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
  ...

10 files changed, 91 insertions, 38 deletions

diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index 3706a872ecaf..a93af55df5fd 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -378,6 +378,8 @@ static int j1939_netdev_notify(struct notifier_block *nb,
 		j1939_ecu_unmap_all(priv);
 		break;
 	case NETDEV_UNREGISTER:
+		j1939_cancel_active_session(priv, NULL);
+		j1939_sk_netdev_event_netdown(priv);
 		j1939_sk_netdev_event_unregister(priv);
 		break;
 	}
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();
 
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index aaeb5d16f0c9..158a30ae7c5f 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -568,20 +568,6 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	return 0;
 }
 
-static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom)
-{
-	/* we must cap headroom to some upperlimit, else pskb_expand_head
-	 * will overflow header offsets in skb_headers_offset_update().
-	 */
-	static const unsigned int max_allowed = 512;
-
-	if (headroom > max_allowed)
-		headroom = max_allowed;
-
-	if (headroom > READ_ONCE(dev->needed_headroom))
-		WRITE_ONCE(dev->needed_headroom, headroom);
-}
-
 void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		       u8 proto, int tunnel_hlen)
 {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bb3576ac0ad7..b94efb3050d2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2369,7 +2369,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 				 u32 max_segs)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 send_win, cong_win, limit, in_flight;
+	u32 send_win, cong_win, limit, in_flight, threshold;
+	u64 srtt_in_ns, expected_ack, how_far_is_the_ack;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *head;
 	int win_divisor;
@@ -2431,9 +2432,19 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	head = tcp_rtx_queue_head(sk);
 	if (!head)
 		goto send_now;
-	delta = tp->tcp_clock_cache - head->tstamp;
-	/* If next ACK is likely to come too late (half srtt), do not defer */
-	if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0)
+
+	srtt_in_ns = (u64)(NSEC_PER_USEC >> 3) * tp->srtt_us;
+	/* When is the ACK expected ? */
+	expected_ack = head->tstamp + srtt_in_ns;
+	/* How far from now is the ACK expected ? */
+	how_far_is_the_ack = expected_ack - tp->tcp_clock_cache;
+
+	/* If next ACK is likely to come too late,
+	 * ie in more than min(1ms, half srtt), do not defer.
+	 */
+	threshold = min(srtt_in_ns >> 1, NSEC_PER_MSEC);
+
+	if ((s64)(how_far_is_the_ack - threshold) > 0)
 		goto send_now;
 
 	/* Ok, it looks like it is advisable to defer.
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 95241093b7f0..30dfbf73729d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1851,8 +1851,6 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
 		sk_peek_offset_bwd(sk, len);
 
 	if (!skb_shared(skb)) {
-		if (unlikely(udp_skb_has_head_state(skb)))
-			skb_release_head_state(skb);
 		skb_attempt_defer_free(skb);
 		return;
 	}
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 3262e81223df..6405072050e0 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1257,8 +1257,7 @@ route_lookup:
 	 */
 	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr)
 			+ dst->header_len + t->hlen;
-	if (max_headroom > READ_ONCE(dev->needed_headroom))
-		WRITE_ONCE(dev->needed_headroom, max_headroom);
+	ip_tunnel_adj_headroom(dev, max_headroom);
 
 	err = ip6_tnl_encap(skb, t, &proto, fl6);
 	if (err)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index a3ccb3135e51..39a2ab47fe72 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -255,12 +255,9 @@ int tls_process_cmsg(struct sock *sk, struct msghdr *msg,
 			if (msg->msg_flags & MSG_MORE)
 				return -EINVAL;
 
-			rc = tls_handle_open_record(sk, msg->msg_flags);
-			if (rc)
-				return rc;
-
 			*record_type = *(unsigned char *)CMSG_DATA(cmsg);
-			rc = 0;
+
+			rc = tls_handle_open_record(sk, msg->msg_flags);
 			break;
 		default:
 			return -EINVAL;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index daac9fd4be7e..d17135369980 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1054,7 +1054,7 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
 			if (ret == -EINPROGRESS)
 				num_async++;
 			else if (ret != -EAGAIN)
-				goto send_end;
+				goto end;
 		}
 	}
 
@@ -1112,8 +1112,11 @@ alloc_encrypted:
 				goto send_end;
 			tls_ctx->pending_open_record_frags = true;
 
-			if (sk_msg_full(msg_pl))
+			if (sk_msg_full(msg_pl)) {
 				full_record = true;
+				sk_msg_trim(sk, msg_en,
+					    msg_pl->sg.size + prot->overhead_size);
+			}
 
 			if (full_record || eor)
 				goto copied;
@@ -1149,6 +1152,13 @@ alloc_encrypted:
 				} else if (ret != -EAGAIN)
 					goto send_end;
 			}
+
+			/* Transmit if any encryptions have completed */
+			if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
+				cancel_delayed_work(&ctx->tx_work.work);
+				tls_tx_records(sk, msg->msg_flags);
+			}
+
 			continue;
 rollback_iter:
 			copied -= try_to_copy;
@@ -1204,6 +1214,12 @@ copied:
 					goto send_end;
 				}
 			}
+
+			/* Transmit if any encryptions have completed */
+			if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
+				cancel_delayed_work(&ctx->tx_work.work);
+				tls_tx_records(sk, msg->msg_flags);
+			}
 		}
 
 		continue;
@@ -1223,8 +1239,9 @@ trim_sgl:
 			goto alloc_encrypted;
 	}
 
+send_end:
 	if (!num_async) {
-		goto send_end;
+		goto end;
 	} else if (num_zc || eor) {
 		int err;
 
@@ -1242,7 +1259,7 @@ trim_sgl:
 		tls_tx_records(sk, msg->msg_flags);
 	}
 
-send_end:
+end:
 	ret = sk_stream_error(sk, msg->msg_flags, ret);
 	return copied > 0 ? copied : ret;
 }
@@ -1637,8 +1654,10 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov,
 
 	if (unlikely(darg->async)) {
 		err = tls_strp_msg_hold(&ctx->strp, &ctx->async_hold);
-		if (err)
-			__skb_queue_tail(&ctx->async_hold, darg->skb);
+		if (err) {
+			err = tls_decrypt_async_wait(ctx);
+			darg->async = false;
+		}
 		return err;
 	}