1 files changed, 328 insertions, 135 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 0d891634c692..b28ce68830b2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -462,7 +462,9 @@ EXPORT_PER_CPU_SYMBOL(softnet_data);
  * PP consumers must pay attention to run APIs in the appropriate context
  * (e.g. NAPI context).
  */
-DEFINE_PER_CPU(struct page_pool *, system_page_pool);
+DEFINE_PER_CPU(struct page_pool_bh, system_page_pool) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 
 #ifdef CONFIG_LOCKDEP
 /*
@@ -828,7 +830,7 @@ netdev_napi_by_id_lock(struct net *net, unsigned int napi_id)
 	dev_hold(dev);
 	rcu_read_unlock();
 
-	dev = __netdev_put_lock(dev);
+	dev = __netdev_put_lock(dev, net);
 	if (!dev)
 		return NULL;
 
@@ -1039,10 +1041,11 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id)
  * This helper is intended for locking net_device after it has been looked up
  * using a lockless lookup helper. Lock prevents the instance from going away.
  */
-struct net_device *__netdev_put_lock(struct net_device *dev)
+struct net_device *__netdev_put_lock(struct net_device *dev, struct net *net)
 {
 	netdev_lock(dev);
-	if (dev->reg_state > NETREG_REGISTERED) {
+	if (dev->reg_state > NETREG_REGISTERED ||
+	    dev->moving_ns || !net_eq(dev_net(dev), net)) {
 		netdev_unlock(dev);
 		dev_put(dev);
 		return NULL;
@@ -1051,6 +1054,20 @@ struct net_device *__netdev_put_lock(struct net_device *dev)
 	return dev;
 }
 
+static struct net_device *
+__netdev_put_lock_ops_compat(struct net_device *dev, struct net *net)
+{
+	netdev_lock_ops_compat(dev);
+	if (dev->reg_state > NETREG_REGISTERED ||
+	    dev->moving_ns || !net_eq(dev_net(dev), net)) {
+		netdev_unlock_ops_compat(dev);
+		dev_put(dev);
+		return NULL;
+	}
+	dev_put(dev);
+	return dev;
+}
+
 /**
  *	netdev_get_by_index_lock() - find a device by its ifindex
  *	@net: the applicable net namespace
@@ -1070,7 +1087,19 @@ struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex)
 	if (!dev)
 		return NULL;
 
-	return __netdev_put_lock(dev);
+	return __netdev_put_lock(dev, net);
+}
+
+struct net_device *
+netdev_get_by_index_lock_ops_compat(struct net *net, int ifindex)
+{
+	struct net_device *dev;
+
+	dev = dev_get_by_index(net, ifindex);
+	if (!dev)
+		return NULL;
+
+	return __netdev_put_lock_ops_compat(dev, net);
 }
 
 struct net_device *
@@ -1090,7 +1119,32 @@ netdev_xa_find_lock(struct net *net, struct net_device *dev,
 		dev_hold(dev);
 		rcu_read_unlock();
 
-		dev = __netdev_put_lock(dev);
+		dev = __netdev_put_lock(dev, net);
+		if (dev)
+			return dev;
+
+		(*index)++;
+	} while (true);
+}
+
+struct net_device *
+netdev_xa_find_lock_ops_compat(struct net *net, struct net_device *dev,
+			       unsigned long *index)
+{
+	if (dev)
+		netdev_unlock_ops_compat(dev);
+
+	do {
+		rcu_read_lock();
+		dev = xa_find(&net->dev_by_index, index, ULONG_MAX, XA_PRESENT);
+		if (!dev) {
+			rcu_read_unlock();
+			return NULL;
+		}
+		dev_hold(dev);
+		rcu_read_unlock();
+
+		dev = __netdev_put_lock_ops_compat(dev, net);
 		if (dev)
 			return dev;
 
@@ -1213,33 +1267,32 @@ struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
 EXPORT_SYMBOL(dev_getfirstbyhwtype);
 
 /**
- *	__dev_get_by_flags - find any device with given flags
- *	@net: the applicable net namespace
- *	@if_flags: IFF_* values
- *	@mask: bitmask of bits in if_flags to check
+ * netdev_get_by_flags_rcu - find any device with given flags
+ * @net: the applicable net namespace
+ * @tracker: tracking object for the acquired reference
+ * @if_flags: IFF_* values
+ * @mask: bitmask of bits in if_flags to check
+ *
+ * Search for any interface with the given flags.
  *
- *	Search for any interface with the given flags. Returns NULL if a device
- *	is not found or a pointer to the device. Must be called inside
- *	rtnl_lock(), and result refcount is unchanged.
+ * Context: rcu_read_lock() must be held.
+ * Returns: NULL if a device is not found or a pointer to the device.
  */
-
-struct net_device *__dev_get_by_flags(struct net *net, unsigned short if_flags,
-				      unsigned short mask)
+struct net_device *netdev_get_by_flags_rcu(struct net *net, netdevice_tracker *tracker,
+					   unsigned short if_flags, unsigned short mask)
 {
-	struct net_device *dev, *ret;
-
-	ASSERT_RTNL();
+	struct net_device *dev;
 
-	ret = NULL;
-	for_each_netdev(net, dev) {
-		if (((dev->flags ^ if_flags) & mask) == 0) {
-			ret = dev;
-			break;
+	for_each_netdev_rcu(net, dev) {
+		if (((READ_ONCE(dev->flags) ^ if_flags) & mask) == 0) {
+			netdev_hold(dev, tracker, GFP_ATOMIC);
+			return dev;
 		}
 	}
-	return ret;
+
+	return NULL;
 }
-EXPORT_SYMBOL(__dev_get_by_flags);
+EXPORT_IPV6_MOD(netdev_get_by_flags_rcu);
 
 /**
  *	dev_valid_name - check if name is okay for network device
@@ -1715,7 +1768,7 @@ static void __dev_close(struct net_device *dev)
 	list_del(&single);
 }
 
-void dev_close_many(struct list_head *head, bool unlink)
+void netif_close_many(struct list_head *head, bool unlink)
 {
 	struct net_device *dev, *tmp;
 
@@ -1733,7 +1786,7 @@ void dev_close_many(struct list_head *head, bool unlink)
 			list_del_init(&dev->close_list);
 	}
 }
-EXPORT_SYMBOL(dev_close_many);
+EXPORT_SYMBOL_NS_GPL(netif_close_many, "NETDEV_INTERNAL");
 
 void netif_close(struct net_device *dev)
 {
@@ -1741,7 +1794,7 @@ void netif_close(struct net_device *dev)
 		LIST_HEAD(single);
 
 		list_add(&dev->close_list, &single);
-		dev_close_many(&single, true);
+		netif_close_many(&single, true);
 		list_del(&single);
 	}
 }
@@ -3125,7 +3178,6 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
 
 	if (dev->reg_state == NETREG_REGISTERED ||
 	    dev->reg_state == NETREG_UNREGISTERING) {
-		ASSERT_RTNL();
 		netdev_ops_assert_locked(dev);
 
 		rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues,
@@ -3175,7 +3227,6 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq)
 		return -EINVAL;
 
 	if (dev->reg_state == NETREG_REGISTERED) {
-		ASSERT_RTNL();
 		netdev_ops_assert_locked(dev);
 
 		rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues,
@@ -3542,9 +3593,10 @@ out:
 }
 EXPORT_SYMBOL(skb_checksum_help);
 
+#ifdef CONFIG_NET_CRC32C
 int skb_crc32c_csum_help(struct sk_buff *skb)
 {
-	__le32 crc32c_csum;
+	u32 crc;
 	int ret = 0, offset, start;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -3572,15 +3624,14 @@ int skb_crc32c_csum_help(struct sk_buff *skb)
 	if (ret)
 		goto out;
 
-	crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start,
-						  skb->len - start, ~(__u32)0,
-						  crc32c_csum_stub));
-	*(__le32 *)(skb->data + offset) = crc32c_csum;
+	crc = ~skb_crc32c(skb, start, skb->len - start, ~0);
+	*(__le32 *)(skb->data + offset) = cpu_to_le32(crc);
 	skb_reset_csum_not_inet(skb);
 out:
 	return ret;
 }
 EXPORT_SYMBOL(skb_crc32c_csum_help);
+#endif /* CONFIG_NET_CRC32C */
 
 __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
@@ -3844,12 +3895,42 @@ sw_checksum:
 }
 EXPORT_SYMBOL(skb_csum_hwoffload_help);
 
+static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb,
+						    struct net_device *dev)
+{
+	struct skb_shared_info *shinfo;
+	struct net_iov *niov;
+
+	if (likely(skb_frags_readable(skb)))
+		goto out;
+
+	if (!dev->netmem_tx)
+		goto out_free;
+
+	shinfo = skb_shinfo(skb);
+
+	if (shinfo->nr_frags > 0) {
+		niov = netmem_to_net_iov(skb_frag_netmem(&shinfo->frags[0]));
+		if (net_is_devmem_iov(niov) &&
+		    net_devmem_iov_binding(niov)->dev != dev)
+			goto out_free;
+	}
+
+out:
+	return skb;
+
+out_free:
+	kfree_skb(skb);
+	return NULL;
+}
+
 static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again)
 {
 	netdev_features_t features;
 
-	if (!skb_frags_readable(skb))
-		goto out_kfree_skb;
+	skb = validate_xmit_unreadable_skb(skb, dev);
+	if (unlikely(!skb))
+		goto out_null;
 
 	features = netif_skb_features(skb);
 	skb = validate_xmit_vlan(skb, features);
@@ -3944,7 +4025,10 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
 		unsigned int hdr_len;
 
 		/* mac layer + network layer */
-		hdr_len = skb_transport_offset(skb);
+		if (!skb->encapsulation)
+			hdr_len = skb_transport_offset(skb);
+		else
+			hdr_len = skb_inner_transport_offset(skb);
 
 		/* + transport layer */
 		if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) {
@@ -4714,7 +4798,7 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 
 	if (test_bit(NAPI_STATE_THREADED, &napi->state)) {
 		/* Paired with smp_mb__before_atomic() in
-		 * napi_enable()/dev_set_threaded().
+		 * napi_enable()/netif_set_threaded().
 		 * Use READ_ONCE() to guarantee a complete
 		 * read on napi->thread. Only call
 		 * wake_up_process() when it's not NULL.
@@ -4731,6 +4815,7 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 	}
 
 use_local_napi:
+	DEBUG_NET_WARN_ON_ONCE(!list_empty(&napi->poll_list));
 	list_add_tail(&napi->poll_list, &sd->poll_list);
 	WRITE_ONCE(napi->list_owner, smp_processor_id());
 	/* If not called from net_rx_action()
@@ -4946,7 +5031,8 @@ static void rps_trigger_softirq(void *data)
 	struct softnet_data *sd = data;
 
 	____napi_schedule(sd, &sd->backlog);
-	sd->received_rps++;
+	/* Pairs with READ_ONCE() in softnet_seq_show() */
+	WRITE_ONCE(sd->received_rps, sd->received_rps + 1);
 }
 
 #endif /* CONFIG_RPS */
@@ -5031,7 +5117,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
 	rcu_read_lock();
 	fl = rcu_dereference(sd->flow_limit);
 	if (fl) {
-		new_flow = skb_get_hash(skb) & (fl->num_buckets - 1);
+		new_flow = hash_32(skb_get_hash(skb), fl->log_buckets);
 		old_flow = fl->history[fl->history_head];
 		fl->history[fl->history_head] = new_flow;
 
@@ -5042,7 +5128,8 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
 			fl->buckets[old_flow]--;
 
 		if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) {
-			fl->count++;
+			/* Pairs with READ_ONCE() in softnet_seq_show() */
+			WRITE_ONCE(fl->count, fl->count + 1);
 			rcu_read_unlock();
 			return true;
 		}
@@ -5238,7 +5325,10 @@ netif_skb_check_for_xdp(struct sk_buff **pskb, const struct bpf_prog *prog)
 	struct sk_buff *skb = *pskb;
 	int err, hroom, troom;
 
-	if (!skb_cow_data_for_xdp(this_cpu_read(system_page_pool), pskb, prog))
+	local_lock_nested_bh(&system_page_pool.bh_lock);
+	err = skb_cow_data_for_xdp(this_cpu_read(system_page_pool.pool), pskb, prog);
+	local_unlock_nested_bh(&system_page_pool.bh_lock);
+	if (!err)
 		return 0;
 
 	/* In case we have to go down the path and also linearize,
@@ -5659,6 +5749,7 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
 static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 				    struct packet_type **ppt_prev)
 {
+	enum skb_drop_reason drop_reason = SKB_DROP_REASON_UNHANDLED_PROTO;
 	struct packet_type *ptype, *pt_prev;
 	rx_handler_func_t *rx_handler;
 	struct sk_buff *skb = *pskb;
@@ -5750,8 +5841,10 @@ skip_taps:
 #endif
 	skb_reset_redirect(skb);
 skip_classify:
-	if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
+	if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) {
+		drop_reason = SKB_DROP_REASON_PFMEMALLOC;
 		goto drop;
+	}
 
 	if (skb_vlan_tag_present(skb)) {
 		if (pt_prev) {
@@ -5849,8 +5942,6 @@ check_vlan_id:
 	}
 
 	if (pt_prev) {
-		if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
-			goto drop;
 		*ppt_prev = pt_prev;
 	} else {
 drop:
@@ -5858,7 +5949,8 @@ drop:
 			dev_core_stats_rx_dropped_inc(skb->dev);
 		else
 			dev_core_stats_rx_nohandler_inc(skb->dev);
-		kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO);
+
+		kfree_skb_reason(skb, drop_reason);
 		/* Jamal, now you will not able to escape explaining
 		 * me how you were going to use this. :-)
 		 */
@@ -6486,8 +6578,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 	 * it, we need to bound somehow the time packets are kept in
 	 * the GRO layer.
 	 */
-	gro_flush(&n->gro, !!timeout);
-	gro_normal_list(&n->gro);
+	gro_flush_normal(&n->gro, !!timeout);
 
 	if (unlikely(!list_empty(&n->poll_list))) {
 		/* If n->poll_list is not empty, we need to mask irqs */
@@ -6557,8 +6648,7 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
 	}
 
 	/* Flush too old packets. If HZ < 1000, flush all packets */
-	gro_flush(&napi->gro, HZ >= 1000);
-	gro_normal_list(&napi->gro);
+	gro_flush_normal(&napi->gro, HZ >= 1000);
 
 	clear_bit(NAPI_STATE_SCHED, &napi->state);
 }
@@ -6836,22 +6926,83 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-int dev_set_threaded(struct net_device *dev, bool threaded)
+static void napi_stop_kthread(struct napi_struct *napi)
+{
+	unsigned long val, new;
+
+	/* Wait until the napi STATE_THREADED is unset. */
+	while (true) {
+		val = READ_ONCE(napi->state);
+
+		/* If napi kthread own this napi or the napi is idle,
+		 * STATE_THREADED can be unset here.
+		 */
+		if ((val & NAPIF_STATE_SCHED_THREADED) ||
+		    !(val & NAPIF_STATE_SCHED)) {
+			new = val & (~NAPIF_STATE_THREADED);
+		} else {
+			msleep(20);
+			continue;
+		}
+
+		if (try_cmpxchg(&napi->state, &val, new))
+			break;
+	}
+
+	/* Once STATE_THREADED is unset, wait for SCHED_THREADED to be unset by
+	 * the kthread.
+	 */
+	while (true) {
+		if (!test_bit(NAPIF_STATE_SCHED_THREADED, &napi->state))
+			break;
+
+		msleep(20);
+	}
+
+	kthread_stop(napi->thread);
+	napi->thread = NULL;
+}
+
+int napi_set_threaded(struct napi_struct *napi,
+		      enum netdev_napi_threaded threaded)
+{
+	if (threaded) {
+		if (!napi->thread) {
+			int err = napi_kthread_create(napi);
+
+			if (err)
+				return err;
+		}
+	}
+
+	if (napi->config)
+		napi->config->threaded = threaded;
+
+	if (!threaded && napi->thread) {
+		napi_stop_kthread(napi);
+	} else {
+		/* Make sure kthread is created before THREADED bit is set. */
+		smp_mb__before_atomic();
+		assign_bit(NAPI_STATE_THREADED, &napi->state, threaded);
+	}
+
+	return 0;
+}
+
+int netif_set_threaded(struct net_device *dev,
+		       enum netdev_napi_threaded threaded)
 {
 	struct napi_struct *napi;
 	int err = 0;
 
 	netdev_assert_locked_or_invisible(dev);
 
-	if (dev->threaded == threaded)
-		return 0;
-
 	if (threaded) {
 		list_for_each_entry(napi, &dev->napi_list, dev_list) {
 			if (!napi->thread) {
 				err = napi_kthread_create(napi);
 				if (err) {
-					threaded = false;
+					threaded = NETDEV_NAPI_THREADED_DISABLED;
 					break;
 				}
 			}
@@ -6871,12 +7022,32 @@ int dev_set_threaded(struct net_device *dev, bool threaded)
 	 * softirq mode will happen in the next round of napi_schedule().
 	 * This should not cause hiccups/stalls to the live traffic.
 	 */
-	list_for_each_entry(napi, &dev->napi_list, dev_list)
-		assign_bit(NAPI_STATE_THREADED, &napi->state, threaded);
+	list_for_each_entry(napi, &dev->napi_list, dev_list) {
+		if (!threaded && napi->thread)
+			napi_stop_kthread(napi);
+		else
+			assign_bit(NAPI_STATE_THREADED, &napi->state, threaded);
+	}
 
 	return err;
 }
-EXPORT_SYMBOL(dev_set_threaded);
+
+/**
+ * netif_threaded_enable() - enable threaded NAPIs
+ * @dev: net_device instance
+ *
+ * Enable threaded mode for the NAPI instances of the device. This may be useful
+ * for devices where multiple NAPI instances get scheduled by a single
+ * interrupt. Threaded NAPI allows moving the NAPI processing to cores other
+ * than the core where IRQ is mapped.
+ *
+ * This function should be called before @dev is registered.
+ */
+void netif_threaded_enable(struct net_device *dev)
+{
+	WARN_ON_ONCE(netif_set_threaded(dev, NETDEV_NAPI_THREADED_ENABLED));
+}
+EXPORT_SYMBOL(netif_threaded_enable);
 
 /**
  * netif_queue_set_napi - Associate queue with the napi
@@ -7092,6 +7263,8 @@ static void napi_restore_config(struct napi_struct *n)
 		napi_hash_add(n);
 		n->config->napi_id = n->napi_id;
 	}
+
+	WARN_ON_ONCE(napi_set_threaded(n, n->config->threaded));
 }
 
 static void napi_save_config(struct napi_struct *n)
@@ -7189,7 +7362,7 @@ void netif_napi_add_weight_locked(struct net_device *dev,
 	 * threaded mode will not be enabled in napi_enable().
 	 */
 	if (dev->threaded && napi_kthread_create(napi))
-		dev->threaded = false;
+		dev->threaded = NETDEV_NAPI_THREADED_DISABLED;
 	netif_napi_set_irq_locked(napi, -1);
 }
 EXPORT_SYMBOL(netif_napi_add_weight_locked);
@@ -7358,8 +7531,7 @@ static int __napi_poll(struct napi_struct *n, bool *repoll)
 	}
 
 	/* Flush too old packets. If HZ < 1000, flush all packets */
-	gro_flush(&n->gro, HZ >= 1000);
-	gro_normal_list(&n->gro);
+	gro_flush_normal(&n->gro, HZ >= 1000);
 
 	/* Some drivers may have called napi_schedule
 	 * prior to exhausting their budget.
@@ -7387,9 +7559,14 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 
 	work = __napi_poll(n, &do_repoll);
 
-	if (do_repoll)
+	if (do_repoll) {
+#if defined(CONFIG_DEBUG_NET)
+		if (unlikely(!napi_is_scheduled(n)))
+			pr_crit("repoll requested for device %s %ps but napi is not scheduled.\n",
+				n->dev->name, n->poll);
+#endif
 		list_add_tail(&n->poll_list, repoll);
-
+	}
 	netpoll_poll_unlock(have);
 
 	return work;
@@ -7515,7 +7692,8 @@ start:
 		 */
 		if (unlikely(budget <= 0 ||
 			     time_after_eq(jiffies, time_limit))) {
-			sd->time_squeeze++;
+			/* Pairs with READ_ONCE() in softnet_seq_show() */
+			WRITE_ONCE(sd->time_squeeze, sd->time_squeeze + 1);
 			break;
 		}
 	}
@@ -9188,8 +9366,16 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
 
 		dev_change_rx_flags(dev, IFF_PROMISC);
 	}
-	if (notify)
+	if (notify) {
+		/* The ops lock is only required to ensure consistent locking
+		 * for `NETDEV_CHANGE` notifiers. This function is sometimes
+		 * called without the lock, even for devices that are ops
+		 * locked, such as in `dev_uc_sync_multiple` when using
+		 * bonding or teaming.
+		 */
+		netdev_ops_assert_locked(dev);
 		__dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL);
+	}
 	return 0;
 }
 
@@ -9283,12 +9469,12 @@ void dev_set_rx_mode(struct net_device *dev)
 }
 
 /**
- *	dev_get_flags - get flags reported to userspace
- *	@dev: device
+ * netif_get_flags() - get flags reported to userspace
+ * @dev: device
  *
- *	Get the combination of flag bits exported through APIs to userspace.
+ * Get the combination of flag bits exported through APIs to userspace.
  */
-unsigned int dev_get_flags(const struct net_device *dev)
+unsigned int netif_get_flags(const struct net_device *dev)
 {
 	unsigned int flags;
 
@@ -9311,7 +9497,7 @@ unsigned int dev_get_flags(const struct net_device *dev)
 
 	return flags;
 }
-EXPORT_SYMBOL(dev_get_flags);
+EXPORT_SYMBOL(netif_get_flags);
 
 int __dev_change_flags(struct net_device *dev, unsigned int flags,
 		       struct netlink_ext_ack *extack)
@@ -9423,7 +9609,7 @@ int netif_change_flags(struct net_device *dev, unsigned int flags,
 	return ret;
 }
 
-int __dev_set_mtu(struct net_device *dev, int new_mtu)
+int __netif_set_mtu(struct net_device *dev, int new_mtu)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 
@@ -9434,7 +9620,7 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu)
 	WRITE_ONCE(dev->mtu, new_mtu);
 	return 0;
 }
-EXPORT_SYMBOL(__dev_set_mtu);
+EXPORT_SYMBOL_NS_GPL(__netif_set_mtu, "NETDEV_INTERNAL");
 
 int dev_validate_mtu(struct net_device *dev, int new_mtu,
 		     struct netlink_ext_ack *extack)
@@ -9453,18 +9639,22 @@ int dev_validate_mtu(struct net_device *dev, int new_mtu,
 }
 
 /**
- *	netif_set_mtu_ext - Change maximum transfer unit
- *	@dev: device
- *	@new_mtu: new transfer unit
- *	@extack: netlink extended ack
+ * netif_set_mtu_ext() - Change maximum transfer unit
+ * @dev: device
+ * @new_mtu: new transfer unit
+ * @extack: netlink extended ack
  *
- *	Change the maximum transfer size of the network device.
+ * Change the maximum transfer size of the network device.
+ *
+ * Return: 0 on success, -errno on failure.
  */
 int netif_set_mtu_ext(struct net_device *dev, int new_mtu,
 		      struct netlink_ext_ack *extack)
 {
 	int err, orig_mtu;
 
+	netdev_ops_assert_locked(dev);
+
 	if (new_mtu == dev->mtu)
 		return 0;
 
@@ -9481,7 +9671,7 @@ int netif_set_mtu_ext(struct net_device *dev, int new_mtu,
 		return err;
 
 	orig_mtu = dev->mtu;
-	err = __dev_set_mtu(dev, new_mtu);
+	err = __netif_set_mtu(dev, new_mtu);
 
 	if (!err) {
 		err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev,
@@ -9491,7 +9681,7 @@ int netif_set_mtu_ext(struct net_device *dev, int new_mtu,
 			/* setting mtu back and notifying everyone again,
 			 * so that they have a chance to revert changes.
 			 */
-			__dev_set_mtu(dev, orig_mtu);
+			__netif_set_mtu(dev, orig_mtu);
 			call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev,
 						     new_mtu);
 		}
@@ -9545,13 +9735,15 @@ void netif_set_group(struct net_device *dev, int new_group)
 }
 
 /**
- *	dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR.
- *	@dev: device
- *	@addr: new address
- *	@extack: netlink extended ack
+ * netif_pre_changeaddr_notify() - Call NETDEV_PRE_CHANGEADDR.
+ * @dev: device
+ * @addr: new address
+ * @extack: netlink extended ack
+ *
+ * Return: 0 on success, -errno on failure.
  */
-int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
-			      struct netlink_ext_ack *extack)
+int netif_pre_changeaddr_notify(struct net_device *dev, const char *addr,
+				struct netlink_ext_ack *extack)
 {
 	struct netdev_notifier_pre_changeaddr_info info = {
 		.info.dev = dev,
@@ -9563,9 +9755,9 @@ int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
 	rc = call_netdevice_notifiers_info(NETDEV_PRE_CHANGEADDR, &info.info);
 	return notifier_to_errno(rc);
 }
-EXPORT_SYMBOL(dev_pre_changeaddr_notify);
+EXPORT_SYMBOL_NS_GPL(netif_pre_changeaddr_notify, "NETDEV_INTERNAL");
 
-int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa,
+int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss,
 			  struct netlink_ext_ack *extack)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -9573,15 +9765,15 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 
 	if (!ops->ndo_set_mac_address)
 		return -EOPNOTSUPP;
-	if (sa->sa_family != dev->type)
+	if (ss->ss_family != dev->type)
 		return -EINVAL;
 	if (!netif_device_present(dev))
 		return -ENODEV;
-	err = dev_pre_changeaddr_notify(dev, sa->sa_data, extack);
+	err = netif_pre_changeaddr_notify(dev, ss->__data, extack);
 	if (err)
 		return err;
-	if (memcmp(dev->dev_addr, sa->sa_data, dev->addr_len)) {
-		err = ops->ndo_set_mac_address(dev, sa);
+	if (memcmp(dev->dev_addr, ss->__data, dev->addr_len)) {
+		err = ops->ndo_set_mac_address(dev, ss);
 		if (err)
 			return err;
 	}
@@ -9593,7 +9785,8 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 
 DECLARE_RWSEM(dev_addr_sem);
 
-int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name)
+/* "sa" is a true struct sockaddr with limited "sa_data" member. */
+int netif_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name)
 {
 	size_t size = sizeof(sa->sa_data_min);
 	struct net_device *dev;
@@ -9619,7 +9812,7 @@ unlock:
 	up_read(&dev_addr_sem);
 	return ret;
 }
-EXPORT_SYMBOL(dev_get_mac_address);
+EXPORT_SYMBOL_NS_GPL(netif_get_mac_address, "NETDEV_INTERNAL");
 
 int netif_change_carrier(struct net_device *dev, bool new_carrier)
 {
@@ -9672,16 +9865,17 @@ int dev_get_phys_port_name(struct net_device *dev,
 }
 
 /**
- *	dev_get_port_parent_id - Get the device's port parent identifier
- *	@dev: network device
- *	@ppid: pointer to a storage for the port's parent identifier
- *	@recurse: allow/disallow recursion to lower devices
+ * netif_get_port_parent_id() - Get the device's port parent identifier
+ * @dev: network device
+ * @ppid: pointer to a storage for the port's parent identifier
+ * @recurse: allow/disallow recursion to lower devices
+ *
+ * Get the devices's port parent identifier.
  *
- *	Get the devices's port parent identifier
+ * Return: 0 on success, -errno on failure.
  */
-int dev_get_port_parent_id(struct net_device *dev,
-			   struct netdev_phys_item_id *ppid,
-			   bool recurse)
+int netif_get_port_parent_id(struct net_device *dev,
+			     struct netdev_phys_item_id *ppid, bool recurse)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	struct netdev_phys_item_id first = { };
@@ -9700,7 +9894,7 @@ int dev_get_port_parent_id(struct net_device *dev,
 		return err;
 
 	netdev_for_each_lower_dev(dev, lower_dev, iter) {
-		err = dev_get_port_parent_id(lower_dev, ppid, true);
+		err = netif_get_port_parent_id(lower_dev, ppid, true);
 		if (err)
 			break;
 		if (!first.id_len)
@@ -9711,7 +9905,7 @@ int dev_get_port_parent_id(struct net_device *dev,
 
 	return err;
 }
-EXPORT_SYMBOL(dev_get_port_parent_id);
+EXPORT_SYMBOL(netif_get_port_parent_id);
 
 /**
  *	netdev_port_same_parent_id - Indicate if two network devices have
@@ -9724,8 +9918,8 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b)
 	struct netdev_phys_item_id a_id = { };
 	struct netdev_phys_item_id b_id = { };
 
-	if (dev_get_port_parent_id(a, &a_id, true) ||
-	    dev_get_port_parent_id(b, &b_id, true))
+	if (netif_get_port_parent_id(a, &a_id, true) ||
+	    netif_get_port_parent_id(b, &b_id, true))
 		return false;
 
 	return netdev_phys_item_id_same(&a_id, &b_id);
@@ -9863,6 +10057,7 @@ int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
 
 	return dev->netdev_ops->ndo_bpf(dev, bpf);
 }
+EXPORT_SYMBOL_GPL(netif_xdp_propagate);
 
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode)
 {
@@ -10258,7 +10453,8 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 		goto unlock;
 	}
 
-	bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog);
+	bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog,
+		      attr->link_create.attach_type);
 	link->dev = dev;
 	link->flags = attr->link_create.flags;
 
@@ -10393,7 +10589,7 @@ static void dev_index_release(struct net *net, int ifindex)
 static bool from_cleanup_net(void)
 {
 #ifdef CONFIG_NET_NS
-	return current == cleanup_net_task;
+	return current == READ_ONCE(cleanup_net_task);
 #else
 	return false;
 #endif
@@ -10624,12 +10820,14 @@ sync_lower:
 			 * *before* calling udp_tunnel_get_rx_info,
 			 * but *after* calling udp_tunnel_drop_rx_info.
 			 */
+			udp_tunnel_nic_lock(dev);
 			if (features & NETIF_F_RX_UDP_TUNNEL_PORT) {
 				dev->features = features;
 				udp_tunnel_get_rx_info(dev);
 			} else {
 				udp_tunnel_drop_rx_info(dev);
 			}
+			udp_tunnel_nic_unlock(dev);
 		}
 
 		if (diff & NETIF_F_HW_VLAN_CTAG_FILTER) {
@@ -11047,8 +11245,7 @@ int register_netdevice(struct net_device *dev)
 	 *	Prevent userspace races by waiting until the network
 	 *	device is fully setup before sending notifications.
 	 */
-	if (!dev->rtnl_link_ops ||
-	    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
+	if (!(dev->rtnl_link_ops && dev->rtnl_link_initializing))
 		rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL);
 
 out:
@@ -11610,7 +11807,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev->priv_len = sizeof_priv;
 
-	ref_tracker_dir_init(&dev->refcnt_tracker, 128, name);
+	ref_tracker_dir_init(&dev->refcnt_tracker, 128, "netdev");
 #ifdef CONFIG_PCPU_DEV_REFCNT
 	dev->pcpu_refcnt = alloc_percpu(int);
 	if (!dev->pcpu_refcnt)
@@ -11832,21 +12029,8 @@ static void netdev_rss_contexts_free(struct net_device *dev)
 
 	mutex_lock(&dev->ethtool->rss_lock);
 	xa_for_each(&dev->ethtool->rss_ctx, context, ctx) {
-		struct ethtool_rxfh_param rxfh;
-
-		rxfh.indir = ethtool_rxfh_context_indir(ctx);
-		rxfh.key = ethtool_rxfh_context_key(ctx);
-		rxfh.hfunc = ctx->hfunc;
-		rxfh.input_xfrm = ctx->input_xfrm;
-		rxfh.rss_context = context;
-		rxfh.rss_delete = true;
-
 		xa_erase(&dev->ethtool->rss_ctx, context);
-		if (dev->ethtool_ops->create_rxfh_context)
-			dev->ethtool_ops->remove_rxfh_context(dev, ctx,
-							      context, NULL);
-		else
-			dev->ethtool_ops->set_rxfh(dev, &rxfh, NULL);
+		dev->ethtool_ops->remove_rxfh_context(dev, ctx, context, NULL);
 		kfree(ctx);
 	}
 	xa_destroy(&dev->ethtool->rss_ctx);
@@ -11931,7 +12115,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 			netdev_lock(dev);
 		}
 	}
-	dev_close_many(&close_head, true);
+	netif_close_many(&close_head, true);
 	/* ... now unlock them and go over the rest. */
 	list_for_each_entry(dev, head, unreg_list) {
 		if (netdev_need_ops_lock(dev))
@@ -11939,7 +12123,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		else
 			list_add_tail(&dev->close_list, &close_head);
 	}
-	dev_close_many(&close_head, true);
+	netif_close_many(&close_head, true);
 
 	list_for_each_entry(dev, head, unreg_list) {
 		/* And unlink it from device chain. */
@@ -11971,8 +12155,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		 */
 		call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 
-		if (!dev->rtnl_link_ops ||
-		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
+		if (!(dev->rtnl_link_ops && dev->rtnl_link_initializing))
 			skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0,
 						     GFP_KERNEL, NULL, 0,
 						     portid, nlh);
@@ -12146,7 +12329,11 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 	netif_close(dev);
 	/* And unlink it from device chain */
 	unlist_netdevice(dev);
-	netdev_unlock_ops(dev);
+
+	if (!netdev_need_ops_lock(dev))
+		netdev_lock(dev);
+	dev->moving_ns = true;
+	netdev_unlock(dev);
 
 	synchronize_net();
 
@@ -12184,7 +12371,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 	move_netdevice_notifiers_dev_net(dev, net);
 
 	/* Actually switch the network namespace */
+	netdev_lock(dev);
 	dev_net_set(dev, net);
+	netdev_unlock(dev);
 	dev->ifindex = new_ifindex;
 
 	if (new_name[0]) {
@@ -12210,7 +12399,11 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 	err = netdev_change_owner(dev, net_old, net);
 	WARN_ON(err);
 
-	netdev_lock_ops(dev);
+	netdev_lock(dev);
+	dev->moving_ns = false;
+	if (!netdev_need_ops_lock(dev))
+		netdev_unlock(dev);
+
 	/* Add the device back in the hashes */
 	list_netdevice(dev);
 	/* Notify protocols, that a new device appeared. */
@@ -12621,7 +12814,7 @@ static int net_page_pool_create(int cpuid)
 		return err;
 	}
 
-	per_cpu(system_page_pool, cpuid) = pp_ptr;
+	per_cpu(system_page_pool.pool, cpuid) = pp_ptr;
 #endif
 	return 0;
 }
@@ -12751,13 +12944,13 @@ out:
 		for_each_possible_cpu(i) {
 			struct page_pool *pp_ptr;
 
-			pp_ptr = per_cpu(system_page_pool, i);
+			pp_ptr = per_cpu(system_page_pool.pool, i);
 			if (!pp_ptr)
 				continue;
 
 			xdp_unreg_page_pool(pp_ptr);
 			page_pool_destroy(pp_ptr);
-			per_cpu(system_page_pool, i) = NULL;
+			per_cpu(system_page_pool.pool, i) = NULL;
 		}
 	}