Merge tag 'net-6.14-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bluetooth.

  We didn't get netfilter or wireless PRs this week, so next week's PR
  is probably going to be bigger. A healthy dose of fixes for bugs
  introduced in the current release nonetheless.

  Current release - regressions:

   - Bluetooth: always allow SCO packets for user channel

   - af_unix: fix memory leak in unix_dgram_sendmsg()

   - rxrpc:
       - remove redundant peer->mtu_lock causing lockdep splats
       - fix spinlock flavor issues with the peer record hash

   - eth: iavf: fix circular lock dependency with netdev_lock

   - net: use rtnl_net_dev_lock() in
     register_netdevice_notifier_dev_net() RDMA driver register notifier
     after the device

  Current release - new code bugs:

   - ethtool: fix ioctl confusing drivers about desired HDS user config

   - eth: ixgbe: fix media cage present detection for E610 device

  Previous releases - regressions:

   - loopback: avoid sending IP packets without an Ethernet header

   - mptcp: reset connection when MPTCP opts are dropped after join

  Previous releases - always broken:

   - net: better track kernel sockets lifetime

   - ipv6: fix dst ref loop on input in seg6 and rpl lw tunnels

   - phy: qca807x: use right value from DTS for DAC_DSP_BIAS_CURRENT

   - eth: enetc: number of error handling fixes

   - dsa: rtl8366rb: reshuffle the code to fix config / build issue with
     LED support"

* tag 'net-6.14-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (53 commits)
  net: ti: icss-iep: Reject perout generation request
  idpf: fix checksums set in idpf_rx_rsc()
  selftests: drv-net: Check if combined-count exists
  net: ipv6: fix dst ref loop on input in rpl lwt
  net: ipv6: fix dst ref loop on input in seg6 lwt
  usbnet: gl620a: fix endpoint checking in genelink_bind()
  net/mlx5: IRQ, Fix null string in debug print
  net/mlx5: Restore missing trace event when enabling vport QoS
  net/mlx5: Fix vport QoS cleanup on error
  net: mvpp2: cls: Fixed Non IP flow, with vlan tag flow defination.
  af_unix: Fix memory leak in unix_dgram_sendmsg()
  net: Handle napi_schedule() calls from non-interrupt
  net: Clear old fragment checksum value in napi_reuse_skb
  gve: unlink old napi when stopping a queue using queue API
  net: Use rtnl_net_dev_lock() in register_netdevice_notifier_dev_net().
  tcp: Defer ts_recent changes until req is owned
  net: enetc: fix the off-by-one issue in enetc_map_tx_tso_buffs()
  net: enetc: remove the mm_lock from the ENETC v4 driver
  net: enetc: add missing enetc4_link_deinit()
  net: enetc: update UDP checksum when updating originTimestamp field
  ...

6 files changed, 40 insertions, 17 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 1b252e9459fd..30da277c5a6f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2141,21 +2141,15 @@ int register_netdevice_notifier_dev_net(struct net_device *dev,
 					struct notifier_block *nb,
 					struct netdev_net_notifier *nn)
 {
-	struct net *net = dev_net(dev);
 	int err;
 
-	/* rtnl_net_lock() assumes dev is not yet published by
-	 * register_netdevice().
-	 */
-	DEBUG_NET_WARN_ON_ONCE(!list_empty(&dev->dev_list));
-
-	rtnl_net_lock(net);
-	err = __register_netdevice_notifier_net(net, nb, false);
+	rtnl_net_dev_lock(dev);
+	err = __register_netdevice_notifier_net(dev_net(dev), nb, false);
 	if (!err) {
 		nn->nb = nb;
 		list_add(&nn->list, &dev->net_notifier_list);
 	}
-	rtnl_net_unlock(net);
+	rtnl_net_dev_unlock(dev);
 
 	return err;
 }
@@ -4763,7 +4757,7 @@ use_local_napi:
 	 * we have to raise NET_RX_SOFTIRQ.
 	 */
 	if (!sd->in_net_rx_action)
-		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+		raise_softirq_irqoff(NET_RX_SOFTIRQ);
 }
 
 #ifdef CONFIG_RPS
diff --git a/net/core/gro.c b/net/core/gro.c
index 78b320b63174..0ad549b07e03 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -653,6 +653,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb->pkt_type = PACKET_HOST;
 
 	skb->encapsulation = 0;
+	skb->ip_summed = CHECKSUM_NONE;
 	skb_shinfo(skb)->gso_type = 0;
 	skb_shinfo(skb)->gso_size = 0;
 	if (unlikely(skb->slow_gro)) {
diff --git a/net/core/scm.c b/net/core/scm.c
index 4f6a14babe5a..733c0cbd393d 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -282,6 +282,16 @@ efault:
 }
 EXPORT_SYMBOL(put_cmsg);
 
+int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len,
+		     void *data)
+{
+	/* Don't produce truncated CMSGs */
+	if (!msg->msg_control || msg->msg_controllen < CMSG_LEN(len))
+		return -ETOOSMALL;
+
+	return put_cmsg(msg, level, type, len, data);
+}
+
 void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal)
 {
 	struct scm_timestamping64 tss;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7b03b64fdcb2..b1c81687e9d8 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -6033,11 +6033,11 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	skb->offload_fwd_mark = 0;
 	skb->offload_l3_fwd_mark = 0;
 #endif
+	ipvs_reset(skb);
 
 	if (!xnet)
 		return;
 
-	ipvs_reset(skb);
 	skb->mark = 0;
 	skb_clear_tstamp(skb);
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index eae2ae70a2e0..6c0e87f97fa4 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2246,6 +2246,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 			get_net_track(net, &sk->ns_tracker, priority);
 			sock_inuse_add(net, 1);
 		} else {
+			net_passive_inc(net);
 			__netns_tracker_alloc(net, &sk->ns_tracker,
 					      false, priority);
 		}
@@ -2270,6 +2271,7 @@ EXPORT_SYMBOL(sk_alloc);
 static void __sk_destruct(struct rcu_head *head)
 {
 	struct sock *sk = container_of(head, struct sock, sk_rcu);
+	struct net *net = sock_net(sk);
 	struct sk_filter *filter;
 
 	if (sk->sk_destruct)
@@ -2301,14 +2303,28 @@ static void __sk_destruct(struct rcu_head *head)
 	put_cred(sk->sk_peer_cred);
 	put_pid(sk->sk_peer_pid);
 
-	if (likely(sk->sk_net_refcnt))
-		put_net_track(sock_net(sk), &sk->ns_tracker);
-	else
-		__netns_tracker_free(sock_net(sk), &sk->ns_tracker, false);
-
+	if (likely(sk->sk_net_refcnt)) {
+		put_net_track(net, &sk->ns_tracker);
+	} else {
+		__netns_tracker_free(net, &sk->ns_tracker, false);
+		net_passive_dec(net);
+	}
 	sk_prot_free(sk->sk_prot_creator, sk);
 }
 
+void sk_net_refcnt_upgrade(struct sock *sk)
+{
+	struct net *net = sock_net(sk);
+
+	WARN_ON_ONCE(sk->sk_net_refcnt);
+	__netns_tracker_free(net, &sk->ns_tracker, false);
+	net_passive_dec(net);
+	sk->sk_net_refcnt = 1;
+	get_net_track(net, &sk->ns_tracker, GFP_KERNEL);
+	sock_inuse_add(net, 1);
+}
+EXPORT_SYMBOL_GPL(sk_net_refcnt_upgrade);
+
 void sk_destruct(struct sock *sk)
 {
 	bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE);
@@ -2405,6 +2421,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 * is not properly dismantling its kernel sockets at netns
 		 * destroy time.
 		 */
+		net_passive_inc(sock_net(newsk));
 		__netns_tracker_alloc(sock_net(newsk), &newsk->ns_tracker,
 				      false, priority);
 	}
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index ad2741f1346a..c7769ee0d9c5 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -34,6 +34,7 @@ static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
 static int max_skb_frags = MAX_SKB_FRAGS;
 static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE;
+static int netdev_budget_usecs_min = 2 * USEC_PER_SEC / HZ;
 
 static int net_msg_warn;	/* Unused, but still a sysctl */
 
@@ -587,7 +588,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
+		.extra1		= &netdev_budget_usecs_min,
 	},
 	{
 		.procname	= "fb_tunnels_only_for_init_net",