Merge branch 'mlxsw-GRE-mtu-changes'

Ido Schimmel says:

====================
mlxsw: Handle changes to MTU in GRE tunnels

Petr says:

When offloading GRE tunnels, the MTU setting is kept fixed after the
initial offload even as the slow-path configuration changed. Worse: the
offloaded MTU setting is actually just a transient value set at the time
of NETDEV_REGISTER of the tunnel. As of commit ffc2b6e ("ip_gre:
fix IFLA_MTU ignored on NEWLINK"), that transient value is zero, and
unless there's e.g. a VRF migration that prompts re-offload, it stays at
zero, and all GRE packets end up trapping.

Thus, in patch #1, change the way the MTU is changed post-registration,
so that the full event protocol is observed. That way the drivers get to
see the change and have a chance to react.

In the remaining two patches, implement support for MTU change in mlxsw
driver.
====================

Signed-off-by: David S. Miller <[email protected]>

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c

@@ -1380,6 +1380,55 @@ mlxsw_sp_ipip_entry_ol_up_event(struct mlxsw_sp *mlxsw_sp,
 						  decap_fib_entry);
 }
 
+static int
+mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif,
+			struct mlxsw_sp_vr *ul_vr, bool enable)
+{
+	struct mlxsw_sp_rif_ipip_lb_config lb_cf = lb_rif->lb_config;
+	struct mlxsw_sp_rif *rif = &lb_rif->common;
+	struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+	u32 saddr4;
+
+	switch (lb_cf.ul_protocol) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		saddr4 = be32_to_cpu(lb_cf.saddr.addr4);
+		mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_LOOPBACK_IF,
+				    rif->rif_index, rif->vr_id, rif->dev->mtu);
+		mlxsw_reg_ritr_loopback_ipip4_pack(ritr_pl, lb_cf.lb_ipipt,
+			    MLXSW_REG_RITR_LOOPBACK_IPIP_OPTIONS_GRE_KEY_PRESET,
+			    ul_vr->id, saddr4, lb_cf.okey);
+		break;
+
+	case MLXSW_SP_L3_PROTO_IPV6:
+		return -EAFNOSUPPORT;
+	}
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static int mlxsw_sp_netdevice_ipip_ol_update_mtu(struct mlxsw_sp *mlxsw_sp,
+						 struct net_device *ol_dev)
+{
+	struct mlxsw_sp_ipip_entry *ipip_entry;
+	struct mlxsw_sp_rif_ipip_lb *lb_rif;
+	struct mlxsw_sp_vr *ul_vr;
+	int err = 0;
+
+	ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
+	if (ipip_entry) {
+		lb_rif = ipip_entry->ol_lb;
+		ul_vr = &mlxsw_sp->router->vrs[lb_rif->ul_vr_id];
+		err = mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr, true);
+		if (err)
+			goto out;
+		lb_rif->common.mtu = ol_dev->mtu;
+	}
+
+out:
+	return err;
+}
+
 static void mlxsw_sp_netdevice_ipip_ol_up_event(struct mlxsw_sp *mlxsw_sp,
 						struct net_device *ol_dev)
 {
@@ -1660,6 +1709,8 @@ int mlxsw_sp_netdevice_ipip_ol_event(struct mlxsw_sp *mlxsw_sp,
 		extack = info->extack;
 		return mlxsw_sp_netdevice_ipip_ol_change_event(mlxsw_sp,
 							       ol_dev, extack);
+	case NETDEV_CHANGEMTU:
+		return mlxsw_sp_netdevice_ipip_ol_update_mtu(mlxsw_sp, ol_dev);
 	}
 	return 0;
 }
@@ -6843,33 +6894,6 @@ mlxsw_sp_rif_ipip_lb_setup(struct mlxsw_sp_rif *rif,
 	rif_lb->lb_config = params_lb->lb_config;
 }
 
-static int
-mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif,
-			struct mlxsw_sp_vr *ul_vr, bool enable)
-{
-	struct mlxsw_sp_rif_ipip_lb_config lb_cf = lb_rif->lb_config;
-	struct mlxsw_sp_rif *rif = &lb_rif->common;
-	struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
-	char ritr_pl[MLXSW_REG_RITR_LEN];
-	u32 saddr4;
-
-	switch (lb_cf.ul_protocol) {
-	case MLXSW_SP_L3_PROTO_IPV4:
-		saddr4 = be32_to_cpu(lb_cf.saddr.addr4);
-		mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_LOOPBACK_IF,
-				    rif->rif_index, rif->vr_id, rif->dev->mtu);
-		mlxsw_reg_ritr_loopback_ipip4_pack(ritr_pl, lb_cf.lb_ipipt,
-			    MLXSW_REG_RITR_LOOPBACK_IPIP_OPTIONS_GRE_KEY_PRESET,
-			    ul_vr->id, saddr4, lb_cf.okey);
-		break;
-
-	case MLXSW_SP_L3_PROTO_IPV6:
-		return -EAFNOSUPPORT;
-	}
-
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-}
-
 static int
 mlxsw_sp_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif)
 {

net/ipv4/ip_tunnel.c

@@ -362,20 +362,29 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 	struct ip_tunnel *nt;
 	struct net_device *dev;
 	int t_hlen;
+	int mtu;
+	int err;
 
 	BUG_ON(!itn->fb_tunnel_dev);
 	dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
 	if (IS_ERR(dev))
 		return ERR_CAST(dev);
 
-	dev->mtu = ip_tunnel_bind_dev(dev);
+	mtu = ip_tunnel_bind_dev(dev);
+	err = dev_set_mtu(dev, mtu);
+	if (err)
+		goto err_dev_set_mtu;
 
 	nt = netdev_priv(dev);
 	t_hlen = nt->hlen + sizeof(struct iphdr);
 	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
 	ip_tunnel_add(itn, nt);
 	return nt;
+
+err_dev_set_mtu:
+	unregister_netdevice(dev);
+	return ERR_PTR(err);
 }
 
 int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
@@ -1102,17 +1111,24 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 	nt->fwmark = fwmark;
 	err = register_netdevice(dev);
 	if (err)
-		goto out;
+		goto err_register_netdevice;
 
 	if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
 		eth_hw_addr_random(dev);
 
 	mtu = ip_tunnel_bind_dev(dev);
-	if (!tb[IFLA_MTU])
-		dev->mtu = mtu;
+	if (!tb[IFLA_MTU]) {
+		err = dev_set_mtu(dev, mtu);
+		if (err)
+			goto err_dev_set_mtu;
+	}
 
 	ip_tunnel_add(itn, nt);
-out:
+	return 0;
+
+err_dev_set_mtu:
+	unregister_netdevice(dev);
+err_register_netdevice:
 	return err;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_newlink);