Merge tag 'net-7.1-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from Netfilter, IPsec, Bluetooth and WiFi.

  Current release - fix to a fix:

   - ipmr: add __rcu to netns_ipv4.mrt, make sure we hold the RCU lock
     in all relevant places

  Current release - new code bugs:

   - fixes for the recently added resizable hash tables

   - ipv6: make sure we default IPv6 tunnel drivers to =m now that IPv6
     itself is built in

   - drv: octeontx2-af: fixes for parser/CAM fixes

  Previous releases - regressions:

   - phy: micrel: fix LAN8814 QSGMII soft reset

   - wifi:
       - cw1200: revert "Fix locking in error paths"
       - ath12k: fix crash on WCN7850, due to adding the same queue
         buffer to a list multiple times

  Previous releases - always broken:

   - number of info leak fixes

   - ipv6: implement limits on extension header parsing

   - wifi: number of fixes for missing bound checks in the drivers

   - Bluetooth: fixes for races and locking issues

   - af_unix:
       - fix an issue between garbage collection and PEEK
       - fix yet another issue with OOB data

   - xfrm: esp: avoid in-place decrypt on shared skb frags

   - netfilter: replace skb_try_make_writable() by skb_ensure_writable()

   - openvswitch: vport: fix race between tunnel creation and linking
     leading to invalid memory accesses (type confusion)

   - drv: amd-xgbe: fix PTP addend overflow causing frozen clock

  Misc:

   - sched/isolation: make HK_TYPE_KTHREAD an alias of HK_TYPE_DOMAIN
     (for relevant IPVS change)"

* tag 'net-7.1-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (190 commits)
  net: sparx5: configure serdes for 1000BASE-X in sparx5_port_init()
  net: sparx5: fix wrong chip ids for TSN SKUs
  net: stmmac: dwmac-nuvoton: fix NULL pointer dereference in nvt_set_phy_intf_sel()
  tcp: Fix dst leak in tcp_v6_connect().
  ipmr: Call ipmr_fib_lookup() under RCU.
  net: phy: broadcom: Save PHY counters during suspend
  net/smc: fix missing sk_err when TCP handshake fails
  af_unix: Reject SIOCATMARK on non-stream sockets
  veth: fix OOB txq access in veth_poll() with asymmetric queue counts
  eth: fbnic: fix double-free of PCS on phylink creation failure
  net: ethernet: cortina: Drop half-assembled SKB
  selftests: mptcp: pm: restrict 'unknown' check to pm_nl_ctl
  selftests: mptcp: check output: catch cmd errors
  mptcp: pm: prio: skip closed subflows
  mptcp: pm: ADD_ADDR rtx: return early if no retrans
  mptcp: pm: ADD_ADDR rtx: skip inactive subflows
  mptcp: pm: ADD_ADDR rtx: resched blocked ADD_ADDR quicker
  mptcp: pm: ADD_ADDR rtx: free sk if last
  mptcp: pm: ADD_ADDR rtx: always decrease sk refcount
  mptcp: pm: ADD_ADDR rtx: fix potential data-race
  ...

1 files changed, 40 insertions, 24 deletions

diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index 12055af832dc..c42642075685 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -73,37 +73,21 @@ static struct net_device *get_dpdev(const struct datapath *dp)
 	return local->dev;
 }
 
-struct vport *ovs_netdev_link(struct vport *vport, const char *name)
+struct vport *ovs_netdev_link(struct vport *vport, bool tunnel)
 {
 	int err;
 
-	vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), name);
-	if (!vport->dev) {
+	if (WARN_ON_ONCE(!vport->dev)) {
 		err = -ENODEV;
 		goto error_free_vport;
 	}
-	/* Ensure that the device exists and that the provided
-	 * name is not one of its aliases.
-	 */
-	if (strcmp(name, ovs_vport_name(vport))) {
-		err = -ENODEV;
-		goto error_put;
-	}
-	netdev_tracker_alloc(vport->dev, &vport->dev_tracker, GFP_KERNEL);
-	if (vport->dev->flags & IFF_LOOPBACK ||
-	    (vport->dev->type != ARPHRD_ETHER &&
-	     vport->dev->type != ARPHRD_NONE) ||
-	    ovs_is_internal_dev(vport->dev)) {
-		err = -EINVAL;
-		goto error_put;
-	}
 
 	rtnl_lock();
 	err = netdev_master_upper_dev_link(vport->dev,
 					   get_dpdev(vport->dp),
 					   NULL, NULL, NULL);
 	if (err)
-		goto error_unlock;
+		goto error_put_unlock;
 
 	err = netdev_rx_handler_register(vport->dev, netdev_frame_hook,
 					 vport);
@@ -119,10 +103,11 @@ struct vport *ovs_netdev_link(struct vport *vport, const char *name)
 
 error_master_upper_dev_unlink:
 	netdev_upper_dev_unlink(vport->dev, get_dpdev(vport->dp));
-error_unlock:
-	rtnl_unlock();
-error_put:
+error_put_unlock:
+	if (tunnel && vport->dev->reg_state == NETREG_REGISTERED)
+		rtnl_delete_link(vport->dev, 0, NULL);
 	netdev_put(vport->dev, &vport->dev_tracker);
+	rtnl_unlock();
 error_free_vport:
 	ovs_vport_free(vport);
 	return ERR_PTR(err);
@@ -132,12 +117,39 @@ EXPORT_SYMBOL_GPL(ovs_netdev_link);
 static struct vport *netdev_create(const struct vport_parms *parms)
 {
 	struct vport *vport;
+	int err;
 
 	vport = ovs_vport_alloc(0, &ovs_netdev_vport_ops, parms);
 	if (IS_ERR(vport))
 		return vport;
 
-	return ovs_netdev_link(vport, parms->name);
+	vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), parms->name);
+	if (!vport->dev) {
+		err = -ENODEV;
+		goto error_free_vport;
+	}
+	netdev_tracker_alloc(vport->dev, &vport->dev_tracker, GFP_KERNEL);
+
+	/* Ensure that the provided name is not an alias. */
+	if (strcmp(parms->name, ovs_vport_name(vport))) {
+		err = -ENODEV;
+		goto error_put;
+	}
+
+	if (vport->dev->flags & IFF_LOOPBACK ||
+	    (vport->dev->type != ARPHRD_ETHER &&
+	     vport->dev->type != ARPHRD_NONE) ||
+	    ovs_is_internal_dev(vport->dev)) {
+		err = -EINVAL;
+		goto error_put;
+	}
+
+	return ovs_netdev_link(vport, false);
+error_put:
+	netdev_put(vport->dev, &vport->dev_tracker);
+error_free_vport:
+	ovs_vport_free(vport);
+	return ERR_PTR(err);
 }
 
 static void vport_netdev_free(struct rcu_head *rcu)
@@ -196,9 +208,13 @@ void ovs_netdev_tunnel_destroy(struct vport *vport)
 	 */
 	if (vport->dev->reg_state == NETREG_REGISTERED)
 		rtnl_delete_link(vport->dev, 0, NULL);
-	rtnl_unlock();
 
+	/* We can't put the device reference yet, since it can still be in
+	 * use, but rtnl_unlock()->netdev_run_todo() will block until all
+	 * the references are released, so the RCU call must be before it.
+	 */
 	call_rcu(&vport->rcu, vport_netdev_free);
+	rtnl_unlock();
 }
 EXPORT_SYMBOL_GPL(ovs_netdev_tunnel_destroy);