1 files changed, 108 insertions, 86 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 7ee808eb068e..354d3453b407 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1267,33 +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. 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.
+ * Search for any interface with the given flags.
+ *
+ * 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
@@ -1769,7 +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;
 
@@ -1787,7 +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)
 {
@@ -1795,7 +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);
 	}
 }
@@ -4026,7 +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))) {
@@ -4796,7 +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.
@@ -5747,6 +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;
@@ -5838,8 +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) {
@@ -5937,8 +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:
@@ -5946,7 +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. :-)
 		 */
@@ -6961,16 +6965,38 @@ static void napi_stop_kthread(struct napi_struct *napi)
 	napi->thread = NULL;
 }
 
-int dev_set_threaded(struct net_device *dev, bool threaded)
+int napi_set_threaded(struct napi_struct *napi, bool 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, bool 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) {
@@ -7005,7 +7031,7 @@ int dev_set_threaded(struct net_device *dev, bool threaded)
 
 	return err;
 }
-EXPORT_SYMBOL(dev_set_threaded);
+EXPORT_SYMBOL(netif_set_threaded);
 
 /**
  * netif_queue_set_napi - Associate queue with the napi
@@ -7221,6 +7247,8 @@ 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)
@@ -9426,12 +9454,12 @@ 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;
 
@@ -9454,7 +9482,7 @@ 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)
@@ -9566,7 +9594,7 @@ 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;
 
@@ -9577,7 +9605,7 @@ 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)
@@ -9596,18 +9624,22 @@ 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;
 
@@ -9624,7 +9656,7 @@ 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,
@@ -9634,7 +9666,7 @@ 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);
 		}
@@ -9688,13 +9720,15 @@ 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,
@@ -9706,7 +9740,7 @@ 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_storage *ss,
 			  struct netlink_ext_ack *extack)
@@ -9720,7 +9754,7 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss,
 		return -EINVAL;
 	if (!netif_device_present(dev))
 		return -ENODEV;
-	err = dev_pre_changeaddr_notify(dev, ss->__data, extack);
+	err = netif_pre_changeaddr_notify(dev, ss->__data, extack);
 	if (err)
 		return err;
 	if (memcmp(dev->dev_addr, ss->__data, dev->addr_len)) {
@@ -9737,7 +9771,7 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss,
 DECLARE_RWSEM(dev_addr_sem);
 
 /* "sa" is a true struct sockaddr with limited "sa_data" member. */
-int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name)
+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;
@@ -9763,7 +9797,7 @@ 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)
 {
@@ -9816,16 +9850,17 @@ 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 = { };
@@ -9844,7 +9879,7 @@ 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)
@@ -9855,7 +9890,7 @@ 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
@@ -9868,8 +9903,8 @@ 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);
@@ -11978,21 +12013,8 @@ 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);
@@ -12077,7 +12099,7 @@ 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))
@@ -12085,7 +12107,7 @@ 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. */