Merge tag 'net-7.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from netfilter and IPsec.

  Current release - regressions:

   - do not acquire dev->tx_global_lock in netdev_watchdog_up()

   - ethtool: keep rtnl_lock for ops using ethtool_op_get_link()

   - fix deadlock in nested UP notifier events

  Current release - new code bugs:

   - eth:
      - cn20k: fix subbank free list indexing for search order
      - airoha: fix BQL underflow in shared QDMA TX ring

  Previous releases - regressions:

   - netfilter:
     - flowtable: fix offloaded ct timeout never being extended
     - nf_conncount: prevent connlimit drops for early confirmed ct

  Previous releases - always broken:

   - require CAP_NET_ADMIN in the originating netns when modifying
     cross-netns devices

   - report NAPI thread PID in the caller's pid namespace

   - mac802154: fix dirty frag in in-place crypto for IOT radios

   - sctp: hold socket lock when dumping endpoints in sctp_diag, avoid
     an overflow

   - eth: gve: fix header buffer corruption with header-split and HW-GRO

   - af_key: initialize alg_key_len for IPComp states, prevent OOB read"

* tag 'net-7.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (213 commits)
  selftests: bonding: add a test for VLAN propagation over a bonded real device
  vlan: defer real device state propagation to netdev_work
  net: add the driver-facing netdev_work scheduling API
  net: turn the rx_mode work into a generic netdev_work facility
  net: ethtool: keep rtnl_lock for ops using ethtool_op_get_link()
  rxrpc: Fix rxrpc_rotate_tx_rotate() to check there's something to rotate
  rxrpc: Fix leak of released call in recvmsg(MSG_PEEK)
  rxrpc: Fix socket notification race
  rxrpc: Fix potential infinite loop in rxrpc_recvmsg()
  rxrpc: Fix oob challenge leak in cleanup after notification failure
  rxrpc: Fix the reception of a reply packet before data transmission
  afs: Fix uncancelled rxrpc OOB message handler
  afs: Fix further netns teardown to cancel the preallocation charger
  rxrpc: Fix double unlock in rxrpc_recvmsg()
  rxrpc: Fix leak of connection from OOB challenge
  rxrpc: Fix ACKALL packet handling
  net: hns3: differentiate autoneg default values between copper and fiber
  net: hns3: fix permanent link down deadlock after reset
  net: hns3: refactor MAC autoneg and speed configuration
  net: hns3: unify copper port ksettings configuration path
  ...

10 files changed, 30 insertions, 13 deletions

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 208dd48012d9..3efdfb4ffa21 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1457,6 +1457,9 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 	__u32 fwmark = t->fwmark;
 	int err;
 
+	if (!rtnl_dev_link_net_capable(dev, t->net))
+		return -EPERM;
+
 	err = ipgre_newlink_encap_setup(dev, data);
 	if (err)
 		return err;
@@ -1486,6 +1489,9 @@ static int erspan_changelink(struct net_device *dev, struct nlattr *tb[],
 	__u32 fwmark = t->fwmark;
 	int err;
 
+	if (!rtnl_dev_link_net_capable(dev, t->net))
+		return -EPERM;
+
 	err = ipgre_newlink_encap_setup(dev, data);
 	if (err)
 		return err;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 3b4e9b8af044..e6dd1e5b8c32 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1116,8 +1116,8 @@ alloc_new_skb:
 				  !(rt->dst.dev->features & NETIF_F_SG)))
 				alloclen = fraglen;
 			else {
-				alloclen = fragheaderlen + transhdrlen;
-				pagedlen = datalen - transhdrlen;
+				alloclen = fragheaderlen + transhdrlen + fraggap;
+				pagedlen = datalen - transhdrlen - fraggap;
 			}
 
 			alloclen += alloc_extra;
@@ -1164,9 +1164,6 @@ alloc_new_skb:
 			}
 
 			copy = datalen - transhdrlen - fraggap - pagedlen;
-			/* [!] NOTE: copy will be negative if pagedlen>0
-			 * because then the equation reduces to -fraggap.
-			 */
 			if (copy > 0 &&
 			    INDIRECT_CALL_1(getfrag, ip_generic_getfrag,
 					    from, data + transhdrlen, offset,
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 95b6bb78fcd2..3b80929994a0 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -596,6 +596,9 @@ static int vti_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct ip_tunnel_parm_kern p;
 	__u32 fwmark = t->fwmark;
 
+	if (!rtnl_dev_link_net_capable(dev, t->net))
+		return -EPERM;
+
 	vti_netlink_parms(data, &p, &fwmark);
 	return ip_tunnel_changelink(dev, tb, &p, fwmark);
 }
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 4f89a03e0b49..b643194f57d2 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -494,6 +494,9 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
 	bool collect_md;
 	__u32 fwmark = t->fwmark;
 
+	if (!rtnl_dev_link_net_capable(dev, t->net))
+		return -EPERM;
+
 	if (ip_tunnel_netlink_encap_parms(data, &ipencap)) {
 		int err = ip_tunnel_encap_setup(t, &ipencap);
 
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index fecf6621f679..4626dc46808f 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -89,7 +89,7 @@ static bool nf_skb_is_icmp_unreach(const struct sk_buff *skb)
 	if (iph->protocol != IPPROTO_ICMP)
 		return false;
 
-	thoff = skb_network_offset(skb) + sizeof(*iph);
+	thoff = skb_network_offset(skb) + ip_hdrlen(skb);
 
 	tp = skb_header_pointer(skb,
 				thoff + offsetof(struct icmphdr, type),
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index c0e85cc171ae..ca1180dba1de 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1058,7 +1058,9 @@ static struct ctl_table ipv4_net_table[] = {
 		.data		= &init_net.ipv4.sysctl_tcp_reordering,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= &init_net.ipv4.sysctl_tcp_max_reordering,
 	},
 	{
 		.procname	= "tcp_retries1",
@@ -1293,7 +1295,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.data		= &init_net.ipv4.sysctl_tcp_max_reordering,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "tcp_dsack",
@@ -1676,6 +1679,9 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 				 */
 				table[i].mode &= ~0222;
 			}
+			if (table[i].extra2 >= (void *)&init_net.ipv4 &&
+			    table[i].extra2 < (void *)(&init_net.ipv4 + 1))
+				table[i].extra2 += (void *)net - (void *)&init_net;
 		}
 	}
 
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 2f69bcecae78..a56bb79e15e0 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -1747,6 +1747,10 @@ static int tcp_ao_delete_key(struct sock *sk, struct tcp_ao_info *ao_info,
 	 * them and we can just free all resources in RCU fashion.
 	 */
 	if (del_async) {
+		if (ao_info->current_key == key)
+			WRITE_ONCE(ao_info->current_key, NULL);
+		if (ao_info->rnext_key == key)
+			WRITE_ONCE(ao_info->rnext_key, NULL);
 		atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc);
 		call_rcu(&key->rcu, tcp_ao_key_free_rcu);
 		return 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 26dd751ec72a..00ec4b5900f2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2688,7 +2688,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	struct sk_buff *skb, *nskb, *next;
 	struct net *net = sock_net(sk);
 	int probe_size;
-	int size_needed;
+	u64 size_needed;
 	int copy, len;
 	int mss_now;
 	int interval;
@@ -2712,7 +2712,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	mss_now = tcp_current_mss(sk);
 	probe_size = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high +
 				    icsk->icsk_mtup.search_low) >> 1);
-	size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
+	size_needed = probe_size + (tp->reordering + 1) * (u64)tp->mss_cache;
 	interval = icsk->icsk_mtup.search_high - icsk->icsk_mtup.search_low;
 	/* When misfortune happens, we are reprobing actively,
 	 * and then reprobe timer has expired. We stick with current
diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c
index 9944ed923ddf..3b32a0afa979 100644
--- a/net/ipv4/udp_tunnel_nic.c
+++ b/net/ipv4/udp_tunnel_nic.c
@@ -301,7 +301,7 @@ __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn)
 static void
 udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn)
 {
-	if (!utn->need_sync)
+	if (!utn->need_sync || utn->work_pending)
 		return;
 
 	queue_work(udp_tunnel_nic_workqueue, &utn->work);
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index c2eac844bcdb..f6f2a8ef3f88 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -76,8 +76,6 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
 	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
 		dev_net(dev), NULL, skb, dev, NULL,
 		xfrm4_rcv_encap_finish);
-	if (async)
-		dev_put(dev);
 	return 0;
 }