Merge tag 'net-5.16-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Networking fixes, including fixes from netfilter.

  Current release - regressions:

   - r8169: fix incorrect mac address assignment

   - vlan: fix underflow for the real_dev refcnt when vlan creation
     fails

   - smc: avoid warning of possible recursive locking

  Current release - new code bugs:

   - vsock/virtio: suppress used length validation

   - neigh: fix crash in v6 module initialization error path

  Previous releases - regressions:

   - af_unix: fix change in behavior in read after shutdown

   - igb: fix netpoll exit with traffic, avoid warning

   - tls: fix splice_read() when starting mid-record

   - lan743x: fix deadlock in lan743x_phy_link_status_change()

   - marvell: prestera: fix bridge port operation

  Previous releases - always broken:

   - tcp_cubic: fix spurious Hystart ACK train detections for
     not-cwnd-limited flows

   - nexthop: fix refcount issues when replacing IPv6 groups

   - nexthop: fix null pointer dereference when IPv6 is not enabled

   - phylink: force link down and retrigger resolve on interface change

   - mptcp: fix delack timer length calculation and incorrect early
     clearing

   - ieee802154: handle iftypes as u32, prevent shift-out-of-bounds

   - nfc: virtual_ncidev: change default device permissions

   - netfilter: ctnetlink: fix error codes and flags used for kernel
     side filtering of dumps

   - netfilter: flowtable: fix IPv6 tunnel addr match

   - ncsi: align payload to 32-bit to fix dropped packets

   - iavf: fix deadlock and loss of config during VF interface reset

   - ice: avoid bpf_prog refcount underflow

   - ocelot: fix broken PTP over IP and PTP API violations

  Misc:

   - marvell: mvpp2: increase MTU limit when XDP enabled"

* tag 'net-5.16-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (94 commits)
  net: dsa: microchip: implement multi-bridge support
  net: mscc: ocelot: correctly report the timestamping RX filters in ethtool
  net: mscc: ocelot: set up traps for PTP packets
  net: ptp: add a definition for the UDP port for IEEE 1588 general messages
  net: mscc: ocelot: create a function that replaces an existing VCAP filter
  net: mscc: ocelot: don't downgrade timestamping RX filters in SIOCSHWTSTAMP
  net: hns3: fix incorrect components info of ethtool --reset command
  net: hns3: fix one incorrect value of page pool info when queried by debugfs
  net: hns3: add check NULL address for page pool
  net: hns3: fix VF RSS failed problem after PF enable multi-TCs
  net: qed: fix the array may be out of bound
  net/smc: Don't call clcsock shutdown twice when smc shutdown
  net: vlan: fix underflow for the real_dev refcnt
  ptp: fix filter names in the documentation
  ethtool: ioctl: fix potential NULL deref in ethtool_set_coalesce()
  nfc: virtual_ncidev: change default device permissions
  net/sched: sch_ets: don't peek at classes beyond 'nbands'
  net: stmmac: Disable Tx queues when reconfiguring the interface
  selftests: tls: test for correct proto_ops
  tls: fix replacing proto_ops
  ...

1 files changed, 30 insertions, 5 deletions

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 9e8100728d46..5dbd4b5505eb 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1899,15 +1899,36 @@ static void remove_nexthop(struct net *net, struct nexthop *nh,
 /* if any FIB entries reference this nexthop, any dst entries
  * need to be regenerated
  */
-static void nh_rt_cache_flush(struct net *net, struct nexthop *nh)
+static void nh_rt_cache_flush(struct net *net, struct nexthop *nh,
+			      struct nexthop *replaced_nh)
 {
 	struct fib6_info *f6i;
+	struct nh_group *nhg;
+	int i;
 
 	if (!list_empty(&nh->fi_list))
 		rt_cache_flush(net);
 
 	list_for_each_entry(f6i, &nh->f6i_list, nh_list)
 		ipv6_stub->fib6_update_sernum(net, f6i);
+
+	/* if an IPv6 group was replaced, we have to release all old
+	 * dsts to make sure all refcounts are released
+	 */
+	if (!replaced_nh->is_group)
+		return;
+
+	/* new dsts must use only the new nexthop group */
+	synchronize_net();
+
+	nhg = rtnl_dereference(replaced_nh->nh_grp);
+	for (i = 0; i < nhg->num_nh; i++) {
+		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+		struct nh_info *nhi = rtnl_dereference(nhge->nh->nh_info);
+
+		if (nhi->family == AF_INET6)
+			ipv6_stub->fib6_nh_release_dsts(&nhi->fib6_nh);
+	}
 }
 
 static int replace_nexthop_grp(struct net *net, struct nexthop *old,
@@ -2247,7 +2268,7 @@ static int replace_nexthop(struct net *net, struct nexthop *old,
 		err = replace_nexthop_single(net, old, new, extack);
 
 	if (!err) {
-		nh_rt_cache_flush(net, old);
+		nh_rt_cache_flush(net, old, new);
 
 		__remove_nexthop(net, new, NULL);
 		nexthop_put(new);
@@ -2544,11 +2565,15 @@ static int nh_create_ipv6(struct net *net,  struct nexthop *nh,
 	/* sets nh_dev if successful */
 	err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL,
 				      extack);
-	if (err)
+	if (err) {
+		/* IPv6 is not enabled, don't call fib6_nh_release */
+		if (err == -EAFNOSUPPORT)
+			goto out;
 		ipv6_stub->fib6_nh_release(fib6_nh);
-	else
+	} else {
 		nh->nh_flags = fib6_nh->fib_nh_flags;
-
+	}
+out:
 	return err;
 }