Merge tag 'net-5.11-rc3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull more networking fixes from Jakub Kicinski:
 "Slightly lighter pull request to get back into the Thursday cadence.

  Current release - always broken:

   - can: mcp251xfd: fix Tx/Rx ring buffer driver race conditions

   - dsa: hellcreek: fix led_classdev build errors

  Previous releases - regressions:

   - ipv6: fib: flush exceptions when purging route to avoid netdev
     reference leak

   - ip_tunnels: fix pmtu check in nopmtudisc mode

   - ip: always refragment ip defragmented packets to avoid MTU issues
     when forwarding through tunnels, correct "packet too big" message
     is prohibitively tricky to generate

   - s390/qeth: fix locking for discipline setup / removal and during
     recovery to prevent both deadlocks and races

   - mlx5: Use port_num 1 instead of 0 when delete a RoCE address

  Previous releases - always broken:

   - cdc_ncm: correct overhead calculation in delayed_ndp_size to
     prevent out of bound accesses with Huawei 909s-120 LTE module

   - fix stmmac dwmac-sun8i suspend/resume:
           - PHY being left powered off
           - MAC syscon configuration being reset
           - reference to the reset controller being improperly dropped

   - qrtr: fix null-ptr-deref in qrtr_ns_remove

   - can: tcan4x5x: fix bittiming const, use common bittiming from m_can
     driver

   - mlx5e: CT: Use per flow counter when CT flow accounting is enabled

   - mlx5e: Fix SWP offsets when vlan inserted by driver

  Misc:

   - bpf: Fix a task_iter bug caused by a bpf -> net merge conflict
     resolution

  And the usual many fixes to various error paths"

* tag 'net-5.11-rc3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (69 commits)
  net: dsa: lantiq_gswip: Exclude RMII from modes that report 1 GbE
  s390/qeth: fix L2 header access in qeth_l3_osa_features_check()
  s390/qeth: fix locking for discipline setup / removal
  s390/qeth: fix deadlock during recovery
  selftests: fib_nexthops: Fix wrong mausezahn invocation
  nexthop: Bounce NHA_GATEWAY in FDB nexthop groups
  nexthop: Unlink nexthop group entry in error path
  nexthop: Fix off-by-one error in error path
  octeontx2-af: fix memory leak of lmac and lmac->name
  chtls: Fix chtls resources release sequence
  chtls: Added a check to avoid NULL pointer dereference
  chtls: Replace skb_dequeue with skb_peek
  chtls: Avoid unnecessary freeing of oreq pointer
  chtls: Fix panic when route to peer not configured
  chtls: Remove invalid set_tcb call
  chtls: Fix hardware tid leak
  net: ip: always refragment ip defragmented packets
  net: fix pmtu check in nopmtudisc mode
  selftests: netfilter: add selftest for ipip pmtu discovery with enabled connection tracking
  docs: octeontx2: tune rst markup
  ...

3 files changed, 10 insertions, 9 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 89fff5f59eea..2ed0b01f72f0 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -302,7 +302,7 @@ static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *
 	if (skb_is_gso(skb))
 		return ip_finish_output_gso(net, sk, skb, mtu);
 
-	if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU))
+	if (skb->len > mtu || IPCB(skb)->frag_max_size)
 		return ip_fragment(net, sk, skb, mtu, ip_finish_output2);
 
 	return ip_finish_output2(net, sk, skb);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index ee65c9225178..64594aa755f0 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -759,8 +759,11 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto tx_error;
 	}
 
-	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph,
-			    0, 0, false)) {
+	df = tnl_params->frag_off;
+	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
+		df |= (inner_iph->frag_off & htons(IP_DF));
+
+	if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) {
 		ip_rt_put(rt);
 		goto tx_error;
 	}
@@ -788,10 +791,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			ttl = ip4_dst_hoplimit(&rt->dst);
 	}
 
-	df = tnl_params->frag_off;
-	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
-		df |= (inner_iph->frag_off&htons(IP_DF));
-
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
 			+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
 	if (max_headroom > dev->needed_headroom)
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 5e1b22d4f939..e53e43aef785 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -627,7 +627,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[],
 	for (i = NHA_GROUP_TYPE + 1; i < __NHA_MAX; ++i) {
 		if (!tb[i])
 			continue;
-		if (tb[NHA_FDB])
+		if (i == NHA_FDB)
 			continue;
 		NL_SET_ERR_MSG(extack,
 			       "No other attributes can be set in nexthop groups");
@@ -1459,8 +1459,10 @@ static struct nexthop *nexthop_create_group(struct net *net,
 	return nh;
 
 out_no_nh:
-	for (; i >= 0; --i)
+	for (i--; i >= 0; --i) {
+		list_del(&nhg->nh_entries[i].nh_list);
 		nexthop_put(nhg->nh_entries[i].nh);
+	}
 
 	kfree(nhg->spare);
 	kfree(nhg);