac_test_get_udp_skb(struct stmmac_priv *priv,
 	} else {
 		uhdr->source = htons(attr->sport);
 		uhdr->dest = htons(attr->dport);
-		uhdr->len = htons(sizeof(*shdr) + sizeof(*uhdr) + attr->size);
+		udp_set_len_short(uhdr, sizeof(*shdr) + sizeof(*uhdr) + attr->size);
 		if (attr->max_size)
-			uhdr->len = htons(attr->max_size -
+			udp_set_len_short(uhdr, attr->max_size -
 					  (sizeof(*ihdr) + sizeof(*ehdr)));
 		uhdr->check = 0;
 	}
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
index 5df971aca9e3..22037f015ded 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
@@ -9,6 +9,8 @@
 #include "wx_ethtool.h"
 #include "wx_hw.h"
 #include "wx_lib.h"
+#include "wx_vf_common.h"
+#include "wx_vf_lib.h"
 
 struct wx_stats {
 	char stat_string[ETH_GSTRING_LEN];
@@ -487,7 +489,10 @@ int wx_set_coalesce(struct net_device *netdev,
 		else
 			/* rx only or mixed */
 			q_vector->itr = rx_itr_param;
-		wx_write_eitr(q_vector);
+		if (wx->pdev->is_virtfn)
+			wx_write_eitr_vf(q_vector);
+		else
+			wx_write_eitr(q_vector);
 	}
 
 	wx_update_rsc(wx);
@@ -775,6 +780,65 @@ static int wx_get_link_ksettings_vf(struct net_device *netdev,
 	return 0;
 }
 
+static int wx_set_ringparam_vf(struct net_device *netdev,
+			       struct ethtool_ringparam *ring,
+			       struct kernel_ethtool_ringparam *kernel_ring,
+			       struct netlink_ext_ack *extack)
+{
+	struct wx *wx = netdev_priv(netdev);
+	u32 new_rx_count, new_tx_count;
+	struct wx_ring *temp_ring;
+	int i, err = 0;
+
+	new_tx_count = clamp_t(u32, ring->tx_pending, WX_MIN_TXD, WX_MAX_TXD);
+	new_tx_count = ALIGN(new_tx_count, WX_REQ_TX_DESCRIPTOR_MULTIPLE);
+
+	new_rx_count = clamp_t(u32, ring->rx_pending, WX_MIN_RXD, WX_MAX_RXD);
+	new_rx_count = ALIGN(new_rx_count, WX_REQ_RX_DESCRIPTOR_MULTIPLE);
+
+	if (new_tx_count == wx->tx_ring_count &&
+	    new_rx_count == wx->rx_ring_count)
+		return 0;
+
+	mutex_lock(&wx->reset_lock);
+	set_bit(WX_STATE_RESETTING, wx->state);
+
+	if (!netif_running(wx->netdev)) {
+		for (i = 0; i < wx->num_tx_queues; i++)
+			wx->tx_ring[i]->count = new_tx_count;
+		for (i = 0; i < wx->num_rx_queues; i++)
+			wx->rx_ring[i]->count = new_rx_count;
+		wx->tx_ring_count = new_tx_count;
+		wx->rx_ring_count = new_rx_count;
+
+		goto clear_reset;
+	}
+
+	/* allocate temporary buffer to store rings in */
+	i = max_t(int, wx->num_tx_queues, wx->num_rx_queues);
+	temp_ring = kvmalloc_objs(struct wx_ring, i);
+	if (!temp_ring) {
+		err = -ENOMEM;
+		goto clear_reset;
+	}
+
+	wxvf_down(wx);
+	/* wx_set_ring() may partially apply changes before
+	 * returning an error. The error indicates that not all
+	 * requested ring parameters could be configured.
+	 */
+	err = wx_set_ring(wx, new_tx_count, new_rx_count, temp_ring);
+	if (err)
+		wx_err(wx, "failed to set ring parameters: %d", err);
+	wx_configure_vf(wx);
+	wxvf_up_complete(wx);
+	kvfree(temp_ring);
+clear_reset:
+	clear_bit(WX_STATE_RESETTING, wx->state);
+	mutex_unlock(&wx->reset_lock);
+	return err;
+}
+
 static const struct ethtool_ops wx_ethtool_ops_vf = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_TX_MAX_FRAMES_IRQ |
@@ -782,8 +846,10 @@ static const struct ethtool_ops wx_ethtool_ops_vf = {
 	.get_drvinfo		= wx_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_ringparam		= wx_get_ringparam,
+	.set_ringparam		= wx_set_ringparam_vf,
 	.get_msglevel		= wx_get_msglevel,
 	.get_coalesce		= wx_get_coalesce,
+	.set_coalesce		= wx_set_coalesce,
 	.get_ts_info		= ethtool_op_get_ts_info,
 	.get_link_ksettings	= wx_get_link_ksettings_vf,
 };
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 814d88d2aee4..31572f59b9ce 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -3228,6 +3228,30 @@ netdev_features_t wx_features_check(struct sk_buff *skb,
 				    netdev_features_t features)
 {
 	struct wx *wx = netdev_priv(netdev);
+	__be16 type = skb->protocol;
+	u16 vlan_depth = ETH_HLEN;
+	u32 vlan_num = 0;
+
+	if (skb_vlan_tag_present(skb))
+		vlan_num++;
+
+	while (eth_type_vlan(type)) {
+		struct vlan_hdr vhdr, *vh;
+
+		vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr);
+		if (unlikely(!vh))
+			break;
+
+		type = vh->h_vlan_encapsulated_proto;
+		vlan_depth += VLAN_HLEN;
+		vlan_num++;
+
+		if (vlan_num > 2) {
+			features &= ~(NETIF_F_HW_VLAN_CTAG_TX |
+				      NETIF_F_HW_VLAN_STAG_TX);
+			break;
+		}
+	}
 
 	if (!skb->encapsulation)
 		return features;
@@ -3249,8 +3273,8 @@ netdev_features_t wx_features_check(struct sk_buff *skb,
 }
 EXPORT_SYMBOL(wx_features_check);
 
-void wx_set_ring(struct wx *wx, u32 new_tx_count,
-		 u32 new_rx_count, struct wx_ring *temp_ring)
+int wx_set_ring(struct wx *wx, u32 new_tx_count,
+		u32 new_rx_count, struct wx_ring *temp_ring)
 {
 	int i, err = 0;
 
@@ -3272,7 +3296,7 @@ void wx_set_ring(struct wx *wx, u32 new_tx_count,
 					i--;
 					wx_free_tx_resources(&temp_ring[i]);
 				}
-				return;
+				return err;
 			}
 		}
 
@@ -3300,7 +3324,7 @@ void wx_set_ring(struct wx *wx, u32 new_tx_count,
 					i--;
 					wx_free_rx_resources(&temp_ring[i]);
 				}
-				return;
+				return err;
 			}
 		}
 
@@ -3312,6 +3336,7 @@ void wx_set_ring(struct wx *wx, u32 new_tx_count,
 
 		wx->rx_ring_count = new_rx_count;
 	}
+	return 0;
 }
 EXPORT_SYMBOL(wx_set_ring);
 
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.h b/drivers/net/ethernet/wangxun/libwx/wx_lib.h
index aed6ea8cf0d6..bc671786978e 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.h
@@ -36,8 +36,8 @@ netdev_features_t wx_fix_features(struct net_device *netdev,
 netdev_features_t wx_features_check(struct sk_buff *skb,
 				    struct net_device *netdev,
 				    netdev_features_t features);
-void wx_set_ring(struct wx *wx, u32 new_tx_count,
-		 u32 new_rx_count, struct wx_ring *temp_ring);
+int wx_set_ring(struct wx *wx, u32 new_tx_count,
+		u32 new_rx_count, struct wx_ring *temp_ring);
 void wx_service_event_schedule(struct wx *wx);
 void wx_service_event_complete(struct wx *wx);
 void wx_service_timer(struct timer_list *t);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_vf.h b/drivers/net/ethernet/wangxun/libwx/wx_vf.h
index eb6ca3fe4e97..b64a4de089f2 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_vf.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_vf.h
@@ -41,7 +41,6 @@
 #define WX_VF_MAX_RX_QUEUES      4
 
 #define WX_VXITR(i)              (0x200 + (4 * (i))) /* i=[0,1] */
-#define WX_VXITR_MASK            GENMASK(8, 0)
 #define WX_VXITR_CNT_WDIS        BIT(31)
 #define WX_VXIVAR_MISC           0x260
 #define WX_VXIVAR(i)             (0x240 + (4 * (i))) /* i=[0,3] */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_vf_common.c b/drivers/net/ethernet/wangxun/libwx/wx_vf_common.c
index 0d2db8d38cd5..26de78e9a69e 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_vf_common.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_vf_common.c
@@ -269,7 +269,7 @@ static void wxvf_irq_enable(struct wx *wx)
 	wr32(wx, WX_VXIMC, wx->eims_enable_mask);
 }
 
-static void wxvf_up_complete(struct wx *wx)
+void wxvf_up_complete(struct wx *wx)
 {
 	/* Always set the carrier off */
 	netif_carrier_off(wx->netdev);
@@ -324,7 +324,7 @@ err_reset:
 }
 EXPORT_SYMBOL(wxvf_open);
 
-static void wxvf_down(struct wx *wx)
+void wxvf_down(struct wx *wx)
 {
 	struct net_device *netdev = wx->netdev;
 
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_vf_common.h b/drivers/net/ethernet/wangxun/libwx/wx_vf_common.h
index cbbb1b178cb2..d45d5d8ac3ab 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_vf_common.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_vf_common.h
@@ -15,7 +15,9 @@ void wx_set_rx_mode_vf(struct net_device *netdev);
 void wx_configure_vf(struct wx *wx);
 int wx_set_mac_vf(struct net_device *netdev, void *p);
 void wxvf_watchdog_update_link(struct wx *wx);
+void wxvf_up_complete(struct wx *wx);
 int wxvf_open(struct net_device *netdev);
+void wxvf_down(struct wx *wx);
 int wxvf_close(struct net_device *netdev);
 void wxvf_init_service(struct wx *wx);
 
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c
index aa8be036956c..7325b475ee10 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c
@@ -16,7 +16,18 @@ void wx_write_eitr_vf(struct wx_q_vector *q_vector)
 	int v_idx = q_vector->v_idx;
 	u32 itr_reg;
 
-	itr_reg = q_vector->itr & WX_VXITR_MASK;
+	switch (wx->mac.type) {
+	case wx_mac_sp:
+		itr_reg = q_vector->itr & WX_SP_MAX_EITR;
+		break;
+	case wx_mac_aml:
+	case wx_mac_aml40:
+		itr_reg = (q_vector->itr >> 3) & WX_AML_MAX_EITR;
+		break;
+	default:
+		itr_reg = q_vector->itr & WX_EM_MAX_EITR;
+		break;
+	}
 
 	/* set the WDIS bit to not clear the timer bits and cause an
 	 * immediate assertion of the interrupt
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 72023ebd0e1b..542e53f9dc3e 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -91,6 +91,7 @@ struct geneve_config {
 	u16			port_min;
 	u16			port_max;
 
+	struct rcu_head		rcu;
 	/* Must be last --ends in a flexible-array member. */
 	struct ip_tunnel_info	info;
 };
@@ -109,7 +110,7 @@ struct geneve_dev {
 #endif
 	struct list_head   next;	/* geneve's per namespace list */
 	struct gro_cells   gro_cells;
-	struct geneve_config cfg;
+	struct geneve_config __rcu *cfg;
 };
 
 struct geneve_sock {
@@ -191,8 +192,10 @@ static struct geneve_dev *geneve_lookup(struct geneve_sock *gs,
 	hash = geneve_net_vni_hash(vni);
 	vni_list_head = &gs->vni_list[hash];
 	hlist_for_each_entry_rcu(node, vni_list_head, hlist) {
-		if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) &&
-		    addr == node->geneve->cfg.info.key.u.ipv4.dst)
+		const struct geneve_config *cfg = rcu_dereference(node->geneve->cfg);
+
+		if (eq_tun_id_and_vni((u8 *)&cfg->info.key.tun_id, vni) &&
+		    addr == cfg->info.key.u.ipv4.dst)
 			return node->geneve;
 	}
 	return NULL;
@@ -210,8 +213,10 @@ static struct geneve_dev *geneve6_lookup(struct geneve_sock *gs,
 	hash = geneve_net_vni_hash(vni);
 	vni_list_head = &gs->vni_list[hash];
 	hlist_for_each_entry_rcu(node, vni_list_head, hlist) {
-		if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) &&
-		    ipv6_addr_equal(&addr6, &node->geneve->cfg.info.key.u.ipv6.dst))
+		const struct geneve_config *cfg = rcu_dereference(node->geneve->cfg);
+
+		if (eq_tun_id_and_vni((u8 *)&cfg->info.key.tun_id, vni) &&
+		    ipv6_addr_equal(&addr6, &cfg->info.key.u.ipv6.dst))
 			return node->geneve;
 	}
 	return NULL;
@@ -395,11 +400,6 @@ static int geneve_init(struct net_device *dev)
 	if (err)
 		return err;
 
-	err = dst_cache_init(&geneve->cfg.info.dst_cache, GFP_KERNEL);
-	if (err) {
-		gro_cells_destroy(&geneve->gro_cells);
-		return err;
-	}
 	netdev_lockdep_set_classes(dev);
 	return 0;
 }
@@ -408,7 +408,6 @@ static void geneve_uninit(struct net_device *dev)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
 
-	dst_cache_destroy(&geneve->cfg.info.dst_cache);
 	gro_cells_destroy(&geneve->gro_cells);
 }
 
@@ -649,7 +648,7 @@ static int geneve_post_decap_hint(const struct sock *sk, struct sk_buff *skb,
 
 	/* Adjust the nested UDP header len and checksum. */
 	uh = udp_hdr(skb);
-	uh->len = htons(skb->len - gro_hint->nested_tp_offset);
+	udp_set_len_short(uh, skb->len - gro_hint->nested_tp_offset);
 	if (uh->check) {
 		len = skb->len - gro_hint->nested_tp_offset;
 		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
@@ -668,6 +667,7 @@ static int geneve_post_decap_hint(const struct sock *sk, struct sk_buff *skb,
 /* Callback from net/ipv4/udp.c to receive packets */
 static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
+	const struct geneve_config *cfg;
 	struct genevehdr *geneveh;
 	struct geneve_dev *geneve;
 	struct geneve_sock *gs;
@@ -693,8 +693,9 @@ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	inner_proto = geneveh->proto_type;
 
-	if (unlikely((!geneve->cfg.inner_proto_inherit &&
-		      inner_proto != htons(ETH_P_TEB)))) {
+	cfg = rcu_dereference(geneve->cfg);
+	if (unlikely(!cfg || (!cfg->inner_proto_inherit &&
+			      inner_proto != htons(ETH_P_TEB)))) {
 		dev_dstats_rx_dropped(geneve->dev);
 		goto drop;
 	}
@@ -780,9 +781,10 @@ static int geneve_udp_encap_err_lookup(struct sock *sk, struct sk_buff *skb)
 }
 
 static struct sock *geneve_create_sock(struct net *net,
-				       struct geneve_dev *geneve, bool ipv6)
+				       struct geneve_dev *geneve,
+				       const struct geneve_config *cfg, bool ipv6)
 {
-	struct ip_tunnel_info *info = &geneve->cfg.info;
+	const struct ip_tunnel_info *info = &cfg->info;
 	struct udp_port_cfg udp_conf;
 	struct socket *sock;
 	int err;
@@ -793,7 +795,7 @@ static struct sock *geneve_create_sock(struct net *net,
 	if (ipv6) {
 		udp_conf.family = AF_INET6;
 		udp_conf.ipv6_v6only = 1;
-		udp_conf.use_udp6_rx_checksums = geneve->cfg.use_udp6_rx_checksums;
+		udp_conf.use_udp6_rx_checksums = cfg->use_udp6_rx_checksums;
 		udp_conf.local_ip6 = info->key.u.ipv6.src;
 	} else
 #endif
@@ -1009,7 +1011,8 @@ static int geneve_gro_complete(struct sock *sk, struct sk_buff *skb,
 
 /* Create new listen socket if needed */
 static struct geneve_sock *geneve_socket_create(struct net *net,
-						struct geneve_dev *geneve, bool ipv6)
+						struct geneve_dev *geneve,
+						const struct geneve_config *cfg, bool ipv6)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct udp_tunnel_sock_cfg tunnel_cfg;
@@ -1021,7 +1024,7 @@ static struct geneve_sock *geneve_socket_create(struct net *net,
 	if (!gs)
 		return ERR_PTR(-ENOMEM);
 
-	sk = geneve_create_sock(net, geneve, ipv6);
+	sk = geneve_create_sock(net, geneve, cfg, ipv6);
 	if (IS_ERR(sk)) {
 		kfree(gs);
 		return ERR_CAST(sk);
@@ -1078,12 +1081,13 @@ static void geneve_sock_release(struct geneve_dev *geneve)
 }
 
 static struct geneve_sock *geneve_find_sock(struct net *net,
-					    struct geneve_dev *geneve, bool ipv6)
+					    struct geneve_dev *geneve,
+					    const struct geneve_config *cfg, bool ipv6)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
-	struct ip_tunnel_info *info = &geneve->cfg.info;
+	const struct ip_tunnel_info *info = &cfg->info;
 	sa_family_t family = ipv6 ? AF_INET6 : AF_INET;
-	bool gro_hint = geneve->cfg.gro_hint;
+	bool gro_hint = cfg->gro_hint;
 	__be16 dst_port = info->key.tp_dst;
 	struct geneve_sock *gs;
 
@@ -1113,7 +1117,8 @@ static struct geneve_sock *geneve_find_sock(struct net *net,
 	return NULL;
 }
 
-static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6)
+static int geneve_sock_add(struct geneve_dev *geneve,
+			   const struct geneve_config *cfg, bool ipv6)
 {
 	struct net *net = geneve->net;
 	struct geneve_dev_node *node;
@@ -1121,19 +1126,19 @@ static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6)
 	__u8 vni[3];
 	__u32 hash;
 
-	gs = geneve_find_sock(net, geneve, ipv6);
+	gs = geneve_find_sock(net, geneve, cfg, ipv6);
 	if (gs) {
 		gs->refcnt++;
 		goto out;
 	}
 
-	gs = geneve_socket_create(net, geneve, ipv6);
+	gs = geneve_socket_create(net, geneve, cfg, ipv6);
 	if (IS_ERR(gs))
 		return PTR_ERR(gs);
 
 out:
-	gs->collect_md = geneve->cfg.collect_md;
-	gs->gro_hint = geneve->cfg.gro_hint;
+	gs->collect_md = cfg->collect_md;
+	gs->gro_hint = cfg->gro_hint;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (ipv6) {
 		rcu_assign_pointer(geneve->sock6, gs);
@@ -1146,7 +1151,7 @@ out:
 	}
 	node->geneve = geneve;
 
-	tunnel_id_to_vni(geneve->cfg.info.key.tun_id, vni);
+	tunnel_id_to_vni(cfg->info.key.tun_id, vni);
 	hash = geneve_net_vni_hash(vni);
 	hlist_add_head_rcu(&node->hlist, &gs->vni_list[hash]);
 	return 0;
@@ -1155,21 +1160,23 @@ out:
 static int geneve_open(struct net_device *dev)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
-	bool dualstack = geneve->cfg.dualstack;
-	bool ipv4, ipv6;
+	const struct geneve_config *cfg;
+	bool ipv4, ipv6, dualstack;
 	int ret = 0;
 
-	ipv6 = geneve->cfg.info.mode & IP_TUNNEL_INFO_IPV6 || dualstack;
+	cfg = rtnl_dereference(geneve->cfg);
+	dualstack = cfg->dualstack;
+	ipv6 = cfg->info.mode & IP_TUNNEL_INFO_IPV6 || dualstack;
 	ipv4 = !ipv6 || dualstack;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (ipv6) {
-		ret = geneve_sock_add(geneve, true);
+		ret = geneve_sock_add(geneve, cfg, true);
 		if (ret < 0 && ret != -EAFNOSUPPORT)
 			ipv4 = false;
 	}
 #endif
 	if (ipv4)
-		ret = geneve_sock_add(geneve, false);
+		ret = geneve_sock_add(geneve, cfg, false);
 	if (ret < 0)
 		geneve_sock_release(geneve);
 
@@ -1207,6 +1214,7 @@ static void geneve_build_header(struct genevehdr *geneveh,
 }
 
 static int geneve_build_gro_hint_opt(const struct geneve_dev *geneve,
+				     const struct geneve_config *cfg,
 				     struct sk_buff *skb)
 {
 	struct geneve_skb_cb *cb = GENEVE_SKB_CB(skb);
@@ -1219,7 +1227,7 @@ static int geneve_build_gro_hint_opt(const struct geneve_dev *geneve,
 	cb->gro_hint_len = 0;
 
 	/* Try to add the GRO hint only in case of double encap. */
-	if (!geneve->cfg.gro_hint || !skb->encapsulation)
+	if (!cfg->gro_hint || !skb->encapsulation)
 		return 0;
 
 	/*
@@ -1280,10 +1288,11 @@ static void geneve_put_gro_hint_opt(struct genevehdr *gnvh, int opt_size,
 
 static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb,
 			    const struct ip_tunnel_info *info,
-			    const struct geneve_dev *geneve, int ip_hdr_len)
+			    const struct geneve_dev *geneve,
+			    const struct geneve_config *cfg, int ip_hdr_len)
 {
 	bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags);
-	bool inner_proto_inherit = geneve->cfg.inner_proto_inherit;
+	bool inner_proto_inherit = cfg->inner_proto_inherit;
 	bool xnet = !net_eq(geneve->net, dev_net(geneve->dev));
 	struct geneve_skb_cb *cb = GENEVE_SKB_CB(skb);
 	struct genevehdr *gnvh;
@@ -1324,14 +1333,14 @@ free_dst:
 }
 
 static u8 geneve_get_dsfield(struct sk_buff *skb, struct net_device *dev,
+			     const struct geneve_config *cfg,
 			     const struct ip_tunnel_info *info,
 			     bool *use_cache)
 {
-	struct geneve_dev *geneve = netdev_priv(dev);
 	u8 dsfield;
 
 	dsfield = info->key.tos;
-	if (dsfield == 1 && !geneve->cfg.collect_md) {
+	if (cfg && dsfield == 1 && !cfg->collect_md) {
 		dsfield = ip_tunnel_get_dsfield(ip_hdr(skb), skb);
 		*use_cache = false;
 	}
@@ -1341,6 +1350,7 @@ static u8 geneve_get_dsfield(struct sk_buff *skb, struct net_device *dev,
 
 static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 			   struct geneve_dev *geneve,
+			   const struct geneve_config *cfg,
 			   const struct ip_tunnel_info *info)
 {
 	struct geneve_sock *gs4 = rcu_dereference(geneve->sock4);
@@ -1353,35 +1363,35 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be16 sport;
 	int err;
 
-	if (skb_vlan_inet_prepare(skb, geneve->cfg.inner_proto_inherit))
+	if (skb_vlan_inet_prepare(skb, cfg->inner_proto_inherit))
 		return -EINVAL;
 
 	if (!gs4)
 		return -EIO;
 
 	use_cache = ip_tunnel_dst_cache_usable(skb, info);
-	tos = geneve_get_dsfield(skb, dev, info, &use_cache);
+	tos = geneve_get_dsfield(skb, dev, cfg, info, &use_cache);
 	sport = udp_flow_src_port(geneve->net, skb,
-				  geneve->cfg.port_min,
-				  geneve->cfg.port_max, true);
+				  cfg->port_min,
+				  cfg->port_max, true);
 
 	rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr,
 				   &info->key,
-				   sport, geneve->cfg.info.key.tp_dst, tos,
+				   sport, cfg->info.key.tp_dst, tos,
 				   use_cache ?
 				   (struct dst_cache *)&info->dst_cache : NULL);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
-	if (geneve->cfg.info.key.u.ipv4.src &&
-	    saddr != geneve->cfg.info.key.u.ipv4.src) {
+	if (cfg->info.key.u.ipv4.src &&
+	    saddr != cfg->info.key.u.ipv4.src) {
 		dst_release(&rt->dst);
 		return -EADDRNOTAVAIL;
 	}
 
 	err = skb_tunnel_check_pmtu(skb, &rt->dst,
 				    GENEVE_IPV4_HLEN + info->options_len +
-				    geneve_build_gro_hint_opt(geneve, skb),
+				    geneve_build_gro_hint_opt(geneve, cfg, skb),
 				    netif_is_any_bridge_port(dev));
 	if (err < 0) {
 		dst_release(&rt->dst);
@@ -1415,21 +1425,21 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	tos = ip_tunnel_ecn_encap(tos, ip_hdr(skb), skb);
-	if (geneve->cfg.collect_md) {
+	if (cfg->collect_md) {
 		ttl = key->ttl;
 
 		df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ?
 		     htons(IP_DF) : 0;
 	} else {
-		if (geneve->cfg.ttl_inherit)
+		if (cfg->ttl_inherit)
 			ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb);
 		else
 			ttl = key->ttl;
 		ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
 
-		if (geneve->cfg.df == GENEVE_DF_SET) {
+		if (cfg->df == GENEVE_DF_SET) {
 			df = htons(IP_DF);
-		} else if (geneve->cfg.df == GENEVE_DF_INHERIT) {
+		} else if (cfg->df == GENEVE_DF_INHERIT) {
 			struct ethhdr *eth = skb_eth_hdr(skb);
 
 			if (ntohs(eth->h_proto) == ETH_P_IPV6) {
@@ -1443,13 +1453,13 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
-	err = geneve_build_skb(&rt->dst, skb, info, geneve,
+	err = geneve_build_skb(&rt->dst, skb, info, geneve, cfg,
 			       sizeof(struct iphdr));
 	if (unlikely(err))
 		return err;
 
 	udp_tunnel_xmit_skb(rt, gs4->sk, skb, saddr, info->key.u.ipv4.dst,
-			    tos, ttl, df, sport, geneve->cfg.info.key.tp_dst,
+			    tos, ttl, df, sport, cfg->info.key.tp_dst,
 			    !net_eq(geneve->net, dev_net(geneve->dev)),
 			    !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags),
 			    0);
@@ -1459,6 +1469,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 #if IS_ENABLED(CONFIG_IPV6)
 static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 			    struct geneve_dev *geneve,
+			    const struct geneve_config *cfg,
 			    const struct ip_tunnel_info *info)
 {
 	struct geneve_sock *gs6 = rcu_dereference(geneve->sock6);
@@ -1470,35 +1481,35 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be16 sport;
 	int err;
 
-	if (skb_vlan_inet_prepare(skb, geneve->cfg.inner_proto_inherit))
+	if (skb_vlan_inet_prepare(skb, cfg->inner_proto_inherit))
 		return -EINVAL;
 
 	if (!gs6)
 		return -EIO;
 
 	use_cache = ip_tunnel_dst_cache_usable(skb, info);
-	prio = geneve_get_dsfield(skb, dev, info, &use_cache);
+	prio = geneve_get_dsfield(skb, dev, cfg, info, &use_cache);
 	sport = udp_flow_src_port(geneve->net, skb,
-				  geneve->cfg.port_min,
-				  geneve->cfg.port_max, true);
+				  cfg->port_min,
+				  cfg->port_max, true);
 
 	dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sk, 0,
 				     &saddr, key, sport,
-				     geneve->cfg.info.key.tp_dst, prio,
+				     cfg->info.key.tp_dst, prio,
 				     use_cache ?
 				     (struct dst_cache *)&info->dst_cache : NULL);
 	if (IS_ERR(dst))
 		return PTR_ERR(dst);
 
-	if (!ipv6_addr_any(&geneve->cfg.info.key.u.ipv6.src) &&
-	    !ipv6_addr_equal(&saddr, &geneve->cfg.info.key.u.ipv6.src)) {
+	if (!ipv6_addr_any(&cfg->info.key.u.ipv6.src) &&
+	    !ipv6_addr_equal(&saddr, &cfg->info.key.u.ipv6.src)) {
 		dst_release(dst);
 		return -EADDRNOTAVAIL;
 	}
 
 	err = skb_tunnel_check_pmtu(skb, dst,
 				    GENEVE_IPV6_HLEN + info->options_len +
-				    geneve_build_gro_hint_opt(geneve, skb),
+				    geneve_build_gro_hint_opt(geneve, cfg, skb),
 				    netif_is_any_bridge_port(dev));
 	if (err < 0) {
 		dst_release(dst);
@@ -1531,22 +1542,22 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	prio = ip_tunnel_ecn_encap(prio, ip_hdr(skb), skb);
-	if (geneve->cfg.collect_md) {
+	if (cfg->collect_md) {
 		ttl = key->ttl;
 	} else {
-		if (geneve->cfg.ttl_inherit)
+		if (cfg->ttl_inherit)
 			ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb);
 		else
 			ttl = key->ttl;
 		ttl = ttl ? : ip6_dst_hoplimit(dst);
 	}
-	err = geneve_build_skb(dst, skb, info, geneve, sizeof(struct ipv6hdr));
+	err = geneve_build_skb(dst, skb, info, geneve, cfg, sizeof(struct ipv6hdr));
 	if (unlikely(err))
 		return err;
 
 	udp_tunnel6_xmit_skb(dst, gs6->sk, skb, dev,
 			     &saddr, &key->u.ipv6.dst, prio, ttl,
-			     info->key.label, sport, geneve->cfg.info.key.tp_dst,
+			     info->key.label, sport, cfg->info.key.tp_dst,
 			     !test_bit(IP_TUNNEL_CSUM_BIT,
 				       info->key.tun_flags),
 			     0);
@@ -1557,28 +1568,31 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
-	struct ip_tunnel_info *info = NULL;
+	const struct ip_tunnel_info *info = NULL;
+	const struct geneve_config *cfg;
 	int err;
 
-	if (geneve->cfg.collect_md) {
+	rcu_read_lock();
+	cfg = rcu_dereference(geneve->cfg);
+	if (cfg->collect_md) {
 		info = skb_tunnel_info(skb);
 		if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) {
 			netdev_dbg(dev, "no tunnel metadata\n");
 			dev_kfree_skb(skb);
 			dev_dstats_tx_dropped(dev);
+			rcu_read_unlock();
 			return NETDEV_TX_OK;
 		}
 	} else {
-		info = &geneve->cfg.info;
+		info = &cfg->info;
 	}
 
-	rcu_read_lock();
 #if IS_ENABLED(CONFIG_IPV6)
 	if (info->mode & IP_TUNNEL_INFO_IPV6)
-		err = geneve6_xmit_skb(skb, dev, geneve, info);
+		err = geneve6_xmit_skb(skb, dev, geneve, cfg, info);
 	else
 #endif
-		err = geneve_xmit_skb(skb, dev, geneve, info);
+		err = geneve_xmit_skb(skb, dev, geneve, cfg, info);
 	rcu_read_unlock();
 
 	if (likely(!err))
@@ -1611,8 +1625,13 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 {
 	struct ip_tunnel_info *info = skb_tunnel_info(skb);
 	struct geneve_dev *geneve = netdev_priv(dev);
+	const struct geneve_config *cfg;
 	__be16 sport;
 
+	cfg = rcu_dereference(geneve->cfg);
+	if (unlikely(!cfg))
+		return -ENODEV;
+
 	if (ip_tunnel_info_af(info) == AF_INET) {
 		struct rtable *rt;
 		struct geneve_sock *gs4 = rcu_dereference(geneve->sock4);
@@ -1624,14 +1643,14 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 			return -EIO;
 
 		use_cache = ip_tunnel_dst_cache_usable(skb, info);
-		tos = geneve_get_dsfield(skb, dev, info, &use_cache);
+		tos = geneve_get_dsfield(skb, dev, cfg, info, &use_cache);
 		sport = udp_flow_src_port(geneve->net, skb,
-					  geneve->cfg.port_min,
-					  geneve->cfg.port_max, true);
+					  cfg->port_min,
+					  cfg->port_max, true);
 
 		rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr,
 					   &info->key,
-					   sport, geneve->cfg.info.key.tp_dst,
+					   sport, cfg->info.key.tp_dst,
 					   tos,
 					   use_cache ? &info->dst_cache : NULL);
 		if (IS_ERR(rt))
@@ -1651,14 +1670,14 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 			return -EIO;
 
 		use_cache = ip_tunnel_dst_cache_usable(skb, info);
-		prio = geneve_get_dsfield(skb, dev, info, &use_cache);
+		prio = geneve_get_dsfield(skb, dev, cfg, info, &use_cache);
 		sport = udp_flow_src_port(geneve->net, skb,
-					  geneve->cfg.port_min,
-					  geneve->cfg.port_max, true);
+					  cfg->port_min,
+					  cfg->port_max, true);
 
 		dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sk, 0,
 					     &saddr, &info->key, sport,
-					     geneve->cfg.info.key.tp_dst, prio,
+					     cfg->info.key.tp_dst, prio,
 					     use_cache ? &info->dst_cache : NULL);
 		if (IS_ERR(dst))
 			return PTR_ERR(dst);
@@ -1671,7 +1690,7 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 	}
 
 	info->key.tp_src = sport;
-	info->key.tp_dst = geneve->cfg.info.key.tp_dst;
+	info->key.tp_dst = cfg->info.key.tp_dst;
 	return 0;
 }
 
@@ -1727,7 +1746,50 @@ static void geneve_offload_rx_ports(struct net_device *dev, bool push)
 	}
 }
 
+static struct geneve_config *geneve_config_alloc(const struct geneve_config *src)
+{
+	struct geneve_config *cfg;
+	int err;
+
+	cfg = kmemdup(src, sizeof(*src), GFP_KERNEL);
+	if (!cfg)
+		return ERR_PTR(-ENOMEM);
+
+	cfg->info.dst_cache.cache = NULL;
+	err = dst_cache_init(&cfg->info.dst_cache, GFP_KERNEL);
+	if (err) {
+		kfree(cfg);
+		return ERR_PTR(err);
+	}
+
+	return cfg;
+}
+
+static void geneve_config_free(struct geneve_config *cfg)
+{
+	if (cfg) {
+		dst_cache_destroy(&cfg->info.dst_cache);
+		kfree(cfg);
+	}
+}
+
+static void geneve_config_free_rcu(struct rcu_head *head)
+{
+	struct geneve_config *cfg = container_of(head, struct geneve_config, rcu);
+
+	geneve_config_free(cfg);
+}
+
 /* Initialize the device structure. */
+static void geneve_free_dev(struct net_device *dev)
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+	struct geneve_config *cfg = rcu_dereference_protected(geneve->cfg, 1);
+
+	geneve_config_free(cfg);
+	RCU_INIT_POINTER(geneve->cfg, NULL);
+}
+
 static void geneve_setup(struct net_device *dev)
 {
 	ether_setup(dev);
@@ -1735,6 +1797,7 @@ static void geneve_setup(struct net_device *dev)
 	dev->netdev_ops = &geneve_netdev_ops;
 	dev->ethtool_ops = &geneve_ethtool_ops;
 	dev->needs_free_netdev = true;
+	dev->priv_destructor = geneve_free_dev;
 
 	SET_NETDEV_DEVTYPE(dev, &geneve_type);
 
@@ -1763,6 +1826,8 @@ static void geneve_setup(struct net_device *dev)
 	dev->max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len;
 
 	netif_keep_dst(dev);
+	netif_set_tso_max_size(dev, GSO_MAX_SIZE);
+
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
 	dev->lltx = true;
@@ -1896,15 +1961,17 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn,
 	*tun_on_same_port = false;
 	*tun_collect_md = false;
 	list_for_each_entry(geneve, &gn->geneve_list, next) {
-		if (info->key.tp_dst == geneve->cfg.info.key.tp_dst &&
-		    (cfg->dualstack || geneve->cfg.dualstack ||
-		     geneve_saddr_conflict(info, &geneve->cfg.info))) {
-			*tun_collect_md |= geneve->cfg.collect_md;
+		const struct geneve_config *gcfg = rtnl_dereference(geneve->cfg);
+
+		if (info->key.tp_dst == gcfg->info.key.tp_dst &&
+		    (cfg->dualstack || gcfg->dualstack ||
+		     geneve_saddr_conflict(info, &gcfg->info))) {
+			*tun_collect_md |= gcfg->collect_md;
 			*tun_on_same_port = true;
 		}
-		if (info->key.tun_id == geneve->cfg.info.key.tun_id &&
-		    info->key.tp_dst == geneve->cfg.info.key.tp_dst &&
-		    !memcmp(&info->key.u, &geneve->cfg.info.key.u, sizeof(info->key.u)))
+		if (info->key.tun_id == gcfg->info.key.tun_id &&
+		    info->key.tp_dst == gcfg->info.key.tp_dst &&
+		    !memcmp(&info->key.u, &gcfg->info.key.u, sizeof(info->key.u)))
 			t = geneve;
 	}
 	return t;
@@ -1940,6 +2007,7 @@ static int geneve_configure(struct net *net, struct net_device *dev,
 	struct geneve_dev *t, *geneve = netdev_priv(dev);
 	const struct ip_tunnel_info *info = &cfg->info;
 	bool tun_collect_md, tun_on_same_port;
+	struct geneve_config *new_cfg;
 	int err, encap_len;
 
 	if (cfg->collect_md && !is_tnl_info_zero(info)) {
@@ -1980,10 +2048,13 @@ static int geneve_configure(struct net *net, struct net_device *dev,
 		}
 	}
 
-	dst_cache_reset(&geneve->cfg.info.dst_cache);
-	memcpy(&geneve->cfg, cfg, sizeof(*cfg));
+	new_cfg = geneve_config_alloc(cfg);
+	if (IS_ERR(new_cfg))
+		return PTR_ERR(new_cfg);
 
-	if (geneve->cfg.inner_proto_inherit) {
+	rcu_assign_pointer(geneve->cfg, new_cfg);
+
+	if (cfg->inner_proto_inherit) {
 		dev->header_ops = NULL;
 		dev->type = ARPHRD_NONE;
 		dev->hard_header_len = 0;
@@ -1992,8 +2063,10 @@ static int geneve_configure(struct net *net, struct net_device *dev,
 	}
 
 	err = register_netdevice(dev);
-	if (err)
+	if (err) {
+		geneve_free_dev(dev);
 		return err;
+	}
 
 	list_add(&geneve->next, &gn->geneve_list);
 	return 0;
@@ -2341,57 +2414,17 @@ static int geneve_newlink(struct net_device *dev,
 	return 0;
 }
 
-/* Quiesces the geneve device data path for both TX and RX.
- *
- * On transmit geneve checks for non-NULL geneve_sock before it proceeds.
- * So, if we set that socket to NULL under RCU and wait for synchronize_net()
- * to complete for the existing set of in-flight packets to be transmitted,
- * then we would have quiesced the transmit data path. All the future packets
- * will get dropped until we unquiesce the data path.
- *
- * On receive geneve dereference the geneve_sock stashed in the socket. So,
- * if we set that to NULL under RCU and wait for synchronize_net() to
- * complete, then we would have quiesced the receive data path.
+/* Update the device configuration under RTNL.
+ * We use RCU swap to update the configuration atomically, so the data path
+ * (both TX and RX) can continue running without interruption or packet loss.
  */
-static void geneve_quiesce(struct geneve_dev *geneve, struct geneve_sock **gs4,
-			   struct geneve_sock **gs6)
-{
-	*gs4 = rtnl_dereference(geneve->sock4);
-	rcu_assign_pointer(geneve->sock4, NULL);
-	if (*gs4)
-		rcu_assign_sk_user_data((*gs4)->sk, NULL);
-#if IS_ENABLED(CONFIG_IPV6)
-	*gs6 = rtnl_dereference(geneve->sock6);
-	rcu_assign_pointer(geneve->sock6, NULL);
-	if (*gs6)
-		rcu_assign_sk_user_data((*gs6)->sk, NULL);
-#else
-	*gs6 = NULL;
-#endif
-	synchronize_net();
-}
-
-/* Resumes the geneve device data path for both TX and RX. */
-static void geneve_unquiesce(struct geneve_dev *geneve, struct geneve_sock *gs4,
-			     struct geneve_sock __maybe_unused *gs6)
-{
-	rcu_assign_pointer(geneve->sock4, gs4);
-	if (gs4)
-		rcu_assign_sk_user_data(gs4->sk, gs4);
-#if IS_ENABLED(CONFIG_IPV6)
-	rcu_assign_pointer(geneve->sock6, gs6);
-	if (gs6)
-		rcu_assign_sk_user_data(gs6->sk, gs6);
-#endif
-}
-
 static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 			     struct nlattr *data[],
 			     struct netlink_ext_ack *extack)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
-	struct geneve_sock *gs4, *gs6;
-	struct geneve_config cfg;
+	struct geneve_config *old_cfg = rtnl_dereference(geneve->cfg);
+	struct geneve_config *cfg;
 	int err;
 
 	if (!rtnl_dev_link_net_capable(dev, geneve->net))
@@ -2400,25 +2433,29 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 	/* If the geneve device is configured for metadata (or externally
 	 * controlled, for example, OVS), then nothing can be changed.
 	 */
-	if (geneve->cfg.collect_md)
+	if (old_cfg->collect_md)
 		return -EOPNOTSUPP;
 
 	/* Start with the existing info. */
-	memcpy(&cfg, &geneve->cfg, sizeof(cfg));
-	err = geneve_nl2info(tb, data, extack, &cfg, true);
+	cfg = geneve_config_alloc(old_cfg);
+	if (IS_ERR(cfg))
+		return PTR_ERR(cfg);
+
+	err = geneve_nl2info(tb, data, extack, cfg, true);
 	if (err)
-		return err;
+		goto err_free_cfg;
 
-	if (!geneve_dst_addr_equal(&geneve->cfg.info, &cfg.info)) {
-		dst_cache_reset(&cfg.info.dst_cache);
-		geneve_link_config(dev, &cfg.info, tb);
-	}
+	if (!geneve_dst_addr_equal(&old_cfg->info, &cfg->info))
+		geneve_link_config(dev, &cfg->info, tb);
 
-	geneve_quiesce(geneve, &gs4, &gs6);
-	memcpy(&geneve->cfg, &cfg, sizeof(cfg));
-	geneve_unquiesce(geneve, gs4, gs6);
+	rcu_assign_pointer(geneve->cfg, cfg);
 
+	call_rcu_hurry(&old_cfg->rcu, geneve_config_free_rcu);
 	return 0;
+
+err_free_cfg:
+	geneve_config_free(cfg);
+	return err;
 }
 
 static void geneve_dellink(struct net_device *dev, struct list_head *head)
@@ -2452,16 +2489,27 @@ static size_t geneve_get_size(const struct net_device *dev)
 
 static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
-	struct geneve_dev *geneve = netdev_priv(dev);
-	struct ip_tunnel_info *info = &geneve->cfg.info;
-	bool ttl_inherit = geneve->cfg.ttl_inherit;
-	bool metadata = geneve->cfg.collect_md;
-	struct ifla_geneve_port_range ports = {
-		.low	= htons(geneve->cfg.port_min),
-		.high	= htons(geneve->cfg.port_max),
-	};
+	const struct geneve_dev *geneve = netdev_priv(dev);
+	struct ifla_geneve_port_range ports;
+	const struct geneve_config *cfg;
+	const struct ip_tunnel_info *info;
+	bool ttl_inherit, metadata;
 	__u8 tmp_vni[3];
 	__u32 vni;
+	int err = 0;
+
+	rcu_read_lock();
+	cfg = rcu_dereference(geneve->cfg);
+	if (!cfg) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	info = &cfg->info;
+	ttl_inherit = cfg->ttl_inherit;
+	metadata = cfg->collect_md;
+	ports.low = htons(cfg->port_min);
+	ports.high = htons(cfg->port_max);
 
 	tunnel_id_to_vni(info->key.tun_id, tmp_vni);
 	vni = (tmp_vni[0] << 16) | (tmp_vni[1] << 8) | tmp_vni[2];
@@ -2489,17 +2537,17 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 #endif
 	}
 
-	if (!geneve->cfg.dualstack) {
+	if (!cfg->dualstack) {
 		if (ip_tunnel_info_af(info) == AF_INET) {
 			if ((info->key.u.ipv4.src ||
-			     geneve->cfg.collect_md) &&
+			     metadata) &&
 			    nla_put_in_addr(skb, IFLA_GENEVE_LOCAL,
 					    info->key.u.ipv4.src))
 				goto nla_put_failure;
 #if IS_ENABLED(CONFIG_IPV6)
 		} else {
 			if ((!ipv6_addr_any(&info->key.u.ipv6.src) ||
-			     geneve->cfg.collect_md) &&
+			     metadata) &&
 			    nla_put_in6_addr(skb, IFLA_GENEVE_LOCAL6,
 					     &info->key.u.ipv6.src))
 				goto nla_put_failure;
@@ -2512,7 +2560,7 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_be32(skb, IFLA_GENEVE_LABEL, info->key.label))
 		goto nla_put_failure;
 
-	if (nla_put_u8(skb, IFLA_GENEVE_DF, geneve->cfg.df))
+	if (nla_put_u8(skb, IFLA_GENEVE_DF, cfg->df))
 		goto nla_put_failure;
 
 	if (nla_put_be16(skb, IFLA_GENEVE_PORT, info->key.tp_dst))
@@ -2523,28 +2571,31 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
-		       !geneve->cfg.use_udp6_rx_checksums))
+		       !cfg->use_udp6_rx_checksums))
 		goto nla_put_failure;
 #endif
 
 	if (nla_put_u8(skb, IFLA_GENEVE_TTL_INHERIT, ttl_inherit))
 		goto nla_put_failure;
 
-	if (geneve->cfg.inner_proto_inherit &&
+	if (cfg->inner_proto_inherit &&
 	    nla_put_flag(skb, IFLA_GENEVE_INNER_PROTO_INHERIT))
 		goto nla_put_failure;
 
 	if (nla_put(skb, IFLA_GENEVE_PORT_RANGE, sizeof(ports), &ports))
 		goto nla_put_failure;
 
-	if (geneve->cfg.gro_hint &&
+	if (cfg->gro_hint &&
 	    nla_put_flag(skb, IFLA_GENEVE_GRO_HINT))
 		goto nla_put_failure;
 
-	return 0;
+out:
+	rcu_read_unlock();
+	return err;
 
 nla_put_failure:
-	return -EMSGSIZE;
+	err = -EMSGSIZE;
+	goto out;
 }
 
 static struct rtnl_link_ops geneve_link_ops __read_mostly = {
@@ -2692,6 +2743,7 @@ static void __exit geneve_cleanup_module(void)
 	rtnl_link_unregister(&geneve_link_ops);
 	unregister_netdevice_notifier(&geneve_notifier_block);
 	unregister_pernet_subsys(&geneve_net_ops);
+	rcu_barrier();
 }
 module_exit(geneve_cleanup_module);
 
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index 80f84fc87008..8d05ad480438 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -69,6 +69,7 @@ struct ipvl_dev {
 	DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE);
 	netdev_features_t	sfeatures;
 	u32			msg_enable;
+	bool			dying;
 };
 
 struct ipvl_addr {
@@ -91,12 +92,13 @@ struct ipvl_port {
 	struct hlist_head	hlhead[IPVLAN_HASH_SIZE];
 	spinlock_t		addrs_lock; /* guards hash-table and addrs */
 	struct list_head	ipvlans;
+	struct mutex		pnodes_lock;
 	u16			mode;
 	u16			flags;
 	u16			dev_id_start;
 	struct work_struct	wq;
 	struct sk_buff_head	backlog;
-	int			count;
+	refcount_t		count;
 	struct ida		ida;
 	netdevice_tracker	dev_tracker;
 };
@@ -168,7 +170,8 @@ void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
 		     unsigned int len, bool success, bool mcast);
 int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params,
 		    struct netlink_ext_ack *extack);
-void ipvlan_link_delete(struct net_device *dev, struct list_head *head);
+void __ipvlan_link_delete(struct net *net, struct net_device *dev,
+			  struct list_head *head);
 void ipvlan_link_setup(struct net_device *dev);
 int ipvlan_link_register(struct rtnl_link_ops *ops);
 #ifdef CONFIG_IPVLAN_L3S
@@ -207,4 +210,9 @@ static inline bool netif_is_ipvlan_port(const struct net_device *dev)
 	return rcu_access_pointer(dev->rx_handler) == ipvlan_handle_frame;
 }
 
+#if IS_ENABLED(CONFIG_IPVTAP)
+extern void (*__ipvtap_dellink_ptr)(struct net *net, struct net_device *dev,
+				    struct list_head *head);
+#endif
+
 #endif /* __IPVLAN_H */
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index ed46439a9f4e..ee46a55f73d1 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -7,6 +7,12 @@
 
 #include "ipvlan.h"
 
+#if IS_ENABLED(CONFIG_IPVTAP)
+void (*__ipvtap_dellink_ptr)(struct net *net, struct net_device *dev,
+			     struct list_head *head);
+EXPORT_SYMBOL(__ipvtap_dellink_ptr);
+#endif
+
 static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval,
 				struct netlink_ext_ack *extack)
 {
@@ -16,6 +22,8 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval,
 
 	ASSERT_RTNL();
 	if (port->mode != nval) {
+		mutex_lock(&port->pnodes_lock);
+
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
 			flags = ipvlan->dev->flags;
 			if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) {
@@ -40,6 +48,8 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval,
 			ipvlan_l3s_unregister(port);
 		}
 		port->mode = nval;
+
+		mutex_unlock(&port->pnodes_lock);
 	}
 	return 0;
 
@@ -56,6 +66,8 @@ fail:
 					 NULL);
 	}
 
+	mutex_unlock(&port->pnodes_lock);
+
 	return err;
 }
 
@@ -76,6 +88,7 @@ static int ipvlan_port_create(struct net_device *dev)
 		INIT_HLIST_HEAD(&port->hlhead[idx]);
 
 	spin_lock_init(&port->addrs_lock);
+	mutex_init(&port->pnodes_lock);
 	skb_queue_head_init(&port->backlog);
 	INIT_WORK(&port->wq, ipvlan_process_multicast);
 	ida_init(&port->ida);
@@ -86,6 +99,7 @@ static int ipvlan_port_create(struct net_device *dev)
 		goto err;
 
 	netdev_hold(dev, &port->dev_tracker, GFP_KERNEL);
+
 	return 0;
 
 err:
@@ -93,16 +107,18 @@ err:
 	return err;
 }
 
-static void ipvlan_port_destroy(struct net_device *dev)
+static void ipvlan_port_destroy(struct ipvl_port *port)
 {
-	struct ipvl_port *port = ipvlan_port_get_rtnl(dev);
+	struct net_device *dev = port->dev;
 	struct sk_buff *skb;
 
-	netdev_put(dev, &port->dev_tracker);
 	if (port->mode == IPVLAN_MODE_L3S)
 		ipvlan_l3s_unregister(port);
+
 	netdev_rx_handler_unregister(dev);
 	cancel_work_sync(&port->wq);
+	netdev_put(dev, &port->dev_tracker);
+
 	while ((skb = __skb_dequeue(&port->backlog)) != NULL) {
 		dev_put(skb->dev);
 		kfree_skb(skb);
@@ -111,6 +127,27 @@ static void ipvlan_port_destroy(struct net_device *dev)
 	kfree(port);
 }
 
+static void ipvlan_port_put(struct ipvl_port *port)
+{
+	if (refcount_dec_and_test(&port->count))
+		ipvlan_port_destroy(port);
+}
+
+static struct ipvl_port *ipvlan_port_get(struct net_device *dev)
+{
+	struct ipvl_port *port = NULL;
+
+	rcu_read_lock();
+	if (netif_is_ipvlan_port(dev)) {
+		port = ipvlan_port_get_rcu(dev);
+		if (!refcount_inc_not_zero(&port->count))
+			port = NULL;
+	}
+	rcu_read_unlock();
+
+	return port;
+}
+
 #define IPVLAN_ALWAYS_ON_OFLOADS \
 	(NETIF_F_SG | NETIF_F_HW_CSUM | \
 	 NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL)
@@ -153,30 +190,45 @@ static int ipvlan_init(struct net_device *dev)
 	if (!ipvlan->pcpu_stats)
 		return -ENOMEM;
 
+	netdev_lock(phy_dev);
+
 	if (!netif_is_ipvlan_port(phy_dev)) {
 		err = ipvlan_port_create(phy_dev);
 		if (err < 0) {
+			netdev_unlock(phy_dev);
 			free_percpu(ipvlan->pcpu_stats);
 			return err;
 		}
+		port = ipvlan_port_get_rtnl(phy_dev);
+		refcount_set(&port->count, 1);
+	} else {
+		port = ipvlan_port_get_rtnl(phy_dev);
+		refcount_inc(&port->count);
 	}
-	port = ipvlan_port_get_rtnl(phy_dev);
-	port->count += 1;
+
+	netdev_unlock(phy_dev);
+
+	ipvlan->port = port;
+
 	return 0;
 }
 
 static void ipvlan_uninit(struct net_device *dev)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
-	struct net_device *phy_dev = ipvlan->phy_dev;
-	struct ipvl_port *port;
+	netdevice_tracker dev_tracker;
+	struct net_device *phy_dev;
 
 	free_percpu(ipvlan->pcpu_stats);
 
-	port = ipvlan_port_get_rtnl(phy_dev);
-	port->count -= 1;
-	if (!port->count)
-		ipvlan_port_destroy(port->dev);
+	phy_dev = ipvlan->phy_dev;
+	netdev_hold(phy_dev, &dev_tracker, GFP_KERNEL);
+	netdev_lock(phy_dev);
+
+	ipvlan_port_put(ipvlan->port);
+
+	netdev_unlock(phy_dev);
+	netdev_put(phy_dev, &dev_tracker);
 }
 
 static int ipvlan_open(struct net_device *dev)
@@ -594,9 +646,7 @@ int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params,
 	if (err < 0)
 		return err;
 
-	/* ipvlan_init() would have created the port, if required */
-	port = ipvlan_port_get_rtnl(phy_dev);
-	ipvlan->port = port;
+	port = ipvlan->port;
 
 	/* If the port-id base is at the MAX value, then wrap it around and
 	 * begin from 0x1 again. This may be due to a busy system where lots
@@ -639,7 +689,10 @@ int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params,
 	if (err)
 		goto unlink_netdev;
 
+	mutex_lock(&port->pnodes_lock);
 	list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans);
+	mutex_unlock(&port->pnodes_lock);
+
 	netif_stacked_transfer_operstate(phy_dev, dev);
 	return 0;
 
@@ -653,7 +706,8 @@ unregister_netdev:
 }
 EXPORT_SYMBOL_GPL(ipvlan_link_new);
 
-void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
+void __ipvlan_link_delete(struct net *net, struct net_device *dev,
+			  struct list_head *head)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 	struct ipvl_addr *addr, *next;
@@ -668,10 +722,20 @@ void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
 
 	ida_free(&ipvlan->port->ida, dev->dev_id);
 	list_del_rcu(&ipvlan->pnode);
-	unregister_netdevice_queue(dev, head);
+	unregister_netdevice_queue_net(net, dev, head);
 	netdev_upper_dev_unlink(ipvlan->phy_dev, dev);
 }
-EXPORT_SYMBOL_GPL(ipvlan_link_delete);
+EXPORT_SYMBOL(__ipvlan_link_delete);
+
+static void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	mutex_lock(&ipvlan->port->pnodes_lock);
+	if (!ipvlan->dying)
+		__ipvlan_link_delete(dev_net(dev), dev, head);
+	mutex_unlock(&ipvlan->port->pnodes_lock);
+}
 
 void ipvlan_link_setup(struct net_device *dev)
 {
@@ -729,14 +793,19 @@ static int ipvlan_device_event(struct notifier_block *unused,
 	struct netdev_notifier_pre_changeaddr_info *prechaddr_info;
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct ipvl_dev *ipvlan, *next;
+	int err, ret = NOTIFY_DONE;
 	struct ipvl_port *port;
 	LIST_HEAD(lst_kill);
-	int err;
 
-	if (!netif_is_ipvlan_port(dev))
-		return NOTIFY_DONE;
+	if (event == NETDEV_PRECHANGEUPPER ||
+	    event == NETDEV_CHANGEUPPER)
+		return ret;
 
-	port = ipvlan_port_get_rtnl(dev);
+	port = ipvlan_port_get(dev);
+	if (!port)
+		return ret;
+
+	mutex_lock(&port->pnodes_lock);
 
 	switch (event) {
 	case NETDEV_UP:
@@ -760,16 +829,26 @@ static int ipvlan_device_event(struct notifier_block *unused,
 			ipvlan_migrate_l3s_hook(oldnet, newnet);
 		break;
 	}
-	case NETDEV_UNREGISTER:
+	case NETDEV_UNREGISTER: {
+		struct net *net = dev_net(dev);
+
 		if (dev->reg_state != NETREG_UNREGISTERING)
 			break;
 
-		list_for_each_entry_safe(ipvlan, next, &port->ipvlans, pnode)
-			ipvlan->dev->rtnl_link_ops->dellink(ipvlan->dev,
-							    &lst_kill);
+		list_for_each_entry_safe(ipvlan, next, &port->ipvlans, pnode) {
+			ipvlan->dying = true;
+
+#if IS_ENABLED(CONFIG_IPVTAP)
+			if (ipvlan->dev->rtnl_link_ops != &ipvlan_link_ops)
+				__ipvtap_dellink_ptr(net, ipvlan->dev, &lst_kill);
+			else
+#endif
+				__ipvlan_link_delete(net, ipvlan->dev, &lst_kill);
+		}
+
 		unregister_netdevice_many(&lst_kill);
 		break;
-
+	}
 	case NETDEV_FEAT_CHANGE:
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
 			netif_inherit_tso_max(ipvlan->dev, dev);
@@ -788,8 +867,10 @@ static int ipvlan_device_event(struct notifier_block *unused,
 			err = netif_pre_changeaddr_notify(ipvlan->dev,
 							  prechaddr_info->dev_addr,
 							  extack);
-			if (err)
-				return notifier_from_errno(err);
+			if (err) {
+				ret = notifier_from_errno(err);
+				break;
+			}
 		}
 		break;
 
@@ -802,7 +883,8 @@ static int ipvlan_device_event(struct notifier_block *unused,
 
 	case NETDEV_PRE_TYPE_CHANGE:
 		/* Forbid underlying device to change its type. */
-		return NOTIFY_BAD;
+		ret = NOTIFY_BAD;
+		break;
 
 	case NETDEV_NOTIFY_PEERS:
 	case NETDEV_BONDING_FAILOVER:
@@ -810,7 +892,12 @@ static int ipvlan_device_event(struct notifier_block *unused,
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode)
 			call_netdevice_notifiers(event, ipvlan->dev);
 	}
-	return NOTIFY_DONE;
+
+	mutex_unlock(&port->pnodes_lock);
+
+	ipvlan_port_put(port);
+
+	return ret;
 }
 
 /* the caller must held the addrs lock */
diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
index 2d6bbddd1edd..66c949d94261 100644
--- a/drivers/net/ipvlan/ipvtap.c
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -109,14 +109,26 @@ static int ipvtap_newlink(struct net_device *dev,
 	return err;
 }
 
+static void __ipvtap_dellink(struct net *net, struct net_device *dev,
+			     struct list_head *head)
+{
+	struct ipvtap_dev *vlantap = netdev_priv(dev);
+
+	netdev_rx_handler_unregister(dev);
+	tap_del_queues(&vlantap->tap);
+	__ipvlan_link_delete(net, dev, head);
+}
+
 static void ipvtap_dellink(struct net_device *dev,
 			   struct list_head *head)
 {
-	struct ipvtap_dev *vlan = netdev_priv(dev);
+	struct ipvtap_dev *vlantap = netdev_priv(dev);
+	struct ipvl_port *port = vlantap->vlan.port;
 
-	netdev_rx_handler_unregister(dev);
-	tap_del_queues(&vlan->tap);
-	ipvlan_link_delete(dev, head);
+	mutex_lock(&port->pnodes_lock);
+	if (!vlantap->vlan.dying)
+		__ipvtap_dellink(dev_net(dev), dev, head);
+	mutex_unlock(&port->pnodes_lock);
 }
 
 static void ipvtap_setup(struct net_device *dev)
@@ -198,6 +210,8 @@ static int __init ipvtap_init(void)
 {
 	int err;
 
+	__ipvtap_dellink_ptr = __ipvtap_dellink;
+
 	err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap",
 			      THIS_MODULE);
 	if (err)
@@ -224,6 +238,8 @@ out3:
 out2:
 	tap_destroy_cdev(ipvtap_major, &ipvtap_cdev);
 out1:
+	__ipvtap_dellink_ptr = NULL;
+
 	return err;
 }
 module_init(ipvtap_init);
@@ -234,6 +250,7 @@ static void __exit ipvtap_exit(void)
 	unregister_netdevice_notifier(&ipvtap_notifier_block);
 	class_unregister(&ipvtap_class);
 	tap_destroy_cdev(ipvtap_major, &ipvtap_cdev);
+	__ipvtap_dellink_ptr = NULL;
 }
 module_exit(ipvtap_exit);
 MODULE_ALIAS_RTNL_LINK("ipvtap");
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index ee0e2eb7dbc6..6f9f3aceffaa 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -2636,7 +2636,7 @@ static int macsec_update_offload(struct net_device *dev,
 		vlan_drop_rx_ctag_filter_info(dev);
 		vlan_drop_rx_stag_filter_info(dev);
 	}
-	macsec->offload = offload;
+	WRITE_ONCE(macsec->offload, offload);
 	/* Add VLAN filters when enabling offload. */
 	if (prev_offload == MACSEC_OFFLOAD_OFF) {
 		ret = vlan_get_rx_ctag_filter_info(dev);
@@ -2666,7 +2666,7 @@ static int macsec_update_offload(struct net_device *dev,
 	return 0;
 
 rollback_offload:
-	macsec->offload = prev_offload;
+	WRITE_ONCE(macsec->offload, prev_offload);
 	macsec_offload(ops->mdo_del_secy, &ctx);
 
 	return ret;
@@ -3878,52 +3878,53 @@ static int macsec_changelink_common(struct net_device *dev,
 
 	if (data[IFLA_MACSEC_ENCODING_SA]) {
 		struct macsec_tx_sa *tx_sa;
+		u8 encoding_sa = nla_get_u8(data[IFLA_MACSEC_ENCODING_SA]);
 
-		tx_sc->encoding_sa = nla_get_u8(data[IFLA_MACSEC_ENCODING_SA]);
-		tx_sa = rtnl_dereference(tx_sc->sa[tx_sc->encoding_sa]);
+		WRITE_ONCE(tx_sc->encoding_sa, encoding_sa);
+		tx_sa = rtnl_dereference(tx_sc->sa[encoding_sa]);
 
 		secy->operational = tx_sa && tx_sa->active;
 	}
 
 	if (data[IFLA_MACSEC_ENCRYPT])
-		tx_sc->encrypt = !!nla_get_u8(data[IFLA_MACSEC_ENCRYPT]);
+		WRITE_ONCE(tx_sc->encrypt, !!nla_get_u8(data[IFLA_MACSEC_ENCRYPT]));
 
 	if (data[IFLA_MACSEC_PROTECT])
-		secy->protect_frames = !!nla_get_u8(data[IFLA_MACSEC_PROTECT]);
+		WRITE_ONCE(secy->protect_frames, !!nla_get_u8(data[IFLA_MACSEC_PROTECT]));
 
 	if (data[IFLA_MACSEC_INC_SCI])
-		tx_sc->send_sci = !!nla_get_u8(data[IFLA_MACSEC_INC_SCI]);
+		WRITE_ONCE(tx_sc->send_sci, !!nla_get_u8(data[IFLA_MACSEC_INC_SCI]));
 
 	if (data[IFLA_MACSEC_ES])
-		tx_sc->end_station = !!nla_get_u8(data[IFLA_MACSEC_ES]);
+		WRITE_ONCE(tx_sc->end_station, !!nla_get_u8(data[IFLA_MACSEC_ES]));
 
 	if (data[IFLA_MACSEC_SCB])
-		tx_sc->scb = !!nla_get_u8(data[IFLA_MACSEC_SCB]);
+		WRITE_ONCE(tx_sc->scb, !!nla_get_u8(data[IFLA_MACSEC_SCB]));
 
 	if (data[IFLA_MACSEC_REPLAY_PROTECT])
-		secy->replay_protect = !!nla_get_u8(data[IFLA_MACSEC_REPLAY_PROTECT]);
+		WRITE_ONCE(secy->replay_protect, !!nla_get_u8(data[IFLA_MACSEC_REPLAY_PROTECT]));
 
 	if (data[IFLA_MACSEC_VALIDATION])
-		secy->validate_frames = nla_get_u8(data[IFLA_MACSEC_VALIDATION]);
+		WRITE_ONCE(secy->validate_frames, nla_get_u8(data[IFLA_MACSEC_VALIDATION]));
 
 	if (data[IFLA_MACSEC_CIPHER_SUITE]) {
 		switch (nla_get_u64(data[IFLA_MACSEC_CIPHER_SUITE])) {
 		case MACSEC_CIPHER_ID_GCM_AES_128:
 		case MACSEC_DEFAULT_CIPHER_ID:
-			secy->key_len = MACSEC_GCM_AES_128_SAK_LEN;
-			secy->xpn = false;
+			WRITE_ONCE(secy->key_len, MACSEC_GCM_AES_128_SAK_LEN);
+			WRITE_ONCE(secy->xpn, false);
 			break;
 		case MACSEC_CIPHER_ID_GCM_AES_256:
-			secy->key_len = MACSEC_GCM_AES_256_SAK_LEN;
-			secy->xpn = false;
+			WRITE_ONCE(secy->key_len, MACSEC_GCM_AES_256_SAK_LEN);
+			WRITE_ONCE(secy->xpn, false);
 			break;
 		case MACSEC_CIPHER_ID_GCM_AES_XPN_128:
-			secy->key_len = MACSEC_GCM_AES_128_SAK_LEN;
-			secy->xpn = true;
+			WRITE_ONCE(secy->key_len, MACSEC_GCM_AES_128_SAK_LEN);
+			WRITE_ONCE(secy->xpn, true);
 			break;
 		case MACSEC_CIPHER_ID_GCM_AES_XPN_256:
-			secy->key_len = MACSEC_GCM_AES_256_SAK_LEN;
-			secy->xpn = true;
+			WRITE_ONCE(secy->key_len, MACSEC_GCM_AES_256_SAK_LEN);
+			WRITE_ONCE(secy->xpn, true);
 			break;
 		default:
 			return -EINVAL;
@@ -3931,13 +3932,14 @@ static int macsec_changelink_common(struct net_device *dev,
 	}
 
 	if (data[IFLA_MACSEC_WINDOW]) {
-		secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]);
+		u32 replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]);
 
 		/* IEEE 802.1AEbw-2013 10.7.8 - maximum replay window
 		 * for XPN cipher suites */
 		if (secy->xpn &&
-		    secy->replay_window > MACSEC_XPN_MAX_REPLAY_WINDOW)
+		    replay_window > MACSEC_XPN_MAX_REPLAY_WINDOW)
 			return -EINVAL;
+		WRITE_ONCE(secy->replay_window, replay_window);
 	}
 
 	return 0;
@@ -4385,21 +4387,21 @@ static size_t macsec_get_size(const struct net_device *dev)
 static int macsec_fill_info(struct sk_buff *skb,
 			    const struct net_device *dev)
 {
-	struct macsec_tx_sc *tx_sc;
-	struct macsec_dev *macsec;
-	struct macsec_secy *secy;
+	const struct macsec_tx_sc *tx_sc;
+	const struct macsec_dev *macsec;
+	const struct macsec_secy *secy;
 	u64 csid;
 
 	macsec = macsec_priv(dev);
 	secy = &macsec->secy;
 	tx_sc = &secy->tx_sc;
 
-	switch (secy->key_len) {
+	switch (READ_ONCE(secy->key_len)) {
 	case MACSEC_GCM_AES_128_SAK_LEN:
-		csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_128 : MACSEC_DEFAULT_CIPHER_ID;
+		csid = READ_ONCE(secy->xpn) ? MACSEC_CIPHER_ID_GCM_AES_XPN_128 : MACSEC_DEFAULT_CIPHER_ID;
 		break;
 	case MACSEC_GCM_AES_256_SAK_LEN:
-		csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_256 : MACSEC_CIPHER_ID_GCM_AES_256;
+		csid = READ_ONCE(secy->xpn) ? MACSEC_CIPHER_ID_GCM_AES_XPN_256 : MACSEC_CIPHER_ID_GCM_AES_256;
 		break;
 	default:
 		goto nla_put_failure;
@@ -4410,20 +4412,20 @@ static int macsec_fill_info(struct sk_buff *skb,
 	    nla_put_u8(skb, IFLA_MACSEC_ICV_LEN, secy->icv_len) ||
 	    nla_put_u64_64bit(skb, IFLA_MACSEC_CIPHER_SUITE,
 			      csid, IFLA_MACSEC_PAD) ||
-	    nla_put_u8(skb, IFLA_MACSEC_ENCODING_SA, tx_sc->encoding_sa) ||
-	    nla_put_u8(skb, IFLA_MACSEC_ENCRYPT, tx_sc->encrypt) ||
-	    nla_put_u8(skb, IFLA_MACSEC_PROTECT, secy->protect_frames) ||
-	    nla_put_u8(skb, IFLA_MACSEC_INC_SCI, tx_sc->send_sci) ||
-	    nla_put_u8(skb, IFLA_MACSEC_ES, tx_sc->end_station) ||
-	    nla_put_u8(skb, IFLA_MACSEC_SCB, tx_sc->scb) ||
-	    nla_put_u8(skb, IFLA_MACSEC_REPLAY_PROTECT, secy->replay_protect) ||
-	    nla_put_u8(skb, IFLA_MACSEC_VALIDATION, secy->validate_frames) ||
-	    nla_put_u8(skb, IFLA_MACSEC_OFFLOAD, macsec->offload) ||
+	    nla_put_u8(skb, IFLA_MACSEC_ENCODING_SA, READ_ONCE(tx_sc->encoding_sa)) ||
+	    nla_put_u8(skb, IFLA_MACSEC_ENCRYPT, READ_ONCE(tx_sc->encrypt)) ||
+	    nla_put_u8(skb, IFLA_MACSEC_PROTECT, READ_ONCE(secy->protect_frames)) ||
+	    nla_put_u8(skb, IFLA_MACSEC_INC_SCI, READ_ONCE(tx_sc->send_sci)) ||
+	    nla_put_u8(skb, IFLA_MACSEC_ES, READ_ONCE(tx_sc->end_station)) ||
+	    nla_put_u8(skb, IFLA_MACSEC_SCB, READ_ONCE(tx_sc->scb)) ||
+	    nla_put_u8(skb, IFLA_MACSEC_REPLAY_PROTECT, READ_ONCE(secy->replay_protect)) ||
+	    nla_put_u8(skb, IFLA_MACSEC_VALIDATION, READ_ONCE(secy->validate_frames)) ||
+	    nla_put_u8(skb, IFLA_MACSEC_OFFLOAD, READ_ONCE(macsec->offload)) ||
 	    0)
 		goto nla_put_failure;
 
-	if (secy->replay_protect) {
-		if (nla_put_u32(skb, IFLA_MACSEC_WINDOW, secy->replay_window))
+	if (READ_ONCE(secy->replay_protect)) {
+		if (nla_put_u32(skb, IFLA_MACSEC_WINDOW, READ_ONCE(secy->replay_window)))
 			goto nla_put_failure;
 	}
 
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index c40fa331836b..9a4bc99dbf53 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -171,7 +171,7 @@ static int macvlan_hash_add_source(struct macvlan_dev *vlan,
 	RCU_INIT_POINTER(entry->vlan, vlan);
 	h = &port->vlan_source_hash[macvlan_eth_hash(addr)];
 	hlist_add_head_rcu(&entry->hlist, h);
-	vlan->macaddr_count++;
+	WRITE_ONCE(vlan->macaddr_count, vlan->macaddr_count + 1);
 
 	return 0;
 }
@@ -277,7 +277,7 @@ static void macvlan_broadcast(struct sk_buff *skb,
 		return;
 
 	hash_for_each_rcu(port->vlan_hash, i, vlan, hlist) {
-		if (vlan->dev == src || !(vlan->mode & mode))
+		if (vlan->dev == src || !(READ_ONCE(vlan->mode) & mode))
 			continue;
 
 		hash = mc_hash(vlan, eth->h_dest);
@@ -306,7 +306,7 @@ static void macvlan_multicast_rx(const struct macvlan_port *port,
 				  MACVLAN_MODE_VEPA    |
 				  MACVLAN_MODE_PASSTHRU|
 				  MACVLAN_MODE_BRIDGE);
-	else if (src->mode == MACVLAN_MODE_VEPA)
+	else if (READ_ONCE(src->mode) == MACVLAN_MODE_VEPA)
 		/* flood to everyone except source */
 		macvlan_broadcast(skb, port, src->dev,
 				  MACVLAN_MODE_VEPA |
@@ -402,7 +402,7 @@ static void macvlan_flush_sources(struct macvlan_port *port,
 		if (rcu_access_pointer(entry->vlan) == vlan)
 			macvlan_hash_del_source(entry);
 
-	vlan->macaddr_count = 0;
+	WRITE_ONCE(vlan->macaddr_count, 0);
 }
 
 static void macvlan_forward_source_one(struct sk_buff *skb,
@@ -447,7 +447,7 @@ static bool macvlan_forward_source(struct sk_buff *skb,
 			if (!vlan)
 				continue;
 
-			if (vlan->flags & MACVLAN_FLAG_NODST)
+			if (READ_ONCE(vlan->flags) & MACVLAN_FLAG_NODST)
 				consume = true;
 			macvlan_forward_source_one(skb, vlan);
 		}
@@ -487,14 +487,18 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 			return RX_HANDLER_CONSUMED;
 		}
 		src = macvlan_hash_lookup(port, eth->h_source);
-		if (src && src->mode != MACVLAN_MODE_VEPA &&
-		    src->mode != MACVLAN_MODE_BRIDGE) {
-			/* forward to original port. */
-			vlan = src;
-			ret = macvlan_broadcast_one(skb, vlan, eth, 0) ?:
-			      __netif_rx(skb);
-			handle_res = RX_HANDLER_CONSUMED;
-			goto out;
+		if (src) {
+			enum macvlan_mode mode = READ_ONCE(src->mode);
+
+			if (mode != MACVLAN_MODE_VEPA &&
+			    mode != MACVLAN_MODE_BRIDGE) {
+				/* forward to original port. */
+				vlan = src;
+				ret = macvlan_broadcast_one(skb, vlan, eth, 0) ?:
+				      __netif_rx(skb);
+				handle_res = RX_HANDLER_CONSUMED;
+				goto out;
+			}
 		}
 
 		hash = mc_hash(NULL, eth->h_dest);
@@ -515,7 +519,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 					      struct macvlan_dev, list);
 	else
 		vlan = macvlan_hash_lookup(port, eth->h_dest);
-	if (!vlan || vlan->mode == MACVLAN_MODE_SOURCE)
+	if (!vlan || READ_ONCE(vlan->mode) == MACVLAN_MODE_SOURCE)
 		return RX_HANDLER_PASS;
 
 	dev = vlan->dev;
@@ -548,7 +552,7 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 	const struct macvlan_port *port = vlan->port;
 	const struct macvlan_dev *dest;
 
-	if (vlan->mode == MACVLAN_MODE_BRIDGE) {
+	if (READ_ONCE(vlan->mode) == MACVLAN_MODE_BRIDGE) {
 		const struct ethhdr *eth = skb_eth_hdr(skb);
 
 		/* send to other bridge ports directly */
@@ -559,7 +563,7 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 
 		dest = macvlan_hash_lookup(port, eth->h_dest);
-		if (dest && dest->mode == MACVLAN_MODE_BRIDGE) {
+		if (dest && READ_ONCE(dest->mode) == MACVLAN_MODE_BRIDGE) {
 			/* send to lowerdev first for its network taps */
 			dev_forward_skb(vlan->lowerdev, skb);
 
@@ -777,7 +781,7 @@ static int macvlan_set_mac_address(struct net_device *dev, void *p)
 	if (ether_addr_equal(dev->dev_addr, addr->__data))
 		return 0;
 
-	if (vlan->mode == MACVLAN_MODE_PASSTHRU) {
+	if (READ_ONCE(vlan->mode) == MACVLAN_MODE_PASSTHRU) {
 		macvlan_set_addr_change(vlan->port);
 		return dev_set_mac_address(vlan->lowerdev, addr, NULL);
 	}
@@ -870,7 +874,7 @@ static void update_port_bc_cutoff(struct macvlan_dev *vlan, int cutoff)
 	if (vlan->port->bc_cutoff == cutoff)
 		return;
 
-	vlan->port->bc_cutoff = cutoff;
+	WRITE_ONCE(vlan->port->bc_cutoff, cutoff);
 	macvlan_recompute_bc_filter(vlan);
 }
 
@@ -1423,7 +1427,7 @@ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode,
 		entry = macvlan_hash_lookup_source(vlan, addr);
 		if (entry) {
 			macvlan_hash_del_source(entry);
-			vlan->macaddr_count--;
+			WRITE_ONCE(vlan->macaddr_count, vlan->macaddr_count - 1);
 		}
 	} else if (mode == MACVLAN_MACADDR_FLUSH) {
 		macvlan_flush_sources(vlan->port, vlan);
@@ -1645,11 +1649,12 @@ static int macvlan_changelink(struct net_device *dev,
 			if (err < 0)
 				return err;
 		}
-		vlan->flags = flags;
+		WRITE_ONCE(vlan->flags, flags);
 	}
 
 	if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN]) {
-		vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]);
+		WRITE_ONCE(vlan->bc_queue_len_req,
+			   nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]));
 		update_port_bc_queue_len(vlan->port);
 	}
 
@@ -1658,7 +1663,7 @@ static int macvlan_changelink(struct net_device *dev,
 			vlan, nla_get_s32(data[IFLA_MACVLAN_BC_CUTOFF]));
 
 	if (set_mode)
-		vlan->mode = mode;
+		WRITE_ONCE(vlan->mode, mode);
 	if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
 		if (vlan->mode != MACVLAN_MODE_SOURCE)
 			return -EINVAL;
@@ -1672,10 +1677,12 @@ static int macvlan_changelink(struct net_device *dev,
 
 static size_t macvlan_get_size_mac(const struct macvlan_dev *vlan)
 {
-	if (vlan->macaddr_count == 0)
+	unsigned int macaddr_count = READ_ONCE(vlan->macaddr_count);
+
+	if (!macaddr_count)
 		return 0;
 	return nla_total_size(0) /* IFLA_MACVLAN_MACADDR_DATA */
-		+ vlan->macaddr_count * nla_total_size(sizeof(u8) * ETH_ALEN);
+		+ macaddr_count * nla_total_size(sizeof(u8) * ETH_ALEN);
 }
 
 static size_t macvlan_get_size(const struct net_device *dev)
@@ -1698,53 +1705,75 @@ static int macvlan_fill_info_macaddr(struct sk_buff *skb,
 				     const int i)
 {
 	struct hlist_head *h = &vlan->port->vlan_source_hash[i];
-	struct macvlan_source_entry *entry;
+	const struct macvlan_source_entry *entry;
+	int cnt = 0;
 
-	hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) {
+	hlist_for_each_entry_rcu(entry, h, hlist) {
 		if (rcu_access_pointer(entry->vlan) != vlan)
 			continue;
 		if (nla_put(skb, IFLA_MACVLAN_MACADDR, ETH_ALEN, entry->addr))
-			return 1;
+			return -EMSGSIZE;
+		cnt++;
 	}
-	return 0;
+	return cnt;
 }
 
 static int macvlan_fill_info(struct sk_buff *skb,
 				const struct net_device *dev)
 {
-	struct macvlan_dev *vlan = netdev_priv(dev);
+	const struct macvlan_dev *vlan = netdev_priv(dev);
 	struct macvlan_port *port = vlan->port;
-	int i;
-	struct nlattr *nest;
+	unsigned int macaddr_count = 0;
+	struct nlattr *nest, *attr;
+	int bc_cutoff, cnt, i;
 
-	if (nla_put_u32(skb, IFLA_MACVLAN_MODE, vlan->mode))
+	rcu_read_lock();
+	if (nla_put_u32(skb, IFLA_MACVLAN_MODE, READ_ONCE(vlan->mode)))
 		goto nla_put_failure;
-	if (nla_put_u16(skb, IFLA_MACVLAN_FLAGS, vlan->flags))
+
+	if (nla_put_u16(skb, IFLA_MACVLAN_FLAGS, READ_ONCE(vlan->flags)))
 		goto nla_put_failure;
-	if (nla_put_u32(skb, IFLA_MACVLAN_MACADDR_COUNT, vlan->macaddr_count))
+
+	attr = nla_reserve(skb, IFLA_MACVLAN_MACADDR_COUNT, sizeof(u32));
+	if (!attr)
 		goto nla_put_failure;
-	if (vlan->macaddr_count > 0) {
+
+	if (READ_ONCE(vlan->macaddr_count) > 0) {
 		nest = nla_nest_start_noflag(skb, IFLA_MACVLAN_MACADDR_DATA);
 		if (nest == NULL)
 			goto nla_put_failure;
 
 		for (i = 0; i < MACVLAN_HASH_SIZE; i++) {
-			if (macvlan_fill_info_macaddr(skb, vlan, i))
+			cnt = macvlan_fill_info_macaddr(skb, vlan, i);
+			if (cnt < 0)
 				goto nla_put_failure;
+			macaddr_count += cnt;
 		}
-		nla_nest_end(skb, nest);
+		if (!macaddr_count)
+			nla_nest_cancel(skb, nest);
+		else if (nla_nest_end_safe(skb, nest) < 0)
+			goto nla_put_failure;
 	}
-	if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN, vlan->bc_queue_len_req))
+	*(u32 *)nla_data(attr) = macaddr_count;
+
+	if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN,
+			READ_ONCE(vlan->bc_queue_len_req)))
 		goto nla_put_failure;
+
 	if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN_USED,
 			READ_ONCE(port->bc_queue_len_used)))
 		goto nla_put_failure;
-	if (port->bc_cutoff != 1 &&
-	    nla_put_s32(skb, IFLA_MACVLAN_BC_CUTOFF, port->bc_cutoff))
+
+	bc_cutoff = READ_ONCE(port->bc_cutoff);
+	if (bc_cutoff != 1 &&
+	    nla_put_s32(skb, IFLA_MACVLAN_BC_CUTOFF, bc_cutoff))
 		goto nla_put_failure;
+
+	rcu_read_unlock();
 	return 0;
 
 nla_put_failure:
+	rcu_read_unlock();
 	return -EMSGSIZE;
 }
 
diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig
index e57121019153..a05229838cb4 100644
--- a/drivers/net/mdio/Kconfig
+++ b/drivers/net/mdio/Kconfig
@@ -3,7 +3,8 @@
 # MDIO Layer Configuration
 #
 
-if PHYLIB
+menu "MDIO controller drivers"
+	depends on PHYLIB
 
 config FWNODE_MDIO
 	def_tristate (ACPI || OF) || COMPILE_TEST
@@ -198,7 +199,7 @@ config MDIO_THUNDER
 	  ThunderX SoCs when the MDIO bus device appears as a PCI
 	  device.
 
-comment "MDIO Multiplexers"
+menu "MDIO Multiplexers"
 
 config MDIO_BUS_MUX
 	tristate
@@ -288,5 +289,5 @@ config MDIO_BUS_MUX_MMIOREG
 
 	  Currently, only 8/16/32 bits registers are supported.
 
-
-endif
+endmenu
+endmenu
diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 862001d09aa8..7f8851a734fc 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -61,6 +61,19 @@ MODULE_IMPORT_NS("NETDEV_INTERNAL");
 #define MAX_USERDATA_ITEMS		256
 #define MAX_PRINT_CHUNK			1000
 
+/*
+ * Sizing for the per-target fallback skb pool consulted by find_skb()
+ * when its GFP_ATOMIC allocation fails so messages still get out under
+ * memory pressure.
+ */
+#define MAX_UDP_CHUNK			1460
+#define MAX_SKBS			32
+#define MAX_SKB_SIZE							\
+	(sizeof(struct ethhdr) +					\
+	 sizeof(struct iphdr) +						\
+	 sizeof(struct udphdr) +					\
+	 MAX_UDP_CHUNK)
+
 static char config[MAX_PARAM_LENGTH];
 module_param_string(netconsole, config, MAX_PARAM_LENGTH, 0);
 MODULE_PARM_DESC(netconsole, " netconsole=[src-port]@[src-ip]/[dev],[tgt-port]@<tgt-ip>/[tgt-macaddr]");
@@ -162,14 +175,19 @@ enum target_state {
  * @np:		The netpoll structure for this target.
  *		Contains the other userspace visible parameters:
  *		dev_name	(read-write)
- *		local_port	(read-write)
- *		remote_port	(read-write)
  *		local_ip	(read-write)
  *		remote_ip	(read-write)
  *		local_mac	(read-only)
- *		remote_mac	(read-write)
+ * @local_port:	Source UDP port of the target (read-write).
+ * @remote_port: Destination UDP port of the target (read-write).
+ * @remote_mac:	Destination ethernet address of the target (read-write).
  * @buf:	The buffer used to send the full msg to the network stack
  * @resume_wq:	Workqueue to resume deactivated target
+ * @skb_pool:	Per-target fallback skb pool consulted by find_skb() when
+ *		its GFP_ATOMIC allocation fails. Lifetime brackets a
+ *		successful netpoll_setup() / netpoll_cleanup() pair on @np.
+ * @refill_wq:	Work item that asynchronously tops @skb_pool back up to
+ *		MAX_SKBS after find_skb() drains an entry.
  */
 struct netconsole_target {
 	struct list_head	list;
@@ -190,11 +208,15 @@ struct netconsole_target {
 	bool			extended;
 	bool			release;
 	struct netpoll		np;
+	u16			local_port, remote_port;
+	u8			remote_mac[ETH_ALEN];
 	/* protected by target_list_lock; +1 gives scnprintf() room for its
 	 * NUL terminator so a full MAX_PRINT_CHUNK payload is not truncated
 	 */
 	char			buf[MAX_PRINT_CHUNK + 1];
 	struct work_struct	resume_wq;
+	struct sk_buff_head	skb_pool;
+	struct work_struct	refill_wq;
 };
 
 #ifdef	CONFIG_NETCONSOLE_DYNAMIC
@@ -292,11 +314,56 @@ static void netcons_release_dev(struct netconsole_target *nt)
 		memset(&nt->np.dev_name, 0, IFNAMSIZ);
 }
 
+static void refill_skbs(struct netconsole_target *nt)
+{
+	struct sk_buff_head *skb_pool = &nt->skb_pool;
+	struct sk_buff *skb;
+
+	while (READ_ONCE(skb_pool->qlen) < MAX_SKBS) {
+		skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC | __GFP_NOWARN);
+		if (!skb)
+			break;
+
+		skb_queue_tail(skb_pool, skb);
+	}
+}
+
+static void refill_skbs_work_handler(struct work_struct *work)
+{
+	struct netconsole_target *nt =
+		container_of(work, struct netconsole_target, refill_wq);
+
+	refill_skbs(nt);
+}
+
+/* Seed the per-target skb pool that find_skb() falls back to. The queue
+ * head and refill work are set up once in alloc_and_init(); this only
+ * (re)fills the pool. Pair with netconsole_skb_pool_flush().
+ */
+static void netconsole_skb_pool_init(struct netconsole_target *nt)
+{
+	refill_skbs(nt);
+}
+
+static void netconsole_skb_pool_flush(struct netconsole_target *nt)
+{
+	cancel_work_sync(&nt->refill_wq);
+	skb_queue_purge_reason(&nt->skb_pool, SKB_CONSUMED);
+}
+
 /* Attempts to resume logging to a deactivated target. */
 static void resume_target(struct netconsole_target *nt)
 {
+	/* Initialise the skb pool before netpoll_setup() makes nt->np.dev
+	 * visible to target_list walkers (e.g. netconsole_netdev_event),
+	 * which otherwise may move the target to the cleanup list and
+	 * call netconsole_skb_pool_flush() on uninitialised state.
+	 */
+	netconsole_skb_pool_init(nt);
+
 	if (netpoll_setup(&nt->np)) {
 		/* netpoll fails setup once, do not try again. */
+		netconsole_skb_pool_flush(nt);
 		nt->state = STATE_DISABLED;
 		return;
 	}
@@ -358,6 +425,7 @@ static void process_resume_target(struct work_struct *work)
 	rtnl_lock();
 	if (nt->state == STATE_ENABLED && nt->np.dev &&
 	    nt->np.dev->reg_state != NETREG_REGISTERED) {
+		netconsole_skb_pool_flush(nt);
 		netcons_release_dev(nt);
 		nt->state = STATE_DISABLED;
 	}
@@ -393,11 +461,14 @@ static struct netconsole_target *alloc_and_init(void)
 
 	nt->np.name = "netconsole";
 	strscpy(nt->np.dev_name, "eth0", IFNAMSIZ);
-	nt->np.local_port = 6665;
-	nt->np.remote_port = 6666;
-	eth_broadcast_addr(nt->np.remote_mac);
+	nt->local_port = 6665;
+	nt->remote_port = 6666;
+	eth_broadcast_addr(nt->remote_mac);
 	nt->state = STATE_DISABLED;
 	INIT_WORK(&nt->resume_wq, process_resume_target);
+	/* Set up the skb pool primitives once; enabling only refills it. */
+	skb_queue_head_init(&nt->skb_pool);
+	INIT_WORK(&nt->refill_wq, refill_skbs_work_handler);
 
 	return nt;
 }
@@ -417,6 +488,7 @@ static void netconsole_process_cleanups_core(void)
 	list_for_each_entry_safe(nt, tmp, &target_cleanup_list, list) {
 		/* all entries in the cleanup_list needs to be disabled */
 		WARN_ON_ONCE(nt->state == STATE_ENABLED);
+		netconsole_skb_pool_flush(nt);
 		netcons_release_dev(nt);
 		/* moved the cleaned target to target_list. Need to hold both
 		 * locks
@@ -429,21 +501,23 @@ static void netconsole_process_cleanups_core(void)
 	mutex_unlock(&target_cleanup_list_lock);
 }
 
-static void netconsole_print_banner(struct netpoll *np)
+static void netconsole_print_banner(struct netconsole_target *nt)
 {
-	np_info(np, "local port %d\n", np->local_port);
+	struct netpoll *np = &nt->np;
+
+	np_info(np, "local port %d\n", nt->local_port);
 	if (np->ipv6)
 		np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6);
 	else
 		np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip);
 	np_info(np, "interface name '%s'\n", np->dev_name);
 	np_info(np, "local ethernet address '%pM'\n", np->dev_mac);
-	np_info(np, "remote port %d\n", np->remote_port);
+	np_info(np, "remote port %d\n", nt->remote_port);
 	if (np->ipv6)
 		np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6);
 	else
 		np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip);
-	np_info(np, "remote ethernet address %pM\n", np->remote_mac);
+	np_info(np, "remote ethernet address %pM\n", nt->remote_mac);
 }
 
 /* Parse the string and populate the `inet_addr` union. Return 0 if IPv4 is
@@ -561,12 +635,12 @@ static ssize_t dev_name_show(struct config_item *item, char *buf)
 
 static ssize_t local_port_show(struct config_item *item, char *buf)
 {
-	return sysfs_emit(buf, "%d\n", to_target(item)->np.local_port);
+	return sysfs_emit(buf, "%d\n", to_target(item)->local_port);
 }
 
 static ssize_t remote_port_show(struct config_item *item, char *buf)
 {
-	return sysfs_emit(buf, "%d\n", to_target(item)->np.remote_port);
+	return sysfs_emit(buf, "%d\n", to_target(item)->remote_port);
 }
 
 static ssize_t local_ip_show(struct config_item *item, char *buf)
@@ -599,7 +673,7 @@ static ssize_t local_mac_show(struct config_item *item, char *buf)
 
 static ssize_t remote_mac_show(struct config_item *item, char *buf)
 {
-	return sysfs_emit(buf, "%pM\n", to_target(item)->np.remote_mac);
+	return sysfs_emit(buf, "%pM\n", to_target(item)->remote_mac);
 }
 
 static ssize_t transmit_errors_show(struct config_item *item, char *buf)
@@ -756,11 +830,21 @@ static ssize_t enabled_store(struct config_item *item,
 		 * Skip netconsole_parser_cmdline() -- all the attributes are
 		 * already configured via configfs. Just print them out.
 		 */
-		netconsole_print_banner(&nt->np);
+		netconsole_print_banner(nt);
+
+		/* Initialise the skb pool before netpoll_setup() so the pool
+		 * is valid as soon as nt->np.dev becomes visible to
+		 * target_list walkers (netconsole_netdev_event), which would
+		 * otherwise call netconsole_skb_pool_flush() on uninitialised
+		 * state.
+		 */
+		netconsole_skb_pool_init(nt);
 
 		ret = netpoll_setup(&nt->np);
-		if (ret)
+		if (ret) {
+			netconsole_skb_pool_flush(nt);
 			goto out_unlock;
+		}
 
 		nt->state = STATE_ENABLED;
 		pr_info("network logging started\n");
@@ -885,7 +969,7 @@ static ssize_t local_port_store(struct config_item *item, const char *buf,
 		goto out_unlock;
 	}
 
-	ret = kstrtou16(buf, 10, &nt->np.local_port);
+	ret = kstrtou16(buf, 10, &nt->local_port);
 	if (ret < 0)
 		goto out_unlock;
 	ret = count;
@@ -907,7 +991,7 @@ static ssize_t remote_port_store(struct config_item *item,
 		goto out_unlock;
 	}
 
-	ret = kstrtou16(buf, 10, &nt->np.remote_port);
+	ret = kstrtou16(buf, 10, &nt->remote_port);
 	if (ret < 0)
 		goto out_unlock;
 	ret = count;
@@ -994,7 +1078,7 @@ static ssize_t remote_mac_store(struct config_item *item, const char *buf,
 		goto out_unlock;
 	if (buf[MAC_ADDR_STR_LEN] && buf[MAC_ADDR_STR_LEN] != '\n')
 		goto out_unlock;
-	memcpy(nt->np.remote_mac, remote_mac, ETH_ALEN);
+	memcpy(nt->remote_mac, remote_mac, ETH_ALEN);
 
 	ret = count;
 out_unlock:
@@ -1481,15 +1565,15 @@ static void drop_netconsole_target(struct config_group *group,
 
 	mutex_lock(&target_cleanup_list_lock);
 	spin_lock_irqsave(&target_list_lock, flags);
-	/* A STATE_DEACTIVATED target may have been moved to
-	 * target_cleanup_list by netconsole_netdev_event() but not yet
-	 * processed by netconsole_process_cleanups_core(). Unlinking it below
-	 * hides it from the cleanup worker, so this path has to clean it up
-	 * itself. Record that the target still owns a netpoll before the
-	 * state is downgraded.
+	/* A target moved to target_cleanup_list by netconsole_netdev_event()
+	 * but not yet processed still owns a netpoll; unlinking it below hides
+	 * it from the cleanup worker, so this path must tear it down itself.
+	 * This covers NETDEV_UNREGISTER (STATE_DEACTIVATED) and
+	 * NETDEV_RELEASE / NETDEV_JOIN (STATE_DISABLED); key off nt->np.dev,
+	 * which stays set until the netpoll is cleaned up.
 	 */
 	needs_cleanup = nt->state == STATE_ENABLED ||
-			nt->state == STATE_DEACTIVATED;
+			nt->state == STATE_DEACTIVATED || nt->np.dev;
 	/* Disable deactivated target to prevent races between resume attempt
 	 * and target removal.
 	 */
@@ -1514,8 +1598,10 @@ static void drop_netconsole_target(struct config_group *group,
 	 * netpoll_cleanup() is idempotent (it skips when np->dev is NULL), so
 	 * it is safe even if the cleanup worker already tore the netpoll down.
 	 */
-	if (needs_cleanup)
+	if (needs_cleanup) {
+		netconsole_skb_pool_flush(nt);
 		netpoll_cleanup(&nt->np);
+	}
 
 	config_item_put(&nt->group.cg_item);
 }
@@ -1706,7 +1792,7 @@ static struct notifier_block netconsole_netdev_notifier = {
  * pool locks and is therefore not NMI-safe. Skip the refill when called
  * from NMI context; the next non-NMI caller will top the pool back up.
  */
-static struct sk_buff *netcons_skb_pop(struct netpoll *np, int len)
+static struct sk_buff *netcons_skb_pop(struct netconsole_target *nt, int len)
 {
 	struct sk_buff *skb;
 
@@ -1718,28 +1804,30 @@ static struct sk_buff *netcons_skb_pop(struct netpoll *np, int len)
 		if (!in_nmi())
 			net_warn_ratelimited("netconsole: dropping message, requested skb len %d exceeds pool buffer size %zu on %s\n",
 					     len, (size_t)MAX_SKB_SIZE,
-					     np->dev->name);
+					     nt->np.dev->name);
 		return NULL;
 	}
 
-	skb = skb_dequeue(&np->skb_pool);
+	skb = skb_dequeue(&nt->skb_pool);
 	if (!in_nmi())
-		schedule_work(&np->refill_wq);
+		schedule_work(&nt->refill_wq);
 
 	return skb;
 }
 
-static struct sk_buff *find_skb(struct netpoll *np, int len, int reserve)
+static struct sk_buff *find_skb(struct netconsole_target *nt, int len,
+				int reserve)
 {
+	struct netpoll *np = &nt->np;
 	int count = 0;
 	struct sk_buff *skb;
 
 	netpoll_zap_completion_queue();
 repeat:
 
-	skb = alloc_skb(len, GFP_ATOMIC);
+	skb = alloc_skb(len, GFP_ATOMIC | __GFP_NOWARN);
 	if (!skb)
-		skb = netcons_skb_pop(np, len);
+		skb = netcons_skb_pop(nt, len);
 
 	if (!skb) {
 		if (++count < 10) {
@@ -1779,8 +1867,9 @@ static void netpoll_udp_checksum(struct netpoll *np, struct sk_buff *skb,
 		udph->check = CSUM_MANGLED_0;
 }
 
-static void push_udp(struct netpoll *np, struct sk_buff *skb, int len)
+static void push_udp(struct netconsole_target *nt, struct sk_buff *skb, int len)
 {
+	struct netpoll *np = &nt->np;
 	struct udphdr *udph;
 	int udp_len;
 
@@ -1790,21 +1879,22 @@ static void push_udp(struct netpoll *np, struct sk_buff *skb, int len)
 	skb_reset_transport_header(skb);
 
 	udph = udp_hdr(skb);
-	udph->source = htons(np->local_port);
-	udph->dest = htons(np->remote_port);
-	udph->len = htons(udp_len);
+	udph->source = htons(nt->local_port);
+	udph->dest = htons(nt->remote_port);
+	udp_set_len_short(udph, udp_len);
 
 	netpoll_udp_checksum(np, skb, len);
 }
 
-static void push_eth(struct netpoll *np, struct sk_buff *skb)
+static void push_eth(struct netconsole_target *nt, struct sk_buff *skb)
 {
+	struct netpoll *np = &nt->np;
 	struct ethhdr *eth;
 
 	eth = skb_push(skb, ETH_HLEN);
 	skb_reset_mac_header(skb);
 	ether_addr_copy(eth->h_source, np->dev->dev_addr);
-	ether_addr_copy(eth->h_dest, np->remote_mac);
+	ether_addr_copy(eth->h_dest, nt->remote_mac);
 	if (np->ipv6)
 		eth->h_proto = htons(ETH_P_IPV6);
 	else
@@ -1861,8 +1951,10 @@ static void push_ipv6(struct netpoll *np, struct sk_buff *skb, int len)
 	skb->protocol = htons(ETH_P_IPV6);
 }
 
-static int netpoll_send_udp(struct netpoll *np, const char *msg, int len)
+static int netpoll_send_udp(struct netconsole_target *nt, const char *msg,
+			    int len)
 {
+	struct netpoll *np = &nt->np;
 	int total_len, ip_len, udp_len;
 	struct sk_buff *skb;
 
@@ -1877,7 +1969,7 @@ static int netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 
 	total_len = ip_len + LL_RESERVED_SPACE(np->dev);
 
-	skb = find_skb(np, total_len + np->dev->needed_tailroom,
+	skb = find_skb(nt, total_len + np->dev->needed_tailroom,
 		       total_len - len);
 	if (!skb)
 		return -ENOMEM;
@@ -1885,12 +1977,12 @@ static int netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 	skb_copy_to_linear_data(skb, msg, len);
 	skb_put(skb, len);
 
-	push_udp(np, skb, len);
+	push_udp(nt, skb, len);
 	if (np->ipv6)
 		push_ipv6(np, skb, len);
 	else
 		push_ipv4(np, skb, len);
-	push_eth(np, skb);
+	push_eth(nt, skb);
 	skb->dev = np->dev;
 
 	return (int)netpoll_send_skb(np, skb);
@@ -1908,7 +2000,7 @@ static int netpoll_send_udp(struct netpoll *np, const char *msg, int len)
  */
 static void send_udp(struct netconsole_target *nt, const char *msg, int len)
 {
-	int result = netpoll_send_udp(&nt->np, msg, len);
+	int result = netpoll_send_udp(nt, msg, len);
 
 	if (IS_ENABLED(CONFIG_NETCONSOLE_DYNAMIC)) {
 		if (result == NET_XMIT_DROP) {
@@ -2203,8 +2295,9 @@ __releases(&target_list_lock)
 	spin_unlock_irqrestore(&target_list_lock, flags);
 }
 
-static int netconsole_parser_cmdline(struct netpoll *np, char *opt)
+static int netconsole_parser_cmdline(struct netconsole_target *nt, char *opt)
 {
+	struct netpoll *np = &nt->np;
 	bool ipversion_set = false;
 	char *cur = opt;
 	char *delim;
@@ -2215,7 +2308,7 @@ static int netconsole_parser_cmdline(struct netpoll *np, char *opt)
 		if (!delim)
 			goto parse_failed;
 		*delim = 0;
-		if (kstrtou16(cur, 10, &np->local_port))
+		if (kstrtou16(cur, 10, &nt->local_port))
 			goto parse_failed;
 		cur = delim;
 	}
@@ -2262,7 +2355,7 @@ static int netconsole_parser_cmdline(struct netpoll *np, char *opt)
 		*delim = 0;
 		if (*cur == ' ' || *cur == '\t')
 			np_info(np, "warning: whitespace is not allowed\n");
-		if (kstrtou16(cur, 10, &np->remote_port))
+		if (kstrtou16(cur, 10, &nt->remote_port))
 			goto parse_failed;
 		cur = delim;
 	}
@@ -2284,11 +2377,11 @@ static int netconsole_parser_cmdline(struct netpoll *np, char *opt)
 
 	if (*cur != 0) {
 		/* MAC address */
-		if (!mac_pton(cur, np->remote_mac))
+		if (!mac_pton(cur, nt->remote_mac))
 			goto parse_failed;
 	}
 
-	netconsole_print_banner(np);
+	netconsole_print_banner(nt);
 
 	return 0;
 
@@ -2326,14 +2419,22 @@ static struct netconsole_target *alloc_param_target(char *target_config,
 	}
 
 	/* Parse parameters and setup netpoll */
-	err = netconsole_parser_cmdline(&nt->np, target_config);
+	err = netconsole_parser_cmdline(nt, target_config);
 	if (err)
 		goto fail;
 
+	/* Initialise the skb pool before netpoll_setup() so the pool is
+	 * valid as soon as nt->np.dev becomes visible. The target is not
+	 * yet on target_list, so a netdev event cannot reach it here, but
+	 * mirror the configfs path for symmetry.
+	 */
+	netconsole_skb_pool_init(nt);
+
 	err = netpoll_setup(&nt->np);
 	if (err) {
 		pr_err("Not enabling netconsole for %s%d. Netpoll setup failed\n",
 		       NETCONSOLE_PARAM_TARGET_PREFIX, cmdline_count);
+		netconsole_skb_pool_flush(nt);
 		if (!IS_ENABLED(CONFIG_NETCONSOLE_DYNAMIC))
 			/* only fail if dynamic reconfiguration is set,
 			 * otherwise, keep the target in the list, but disabled.
@@ -2355,6 +2456,8 @@ fail:
 static void free_param_target(struct netconsole_target *nt)
 {
 	cancel_work_sync(&nt->resume_wq);
+	if (nt->state == STATE_ENABLED)
+		netconsole_skb_pool_flush(nt);
 	netpoll_cleanup(&nt->np);
 #ifdef	CONFIG_NETCONSOLE_DYNAMIC
 	kfree(nt->userdata);
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index aed9ad5f1b43..f65b4cf4ea39 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -845,7 +845,7 @@ static struct sk_buff *nsim_dev_trap_skb_build(void)
 	udph = skb_put_zero(skb, sizeof(struct udphdr) + data_len);
 	get_random_bytes(&udph->source, sizeof(u16));
 	get_random_bytes(&udph->dest, sizeof(u16));
-	udph->len = htons(sizeof(struct udphdr) + data_len);
+	udp_set_len_short(udph, sizeof(struct udphdr) + data_len);
 
 	return skb;
 }
diff --git a/drivers/net/netdevsim/psample.c b/drivers/net/netdevsim/psample.c
index 717d157c3ae2..1e71c3da4def 100644
--- a/drivers/net/netdevsim/psample.c
+++ b/drivers/net/netdevsim/psample.c
@@ -73,7 +73,7 @@ static struct sk_buff *nsim_dev_psample_skb_build(void)
 	udph = skb_put_zero(skb, sizeof(struct udphdr) + data_len);
 	get_random_bytes(&udph->source, sizeof(u16));
 	get_random_bytes(&udph->dest, sizeof(u16));
-	udph->len = htons(sizeof(struct udphdr) + data_len);
+	udp_set_len_short(udph, sizeof(struct udphdr) + data_len);
 
 	return skb;
 }
diff --git a/drivers/net/netdevsim/psp.c b/drivers/net/netdevsim/psp.c
index 59c990fdc79e..6b3532b5e360 100644
--- a/drivers/net/netdevsim/psp.c
+++ b/drivers/net/netdevsim/psp.c
@@ -84,6 +84,7 @@ nsim_do_psp(struct sk_buff *skb, struct netdevsim *ns,
 		struct iphdr *iph;
 		struct udphdr *uh;
 		__wsum csum;
+		int udplen;
 
 		/* Do not decapsulate. Receive the skb with the udp and psp
 		 * headers still there as if this is a normal udp packet.
@@ -91,19 +92,20 @@ nsim_do_psp(struct sk_buff *skb, struct netdevsim *ns,
 		 * provide a valid checksum here, so the skb isn't dropped.
 		 */
 		uh = udp_hdr(skb);
+		udplen = udp_get_len(skb, uh, skb_transport_offset(skb));
 		csum = skb_checksum(skb, skb_transport_offset(skb),
-				    ntohs(uh->len), 0);
+				    udplen, 0);
 
 		switch (skb->protocol) {
 		case htons(ETH_P_IP):
 			iph = ip_hdr(skb);
-			uh->check = udp_v4_check(ntohs(uh->len), iph->saddr,
+			uh->check = udp_v4_check(udplen, iph->saddr,
 						 iph->daddr, csum);
 			break;
 #if IS_ENABLED(CONFIG_IPV6)
 		case htons(ETH_P_IPV6):
 			ip6h = ipv6_hdr(skb);
-			uh->check = udp_v6_check(ntohs(uh->len), &ip6h->saddr,
+			uh->check = udp_v6_check(udplen, &ip6h->saddr,
 						 &ip6h->daddr, csum);
 			break;
 #endif
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 099f25dceabb..a29d3fed8a05 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -136,6 +136,12 @@ config ADIN1100_PHY
 	  Currently supports the:
 	  - ADIN1100 - Robust,Industrial, Low Power 10BASE-T1L Ethernet PHY
 
+config ADIN1140_PHY
+	tristate "Analog Devices ADIN1140 10BASE-T1S PHY"
+	help
+	  Adds support for the Analog Devices, Inc. ADIN1140's internal
+	  10BASE-T1S PHY.
+
 config AMCC_QT2025_PHY
 	tristate "AMCC QT2025 PHY"
 	depends on RUST_PHYLIB_ABSTRACTIONS
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index de660ae94945..e23df5e836e9 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -29,6 +29,7 @@ obj-y				+= $(sfp-obj-y) $(sfp-obj-m)
 
 obj-$(CONFIG_ADIN_PHY)		+= adin.o
 obj-$(CONFIG_ADIN1100_PHY)	+= adin1100.o
+obj-$(CONFIG_ADIN1140_PHY)	+= adin1140-phy.o
 obj-$(CONFIG_AIR_AN8801_PHY)	+= air_an8801.o
 obj-$(CONFIG_AIR_EN8811H_PHY)   += air_en8811h.o
 obj-$(CONFIG_AIR_NET_PHYLIB)	+= air_phy_lib.o
diff --git a/drivers/net/phy/adin1140-phy.c b/drivers/net/phy/adin1140-phy.c
new file mode 100644
index 000000000000..d35da4ad680d
--- /dev/null
+++ b/drivers/net/phy/adin1140-phy.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Driver for Analog Devices, Inc. ADIN1140 10BASE-T1S PHY
+ *
+ * Copyright 2026 Analog Devices Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+
+#define ADIN1140_PHY_ID		0x0283be00
+
+#define ADIN1140_PCS_CTRL		0x08f3
+#define ADIN1140_PCS_CTRL_LOOPBACK	BIT(14)
+
+static int adin1140_config_aneg(struct phy_device *phydev)
+{
+	/* phylib tries to clear BIT(12) in MDIO_CTRL1, since AN is disabled.
+	 * However, on the ADIN1140, that field is non-standard, being used
+	 * to control the reset status of the PHY (thus it needs to remain set).
+	 */
+	return 0;
+}
+
+static int adin1140_loopback(struct phy_device *phydev, bool enable, int speed)
+{
+	if (enable && speed)
+		return -EOPNOTSUPP;
+
+	return phy_modify_mmd(phydev, MDIO_MMD_PCS, ADIN1140_PCS_CTRL,
+			      ADIN1140_PCS_CTRL_LOOPBACK,
+			      enable ? ADIN1140_PCS_CTRL_LOOPBACK : 0);
+}
+
+static int adin1140_read_status(struct phy_device *phydev)
+{
+	phydev->link = 1;
+	phydev->duplex = DUPLEX_HALF;
+	phydev->speed = SPEED_10;
+	phydev->autoneg = AUTONEG_DISABLE;
+
+	return 0;
+}
+
+static struct phy_driver adin1140_driver[] = {
+	{
+		PHY_ID_MATCH_EXACT(ADIN1140_PHY_ID),
+		.name = "ADIN1140_PHY",
+		.features = PHY_BASIC_T1S_P2MP_FEATURES,
+		.read_status = adin1140_read_status,
+		.config_aneg = adin1140_config_aneg,
+		.set_loopback = adin1140_loopback,
+		.read_mmd = genphy_read_mmd_c45,
+		.write_mmd = genphy_write_mmd_c45,
+		.get_plca_cfg = genphy_c45_plca_get_cfg,
+		.set_plca_cfg = genphy_c45_plca_set_cfg,
+		.get_plca_status = genphy_c45_plca_get_status,
+	},
+};
+module_phy_driver(adin1140_driver);
+
+static const struct mdio_device_id __maybe_unused adin1140_tbl[] = {
+	{ PHY_ID_MATCH_EXACT(ADIN1140_PHY_ID) },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(mdio, adin1140_tbl);
+
+MODULE_DESCRIPTION("Analog Devices, Inc. ADIN1140 10BASE-T1S PHY");
+MODULE_AUTHOR("Ciprian Regus <ciprian.regus@analog.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c
index 56080d3d2d25..06151f207134 100644
--- a/drivers/net/phy/mdio_device.c
+++ b/drivers/net/phy/mdio_device.c
@@ -8,7 +8,6 @@
 
 #include <linux/delay.h>
 #include <linux/errno.h>
-#include <linux/gpio.h>
 #include <linux/gpio/consumer.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
diff --git a/drivers/net/phy/microchip_t1s.c b/drivers/net/phy/microchip_t1s.c
index e601d56b2507..73c23d311d72 100644
--- a/drivers/net/phy/microchip_t1s.c
+++ b/drivers/net/phy/microchip_t1s.c
@@ -506,34 +506,6 @@ static int lan86xx_read_status(struct phy_device *phydev)
 	return 0;
 }
 
-/* OPEN Alliance 10BASE-T1x compliance MAC-PHYs will have both C22 and
- * C45 registers space. If the PHY is discovered via C22 bus protocol it assumes
- * it uses C22 protocol and always uses C22 registers indirect access to access
- * C45 registers. This is because, we don't have a clean separation between
- * C22/C45 register space and C22/C45 MDIO bus protocols. Resulting, PHY C45
- * registers direct access can't be used which can save multiple SPI bus access.
- * To support this feature, set .read_mmd/.write_mmd in the PHY driver to call
- * .read_c45/.write_c45 in the OPEN Alliance framework
- * drivers/net/ethernet/oa_tc6.c
- */
-static int lan865x_phy_read_mmd(struct phy_device *phydev, int devnum,
-				u16 regnum)
-{
-	struct mii_bus *bus = phydev->mdio.bus;
-	int addr = phydev->mdio.addr;
-
-	return __mdiobus_c45_read(bus, addr, devnum, regnum);
-}
-
-static int lan865x_phy_write_mmd(struct phy_device *phydev, int devnum,
-				 u16 regnum, u16 val)
-{
-	struct mii_bus *bus = phydev->mdio.bus;
-	int addr = phydev->mdio.addr;
-
-	return __mdiobus_c45_write(bus, addr, devnum, regnum, val);
-}
-
 static struct phy_driver microchip_t1s_driver[] = {
 	{
 		PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVB1),
@@ -584,8 +556,8 @@ static struct phy_driver microchip_t1s_driver[] = {
 		.features           = PHY_BASIC_T1S_P2MP_FEATURES,
 		.config_init        = lan865x_revb_config_init,
 		.read_status        = lan86xx_read_status,
-		.read_mmd           = lan865x_phy_read_mmd,
-		.write_mmd          = lan865x_phy_write_mmd,
+		.read_mmd           = genphy_read_mmd_c45,
+		.write_mmd          = genphy_write_mmd_c45,
 		.get_plca_cfg	    = genphy_c45_plca_get_cfg,
 		.set_plca_cfg	    = lan86xx_plca_set_cfg,
 		.get_plca_status    = genphy_c45_plca_get_status,
diff --git a/drivers/net/phy/motorcomm.c b/drivers/net/phy/motorcomm.c
index 5071605a1a11..3396a38cfc0f 100644
--- a/drivers/net/phy/motorcomm.c
+++ b/drivers/net/phy/motorcomm.c
@@ -6,6 +6,7 @@
  * Author: Frank <Frank.Sae@motor-comm.com>
  */
 
+#include <linux/clk.h>
 #include <linux/etherdevice.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -1180,9 +1181,15 @@ static int yt8521_probe(struct phy_device *phydev)
 static int yt8531_probe(struct phy_device *phydev)
 {
 	struct device *dev = &phydev->mdio.dev;
+	struct clk *clk;
 	u16 mask, val;
 	u32 freq;
 
+	clk = devm_clk_get_optional_enabled(dev, NULL);
+	if (IS_ERR(clk))
+		return dev_err_probe(dev, PTR_ERR(clk),
+				     "failed to get and enable PHY clock\n");
+
 	if (device_property_read_u32(dev, "motorcomm,clk-out-frequency-hz", &freq))
 		freq = YTPHY_DTS_OUTPUT_CLK_DIS;
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 0615228459ef..94b2e85e00a3 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2770,6 +2770,31 @@ int genphy_read_abilities(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(genphy_read_abilities);
 
+/* Some PHYs support direct C45 register access but not C22 indirect
+ * MMD access (registers 13 and 14). When discovered via C22, phylib
+ * routes MMD access through the indirect path, which won't work on
+ * these devices. These helpers bypass indirect access and use the bus
+ * C45 accessors directly.
+ */
+int genphy_read_mmd_c45(struct phy_device *phydev, int devnum, u16 regnum)
+{
+	struct mii_bus *bus = phydev->mdio.bus;
+	int addr = phydev->mdio.addr;
+
+	return __mdiobus_c45_read(bus, addr, devnum, regnum);
+}
+EXPORT_SYMBOL(genphy_read_mmd_c45);
+
+int genphy_write_mmd_c45(struct phy_device *phydev, int devnum, u16 regnum,
+			 u16 val)
+{
+	struct mii_bus *bus = phydev->mdio.bus;
+	int addr = phydev->mdio.addr;
+
+	return __mdiobus_c45_write(bus, addr, devnum, regnum, val);
+}
+EXPORT_SYMBOL(genphy_write_mmd_c45);
+
 /* This is used for the phy device which doesn't support the MMD extended
  * register access, but it does have side effect when we are trying to access
  * the MMD register via indirect method.
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 087ac63f9193..59dfe35afa54 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -153,8 +153,7 @@ static DECLARE_PHY_INTERFACE_MASK(phylink_sfp_interfaces);
  * phylink_set_port_modes() - set the port type modes in the ethtool mask
  * @mask: ethtool link mode mask
  *
- * Sets all the port type modes in the ethtool mask.  MAC drivers should
- * use this in their 'validate' callback.
+ * Sets all the port type modes in the ethtool mask.
  */
 void phylink_set_port_modes(unsigned long *mask)
 {
@@ -2095,9 +2094,9 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
 	/*
 	 * This is the new way of dealing with flow control for PHYs,
 	 * as described by Timur Tabi in commit 529ed1275263 ("net: phy:
-	 * phy drivers should not set SUPPORTED_[Asym_]Pause") except
-	 * using our validate call to the MAC, we rely upon the MAC
-	 * clearing the bits from both supported and advertising fields.
+	 * phy drivers should not set SUPPORTED_[Asym_]Pause"). MAC drivers
+	 * set their support using the MAC_SYM_PAUSE and MAC_ASYM_PAUSE
+	 * capabilities and must NOT change the phy's pause settings directly.
 	 */
 	phy_support_asym_pause(phy);
 
@@ -3931,9 +3930,9 @@ static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy)
 	/*
 	 * This is the new way of dealing with flow control for PHYs,
 	 * as described by Timur Tabi in commit 529ed1275263 ("net: phy:
-	 * phy drivers should not set SUPPORTED_[Asym_]Pause") except
-	 * using our validate call to the MAC, we rely upon the MAC
-	 * clearing the bits from both supported and advertising fields.
+	 * phy drivers should not set SUPPORTED_[Asym_]Pause"). MAC drivers
+	 * set their support using the MAC_SYM_PAUSE and MAC_ASYM_PAUSE
+	 * capabilities and must NOT change the phy's pause settings directly.
 	 */
 	phy_support_asym_pause(phy);
 
diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c
index ba4dc07752b6..6872dbf77856 100644
--- a/drivers/net/phy/qcom/at803x.c
+++ b/drivers/net/phy/qcom/at803x.c
@@ -537,7 +537,7 @@ static void at803x_link_change_notify(struct phy_device *phydev)
 	 * in the FIFO. In such cases, the FIFO enters an error mode it
 	 * cannot recover from by software.
 	 */
-	if (phydev->state == PHY_NOLINK && phydev->mdio.reset_gpio) {
+	if (phydev->state == PHY_NOLINK && phy_device_has_reset(phydev)) {
 		struct at803x_context context;
 
 		at803x_context_save(phydev, &context);
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index f520206734da..6c25b73c668a 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -594,6 +594,9 @@ static const struct sfp_quirk sfp_quirks[] = {
 
 	SFP_QUIRK_F("YV", "SFP+ONU-XGSPON", sfp_fixup_potron),
 
+	// HORACO HC-10GE-113C uses Rollball protocol to talk to the PHY.
+	SFP_QUIRK_F("OEM", "HC-10GE-113C", sfp_fixup_rollball),
+
 	// OEM SFP-GE-T is a 1000Base-T module with broken TX_FAULT indicator
 	SFP_QUIRK_F("OEM", "SFP-GE-T", sfp_fixup_ignore_tx_fault),
 
diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c
index 93a7b0f6c4e7..583426d06381 100644
--- a/drivers/net/ppp/ppp_async.c
+++ b/drivers/net/ppp/ppp_async.c
@@ -49,8 +49,6 @@ struct asyncppp {
 	unsigned long	xmit_flags;
 	u32		xaccm[8];
 	u32		raccm;
-	unsigned int	bytes_sent;
-	unsigned int	bytes_rcvd;
 
 	struct sk_buff	*tpkt;
 	int		tpkt_pos;
diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c
index b7f243b416f8..0b1bd1635c39 100644
--- a/drivers/net/ppp/ppp_synctty.c
+++ b/drivers/net/ppp/ppp_synctty.c
@@ -59,8 +59,6 @@ struct syncppp {
 	unsigned long	xmit_flags;
 	u32		xaccm[8];
 	u32		raccm;
-	unsigned int	bytes_sent;
-	unsigned int	bytes_rcvd;
 
 	struct sk_buff	*tpkt;
 	unsigned long	last_xmit;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ffbe6f13fb1f..9e2761887896 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -532,7 +532,7 @@ static void tun_disable_queue(struct tun_struct *tun, struct tun_file *tfile)
 {
 	tfile->detached = tun;
 	list_add_tail(&tfile->next, &tun->disabled);
-	++tun->numdisabled;
+	WRITE_ONCE(tun->numdisabled, tun->numdisabled + 1);
 }
 
 static struct tun_struct *tun_enable_queue(struct tun_file *tfile)
@@ -541,7 +541,7 @@ static struct tun_struct *tun_enable_queue(struct tun_file *tfile)
 
 	tfile->detached = NULL;
 	list_del_init(&tfile->next);
-	--tun->numdisabled;
+	WRITE_ONCE(tun->numdisabled, tun->numdisabled - 1);
 	return tun;
 }
 
@@ -600,7 +600,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 		rcu_assign_pointer(tun->tfiles[tun->numqueues - 1],
 				   NULL);
 
-		--tun->numqueues;
+		WRITE_ONCE(tun->numqueues, tun->numqueues - 1);
 		if (clean) {
 			RCU_INIT_POINTER(tfile->tun, NULL);
 			sock_put(&tfile->sk);
@@ -663,7 +663,7 @@ static void tun_detach_all(struct net_device *dev)
 		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
-		--tun->numqueues;
+		WRITE_ONCE(tun->numqueues, tun->numqueues - 1);
 	}
 	list_for_each_entry(tfile, &tun->disabled, next) {
 		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
@@ -786,7 +786,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 	if (publish_tun)
 		rcu_assign_pointer(tfile->tun, tun);
 	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
-	tun->numqueues++;
+	WRITE_ONCE(tun->numqueues, tun->numqueues + 1);
 	tun_set_real_num_queues(tun);
 out:
 	return err;
@@ -2370,32 +2370,36 @@ static size_t tun_get_size(const struct net_device *dev)
 
 static int tun_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
-	struct tun_struct *tun = netdev_priv(dev);
+	const struct tun_struct *tun = netdev_priv(dev);
+	unsigned int flags = READ_ONCE(tun->flags);
+	kuid_t owner = READ_ONCE(tun->owner);
+	kgid_t group = READ_ONCE(tun->group);
 
-	if (nla_put_u8(skb, IFLA_TUN_TYPE, tun->flags & TUN_TYPE_MASK))
+	if (nla_put_u8(skb, IFLA_TUN_TYPE, flags & TUN_TYPE_MASK))
 		goto nla_put_failure;
-	if (uid_valid(tun->owner) &&
+	if (uid_valid(owner) &&
 	    nla_put_u32(skb, IFLA_TUN_OWNER,
-			from_kuid_munged(current_user_ns(), tun->owner)))
+			from_kuid_munged(current_user_ns(), owner)))
 		goto nla_put_failure;
-	if (gid_valid(tun->group) &&
+	if (gid_valid(group) &&
 	    nla_put_u32(skb, IFLA_TUN_GROUP,
-			from_kgid_munged(current_user_ns(), tun->group)))
+			from_kgid_munged(current_user_ns(), group)))
 		goto nla_put_failure;
-	if (nla_put_u8(skb, IFLA_TUN_PI, !(tun->flags & IFF_NO_PI)))
+	if (nla_put_u8(skb, IFLA_TUN_PI, !(flags & IFF_NO_PI)))
 		goto nla_put_failure;
-	if (nla_put_u8(skb, IFLA_TUN_VNET_HDR, !!(tun->flags & IFF_VNET_HDR)))
+	if (nla_put_u8(skb, IFLA_TUN_VNET_HDR, !!(flags & IFF_VNET_HDR)))
 		goto nla_put_failure;
-	if (nla_put_u8(skb, IFLA_TUN_PERSIST, !!(tun->flags & IFF_PERSIST)))
+	if (nla_put_u8(skb, IFLA_TUN_PERSIST, !!(flags & IFF_PERSIST)))
 		goto nla_put_failure;
 	if (nla_put_u8(skb, IFLA_TUN_MULTI_QUEUE,
-		       !!(tun->flags & IFF_MULTI_QUEUE)))
+		       !!(flags & IFF_MULTI_QUEUE)))
 		goto nla_put_failure;
-	if (tun->flags & IFF_MULTI_QUEUE) {
-		if (nla_put_u32(skb, IFLA_TUN_NUM_QUEUES, tun->numqueues))
+	if (flags & IFF_MULTI_QUEUE) {
+		if (nla_put_u32(skb, IFLA_TUN_NUM_QUEUES,
+				READ_ONCE(tun->numqueues)))
 			goto nla_put_failure;
 		if (nla_put_u32(skb, IFLA_TUN_NUM_DISABLED_QUEUES,
-				tun->numdisabled))
+				READ_ONCE(tun->numdisabled)))
 			goto nla_put_failure;
 	}
 
@@ -2814,8 +2818,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 			return 0;
 		}
 
-		tun->flags = (tun->flags & ~TUN_FEATURES) |
-			      (ifr->ifr_flags & TUN_FEATURES);
+		WRITE_ONCE(tun->flags, (tun->flags & ~TUN_FEATURES) |
+				       (ifr->ifr_flags & TUN_FEATURES));
 
 		netdev_state_change(dev);
 	} else {
@@ -3213,13 +3217,13 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		/* Disable/Enable persist mode. Keep an extra reference to the
 		 * module to prevent the module being unprobed.
 		 */
-		if (arg && !(tun->flags & IFF_PERSIST)) {
-			tun->flags |= IFF_PERSIST;
+		if (arg && !(READ_ONCE(tun->flags) & IFF_PERSIST)) {
+			WRITE_ONCE(tun->flags, READ_ONCE(tun->flags) | IFF_PERSIST);
 			__module_get(THIS_MODULE);
 			do_notify = true;
 		}
-		if (!arg && (tun->flags & IFF_PERSIST)) {
-			tun->flags &= ~IFF_PERSIST;
+		if (!arg && (READ_ONCE(tun->flags) & IFF_PERSIST)) {
+			WRITE_ONCE(tun->flags, READ_ONCE(tun->flags) & ~IFF_PERSIST);
 			module_put(THIS_MODULE);
 			do_notify = true;
 		}
@@ -3235,10 +3239,10 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 			ret = -EINVAL;
 			break;
 		}
-		tun->owner = owner;
+		WRITE_ONCE(tun->owner, owner);
 		do_notify = true;
 		netif_info(tun, drv, tun->dev, "owner set to %u\n",
-			   from_kuid(&init_user_ns, tun->owner));
+			   from_kuid(&init_user_ns, owner));
 		break;
 
 	case TUNSETGROUP:
@@ -3248,10 +3252,10 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 			ret = -EINVAL;
 			break;
 		}
-		tun->group = group;
+		WRITE_ONCE(tun->group, group);
 		do_notify = true;
 		netif_info(tun, drv, tun->dev, "group set to %u\n",
-			   from_kgid(&init_user_ns, tun->group));
+			   from_kgid(&init_user_ns, group));
 		break;
 
 	case TUNSETLINK:
diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h
index fa5cab9d3e55..f4c652b1fa44 100644
--- a/drivers/net/tun_vnet.h
+++ b/drivers/net/tun_vnet.h
@@ -40,9 +40,9 @@ static inline long tun_set_vnet_be(unsigned int *flags, int __user *argp)
 		return -EFAULT;
 
 	if (be)
-		*flags |= TUN_VNET_BE;
+		WRITE_ONCE(*flags, *flags | TUN_VNET_BE);
 	else
-		*flags &= ~TUN_VNET_BE;
+		WRITE_ONCE(*flags, *flags & ~TUN_VNET_BE);
 
 	return 0;
 }
@@ -93,9 +93,9 @@ static inline long tun_vnet_ioctl(int *vnet_hdr_sz, unsigned int *flags,
 		if (get_user(s, sp))
 			return -EFAULT;
 		if (s)
-			*flags |= TUN_VNET_LE;
+			WRITE_ONCE(*flags, *flags | TUN_VNET_LE);
 		else
-			*flags &= ~TUN_VNET_LE;
+			WRITE_ONCE(*flags, *flags & ~TUN_VNET_LE);
 		return 0;
 
 	case TUNGETVNETBE:
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index 5e39d05a2d7b..37d4865f5c5e 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -14,6 +14,7 @@
 #include <linux/usb/cdc.h>
 #include <linux/usb/usbnet.h>
 #include <linux/usb/rndis_host.h>
+#include <linux/overflow.h>
 
 
 /*
@@ -506,6 +507,7 @@ int rndis_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		struct rndis_data_hdr	*hdr = (void *)skb->data;
 		struct sk_buff		*skb2;
 		u32			msg_type, msg_len, data_offset, data_len;
+		u32			overflow_check;
 
 		msg_type = le32_to_cpu(hdr->msg_type);
 		msg_len = le32_to_cpu(hdr->msg_len);
@@ -514,7 +516,9 @@ int rndis_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 
 		/* don't choke if we see oob, per-packet data, etc */
 		if (unlikely(msg_type != RNDIS_MSG_PACKET || skb->len < msg_len
-				|| (data_offset + data_len + 8) > msg_len)) {
+				|| (data_offset + data_len + 8) > msg_len
+				|| check_add_overflow(data_offset, data_len, &overflow_check)
+				|| check_add_overflow(overflow_check, 8, &overflow_check))) {
 			dev->net->stats.rx_frame_errors++;
 			netdev_dbg(dev->net, "bad rndis message %d/%d/%d/%d, len %d\n",
 				   le32_to_cpu(hdr->msg_type),
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index c880c95c41a5..d51e43170e03 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -732,7 +732,9 @@ static void set_carrier(struct net_device *netdev)
 	rtl8150_t *dev = netdev_priv(netdev);
 	short tmp;
 
-	get_registers(dev, CSCR, 2, &tmp);
+	if (get_registers(dev, CSCR, 2, &tmp))
+		return;
+
 	if (tmp & CSCR_LINK_STATUS)
 		netif_carrier_on(netdev);
 	else
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 00e34afd858e..42e4f246c91d 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -77,6 +77,7 @@ struct veth_priv {
 	struct bpf_prog		*_xdp_prog;
 	struct veth_rq		*rq;
 	unsigned int		requested_headroom;
+	netdevice_tracker	peer_tracker;
 };
 
 struct veth_xdp_tx_bq {
@@ -1901,15 +1902,17 @@ static int veth_newlink(struct net_device *dev,
 
 	priv = netdev_priv(dev);
 	rcu_assign_pointer(priv->peer, peer);
+	netdev_hold(peer, &priv->peer_tracker, GFP_KERNEL);
 	err = veth_init_queues(dev, tb);
 	if (err)
 		goto err_queues;
 
 	priv = netdev_priv(peer);
 	rcu_assign_pointer(priv->peer, dev);
+	netdev_hold(dev, &priv->peer_tracker, GFP_KERNEL);
 	err = veth_init_queues(peer, tb);
 	if (err)
-		goto err_queues;
+		goto err_peer_queues;
 
 	veth_disable_gro(dev);
 	/* update XDP supported features */
@@ -1918,7 +1921,11 @@ static int veth_newlink(struct net_device *dev,
 
 	return 0;
 
+err_peer_queues:
+	netdev_put(dev, &priv->peer_tracker);
+	priv = netdev_priv(dev);
 err_queues:
+	netdev_put(peer, &priv->peer_tracker);
 	unregister_netdevice(dev);
 err_register_dev:
 	/* nothing to do */
@@ -1933,24 +1940,25 @@ err_register_peer:
 
 static void veth_dellink(struct net_device *dev, struct list_head *head)
 {
-	struct veth_priv *priv;
+	netdevice_tracker *peer_tracker;
 	struct net_device *peer;
+	struct veth_priv *priv;
 
 	priv = netdev_priv(dev);
-	peer = rtnl_dereference(priv->peer);
+	peer_tracker = &priv->peer_tracker;
+	peer = unrcu_pointer(xchg(&priv->peer, NULL));
+	if (!peer)
+		return;
 
-	/* Note : dellink() is called from default_device_exit_batch(),
-	 * before a rcu_synchronize() point. The devices are guaranteed
-	 * not being freed before one RCU grace period.
-	 */
-	RCU_INIT_POINTER(priv->peer, NULL);
 	unregister_netdevice_queue(dev, head);
 
-	if (peer) {
-		priv = netdev_priv(peer);
-		RCU_INIT_POINTER(priv->peer, NULL);
-		unregister_netdevice_queue(peer, head);
-	}
+	priv = netdev_priv(peer);
+	dev = unrcu_pointer(xchg(&priv->peer, NULL));
+	if (dev)
+		unregister_netdevice_queue_net(dev_net(dev), peer, head);
+
+	netdev_put(peer, peer_tracker);
+	netdev_put(dev, &priv->peer_tracker);
 }
 
 static const struct nla_policy veth_policy[VETH_INFO_MAX + 1] = {
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index d834a4865aec..e38c8a04001e 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -3370,6 +3370,8 @@ static void vxlan_setup(struct net_device *dev)
 	dev->mangleid_features = NETIF_F_GSO_PARTIAL;
 
 	netif_keep_dst(dev);
+	netif_set_tso_max_size(dev, GSO_MAX_SIZE);
+
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->change_proto_down = true;
 	dev->lltx = true;
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index eb8851113654..824bbefce61c 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -62,7 +62,7 @@ static int prepare_skb_header(struct sk_buff *skb, struct wg_device *wg)
 		 * to have UDP fields.
 		 */
 		return -EINVAL;
-	data_len = ntohs(udp->len);
+	data_len = udp_get_len_short(udp);
 	if (unlikely(data_len < sizeof(struct udphdr) ||
 		     data_len > skb->len - data_offset))
 		/* UDP packet is reporting too small of a size or lying about