Merge tag 'net-6.18-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from CAN

  Current release - regressions:

    - udp: do not use skb_release_head_state() before
      skb_attempt_defer_free()

    - gro_cells: use nested-BH locking for gro_cell

    - dpll: zl3073x: increase maximum size of flash utility

  Previous releases - regressions:

    - core: fix lockdep splat on device unregister

    - tcp: fix tcp_tso_should_defer() vs large RTT

    - tls:
        - don't rely on tx_work during send()
        - wait for pending async decryptions if tls_strp_msg_hold fails

    - can: j1939: add missing calls in NETDEV_UNREGISTER notification
      handler

    - eth: lan78xx: fix lost EEPROM write timeout in
      lan78xx_write_raw_eeprom

  Previous releases - always broken:

    - ip6_tunnel: prevent perpetual tunnel growth

    - dpll: zl3073x: handle missing or corrupted flash configuration

    - can: m_can: fix pm_runtime and CAN state handling

    - eth:
        - ixgbe: fix too early devlink_free() in ixgbe_remove()
        - ixgbevf: fix mailbox API compatibility
        - gve: Check valid ts bit on RX descriptor before hw timestamping
        - idpf: cleanup remaining SKBs in PTP flows
        - r8169: fix packet truncation after S4 resume on RTL8168H/RTL8111H"

* tag 'net-6.18-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (50 commits)
  udp: do not use skb_release_head_state() before skb_attempt_defer_free()
  net: usb: lan78xx: fix use of improperly initialized dev->chipid in lan78xx_reset
  netdevsim: set the carrier when the device goes up
  selftests: tls: add test for short splice due to full skmsg
  selftests: net: tls: add tests for cmsg vs MSG_MORE
  tls: don't rely on tx_work during send()
  tls: wait for pending async decryptions if tls_strp_msg_hold fails
  tls: always set record_type in tls_process_cmsg
  tls: wait for async encrypt in case of error during latter iterations of sendmsg
  tls: trim encrypted message to match the plaintext on short splice
  tg3: prevent use of uninitialized remote_adv and local_adv variables
  MAINTAINERS: new entry for IPv6 IOAM
  gve: Check valid ts bit on RX descriptor before hw timestamping
  net: core: fix lockdep splat on device unregister
  MAINTAINERS: add myself as maintainer for b53
  selftests: net: check jq command is supported
  net: airoha: Take into account out-of-order tx completions in airoha_dev_xmit()
  tcp: fix tcp_tso_should_defer() vs large RTT
  r8152: add error handling in rtl8152_driver_init
  usbnet: Fix using smp_processor_id() in preemptible code warnings
  ...

3 files changed, 46 insertions, 5 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index a64cef2c537e..2acfa44927da 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -12176,6 +12176,35 @@ static void dev_memory_provider_uninstall(struct net_device *dev)
 	}
 }
 
+/* devices must be UP and netdev_lock()'d */
+static void netif_close_many_and_unlock(struct list_head *close_head)
+{
+	struct net_device *dev, *tmp;
+
+	netif_close_many(close_head, false);
+
+	/* ... now unlock them */
+	list_for_each_entry_safe(dev, tmp, close_head, close_list) {
+		netdev_unlock(dev);
+		list_del_init(&dev->close_list);
+	}
+}
+
+static void netif_close_many_and_unlock_cond(struct list_head *close_head)
+{
+#ifdef CONFIG_LOCKDEP
+	/* We can only track up to MAX_LOCK_DEPTH locks per task.
+	 *
+	 * Reserve half the available slots for additional locks possibly
+	 * taken by notifiers and (soft)irqs.
+	 */
+	unsigned int limit = MAX_LOCK_DEPTH / 2;
+
+	if (lockdep_depth(current) > limit)
+		netif_close_many_and_unlock(close_head);
+#endif
+}
+
 void unregister_netdevice_many_notify(struct list_head *head,
 				      u32 portid, const struct nlmsghdr *nlh)
 {
@@ -12208,17 +12237,18 @@ void unregister_netdevice_many_notify(struct list_head *head,
 
 	/* If device is running, close it first. Start with ops locked... */
 	list_for_each_entry(dev, head, unreg_list) {
+		if (!(dev->flags & IFF_UP))
+			continue;
 		if (netdev_need_ops_lock(dev)) {
 			list_add_tail(&dev->close_list, &close_head);
 			netdev_lock(dev);
 		}
+		netif_close_many_and_unlock_cond(&close_head);
 	}
-	netif_close_many(&close_head, true);
-	/* ... now unlock them and go over the rest. */
+	netif_close_many_and_unlock(&close_head);
+	/* ... now go over the rest. */
 	list_for_each_entry(dev, head, unreg_list) {
-		if (netdev_need_ops_lock(dev))
-			netdev_unlock(dev);
-		else
+		if (!netdev_need_ops_lock(dev))
 			list_add_tail(&dev->close_list, &close_head);
 	}
 	netif_close_many(&close_head, true);
diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index ff8e5b64bf6b..b43911562f4d 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -8,11 +8,13 @@
 struct gro_cell {
 	struct sk_buff_head	napi_skbs;
 	struct napi_struct	napi;
+	local_lock_t		bh_lock;
 };
 
 int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
+	bool have_bh_lock = false;
 	struct gro_cell *cell;
 	int res;
 
@@ -25,6 +27,8 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 		goto unlock;
 	}
 
+	local_lock_nested_bh(&gcells->cells->bh_lock);
+	have_bh_lock = true;
 	cell = this_cpu_ptr(gcells->cells);
 
 	if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(net_hotdata.max_backlog)) {
@@ -39,6 +43,9 @@ drop:
 	if (skb_queue_len(&cell->napi_skbs) == 1)
 		napi_schedule(&cell->napi);
 
+	if (have_bh_lock)
+		local_unlock_nested_bh(&gcells->cells->bh_lock);
+
 	res = NET_RX_SUCCESS;
 
 unlock:
@@ -54,6 +61,7 @@ static int gro_cell_poll(struct napi_struct *napi, int budget)
 	struct sk_buff *skb;
 	int work_done = 0;
 
+	__local_lock_nested_bh(&cell->bh_lock);
 	while (work_done < budget) {
 		skb = __skb_dequeue(&cell->napi_skbs);
 		if (!skb)
@@ -64,6 +72,7 @@ static int gro_cell_poll(struct napi_struct *napi, int budget)
 
 	if (work_done < budget)
 		napi_complete_done(napi, work_done);
+	__local_unlock_nested_bh(&cell->bh_lock);
 	return work_done;
 }
 
@@ -79,6 +88,7 @@ int gro_cells_init(struct gro_cells *gcells, struct net_device *dev)
 		struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
 
 		__skb_queue_head_init(&cell->napi_skbs);
+		local_lock_init(&cell->bh_lock);
 
 		set_bit(NAPI_STATE_NO_BUSY_POLL, &cell->napi.state);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index bc12790017b0..6be01454f262 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -7200,6 +7200,7 @@ nodefer:	kfree_skb_napi_cache(skb);
 
 	DEBUG_NET_WARN_ON_ONCE(skb_dst(skb));
 	DEBUG_NET_WARN_ON_ONCE(skb->destructor);
+	DEBUG_NET_WARN_ON_ONCE(skb_nfct(skb));
 
 	sdn = per_cpu_ptr(net_hotdata.skb_defer_nodes, cpu) + numa_node_id();