aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
diff options
context:
space:
mode:
authorAmit Cohen <amcohen@nvidia.com>2021-09-23 15:37:00 +0300
committerDavid S. Miller <davem@davemloft.net>2021-09-24 10:26:52 +0100
commitba1c71324bc22fae1d9d0f531c2db2fd0934c963 (patch)
tree586c9858538cf3882fdc4e80b134baa1a67def65 /drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
parentmlxsw: spectrum_router: Increase parsing depth for IPv6 decapsulation (diff)
downloadlinux-ba1c71324bc22fae1d9d0f531c2db2fd0934c963.tar.xz
linux-ba1c71324bc22fae1d9d0f531c2db2fd0934c963.zip
mlxsw: Add support for IP-in-IP with IPv6 underlay for Spectrum-2 and above
Currently, mlxsw driver supports IP-in-IP only with IPv4 underlay. Add support for IPv6 underlay for Spectrum-2 and above. Most of the configurations are same to IPv4, the main difference between IPv4 and IPv6 is related to saving IP addresses. IPv6 addresses are saved as part of KVD and the relevant registers hold pointer to them. Add API for that as part of ipip_ops, so then only Spectrum-2 and above will save IPv6 addresses in this way. Signed-off-by: Amit Cohen <amcohen@nvidia.com> Reviewed-by: Petr Machata <petrm@nvidia.com> Signed-off-by: Ido Schimmel <idosch@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c')
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c227
1 files changed, 226 insertions, 1 deletions
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
index 37a1ad92ac91..ad3926de88f2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
@@ -29,23 +29,45 @@ static bool mlxsw_sp_ipip_parms4_has_ikey(const struct ip_tunnel_parm *parms)
return !!(parms->i_flags & TUNNEL_KEY);
}
+static bool mlxsw_sp_ipip_parms6_has_ikey(const struct __ip6_tnl_parm *parms)
+{
+ return !!(parms->i_flags & TUNNEL_KEY);
+}
+
static bool mlxsw_sp_ipip_parms4_has_okey(const struct ip_tunnel_parm *parms)
{
return !!(parms->o_flags & TUNNEL_KEY);
}
+static bool mlxsw_sp_ipip_parms6_has_okey(const struct __ip6_tnl_parm *parms)
+{
+ return !!(parms->o_flags & TUNNEL_KEY);
+}
+
static u32 mlxsw_sp_ipip_parms4_ikey(const struct ip_tunnel_parm *parms)
{
return mlxsw_sp_ipip_parms4_has_ikey(parms) ?
be32_to_cpu(parms->i_key) : 0;
}
+static u32 mlxsw_sp_ipip_parms6_ikey(const struct __ip6_tnl_parm *parms)
+{
+ return mlxsw_sp_ipip_parms6_has_ikey(parms) ?
+ be32_to_cpu(parms->i_key) : 0;
+}
+
static u32 mlxsw_sp_ipip_parms4_okey(const struct ip_tunnel_parm *parms)
{
return mlxsw_sp_ipip_parms4_has_okey(parms) ?
be32_to_cpu(parms->o_key) : 0;
}
+static u32 mlxsw_sp_ipip_parms6_okey(const struct __ip6_tnl_parm *parms)
+{
+ return mlxsw_sp_ipip_parms6_has_okey(parms) ?
+ be32_to_cpu(parms->o_key) : 0;
+}
+
static union mlxsw_sp_l3addr
mlxsw_sp_ipip_parms4_saddr(const struct ip_tunnel_parm *parms)
{
@@ -313,6 +335,19 @@ mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp,
&new_parms, extack);
}
+static int
+mlxsw_sp_ipip_rem_addr_set_gre4(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_ipip_entry *ipip_entry)
+{
+ return 0;
+}
+
+static void
+mlxsw_sp_ipip_rem_addr_unset_gre4(struct mlxsw_sp *mlxsw_sp,
+ const struct mlxsw_sp_ipip_entry *ipip_entry)
+{
+}
+
static const struct mlxsw_sp_ipip_ops mlxsw_sp_ipip_gre4_ops = {
.dev_type = ARPHRD_IPGRE,
.ul_proto = MLXSW_SP_L3_PROTO_IPV4,
@@ -323,6 +358,8 @@ static const struct mlxsw_sp_ipip_ops mlxsw_sp_ipip_gre4_ops = {
.can_offload = mlxsw_sp_ipip_can_offload_gre4,
.ol_loopback_config = mlxsw_sp_ipip_ol_loopback_config_gre4,
.ol_netdev_change = mlxsw_sp_ipip_ol_netdev_change_gre4,
+ .rem_ip_addr_set = mlxsw_sp_ipip_rem_addr_set_gre4,
+ .rem_ip_addr_unset = mlxsw_sp_ipip_rem_addr_unset_gre4,
};
static struct mlxsw_sp_ipip_parms
@@ -377,6 +414,21 @@ mlxsw_sp1_ipip_ol_netdev_change_gre6(struct mlxsw_sp *mlxsw_sp,
return -EINVAL;
}
+static int
+mlxsw_sp1_ipip_rem_addr_set_gre6(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_ipip_entry *ipip_entry)
+{
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+}
+
+static void
+mlxsw_sp1_ipip_rem_addr_unset_gre6(struct mlxsw_sp *mlxsw_sp,
+ const struct mlxsw_sp_ipip_entry *ipip_entry)
+{
+ WARN_ON_ONCE(1);
+}
+
static const struct mlxsw_sp_ipip_ops mlxsw_sp1_ipip_gre6_ops = {
.dev_type = ARPHRD_IP6GRE,
.ul_proto = MLXSW_SP_L3_PROTO_IPV6,
@@ -387,6 +439,8 @@ static const struct mlxsw_sp_ipip_ops mlxsw_sp1_ipip_gre6_ops = {
.can_offload = mlxsw_sp1_ipip_can_offload_gre6,
.ol_loopback_config = mlxsw_sp1_ipip_ol_loopback_config_gre6,
.ol_netdev_change = mlxsw_sp1_ipip_ol_netdev_change_gre6,
+ .rem_ip_addr_set = mlxsw_sp1_ipip_rem_addr_set_gre6,
+ .rem_ip_addr_unset = mlxsw_sp1_ipip_rem_addr_unset_gre6,
};
const struct mlxsw_sp_ipip_ops *mlxsw_sp1_ipip_ops_arr[] = {
@@ -394,9 +448,176 @@ const struct mlxsw_sp_ipip_ops *mlxsw_sp1_ipip_ops_arr[] = {
[MLXSW_SP_IPIP_TYPE_GRE6] = &mlxsw_sp1_ipip_gre6_ops,
};
+static struct mlxsw_sp_ipip_parms
+mlxsw_sp2_ipip_netdev_parms_init_gre6(const struct net_device *ol_dev)
+{
+ struct __ip6_tnl_parm parms = mlxsw_sp_ipip_netdev_parms6(ol_dev);
+
+ return (struct mlxsw_sp_ipip_parms) {
+ .proto = MLXSW_SP_L3_PROTO_IPV6,
+ .saddr = mlxsw_sp_ipip_parms6_saddr(&parms),
+ .daddr = mlxsw_sp_ipip_parms6_daddr(&parms),
+ .link = parms.link,
+ .ikey = mlxsw_sp_ipip_parms6_ikey(&parms),
+ .okey = mlxsw_sp_ipip_parms6_okey(&parms),
+ };
+}
+
+static int
+mlxsw_sp2_ipip_nexthop_update_gre6(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
+ struct mlxsw_sp_ipip_entry *ipip_entry,
+ bool force, char *ratr_pl)
+{
+ u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb);
+ enum mlxsw_reg_ratr_op op;
+
+ op = force ? MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY :
+ MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY_ON_ACTIVITY;
+ mlxsw_reg_ratr_pack(ratr_pl, op, true, MLXSW_REG_RATR_TYPE_IPIP,
+ adj_index, rif_index);
+ mlxsw_reg_ratr_ipip6_entry_pack(ratr_pl,
+ ipip_entry->dip_kvdl_index);
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl);
+}
+
+static int
+mlxsw_sp2_ipip_decap_config_gre6(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_ipip_entry *ipip_entry,
+ u32 tunnel_index)
+{
+ u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb);
+ u16 ul_rif_id = mlxsw_sp_ipip_lb_ul_rif_id(ipip_entry->ol_lb);
+ char rtdp_pl[MLXSW_REG_RTDP_LEN];
+ struct __ip6_tnl_parm parms;
+ unsigned int type_check;
+ bool has_ikey;
+ u32 ikey;
+
+ parms = mlxsw_sp_ipip_netdev_parms6(ipip_entry->ol_dev);
+ has_ikey = mlxsw_sp_ipip_parms6_has_ikey(&parms);
+ ikey = mlxsw_sp_ipip_parms6_ikey(&parms);
+
+ mlxsw_reg_rtdp_pack(rtdp_pl, MLXSW_REG_RTDP_TYPE_IPIP, tunnel_index);
+ mlxsw_reg_rtdp_egress_router_interface_set(rtdp_pl, ul_rif_id);
+
+ type_check = has_ikey ?
+ MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE_KEY :
+ MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE;
+
+ /* Linux demuxes tunnels based on packet SIP (which must match tunnel
+ * remote IP). Thus configure decap so that it filters out packets that
+ * are not IPv6 or have the wrong SIP. IPIP_DECAP_ERROR trap is
+ * generated for packets that fail this criterion. Linux then handles
+ * such packets in slow path and generates ICMP destination unreachable.
+ */
+ mlxsw_reg_rtdp_ipip6_pack(rtdp_pl, rif_index,
+ MLXSW_REG_RTDP_IPIP_SIP_CHECK_FILTER_IPV6,
+ type_check, has_ikey,
+ ipip_entry->dip_kvdl_index, ikey);
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtdp), rtdp_pl);
+}
+
+static bool mlxsw_sp2_ipip_can_offload_gre6(const struct mlxsw_sp *mlxsw_sp,
+ const struct net_device *ol_dev)
+{
+ struct __ip6_tnl_parm tparm = mlxsw_sp_ipip_netdev_parms6(ol_dev);
+ bool inherit_tos = tparm.flags & IP6_TNL_F_USE_ORIG_TCLASS;
+ bool inherit_ttl = tparm.hop_limit == 0;
+ __be16 okflags = TUNNEL_KEY; /* We can't offload any other features. */
+
+ return (tparm.i_flags & ~okflags) == 0 &&
+ (tparm.o_flags & ~okflags) == 0 &&
+ inherit_ttl && inherit_tos &&
+ mlxsw_sp_ipip_tunnel_complete(MLXSW_SP_L3_PROTO_IPV6, ol_dev);
+}
+
+static struct mlxsw_sp_rif_ipip_lb_config
+mlxsw_sp2_ipip_ol_loopback_config_gre6(struct mlxsw_sp *mlxsw_sp,
+ const struct net_device *ol_dev)
+{
+ struct __ip6_tnl_parm parms = mlxsw_sp_ipip_netdev_parms6(ol_dev);
+ enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt;
+
+ lb_ipipt = mlxsw_sp_ipip_parms6_has_okey(&parms) ?
+ MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_KEY_IN_IP :
+ MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_IN_IP;
+ return (struct mlxsw_sp_rif_ipip_lb_config){
+ .lb_ipipt = lb_ipipt,
+ .okey = mlxsw_sp_ipip_parms6_okey(&parms),
+ .ul_protocol = MLXSW_SP_L3_PROTO_IPV6,
+ .saddr = mlxsw_sp_ipip_netdev_saddr(MLXSW_SP_L3_PROTO_IPV6,
+ ol_dev),
+ };
+}
+
+static int
+mlxsw_sp2_ipip_ol_netdev_change_gre6(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_ipip_entry *ipip_entry,
+ struct netlink_ext_ack *extack)
+{
+ struct mlxsw_sp_ipip_parms new_parms;
+
+ new_parms = mlxsw_sp2_ipip_netdev_parms_init_gre6(ipip_entry->ol_dev);
+ return mlxsw_sp_ipip_ol_netdev_change_gre(mlxsw_sp, ipip_entry,
+ &new_parms, extack);
+}
+
+static int
+mlxsw_sp2_ipip_rem_addr_set_gre6(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_ipip_entry *ipip_entry)
+{
+ char rips_pl[MLXSW_REG_RIPS_LEN];
+ struct __ip6_tnl_parm parms6;
+ int err;
+
+ err = mlxsw_sp_kvdl_alloc(mlxsw_sp,
+ MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1,
+ &ipip_entry->dip_kvdl_index);
+ if (err)
+ return err;
+
+ parms6 = mlxsw_sp_ipip_netdev_parms6(ipip_entry->ol_dev);
+ mlxsw_reg_rips_pack(rips_pl, ipip_entry->dip_kvdl_index,
+ &parms6.raddr);
+ err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rips), rips_pl);
+ if (err)
+ goto err_rips_write;
+
+ return 0;
+
+err_rips_write:
+ mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1,
+ ipip_entry->dip_kvdl_index);
+ return err;
+}
+
+static void
+mlxsw_sp2_ipip_rem_addr_unset_gre6(struct mlxsw_sp *mlxsw_sp,
+ const struct mlxsw_sp_ipip_entry *ipip_entry)
+{
+ mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1,
+ ipip_entry->dip_kvdl_index);
+}
+
+static const struct mlxsw_sp_ipip_ops mlxsw_sp2_ipip_gre6_ops = {
+ .dev_type = ARPHRD_IP6GRE,
+ .ul_proto = MLXSW_SP_L3_PROTO_IPV6,
+ .inc_parsing_depth = true,
+ .parms_init = mlxsw_sp2_ipip_netdev_parms_init_gre6,
+ .nexthop_update = mlxsw_sp2_ipip_nexthop_update_gre6,
+ .decap_config = mlxsw_sp2_ipip_decap_config_gre6,
+ .can_offload = mlxsw_sp2_ipip_can_offload_gre6,
+ .ol_loopback_config = mlxsw_sp2_ipip_ol_loopback_config_gre6,
+ .ol_netdev_change = mlxsw_sp2_ipip_ol_netdev_change_gre6,
+ .rem_ip_addr_set = mlxsw_sp2_ipip_rem_addr_set_gre6,
+ .rem_ip_addr_unset = mlxsw_sp2_ipip_rem_addr_unset_gre6,
+};
+
const struct mlxsw_sp_ipip_ops *mlxsw_sp2_ipip_ops_arr[] = {
[MLXSW_SP_IPIP_TYPE_GRE4] = &mlxsw_sp_ipip_gre4_ops,
- [MLXSW_SP_IPIP_TYPE_GRE6] = &mlxsw_sp1_ipip_gre6_ops,
+ [MLXSW_SP_IPIP_TYPE_GRE6] = &mlxsw_sp2_ipip_gre6_ops,
};
static int mlxsw_sp_ipip_ecn_encap_init_one(struct mlxsw_sp *mlxsw_sp,
@@ -461,11 +682,15 @@ mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev)
{
struct net *net = dev_net(ol_dev);
struct ip_tunnel *tun4;
+ struct ip6_tnl *tun6;
switch (ol_dev->type) {
case ARPHRD_IPGRE:
tun4 = netdev_priv(ol_dev);
return dev_get_by_index_rcu(net, tun4->parms.link);
+ case ARPHRD_IP6GRE:
+ tun6 = netdev_priv(ol_dev);
+ return dev_get_by_index_rcu(net, tun6->parms.link);
default:
return NULL;
}