26 files changed, 1255 insertions, 488 deletions

diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 94374d529ea4..bb378c33f542 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -48,10 +48,8 @@ static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map)
 /* Called by __sk_destruct() & bpf_sk_storage_clone() */
 void bpf_sk_storage_free(struct sock *sk)
 {
-	struct bpf_local_storage_elem *selem;
 	struct bpf_local_storage *sk_storage;
 	bool free_sk_storage = false;
-	struct hlist_node *n;
 
 	rcu_read_lock();
 	sk_storage = rcu_dereference(sk->sk_bpf_storage);
@@ -60,24 +58,8 @@ void bpf_sk_storage_free(struct sock *sk)
 		return;
 	}
 
-	/* Netiher the bpf_prog nor the bpf-map's syscall
-	 * could be modifying the sk_storage->list now.
-	 * Thus, no elem can be added-to or deleted-from the
-	 * sk_storage->list by the bpf_prog or by the bpf-map's syscall.
-	 *
-	 * It is racing with bpf_local_storage_map_free() alone
-	 * when unlinking elem from the sk_storage->list and
-	 * the map's bucket->list.
-	 */
 	raw_spin_lock_bh(&sk_storage->lock);
-	hlist_for_each_entry_safe(selem, n, &sk_storage->list, snode) {
-		/* Always unlink from map before unlinking from
-		 * sk_storage.
-		 */
-		bpf_selem_unlink_map(selem);
-		free_sk_storage = bpf_selem_unlink_storage_nolock(
-			sk_storage, selem, true, false);
-	}
+	free_sk_storage = bpf_local_storage_unlink_nolock(sk_storage);
 	raw_spin_unlock_bh(&sk_storage->lock);
 	rcu_read_unlock();
 
@@ -87,23 +69,12 @@ void bpf_sk_storage_free(struct sock *sk)
 
 static void bpf_sk_storage_map_free(struct bpf_map *map)
 {
-	struct bpf_local_storage_map *smap;
-
-	smap = (struct bpf_local_storage_map *)map;
-	bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx);
-	bpf_local_storage_map_free(smap, NULL);
+	bpf_local_storage_map_free(map, &sk_cache, NULL);
 }
 
 static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
 {
-	struct bpf_local_storage_map *smap;
-
-	smap = bpf_local_storage_map_alloc(attr);
-	if (IS_ERR(smap))
-		return ERR_CAST(smap);
-
-	smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache);
-	return &smap->map;
+	return bpf_local_storage_map_alloc(attr, &sk_cache);
 }
 
 static int notsupp_get_next_key(struct bpf_map *map, void *key,
@@ -176,7 +147,7 @@ bpf_sk_storage_clone_elem(struct sock *newsk,
 	if (!copy_selem)
 		return NULL;
 
-	if (map_value_has_spin_lock(&smap->map))
+	if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK))
 		copy_map_value_locked(&smap->map, SDATA(copy_selem)->data,
 				      SDATA(selem)->data, true);
 	else
@@ -339,7 +310,6 @@ bpf_sk_storage_ptr(void *owner)
 	return &sk->sk_bpf_storage;
 }
 
-BTF_ID_LIST_SINGLE(sk_storage_map_btf_ids, struct, bpf_local_storage_map)
 const struct bpf_map_ops sk_storage_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = bpf_local_storage_map_alloc_check,
@@ -350,7 +320,7 @@ const struct bpf_map_ops sk_storage_map_ops = {
 	.map_update_elem = bpf_fd_sk_storage_update_elem,
 	.map_delete_elem = bpf_fd_sk_storage_delete_elem,
 	.map_check_btf = bpf_local_storage_map_check_btf,
-	.map_btf_id = &sk_storage_map_btf_ids[0],
+	.map_btf_id = &bpf_local_storage_map_btf_id[0],
 	.map_local_storage_charge = bpf_sk_storage_charge,
 	.map_local_storage_uncharge = bpf_sk_storage_uncharge,
 	.map_owner_storage_ptr = bpf_sk_storage_ptr,
@@ -595,7 +565,7 @@ static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb)
 	if (!nla_value)
 		goto errout;
 
-	if (map_value_has_spin_lock(&smap->map))
+	if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK))
 		copy_map_value_locked(&smap->map, nla_data(nla_value),
 				      sdata->data, true);
 	else
diff --git a/net/core/dev.c b/net/core/dev.c
index 3be256051e99..b76fb37b381e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1163,22 +1163,6 @@ int dev_change_name(struct net_device *dev, const char *newname)
 
 	net = dev_net(dev);
 
-	/* Some auto-enslaved devices e.g. failover slaves are
-	 * special, as userspace might rename the device after
-	 * the interface had been brought up and running since
-	 * the point kernel initiated auto-enslavement. Allow
-	 * live name change even when these slave devices are
-	 * up and running.
-	 *
-	 * Typically, users of these auto-enslaving devices
-	 * don't actually care about slave name change, as
-	 * they are supposed to operate on master interface
-	 * directly.
-	 */
-	if (dev->flags & IFF_UP &&
-	    likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK)))
-		return -EBUSY;
-
 	down_write(&devnet_rename_sem);
 
 	if (strncmp(newname, dev->name, IFNAMSIZ) == 0) {
@@ -1195,7 +1179,8 @@ int dev_change_name(struct net_device *dev, const char *newname)
 	}
 
 	if (oldname[0] && !strchr(oldname, '%'))
-		netdev_info(dev, "renamed from %s\n", oldname);
+		netdev_info(dev, "renamed from %s%s\n", oldname,
+			    dev->flags & IFF_UP ? " (while UP)" : "");
 
 	old_assign_type = dev->name_assign_type;
 	dev->name_assign_type = NET_NAME_RENAMED;
@@ -1333,7 +1318,7 @@ void netdev_state_change(struct net_device *dev)
 
 		call_netdevice_notifiers_info(NETDEV_CHANGE,
 					      &change_info.info);
-		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
+		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL, 0, NULL);
 	}
 }
 EXPORT_SYMBOL(netdev_state_change);
@@ -1469,7 +1454,7 @@ int dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
 	if (ret < 0)
 		return ret;
 
-	rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL);
+	rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL);
 	call_netdevice_notifiers(NETDEV_UP, dev);
 
 	return ret;
@@ -1541,7 +1526,7 @@ void dev_close_many(struct list_head *head, bool unlink)
 	__dev_close_many(head);
 
 	list_for_each_entry_safe(dev, tmp, head, close_list) {
-		rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL);
+		rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL);
 		call_netdevice_notifiers(NETDEV_DOWN, dev);
 		if (unlink)
 			list_del_init(&dev->close_list);
@@ -1621,10 +1606,10 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd)
 	N(UP) N(DOWN) N(REBOOT) N(CHANGE) N(REGISTER) N(UNREGISTER)
 	N(CHANGEMTU) N(CHANGEADDR) N(GOING_DOWN) N(CHANGENAME) N(FEAT_CHANGE)
 	N(BONDING_FAILOVER) N(PRE_UP) N(PRE_TYPE_CHANGE) N(POST_TYPE_CHANGE)
-	N(POST_INIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) N(CHANGEUPPER)
-	N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO)
-	N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO)
-	N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN)
+	N(POST_INIT) N(PRE_UNINIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN)
+	N(CHANGEUPPER) N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA)
+	N(BONDING_INFO) N(PRECHANGEUPPER) N(CHANGELOWERSTATE)
+	N(UDP_TUNNEL_PUSH_INFO) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN)
 	N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO)
 	N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO)
 	N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE)
@@ -1876,6 +1861,22 @@ int unregister_netdevice_notifier_net(struct net *net,
 }
 EXPORT_SYMBOL(unregister_netdevice_notifier_net);
 
+static void __move_netdevice_notifier_net(struct net *src_net,
+					  struct net *dst_net,
+					  struct notifier_block *nb)
+{
+	__unregister_netdevice_notifier_net(src_net, nb);
+	__register_netdevice_notifier_net(dst_net, nb, true);
+}
+
+void move_netdevice_notifier_net(struct net *src_net, struct net *dst_net,
+				 struct notifier_block *nb)
+{
+	rtnl_lock();
+	__move_netdevice_notifier_net(src_net, dst_net, nb);
+	rtnl_unlock();
+}
+
 int register_netdevice_notifier_dev_net(struct net_device *dev,
 					struct notifier_block *nb,
 					struct netdev_net_notifier *nn)
@@ -1912,10 +1913,8 @@ static void move_netdevice_notifiers_dev_net(struct net_device *dev,
 {
 	struct netdev_net_notifier *nn;
 
-	list_for_each_entry(nn, &dev->net_notifier_list, list) {
-		__unregister_netdevice_notifier_net(dev_net(dev), nn->nb);
-		__register_netdevice_notifier_net(net, nn->nb, true);
-	}
+	list_for_each_entry(nn, &dev->net_notifier_list, list)
+		__move_netdevice_notifier_net(dev_net(dev), net, nn->nb);
 }
 
 /**
@@ -2074,13 +2073,10 @@ static DECLARE_WORK(netstamp_work, netstamp_clear);
 void net_enable_timestamp(void)
 {
 #ifdef CONFIG_JUMP_LABEL
-	int wanted;
+	int wanted = atomic_read(&netstamp_wanted);
 
-	while (1) {
-		wanted = atomic_read(&netstamp_wanted);
-		if (wanted <= 0)
-			break;
-		if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted)
+	while (wanted > 0) {
+		if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted + 1))
 			return;
 	}
 	atomic_inc(&netstamp_needed_deferred);
@@ -2094,13 +2090,10 @@ EXPORT_SYMBOL(net_enable_timestamp);
 void net_disable_timestamp(void)
 {
 #ifdef CONFIG_JUMP_LABEL
-	int wanted;
+	int wanted = atomic_read(&netstamp_wanted);
 
-	while (1) {
-		wanted = atomic_read(&netstamp_wanted);
-		if (wanted <= 1)
-			break;
-		if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted)
+	while (wanted > 1) {
+		if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted - 1))
 			return;
 	}
 	atomic_dec(&netstamp_needed_deferred);
@@ -5986,10 +5979,9 @@ EXPORT_SYMBOL(__napi_schedule);
  */
 bool napi_schedule_prep(struct napi_struct *n)
 {
-	unsigned long val, new;
+	unsigned long new, val = READ_ONCE(n->state);
 
 	do {
-		val = READ_ONCE(n->state);
 		if (unlikely(val & NAPIF_STATE_DISABLE))
 			return false;
 		new = val | NAPIF_STATE_SCHED;
@@ -6002,7 +5994,7 @@ bool napi_schedule_prep(struct napi_struct *n)
 		 */
 		new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED *
 						   NAPIF_STATE_MISSED;
-	} while (cmpxchg(&n->state, val, new) != val);
+	} while (!try_cmpxchg(&n->state, &val, new));
 
 	return !(val & NAPIF_STATE_SCHED);
 }
@@ -6070,9 +6062,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		local_irq_restore(flags);
 	}
 
+	val = READ_ONCE(n->state);
 	do {
-		val = READ_ONCE(n->state);
-
 		WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
 
 		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
@@ -6085,7 +6076,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		 */
 		new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED *
 						    NAPIF_STATE_SCHED;
-	} while (cmpxchg(&n->state, val, new) != val);
+	} while (!try_cmpxchg(&n->state, &val, new));
 
 	if (unlikely(val & NAPIF_STATE_MISSED)) {
 		__napi_schedule(n);
@@ -6406,19 +6397,16 @@ void napi_disable(struct napi_struct *n)
 	might_sleep();
 	set_bit(NAPI_STATE_DISABLE, &n->state);
 
-	for ( ; ; ) {
-		val = READ_ONCE(n->state);
-		if (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) {
+	val = READ_ONCE(n->state);
+	do {
+		while (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) {
 			usleep_range(20, 200);
-			continue;
+			val = READ_ONCE(n->state);
 		}
 
 		new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC;
 		new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL);
-
-		if (cmpxchg(&n->state, val, new) == val)
-			break;
-	}
+	} while (!try_cmpxchg(&n->state, &val, new));
 
 	hrtimer_cancel(&n->timer);
 
@@ -6435,16 +6423,15 @@ EXPORT_SYMBOL(napi_disable);
  */
 void napi_enable(struct napi_struct *n)
 {
-	unsigned long val, new;
+	unsigned long new, val = READ_ONCE(n->state);
 
 	do {
-		val = READ_ONCE(n->state);
 		BUG_ON(!test_bit(NAPI_STATE_SCHED, &val));
 
 		new = val & ~(NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC);
 		if (n->dev->threaded && n->thread)
 			new |= NAPIF_STATE_THREADED;
-	} while (cmpxchg(&n->state, val, new) != val);
+	} while (!try_cmpxchg(&n->state, &val, new));
 }
 EXPORT_SYMBOL(napi_enable);
 
@@ -8351,7 +8338,7 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
 		dev_change_rx_flags(dev, IFF_PROMISC);
 	}
 	if (notify)
-		__dev_notify_flags(dev, old_flags, IFF_PROMISC);
+		__dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL);
 	return 0;
 }
 
@@ -8406,7 +8393,7 @@ static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify)
 		dev_set_rx_mode(dev);
 		if (notify)
 			__dev_notify_flags(dev, old_flags,
-					   dev->gflags ^ old_gflags);
+					   dev->gflags ^ old_gflags, 0, NULL);
 	}
 	return 0;
 }
@@ -8569,12 +8556,13 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags,
 }
 
 void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
-			unsigned int gchanges)
+			unsigned int gchanges, u32 portid,
+			const struct nlmsghdr *nlh)
 {
 	unsigned int changes = dev->flags ^ old_flags;
 
 	if (gchanges)
-		rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC);
+		rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC, portid, nlh);
 
 	if (changes & IFF_UP) {
 		if (dev->flags & IFF_UP)
@@ -8616,7 +8604,7 @@ int dev_change_flags(struct net_device *dev, unsigned int flags,
 		return ret;
 
 	changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags);
-	__dev_notify_flags(dev, old_flags, changes);
+	__dev_notify_flags(dev, old_flags, changes, 0, NULL);
 	return ret;
 }
 EXPORT_SYMBOL(dev_change_flags);
@@ -8822,7 +8810,7 @@ EXPORT_SYMBOL(dev_set_mac_address_user);
 
 int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name)
 {
-	size_t size = sizeof(sa->sa_data);
+	size_t size = sizeof(sa->sa_data_min);
 	struct net_device *dev;
 	int ret = 0;
 
@@ -10059,7 +10047,7 @@ int register_netdevice(struct net_device *dev)
 	dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED;
 	write_unlock(&dev_base_lock);
 	if (ret)
-		goto err_uninit;
+		goto err_uninit_notify;
 
 	__netdev_update_features(dev);
 
@@ -10101,11 +10089,13 @@ int register_netdevice(struct net_device *dev)
 	 */
 	if (!dev->rtnl_link_ops ||
 	    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
-		rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL);
+		rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL);
 
 out:
 	return ret;
 
+err_uninit_notify:
+	call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev);
 err_uninit:
 	if (dev->netdev_ops->ndo_uninit)
 		dev->netdev_ops->ndo_uninit(dev);
@@ -10379,24 +10369,16 @@ void netdev_run_todo(void)
 void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
 			     const struct net_device_stats *netdev_stats)
 {
-#if BITS_PER_LONG == 64
-	BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats));
-	memcpy(stats64, netdev_stats, sizeof(*netdev_stats));
-	/* zero out counters that only exist in rtnl_link_stats64 */
-	memset((char *)stats64 + sizeof(*netdev_stats), 0,
-	       sizeof(*stats64) - sizeof(*netdev_stats));
-#else
-	size_t i, n = sizeof(*netdev_stats) / sizeof(unsigned long);
-	const unsigned long *src = (const unsigned long *)netdev_stats;
+	size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t);
+	const atomic_long_t *src = (atomic_long_t *)netdev_stats;
 	u64 *dst = (u64 *)stats64;
 
 	BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64));
 	for (i = 0; i < n; i++)
-		dst[i] = src[i];
+		dst[i] = atomic_long_read(&src[i]);
 	/* zero out counters that only exist in rtnl_link_stats64 */
 	memset((char *)stats64 + n * sizeof(u64), 0,
 	       sizeof(*stats64) - n * sizeof(u64));
-#endif
 }
 EXPORT_SYMBOL(netdev_stats_to_stats64);
 
@@ -10477,12 +10459,12 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
 
 		stats = per_cpu_ptr(netstats, cpu);
 		do {
-			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			start = u64_stats_fetch_begin(&stats->syncp);
 			rx_packets = u64_stats_read(&stats->rx_packets);
 			rx_bytes   = u64_stats_read(&stats->rx_bytes);
 			tx_packets = u64_stats_read(&stats->tx_packets);
 			tx_bytes   = u64_stats_read(&stats->tx_bytes);
-		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+		} while (u64_stats_fetch_retry(&stats->syncp, start));
 
 		s->rx_packets += rx_packets;
 		s->rx_bytes   += rx_bytes;
@@ -10535,6 +10517,22 @@ void netdev_set_default_ethtool_ops(struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops);
 
+/**
+ * netdev_sw_irq_coalesce_default_on() - enable SW IRQ coalescing by default
+ * @dev: netdev to enable the IRQ coalescing on
+ *
+ * Sets a conservative default for SW IRQ coalescing. Users can use
+ * sysfs attributes to override the default values.
+ */
+void netdev_sw_irq_coalesce_default_on(struct net_device *dev)
+{
+	WARN_ON(dev->reg_state == NETREG_REGISTERED);
+
+	dev->gro_flush_timeout = 20000;
+	dev->napi_defer_hard_irqs = 1;
+}
+EXPORT_SYMBOL_GPL(netdev_sw_irq_coalesce_default_on);
+
 void netdev_freemem(struct net_device *dev)
 {
 	char *addr = (char *)dev - dev->padded;
@@ -10780,14 +10778,8 @@ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head)
 }
 EXPORT_SYMBOL(unregister_netdevice_queue);
 
-/**
- *	unregister_netdevice_many - unregister many devices
- *	@head: list of devices
- *
- *  Note: As most callers use a stack allocated list_head,
- *  we force a list_del() to make sure stack wont be corrupted later.
- */
-void unregister_netdevice_many(struct list_head *head)
+void unregister_netdevice_many_notify(struct list_head *head,
+				      u32 portid, const struct nlmsghdr *nlh)
 {
 	struct net_device *dev, *tmp;
 	LIST_HEAD(close_head);
@@ -10849,7 +10841,8 @@ void unregister_netdevice_many(struct list_head *head)
 		if (!dev->rtnl_link_ops ||
 		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
 			skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0,
-						     GFP_KERNEL, NULL, 0);
+						     GFP_KERNEL, NULL, 0,
+						     portid, nlmsg_seq(nlh));
 
 		/*
 		 *	Flush the unicast and multicast chains
@@ -10860,11 +10853,13 @@ void unregister_netdevice_many(struct list_head *head)
 		netdev_name_node_alt_flush(dev);
 		netdev_name_node_free(dev->name_node);
 
+		call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev);
+
 		if (dev->netdev_ops->ndo_uninit)
 			dev->netdev_ops->ndo_uninit(dev);
 
 		if (skb)
-			rtmsg_ifinfo_send(skb, dev, GFP_KERNEL);
+			rtmsg_ifinfo_send(skb, dev, GFP_KERNEL, portid, nlh);
 
 		/* Notifier chain MUST detach us all upper devices. */
 		WARN_ON(netdev_has_any_upper_dev(dev));
@@ -10887,6 +10882,18 @@ void unregister_netdevice_many(struct list_head *head)
 
 	list_del(head);
 }
+
+/**
+ *	unregister_netdevice_many - unregister many devices
+ *	@head: list of devices
+ *
+ *  Note: As most callers use a stack allocated list_head,
+ *  we force a list_del() to make sure stack wont be corrupted later.
+ */
+void unregister_netdevice_many(struct list_head *head)
+{
+	unregister_netdevice_many_notify(head, 0, NULL);
+}
 EXPORT_SYMBOL(unregister_netdevice_many);
 
 /**
@@ -11042,7 +11049,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 	 *	Prevent userspace races by waiting until the network
 	 *	device is fully setup before sending notifications.
 	 */
-	rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL);
+	rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL);
 
 	synchronize_net();
 	err = 0;
diff --git a/net/core/dev.h b/net/core/dev.h
index cbb8a925175a..814ed5b7b960 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -88,6 +88,13 @@ int dev_change_carrier(struct net_device *dev, bool new_carrier);
 
 void __dev_set_rx_mode(struct net_device *dev);
 
+void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
+			unsigned int gchanges, u32 portid,
+			const struct nlmsghdr *nlh);
+
+void unregister_netdevice_many_notify(struct list_head *head,
+				      u32 portid, const struct nlmsghdr *nlh);
+
 static inline void netif_set_gso_max_size(struct net_device *dev,
 					  unsigned int size)
 {
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 7674bb9f3076..5cdbfbf9a7dc 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -342,7 +342,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data,
 		if (ifr->ifr_hwaddr.sa_family != dev->type)
 			return -EINVAL;
 		memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
-		       min(sizeof(ifr->ifr_hwaddr.sa_data),
+		       min(sizeof(ifr->ifr_hwaddr.sa_data_min),
 			   (size_t)dev->addr_len));
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
 		return 0;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 89baa7c0938b..6004bd0ccee4 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -41,7 +41,7 @@ struct devlink_dev_stats {
 
 struct devlink {
 	u32 index;
-	struct list_head port_list;
+	struct xarray ports;
 	struct list_head rate_list;
 	struct list_head sb_list;
 	struct list_head dpipe_table_list;
@@ -71,6 +71,7 @@ struct devlink {
 	refcount_t refcount;
 	struct completion comp;
 	struct rcu_head rcu;
+	struct notifier_block netdevice_nb;
 	char priv[] __aligned(NETDEV_ALIGN);
 };
 
@@ -194,11 +195,16 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
 
+#define DEVLINK_PORT_FN_CAPS_VALID_MASK \
+	(_BITUL(__DEVLINK_PORT_FN_ATTR_CAPS_MAX) - 1)
+
 static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = {
 	[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY },
 	[DEVLINK_PORT_FN_ATTR_STATE] =
 		NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE,
 				 DEVLINK_PORT_FN_STATE_ACTIVE),
+	[DEVLINK_PORT_FN_ATTR_CAPS] =
+		NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK),
 };
 
 static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = {
@@ -381,19 +387,7 @@ static struct devlink *devlink_get_from_attrs(struct net *net,
 static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink,
 						      unsigned int port_index)
 {
-	struct devlink_port *devlink_port;
-
-	list_for_each_entry(devlink_port, &devlink->port_list, list) {
-		if (devlink_port->index == port_index)
-			return devlink_port;
-	}
-	return NULL;
-}
-
-static bool devlink_port_index_exists(struct devlink *devlink,
-				      unsigned int port_index)
-{
-	return devlink_port_get_by_index(devlink, port_index);
+	return xa_load(&devlink->ports, port_index);
 }
 
 static struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink,
@@ -691,6 +685,87 @@ devlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb,
 	return 0;
 }
 
+static void devlink_port_fn_cap_fill(struct nla_bitfield32 *caps,
+				     u32 cap, bool is_enable)
+{
+	caps->selector |= cap;
+	if (is_enable)
+		caps->value |= cap;
+}
+
+static int devlink_port_fn_roce_fill(const struct devlink_ops *ops,
+				     struct devlink_port *devlink_port,
+				     struct nla_bitfield32 *caps,
+				     struct netlink_ext_ack *extack)
+{
+	bool is_enable;
+	int err;
+
+	if (!ops->port_fn_roce_get)
+		return 0;
+
+	err = ops->port_fn_roce_get(devlink_port, &is_enable, extack);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_ROCE, is_enable);
+	return 0;
+}
+
+static int devlink_port_fn_migratable_fill(const struct devlink_ops *ops,
+					   struct devlink_port *devlink_port,
+					   struct nla_bitfield32 *caps,
+					   struct netlink_ext_ack *extack)
+{
+	bool is_enable;
+	int err;
+
+	if (!ops->port_fn_migratable_get ||
+	    devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF)
+		return 0;
+
+	err = ops->port_fn_migratable_get(devlink_port, &is_enable, extack);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_MIGRATABLE, is_enable);
+	return 0;
+}
+
+static int devlink_port_fn_caps_fill(const struct devlink_ops *ops,
+				     struct devlink_port *devlink_port,
+				     struct sk_buff *msg,
+				     struct netlink_ext_ack *extack,
+				     bool *msg_updated)
+{
+	struct nla_bitfield32 caps = {};
+	int err;
+
+	err = devlink_port_fn_roce_fill(ops, devlink_port, &caps, extack);
+	if (err)
+		return err;
+
+	err = devlink_port_fn_migratable_fill(ops, devlink_port, &caps, extack);
+	if (err)
+		return err;
+
+	if (!caps.selector)
+		return 0;
+	err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value,
+				 caps.selector);
+	if (err)
+		return err;
+
+	*msg_updated = true;
+	return 0;
+}
+
 static int
 devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb,
 				  struct genl_info *info,
@@ -769,7 +844,7 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id)
 #define DEVLINK_NL_FLAG_NEED_RATE_NODE		BIT(3)
 #define DEVLINK_NL_FLAG_NEED_LINECARD		BIT(4)
 
-static int devlink_nl_pre_doit(const struct genl_ops *ops,
+static int devlink_nl_pre_doit(const struct genl_split_ops *ops,
 			       struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink_linecard *linecard;
@@ -827,7 +902,7 @@ unlock:
 	return err;
 }
 
-static void devlink_nl_post_doit(const struct genl_ops *ops,
+static void devlink_nl_post_doit(const struct genl_split_ops *ops,
 				 struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink_linecard *linecard;
@@ -879,6 +954,24 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port)
+{
+	if (devlink_nl_put_handle(msg, devlink_port->devlink))
+		return -EMSGSIZE;
+	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
+		return -EMSGSIZE;
+	return 0;
+}
+
+size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port)
+{
+	struct devlink *devlink = devlink_port->devlink;
+
+	return nla_total_size(strlen(devlink->dev->bus->name) + 1) /* DEVLINK_ATTR_BUS_NAME */
+	     + nla_total_size(strlen(dev_name(devlink->dev)) + 1) /* DEVLINK_ATTR_DEV_NAME */
+	     + nla_total_size(4); /* DEVLINK_ATTR_PORT_INDEX */
+}
+
 struct devlink_reload_combination {
 	enum devlink_reload_action action;
 	enum devlink_reload_limit limit;
@@ -1184,6 +1277,14 @@ static int devlink_nl_rate_fill(struct sk_buff *msg,
 			      devlink_rate->tx_max, DEVLINK_ATTR_PAD))
 		goto nla_put_failure;
 
+	if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_PRIORITY,
+			devlink_rate->tx_priority))
+		goto nla_put_failure;
+
+	if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_WEIGHT,
+			devlink_rate->tx_weight))
+		goto nla_put_failure;
+
 	if (devlink_rate->parent)
 		if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME,
 				   devlink_rate->parent->name))
@@ -1249,6 +1350,51 @@ static int devlink_port_fn_state_fill(const struct devlink_ops *ops,
 }
 
 static int
+devlink_port_fn_mig_set(struct devlink_port *devlink_port, bool enable,
+			struct netlink_ext_ack *extack)
+{
+	const struct devlink_ops *ops = devlink_port->devlink->ops;
+
+	return ops->port_fn_migratable_set(devlink_port, enable, extack);
+}
+
+static int
+devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable,
+			 struct netlink_ext_ack *extack)
+{
+	const struct devlink_ops *ops = devlink_port->devlink->ops;
+
+	return ops->port_fn_roce_set(devlink_port, enable, extack);
+}
+
+static int devlink_port_fn_caps_set(struct devlink_port *devlink_port,
+				    const struct nlattr *attr,
+				    struct netlink_ext_ack *extack)
+{
+	struct nla_bitfield32 caps;
+	u32 caps_value;
+	int err;
+
+	caps = nla_get_bitfield32(attr);
+	caps_value = caps.value & caps.selector;
+	if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE) {
+		err = devlink_port_fn_roce_set(devlink_port,
+					       caps_value & DEVLINK_PORT_FN_CAP_ROCE,
+					       extack);
+		if (err)
+			return err;
+	}
+	if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) {
+		err = devlink_port_fn_mig_set(devlink_port, caps_value &
+					      DEVLINK_PORT_FN_CAP_MIGRATABLE,
+					      extack);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int
 devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port,
 				   struct netlink_ext_ack *extack)
 {
@@ -1266,6 +1412,10 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por
 					   &msg_updated);
 	if (err)
 		goto out;
+	err = devlink_port_fn_caps_fill(ops, port, msg, extack,
+					&msg_updated);
+	if (err)
+		goto out;
 	err = devlink_port_fn_state_fill(ops, port, msg, extack, &msg_updated);
 out:
 	if (err || !msg_updated)
@@ -1292,8 +1442,6 @@ static int devlink_nl_port_fill(struct sk_buff *msg,
 	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
 		goto nla_put_failure;
 
-	/* Hold rtnl lock while accessing port's netdev attributes. */
-	rtnl_lock();
 	spin_lock_bh(&devlink_port->type_lock);
 	if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type))
 		goto nla_put_failure_type_locked;
@@ -1302,18 +1450,15 @@ static int devlink_nl_port_fill(struct sk_buff *msg,
 			devlink_port->desi