Merge tag 'net-6.15-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from netfilter.

  Current release - regressions:

    - core: hold instance lock during NETDEV_CHANGE

    - rtnetlink: fix bad unlock balance in do_setlink()

    - ipv6:
       - fix null-ptr-deref in addrconf_add_ifaddr()
       - align behavior across nexthops during path selection

  Previous releases - regressions:

    - sctp: prevent transport UaF in sendmsg

    - mptcp: only inc MPJoinAckHMacFailure for HMAC failures

  Previous releases - always broken:

    - sched:
       - make ->qlen_notify() idempotent
       - ensure sufficient space when sending filter netlink notifications
       - sch_sfq: really don't allow 1 packet limit

    - netfilter: fix incorrect avx2 match of 5th field octet

    - tls: explicitly disallow disconnect

    - eth: octeontx2-pf: fix VF root node parent queue priority"

* tag 'net-6.15-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (38 commits)
  ethtool: cmis_cdb: Fix incorrect read / write length extension
  selftests: netfilter: add test case for recent mismatch bug
  nft_set_pipapo: fix incorrect avx2 match of 5th field octet
  net: ppp: Add bound checking for skb data on ppp_sync_txmung
  net: Fix null-ptr-deref by sock_lock_init_class_and_name() and rmmod.
  ipv6: Align behavior across nexthops during path selection
  net: phy: allow MDIO bus PM ops to start/stop state machine for phylink-controlled PHY
  net: phy: move phy_link_change() prior to mdio_bus_phy_may_suspend()
  selftests/tc-testing: sfq: check that a derived limit of 1 is rejected
  net_sched: sch_sfq: move the limit validation
  net_sched: sch_sfq: use a temporary work area for validating configuration
  net: libwx: handle page_pool_dev_alloc_pages error
  selftests: mptcp: validate MPJoin HMacFailure counters
  mptcp: only inc MPJoinAckHMacFailure for HMAC failures
  rtnetlink: Fix bad unlock balance in do_setlink().
  net: ethtool: Don't call .cleanup_data when prepare_data fails
  tc: Ensure we have enough buffer space when sending filter netlink notifications
  net: libwx: Fix the wrong Rx descriptor field
  octeontx2-pf: qos: fix VF root node parent queue index
  selftests: tls: check that disconnect does nothing
  ...

6 files changed, 56 insertions, 23 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 0608605cfc242..75e104322ad52 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1518,15 +1518,7 @@ void netdev_features_change(struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_features_change);
 
-/**
- *	netdev_state_change - device changes state
- *	@dev: device to cause notification
- *
- *	Called to indicate a device has changed state. This function calls
- *	the notifier chains for netdev_chain and sends a NEWLINK message
- *	to the routing socket.
- */
-void netdev_state_change(struct net_device *dev)
+void netif_state_change(struct net_device *dev)
 {
 	if (dev->flags & IFF_UP) {
 		struct netdev_notifier_change_info change_info = {
@@ -1538,7 +1530,6 @@ void netdev_state_change(struct net_device *dev)
 		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL, 0, NULL);
 	}
 }
-EXPORT_SYMBOL(netdev_state_change);
 
 /**
  * __netdev_notify_peers - notify network peers about existence of @dev,
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 90bafb0b1b8c3..90898cd540ced 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -327,3 +327,19 @@ int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_xdp_propagate);
+
+/**
+ * netdev_state_change() - device changes state
+ * @dev: device to cause notification
+ *
+ * Called to indicate a device has changed state. This function calls
+ * the notifier chains for netdev_chain and sends a NEWLINK message
+ * to the routing socket.
+ */
+void netdev_state_change(struct net_device *dev)
+{
+	netdev_lock_ops(dev);
+	netif_state_change(dev);
+	netdev_unlock_ops(dev);
+}
+EXPORT_SYMBOL(netdev_state_change);
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index cb04ef2b9807c..864f3bbc3a4c5 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -183,7 +183,7 @@ static void linkwatch_do_dev(struct net_device *dev)
 		else
 			dev_deactivate(dev);
 
-		netdev_state_change(dev);
+		netif_state_change(dev);
 	}
 	/* Note: our callers are responsible for calling netdev_tracker_free().
 	 * This is the reason we use __dev_put() instead of dev_put().
@@ -240,7 +240,9 @@ static void __linkwatch_run_queue(int urgent_only)
 		 */
 		netdev_tracker_free(dev, &dev->linkwatch_dev_tracker);
 		spin_unlock_irq(&lweventlist_lock);
+		netdev_lock_ops(dev);
 		linkwatch_do_dev(dev);
+		netdev_unlock_ops(dev);
 		do_dev--;
 		spin_lock_irq(&lweventlist_lock);
 	}
@@ -253,25 +255,41 @@ static void __linkwatch_run_queue(int urgent_only)
 	spin_unlock_irq(&lweventlist_lock);
 }
 
-void linkwatch_sync_dev(struct net_device *dev)
+static bool linkwatch_clean_dev(struct net_device *dev)
 {
 	unsigned long flags;
-	int clean = 0;
+	bool clean = false;
 
 	spin_lock_irqsave(&lweventlist_lock, flags);
 	if (!list_empty(&dev->link_watch_list)) {
 		list_del_init(&dev->link_watch_list);
-		clean = 1;
+		clean = true;
 		/* We must release netdev tracker under
 		 * the spinlock protection.
 		 */
 		netdev_tracker_free(dev, &dev->linkwatch_dev_tracker);
 	}
 	spin_unlock_irqrestore(&lweventlist_lock, flags);
-	if (clean)
+
+	return clean;
+}
+
+void __linkwatch_sync_dev(struct net_device *dev)
+{
+	netdev_ops_assert_locked(dev);
+
+	if (linkwatch_clean_dev(dev))
 		linkwatch_do_dev(dev);
 }
 
+void linkwatch_sync_dev(struct net_device *dev)
+{
+	if (linkwatch_clean_dev(dev)) {
+		netdev_lock_ops(dev);
+		linkwatch_do_dev(dev);
+		netdev_unlock_ops(dev);
+	}
+}
 
 /* Must be called with the rtnl semaphore held */
 void linkwatch_run_queue(void)
diff --git a/net/core/lock_debug.c b/net/core/lock_debug.c
index b7f22dc92a6f3..941e26c1343de 100644
--- a/net/core/lock_debug.c
+++ b/net/core/lock_debug.c
@@ -20,11 +20,11 @@ int netdev_debug_event(struct notifier_block *nb, unsigned long event,
 	switch (cmd) {
 	case NETDEV_REGISTER:
 	case NETDEV_UP:
+	case NETDEV_CHANGE:
 		netdev_ops_assert_locked(dev);
 		fallthrough;
 	case NETDEV_DOWN:
 	case NETDEV_REBOOT:
-	case NETDEV_CHANGE:
 	case NETDEV_UNREGISTER:
 	case NETDEV_CHANGEMTU:
 	case NETDEV_CHANGEADDR:
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c238528350506..39a5b72e861f6 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1043,7 +1043,7 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
 }
 EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
 
-void netdev_set_operstate(struct net_device *dev, int newstate)
+void netif_set_operstate(struct net_device *dev, int newstate)
 {
 	unsigned int old = READ_ONCE(dev->operstate);
 
@@ -1052,9 +1052,9 @@ void netdev_set_operstate(struct net_device *dev, int newstate)
 			return;
 	} while (!try_cmpxchg(&dev->operstate, &old, newstate));
 
-	netdev_state_change(dev);
+	netif_state_change(dev);
 }
-EXPORT_SYMBOL(netdev_set_operstate);
+EXPORT_SYMBOL(netif_set_operstate);
 
 static void set_operstate(struct net_device *dev, unsigned char transition)
 {
@@ -1080,7 +1080,7 @@ static void set_operstate(struct net_device *dev, unsigned char transition)
 		break;
 	}
 
-	netdev_set_operstate(dev, operstate);
+	netif_set_operstate(dev, operstate);
 }
 
 static unsigned int rtnl_dev_get_flags(const struct net_device *dev)
@@ -3027,7 +3027,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 
 	err = validate_linkmsg(dev, tb, extack);
 	if (err < 0)
-		goto errout;
+		return err;
 
 	if (tb[IFLA_IFNAME])
 		nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
@@ -3396,7 +3396,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 errout:
 	if (status & DO_SETLINK_MODIFIED) {
 		if ((status & DO_SETLINK_NOTIFY) == DO_SETLINK_NOTIFY)
-			netdev_state_change(dev);
+			netif_state_change(dev);
 
 		if (err < 0)
 			net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n",
@@ -3676,8 +3676,11 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 				nla_len(tb[IFLA_BROADCAST]));
 	if (tb[IFLA_TXQLEN])
 		dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]);
-	if (tb[IFLA_OPERSTATE])
+	if (tb[IFLA_OPERSTATE]) {
+		netdev_lock_ops(dev);
 		set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
+		netdev_unlock_ops(dev);
+	}
 	if (tb[IFLA_LINKMODE])
 		dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]);
 	if (tb[IFLA_GROUP])
diff --git a/net/core/sock.c b/net/core/sock.c
index f67a3c5b09884..e54449c9ab0ba 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2130,6 +2130,8 @@ lenout:
  */
 static inline void sock_lock_init(struct sock *sk)
 {
+	sk_owner_clear(sk);
+
 	if (sk->sk_kern_sock)
 		sock_lock_init_class_and_name(
 			sk,
@@ -2226,6 +2228,9 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
 	cgroup_sk_free(&sk->sk_cgrp_data);
 	mem_cgroup_sk_free(sk);
 	security_sk_free(sk);
+
+	sk_owner_put(sk);
+
 	if (slab != NULL)
 		kmem_cache_free(slab, sk);
 	else