diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c')
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 623 |
1 files changed, 458 insertions, 165 deletions
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 52fed8c7bf1e..30bfe3880faf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -13,14 +13,16 @@ #include <linux/socket.h> #include <linux/route.h> #include <linux/gcd.h> -#include <linux/random.h> #include <linux/if_macvlan.h> #include <linux/refcount.h> +#include <linux/jhash.h> +#include <linux/net_namespace.h> #include <net/netevent.h> #include <net/neighbour.h> #include <net/arp.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> +#include <net/nexthop.h> #include <net/fib_rules.h> #include <net/ip_tunnels.h> #include <net/l3mdev.h> @@ -75,6 +77,8 @@ struct mlxsw_sp_router { struct notifier_block inet6addr_nb; const struct mlxsw_sp_rif_ops **rif_ops_arr; const struct mlxsw_sp_ipip_ops **ipip_ops_arr; + u32 adj_discard_index; + bool adj_discard_index_valid; }; struct mlxsw_sp_rif { @@ -365,6 +369,7 @@ enum mlxsw_sp_fib_entry_type { MLXSW_SP_FIB_ENTRY_TYPE_LOCAL, MLXSW_SP_FIB_ENTRY_TYPE_TRAP, MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE, + MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE, /* This is a special case of local delivery, where a packet should be * decapsulated on reception. Note that there is no corresponding ENCAP, @@ -993,7 +998,7 @@ u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev) if (d) return l3mdev_fib_table(d) ? : RT_TABLE_MAIN; else - return l3mdev_fib_table(ol_dev) ? : RT_TABLE_MAIN; + return RT_TABLE_MAIN; } static struct mlxsw_sp_rif * @@ -1597,27 +1602,10 @@ static int mlxsw_sp_netdevice_ipip_ol_vrf_event(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_ipip_entry *ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); - enum mlxsw_sp_l3proto ul_proto; - union mlxsw_sp_l3addr saddr; - u32 ul_tb_id; if (!ipip_entry) return 0; - /* For flat configuration cases, moving overlay to a different VRF might - * cause local address conflict, and the conflicting tunnels need to be - * demoted. - */ - ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev); - ul_proto = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto; - saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev); - if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, ul_proto, - saddr, ul_tb_id, - ipip_entry)) { - mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry); - return 0; - } - return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry, true, false, false, extack); } @@ -1626,8 +1614,25 @@ static int mlxsw_sp_netdevice_ipip_ul_vrf_event(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry, struct net_device *ul_dev, + bool *demote_this, struct netlink_ext_ack *extack) { + u32 ul_tb_id = l3mdev_fib_table(ul_dev) ? : RT_TABLE_MAIN; + enum mlxsw_sp_l3proto ul_proto; + union mlxsw_sp_l3addr saddr; + + /* Moving underlay to a different VRF might cause local address + * conflict, and the conflicting tunnels need to be demoted. + */ + ul_proto = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto; + saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ipip_entry->ol_dev); + if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, ul_proto, + saddr, ul_tb_id, + ipip_entry)) { + *demote_this = true; + return 0; + } + return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry, true, true, false, extack); } @@ -1778,6 +1783,7 @@ static int __mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry, struct net_device *ul_dev, + bool *demote_this, unsigned long event, struct netdev_notifier_info *info) { @@ -1792,6 +1798,7 @@ __mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_netdevice_ipip_ul_vrf_event(mlxsw_sp, ipip_entry, ul_dev, + demote_this, extack); break; @@ -1818,13 +1825,31 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, while ((ipip_entry = mlxsw_sp_ipip_entry_find_by_ul_dev(mlxsw_sp, ul_dev, ipip_entry))) { + struct mlxsw_sp_ipip_entry *prev; + bool demote_this = false; + err = __mlxsw_sp_netdevice_ipip_ul_event(mlxsw_sp, ipip_entry, - ul_dev, event, info); + ul_dev, &demote_this, + event, info); if (err) { mlxsw_sp_ipip_demote_tunnel_by_ul_netdev(mlxsw_sp, ul_dev); return err; } + + if (demote_this) { + if (list_is_first(&ipip_entry->ipip_list_node, + &mlxsw_sp->router->ipip_list)) + prev = NULL; + else + /* This can't be cached from previous iteration, + * because that entry could be gone now. + */ + prev = list_prev_entry(ipip_entry, + ipip_list_node); + mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry); + ipip_entry = prev; + } } return 0; @@ -2363,7 +2388,7 @@ static void mlxsw_sp_router_probe_unresolved_nexthops(struct work_struct *work) static void mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_neigh_entry *neigh_entry, - bool removing); + bool removing, bool dead); static enum mlxsw_reg_rauht_op mlxsw_sp_rauht_op(bool adding) { @@ -2371,7 +2396,7 @@ static enum mlxsw_reg_rauht_op mlxsw_sp_rauht_op(bool adding) MLXSW_REG_RAUHT_OP_WRITE_DELETE; } -static void +static int mlxsw_sp_router_neigh_entry_op4(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_neigh_entry *neigh_entry, enum mlxsw_reg_rauht_op op) @@ -2385,10 +2410,10 @@ mlxsw_sp_router_neigh_entry_op4(struct mlxsw_sp *mlxsw_sp, if (neigh_entry->counter_valid) mlxsw_reg_rauht_pack_counter(rauht_pl, neigh_entry->counter_index); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl); } -static void +static int mlxsw_sp_router_neigh_entry_op6(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_neigh_entry *neigh_entry, enum mlxsw_reg_rauht_op op) @@ -2402,7 +2427,7 @@ mlxsw_sp_router_neigh_entry_op6(struct mlxsw_sp *mlxsw_sp, if (neigh_entry->counter_valid) mlxsw_reg_rauht_pack_counter(rauht_pl, neigh_entry->counter_index); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl); } bool mlxsw_sp_neigh_ipv6_ignore(struct mlxsw_sp_neigh_entry *neigh_entry) @@ -2424,20 +2449,33 @@ mlxsw_sp_neigh_entry_update(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_neigh_entry *neigh_entry, bool adding) { + enum mlxsw_reg_rauht_op op = mlxsw_sp_rauht_op(adding); + int err; + if (!adding && !neigh_entry->connected) return; neigh_entry->connected = adding; if (neigh_entry->key.n->tbl->family == AF_INET) { - mlxsw_sp_router_neigh_entry_op4(mlxsw_sp, neigh_entry, - mlxsw_sp_rauht_op(adding)); + err = mlxsw_sp_router_neigh_entry_op4(mlxsw_sp, neigh_entry, + op); + if (err) + return; } else if (neigh_entry->key.n->tbl->family == AF_INET6) { if (mlxsw_sp_neigh_ipv6_ignore(neigh_entry)) return; - mlxsw_sp_router_neigh_entry_op6(mlxsw_sp, neigh_entry, - mlxsw_sp_rauht_op(adding)); + err = mlxsw_sp_router_neigh_entry_op6(mlxsw_sp, neigh_entry, + op); + if (err) + return; } else { WARN_ON_ONCE(1); + return; } + + if (adding) + neigh_entry->key.n->flags |= NTF_OFFLOADED; + else + neigh_entry->key.n->flags &= ~NTF_OFFLOADED; } void @@ -2494,7 +2532,8 @@ static void mlxsw_sp_router_neigh_event_work(struct work_struct *work) memcpy(neigh_entry->ha, ha, ETH_ALEN); mlxsw_sp_neigh_entry_update(mlxsw_sp, neigh_entry, entry_connected); - mlxsw_sp_nexthop_neigh_update(mlxsw_sp, neigh_entry, !entry_connected); + mlxsw_sp_nexthop_neigh_update(mlxsw_sp, neigh_entry, !entry_connected, + dead); if (!neigh_entry->connected && list_empty(&neigh_entry->nexthop_list)) mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry); @@ -2536,14 +2575,14 @@ static int mlxsw_sp_router_schedule_work(struct net *net, struct mlxsw_sp_netevent_work *net_work; struct mlxsw_sp_router *router; - if (!net_eq(net, &init_net)) + router = container_of(nb, struct mlxsw_sp_router, netevent_nb); + if (!net_eq(net, mlxsw_sp_net(router->mlxsw_sp))) return NOTIFY_DONE; net_work = kzalloc(sizeof(*net_work), GFP_ATOMIC); if (!net_work) return NOTIFY_BAD; - router = container_of(nb, struct mlxsw_sp_router, netevent_nb); INIT_WORK(&net_work->work, cb); net_work->mlxsw_sp = router->mlxsw_sp; mlxsw_core_schedule_work(&net_work->work); @@ -2873,12 +2912,13 @@ mlxsw_sp_nexthop6_group_cmp(const struct mlxsw_sp_nexthop_group *nh_grp, return false; list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { + struct fib6_nh *fib6_nh = mlxsw_sp_rt6->rt->fib6_nh; struct in6_addr *gw; int ifindex, weight; - ifindex = mlxsw_sp_rt6->rt->fib6_nh.nh_dev->ifindex; - weight = mlxsw_sp_rt6->rt->fib6_nh.nh_weight; - gw = &mlxsw_sp_rt6->rt->fib6_nh.nh_gw; + ifindex = fib6_nh->fib_nh_dev->ifindex; + weight = fib6_nh->fib_nh_weight; + gw = &fib6_nh->fib_nh_gw6; if (!mlxsw_sp_nexthop6_group_has_nexthop(nh_grp, gw, ifindex, weight)) return false; @@ -2927,7 +2967,7 @@ static u32 mlxsw_sp_nexthop_group_hash_obj(const void *data, u32 len, u32 seed) val = nh_grp->count; for (i = 0; i < nh_grp->count; i++) { nh = &nh_grp->nexthops[i]; - val ^= nh->ifindex; + val ^= jhash(&nh->ifindex, sizeof(nh->ifindex), seed); } return jhash(&val, sizeof(val), seed); default: @@ -2944,8 +2984,8 @@ mlxsw_sp_nexthop6_group_hash(struct mlxsw_sp_fib6_entry *fib6_entry, u32 seed) struct net_device *dev; list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { - dev = mlxsw_sp_rt6->rt->fib6_nh.nh_dev; - val ^= dev->ifindex; + dev = mlxsw_sp_rt6->rt->fib6_nh->fib_nh_dev; + val ^= jhash(&dev->ifindex, sizeof(dev->ifindex), seed); } return jhash(&val, sizeof(val), seed); @@ -3458,13 +3498,79 @@ static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh, nh->update = 1; } +static int +mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_neigh_entry *neigh_entry) +{ + struct neighbour *n, *old_n = neigh_entry->key.n; + struct mlxsw_sp_nexthop *nh; + bool entry_connected; + u8 nud_state, dead; + int err; + + nh = list_first_entry(&neigh_entry->nexthop_list, + struct mlxsw_sp_nexthop, neigh_list_node); + + n = neigh_lookup(nh->nh_grp->neigh_tbl, &nh->gw_addr, nh->rif->dev); + if (!n) { + n = neigh_create(nh->nh_grp->neigh_tbl, &nh->gw_addr, + nh->rif->dev); + if (IS_ERR(n)) + return PTR_ERR(n); + neigh_event_send(n, NULL); + } + + mlxsw_sp_neigh_entry_remove(mlxsw_sp, neigh_entry); + neigh_entry->key.n = n; + err = mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry); + if (err) + goto err_neigh_entry_insert; + + read_lock_bh(&n->lock); + nud_state = n->nud_state; + dead = n->dead; + read_unlock_bh(&n->lock); + entry_connected = nud_state & NUD_VALID && !dead; + + list_for_each_entry(nh, &neigh_entry->nexthop_list, + neigh_list_node) { + neigh_release(old_n); + neigh_clone(n); + __mlxsw_sp_nexthop_neigh_update(nh, !entry_connected); + mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp); + } + + neigh_release(n); + + return 0; + +err_neigh_entry_insert: + neigh_entry->key.n = old_n; + mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry); + neigh_release(n); + return err; +} + static void mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_neigh_entry *neigh_entry, - bool removing) + bool removing, bool dead) { struct mlxsw_sp_nexthop *nh; + if (list_empty(&neigh_entry->nexthop_list)) + return; + + if (dead) { + int err; + + err = mlxsw_sp_nexthop_dead_neigh_replace(mlxsw_sp, + neigh_entry); + if (err) + dev_err(mlxsw_sp->bus_info->dev, "Failed to replace dead neigh\n"); + return; + } + list_for_each_entry(nh, &neigh_entry->nexthop_list, neigh_list_node) { __mlxsw_sp_nexthop_neigh_update(nh, removing); @@ -3610,7 +3716,7 @@ static bool mlxsw_sp_nexthop4_ipip_type(const struct mlxsw_sp *mlxsw_sp, const struct fib_nh *fib_nh, enum mlxsw_sp_ipip_type *p_ipipt) { - struct net_device *dev = fib_nh->nh_dev; + struct net_device *dev = fib_nh->fib_nh_dev; return dev && fib_nh->nh_parent->fib_type == RTN_UNICAST && @@ -3637,7 +3743,7 @@ static int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp, struct fib_nh *fib_nh) { const struct mlxsw_sp_ipip_ops *ipip_ops; - struct net_device *dev = fib_nh->nh_dev; + struct net_device *dev = fib_nh->fib_nh_dev; struct mlxsw_sp_ipip_entry *ipip_entry; struct mlxsw_sp_rif *rif; int err; @@ -3681,18 +3787,18 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh, struct fib_nh *fib_nh) { - struct net_device *dev = fib_nh->nh_dev; + struct net_device *dev = fib_nh->fib_nh_dev; struct in_device *in_dev; int err; nh->nh_grp = nh_grp; nh->key.fib_nh = fib_nh; #ifdef CONFIG_IP_ROUTE_MULTIPATH - nh->nh_weight = fib_nh->nh_weight; + nh->nh_weight = fib_nh->fib_nh_weight; #else nh->nh_weight = 1; #endif - memcpy(&nh->gw_addr, &fib_nh->nh_gw, sizeof(fib_nh->nh_gw)); + memcpy(&nh->gw_addr, &fib_nh->fib_nh_gw4, sizeof(fib_nh->fib_nh_gw4)); err = mlxsw_sp_nexthop_insert(mlxsw_sp, nh); if (err) return err; @@ -3705,7 +3811,7 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, in_dev = __in_dev_get_rtnl(dev); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && - fib_nh->nh_flags & RTNH_F_LINKDOWN) + fib_nh->fib_nh_flags & RTNH_F_LINKDOWN) return 0; err = mlxsw_sp_nexthop4_type_init(mlxsw_sp, nh, fib_nh); @@ -3802,23 +3908,25 @@ static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, } static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp, - const struct fib_info *fi) + struct fib_info *fi) { - return fi->fib_nh->nh_scope == RT_SCOPE_LINK || - mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, fi->fib_nh, NULL); + const struct fib_nh *nh = fib_info_nh(fi, 0); + + return nh->fib_nh_scope == RT_SCOPE_LINK || + mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, nh, NULL); } static struct mlxsw_sp_nexthop_group * mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi) { + unsigned int nhs = fib_info_num_path(fi); struct mlxsw_sp_nexthop_group *nh_grp; struct mlxsw_sp_nexthop *nh; struct fib_nh *fib_nh; int i; int err; - nh_grp = kzalloc(struct_size(nh_grp, nexthops, fi->fib_nhs), - GFP_KERNEL); + nh_grp = kzalloc(struct_size(nh_grp, nexthops, nhs), GFP_KERNEL); if (!nh_grp) return ERR_PTR(-ENOMEM); nh_grp->priv = fi; @@ -3826,11 +3934,11 @@ mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi) nh_grp->neigh_tbl = &arp_tbl; nh_grp->gateway = mlxsw_sp_fi_is_gateway(mlxsw_sp, fi); - nh_grp->count = fi->fib_nhs; + nh_grp->count = nhs; fib_info_hold(fi); for (i = 0; i < nh_grp->count; i++) { nh = &nh_grp->nexthops[i]; - fib_nh = &fi->fib_nh[i]; + fib_nh = fib_info_nh(fi, i); err = mlxsw_sp_nexthop4_init(mlxsw_sp, nh_grp, nh, fib_nh); if (err) goto err_nexthop4_init; @@ -3946,9 +4054,9 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp, struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i]; struct fib6_info *rt = mlxsw_sp_rt6->rt; - if (nh->rif && nh->rif->dev == rt->fib6_nh.nh_dev && + if (nh->rif && nh->rif->dev == rt->fib6_nh->fib_nh_dev && ipv6_addr_equal((const struct in6_addr *) &nh->gw_addr, - &rt->fib6_nh.nh_gw)) + &rt->fib6_nh->fib_nh_gw6)) return nh; continue; } @@ -3966,7 +4074,7 @@ mlxsw_sp_fib4_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE || fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP || fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP) { - nh_grp->nexthops->key.fib_nh->nh_flags |= RTNH_F_OFFLOAD; + nh_grp->nexthops->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD; return; } @@ -3974,9 +4082,9 @@ mlxsw_sp_fib4_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i]; if (nh->offloaded) - nh->key.fib_nh->nh_flags |= RTNH_F_OFFLOAD; + nh->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD; else - nh->key.fib_nh->nh_flags &= ~RTNH_F_OFFLOAD; + nh->key.fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD; } } @@ -3992,7 +4100,7 @@ mlxsw_sp_fib4_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry) for (i = 0; i < nh_grp->count; i++) { struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i]; - nh->key.fib_nh->nh_flags &= ~RTNH_F_OFFLOAD; + nh->key.fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD; } } @@ -4008,19 +4116,20 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL || fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE) { list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6, - list)->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD; + list)->rt->fib6_nh->fib_nh_flags |= RTNH_F_OFFLOAD; return; } list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group; + struct fib6_nh *fib6_nh = mlxsw_sp_rt6->rt->fib6_nh; struct mlxsw_sp_nexthop *nh; nh = mlxsw_sp_rt6_nexthop(nh_grp, mlxsw_sp_rt6); if (nh && nh->offloaded) - mlxsw_sp_rt6->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD; + fib6_nh->fib_nh_flags |= RTNH_F_OFFLOAD; else - mlxsw_sp_rt6->rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD; + fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD; } } @@ -4035,7 +4144,7 @@ mlxsw_sp_fib6_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry) list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { struct fib6_info *rt = mlxsw_sp_rt6->rt; - rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD; + rt->fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD; } } @@ -4110,15 +4219,50 @@ mlxsw_sp_fib_entry_ralue_pack(char *ralue_pl, } } +static int mlxsw_sp_adj_discard_write(struct mlxsw_sp *mlxsw_sp, u16 rif_index) +{ + enum mlxsw_reg_ratr_trap_action trap_action; + char ratr_pl[MLXSW_REG_RATR_LEN]; + int err; + + if (mlxsw_sp->router->adj_discard_index_valid) + return 0; + + err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + &mlxsw_sp->router->adj_discard_index); + if (err) + return err; + + trap_action = MLXSW_REG_RATR_TRAP_ACTION_DISCARD_ERRORS; + mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, true, + MLXSW_REG_RATR_TYPE_ETHERNET, + mlxsw_sp->router->adj_discard_index, rif_index); + mlxsw_reg_ratr_trap_action_set(ratr_pl, trap_action); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); + if (err) + goto err_ratr_write; + + mlxsw_sp->router->adj_discard_index_valid = true; + + return 0; + +err_ratr_write: + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + mlxsw_sp->router->adj_discard_index); + return err; +} + static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, enum mlxsw_reg_ralue_op op) { + struct mlxsw_sp_nexthop_group *nh_group = fib_entry->nh_group; char ralue_pl[MLXSW_REG_RALUE_LEN]; enum mlxsw_reg_ralue_trap_action trap_action; u16 trap_id = 0; u32 adjacency_index = 0; u16 ecmp_size = 0; + int err; /* In case the nexthop group adjacency index is valid, use it * with provided ECMP size. Otherwise, setup trap and pass @@ -4128,6 +4272,15 @@ static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP; adjacency_index = fib_entry->nh_group->adj_index; ecmp_size = fib_entry->nh_group->ecmp_size; + } else if (!nh_group->adj_index_valid && nh_group->count && + nh_group->nh_rif) { + err = mlxsw_sp_adj_discard_write(mlxsw_sp, + nh_group->nh_rif->rif_index); + if (err) + return err; + trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP; + adjacency_index = mlxsw_sp->router->adj_discard_index; + ecmp_size = 1; } else { trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP; trap_id = MLXSW_TRAP_ID_RTR_INGRESS0; @@ -4188,6 +4341,23 @@ static int mlxsw_sp_fib_entry_op_blackhole(struct mlxsw_sp *mlxsw_sp, } static int +mlxsw_sp_fib_entry_op_unreachable(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) +{ + enum mlxsw_reg_ralue_trap_action trap_action; + char ralue_pl[MLXSW_REG_RALUE_LEN]; + u16 trap_id; + + trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP; + trap_id = MLXSW_TRAP_ID_RTR_INGRESS1; + + mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); + mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, 0); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); +} + +static int mlxsw_sp_fib_entry_op_ipip_decap(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, enum mlxsw_reg_ralue_op op) @@ -4228,6 +4398,9 @@ static int __mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_fib_entry_op_trap(mlxsw_sp, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE: return mlxsw_sp_fib_entry_op_blackhole(mlxsw_sp, fib_entry, op); + case MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE: + return mlxsw_sp_fib_entry_op_unreachable(mlxsw_sp, fib_entry, + op); case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP: return mlxsw_sp_fib_entry_op_ipip_decap(mlxsw_sp, fib_entry, op); @@ -4267,9 +4440,9 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, const struct fib_entry_notifier_info *fen_info, struct mlxsw_sp_fib_entry *fib_entry) { + struct net_device *dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev; union mlxsw_sp_l3addr dip = { .addr4 = htonl(fen_info->dst) }; u32 tb_id = mlxsw_sp_fix_tb_id(fen_info->tb_id); - struct net_device *dev = fen_info->fi->fib_dev; struct mlxsw_sp_ipip_entry *ipip_entry; struct fib_info *fi = fen_info->fi; @@ -4305,7 +4478,7 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, * can do so with a lower priority than packets directed * at the host, so use action type local instead of trap. */ - fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE; return 0; case RTN_UNICAST: if (mlxsw_sp_fi_is_gateway(mlxsw_sp, fi)) @@ -4913,7 +5086,8 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6) static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt) { /* RTF_CACHE routes are ignored */ - return (rt->fib6_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY; + return !(rt->fib6_flags & RTF_ADDRCONF) && + rt->fib6_nh->fib_nh_gw_family; } static struct fib6_info * @@ -4972,8 +5146,8 @@ static bool mlxsw_sp_nexthop6_ipip_type(const struct mlxsw_sp *mlxsw_sp, const struct fib6_info *rt, enum mlxsw_sp_ipip_type *ret) { - return rt->fib6_nh.nh_dev && - mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->fib6_nh.nh_dev, ret); + return rt->fib6_nh->fib_nh_dev && + mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->fib6_nh->fib_nh_dev, ret); } static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp, @@ -4983,7 +5157,7 @@ static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp, { const struct mlxsw_sp_ipip_ops *ipip_ops; struct mlxsw_sp_ipip_entry *ipip_entry; - struct net_device *dev = rt->fib6_nh.nh_dev; + struct net_device *dev = rt->fib6_nh->fib_nh_dev; struct mlxsw_sp_rif *rif; int err; @@ -5026,11 +5200,11 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh, const struct fib6_info *rt) { - struct net_device *dev = rt->fib6_nh.nh_dev; + struct net_device *dev = rt->fib6_nh->fib_nh_dev; nh->nh_grp = nh_grp; - nh->nh_weight = rt->fib6_nh.nh_weight; - memcpy(&nh->gw_addr, &rt->fib6_nh.nh_gw, sizeof(nh->gw_addr)); + nh->nh_weight = rt->fib6_nh->fib_nh_weight; + memcpy(&nh->gw_addr, &rt->fib6_nh->fib_nh_gw6, sizeof(nh->gw_addr)); mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh); list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list); @@ -5053,7 +5227,7 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp, static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp, const struct fib6_info *rt) { - return rt->fib6_flags & RTF_GATEWAY || + return rt->fib6_nh->fib_nh_gw_family || mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, NULL); } @@ -5192,17 +5366,21 @@ err_nexthop6_group_get: static int mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib6_entry *fib6_entry, - struct fib6_info *rt) + struct fib6_info **rt_arr, unsigned int nrt6) { struct mlxsw_sp_rt6 *mlxsw_sp_rt6; - int err; + int err, i; - mlxsw_sp_rt6 = mlxsw_sp_rt6_create(rt); - if (IS_ERR(mlxsw_sp_rt6)) - return PTR_ERR(mlxsw_sp_rt6); + for (i = 0; i < nrt6; i++) { + mlxsw_sp_rt6 = mlxsw_sp_rt6_create(rt_arr[i]); + if (IS_ERR(mlxsw_sp_rt6)) { + err = PTR_ERR(mlxsw_sp_rt6); + goto err_rt6_create; + } - list_add_tail(&mlxsw_sp_rt6->list, &fib6_entry->rt6_list); - fib6_entry->nrt6++; + list_add_tail(&mlxsw_sp_rt6->list, &fib6_entry->rt6_list); + fib6_entry->nrt6++; + } err = mlxsw_sp_nexthop6_group_update(mlxsw_sp, fib6_entry); if (err) @@ -5211,27 +5389,38 @@ mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp, return 0; err_nexthop6_group_update: - fib6_entry->nrt6--; - list_del(&mlxsw_sp_rt6->list); - mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); + i = nrt6; +err_rt6_create: + for (i--; i >= 0; i--) { + fib6_entry->nrt6--; + mlxsw_sp_rt6 = list_last_entry(&fib6_entry->rt6_list, + struct mlxsw_sp_rt6, list); + list_del(&mlxsw_sp_rt6->list); + mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); + } return err; } static void mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib6_entry *fib6_entry, - struct fib6_info *rt) + struct fib6_info **rt_arr, unsigned int nrt6) { struct mlxsw_sp_rt6 *mlxsw_sp_rt6; + int i; - mlxsw_sp_rt6 = mlxsw_sp_fib6_entry_rt_find(fib6_entry, rt); - if (WARN_ON(!mlxsw_sp_rt6)) - return; + for (i = 0; i < nrt6; i++) { + mlxsw_sp_rt6 = mlxsw_sp_fib6_entry_rt_find(fib6_entry, + rt_arr[i]); + if (WARN_ON_ONCE(!mlxsw_sp_rt6)) + continue; + + fib6_entry->nrt6--; + list_del(&mlxsw_sp_rt6->list); + mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); + } - fib6_entry->nrt6--; - list_del(&mlxsw_sp_rt6->list); mlxsw_sp_nexthop6_group_update(mlxsw_sp, fib6_entry); - mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); } static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, @@ -5249,7 +5438,7 @@ static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, else if (rt->fib6_type == RTN_BLACKHOLE) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE; else if (rt->fib6_flags & RTF_REJECT) - fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE; else if (mlxsw_sp_rt6_is_gateway(mlxsw_sp, rt)) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; else @@ -5272,29 +5461,32 @@ mlxsw_sp_fib6_entry_rt_destroy_all(struct mlxsw_sp_fib6_entry *fib6_entry) static struct mlxsw_sp_fib6_entry * mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node, - struct fib6_info *rt) + struct fib6_info **rt_arr, unsigned int nrt6) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_entry *fib_entry; struct mlxsw_sp_rt6 *mlxsw_sp_rt6; - int err; + int err, i; fib6_entry = kzalloc(sizeof(*fib6_entry), GFP_KERNEL); if (!fib6_entry) return ERR_PTR(-ENOMEM); fib_entry = &fib6_entry->common; - mlxsw_sp_rt6 = mlxsw_sp_rt6_create(rt); - if (IS_ERR(mlxsw_sp_rt6)) { - err = PTR_ERR(mlxsw_sp_rt6); - goto err_rt6_create; + INIT_LIST_HEAD(&fib6_entry->rt6_list); + + for (i = 0; i < nrt6; i++) { + mlxsw_sp_rt6 = mlxsw_sp_rt6_create(rt_arr[i]); + if (IS_ERR(mlxsw_sp_rt6)) { + err = PTR_ERR(mlxsw_sp_rt6); + goto err_rt6_create; + } + list_add_tail(&mlxsw_sp_rt6->list, &fib6_entry->rt6_list); + fib6_entry->nrt6++; } - mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, mlxsw_sp_rt6->rt); + mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, rt_arr[0]); - INIT_LIST_HEAD(&fib6_entry->rt6_list); - list_add_tail(&mlxsw_sp_rt6->list, &fib6_entry->rt6_list); - fib6_entry->nrt6 = 1; err = mlxsw_sp_nexthop6_group_get(mlxsw_sp, fib6_entry); if (err) goto err_nexthop6_group_get; @@ -5304,9 +5496,15 @@ mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp, return fib6_entry; err_nexthop6_group_get: - list_del(&mlxsw_sp_rt6->list); - mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); + i = nrt6; err_rt6_create: + for (i--; i >= 0; i--) { + fib6_entry->nrt6--; + mlxsw_sp_rt6 = list_last_entry(&fib6_entry->rt6_list, + struct mlxsw_sp_rt6, list); + list_del(&mlxsw_sp_rt6->list); + mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); + } kfree(fib6_entry); return ERR_PTR(err); } @@ -5349,16 +5547,16 @@ mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node, static int mlxsw_sp_fib6_node_list_insert(struct mlxsw_sp_fib6_entry *new6_entry, - bool replace) + bool *p_replace) { struct mlxsw_sp_fib_node *fib_node = new6_entry->common.fib_node; struct fib6_info *nrt = mlxsw_sp_fib6_entry_rt(new6_entry); struct mlxsw_sp_fib6_entry *fib6_entry; - fib6_entry = mlxsw_sp_fib6_node_entry_find(fib_node, nrt, replace); + fib6_entry = mlxsw_sp_fib6_node_entry_find(fib_node, nrt, *p_replace); - if (replace && WARN_ON(!fib6_entry)) - return -EINVAL; + if (*p_replace && !fib6_entry) + *p_replace = false; if (fib6_entry) { list_add_tail(&new6_entry->common.list, @@ -5393,11 +5591,11 @@ mlxsw_sp_fib6_node_list_remove(struct mlxsw_sp_fib6_entry *fib6_entry) static int mlxsw_sp_fib6_node_entry_link(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib6_entry *fib6_entry, - bool replace) + bool *p_replace) { int err; - err = mlxsw_sp_fib6_node_list_insert(fib6_entry, replace); + err = mlxsw_sp_fib6_node_list_insert(fib6_entry, p_replace); if (err) return err; @@ -5470,10 +5668,12 @@ static void mlxsw_sp_fib6_entry_replace(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, - struct fib6_info *rt, bool replace) + struct fib6_info **rt_arr, + unsigned int nrt6, bool replace) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; + struct fib6_info *rt = rt_arr[0]; int err; if (mlxsw_sp->router->aborted) @@ -5498,19 +5698,21 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, */ fib6_entry = mlxsw_sp_fib6_node_mp_entry_find(fib_node, rt, replace); if (fib6_entry) { - err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, fib6_entry, rt); + err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, fib6_entry, + rt_arr, nrt6); if (err) goto err_fib6_entry_nexthop_add; return 0; } - fib6_entry = mlxsw_sp_fib6_entry_create(mlxsw_sp, fib_node, rt); + fib6_entry = mlxsw_sp_fib6_entry_create(mlxsw_sp, fib_node, rt_arr, + nrt6); if (IS_ERR(fib6_entry)) { err = PTR_ERR(fib6_entry); goto err_fib6_entry_create; } - err = mlxsw_sp_fib6_node_entry_link(mlxsw_sp, fib6_entry, replace); + err = mlxsw_sp_fib6_node_entry_link(mlxsw_sp, fib6_entry, &replace); if (err) goto err_fib6_node_entry_link; @@ -5527,10 +5729,12 @@ err_fib6_entry_nexthop_add: } static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, - struct fib6_info *rt) + struct fib6_info **rt_arr, + unsigned int nrt6) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; + struct fib6_info *rt = rt_arr[0]; if (mlxsw_sp->router->aborted) return; @@ -5542,11 +5746,12 @@ static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, if (WARN_ON(!fib6_entry)) return; - /* If route is part of a multipath entry, but not the last one - * removed, then only reduce its nexthop group. + /* If not all the nexthops are deleted, then only reduce the nexthop + * group. */ - if (!list_is_singular(&fib6_entry->rt6_list)) { - mlxsw_sp_fib6_entry_nexthop_del(mlxsw_sp, fib6_entry, rt); + if (nrt6 != fib6_entry->nrt6) { + mlxsw_sp_fib6_entry_nexthop_del(mlxsw_sp, fib6_entry, rt_arr, + nrt6); return; } @@ -5791,6 +5996,16 @@ static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) continue; mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV6); } + + /* After flushing all the routes, it is not possible anyone is still + * using the adjacency index that is discarding packets, so free it in + * case it was allocated. + */ + if (!mlxsw_sp->router->adj_discard_index_valid) + return; + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + mlxsw_sp->router->adj_discard_index); + mlxsw_sp->router->adj_discard_index_valid = false; } static void mlxsw_sp_router_fib_abort(struct mlxsw_sp *mlxsw_sp) @@ -5807,10 +6022,15 @@ static void mlxsw_sp_router_fib_abort(struct mlxsw_sp *mlxsw_sp) dev_warn(mlxsw_sp->bus_info->dev, "Failed to set abort trap.\n"); } +struct mlxsw_sp_fib6_event_work { + struct fib6_info **rt_arr; + unsigned int nrt6; +}; + struct mlxsw_sp_fib_event_work { struct work_struct work; union { - struct fib6_entry_notifier_info fen6_info; + struct mlxsw_sp_fib6_event_work fib6_work; struct fib_entry_notifier_info fen_info; struct fib_rule_notifier_info fr_info; struct fib_nh_notifier_info fnh_info; @@ -5821,6 +6041,54 @@ struct mlxsw_sp_fib_event_work { unsigned long event; }; +static int +mlxsw_sp_router_fib6_work_init(struct mlxsw_sp_fib6_event_work *fib6_work, + struct fib6_entry_notifier_info *fen6_info) +{ + struct fib6_info *rt = fen6_info->rt; + struct fib6_info **rt_arr; + struct fib6_info *iter; + unsigned int nrt6; + int i = 0; + + nrt6 = fen6_info->nsiblings + 1; + + rt_arr = kcalloc(nrt6, sizeof(struct fib6_info *), GFP_ATOMIC); + if (!rt_arr) + return -ENOMEM; + + fib6_work->rt_arr = rt_arr; + fib6_work->nrt6 = nrt6; + + rt_arr[0] = rt; + fib6_info_hold(rt); + + if (!fen6_info->nsiblings) + return 0; + + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { + if (i == fen6_info->nsiblings) + break; + + rt_arr[i + 1] = iter; + fib6_info_hold(iter); + i++; + } + WARN_ON_ONCE(i != fen6_info->nsiblings); + + return 0; +} + +static void +mlxsw_sp_router_fib6_work_fini(struct mlxsw_sp_fib6_event_work *fib6_work) +{ + int i; + + for (i = 0; i < fib6_work->nrt6; i++) + mlxsw_sp_rt6_release(fib6_work->rt_arr[i]); + kfree(fib6_work->rt_arr); +} + static void mlxsw_sp_router_fib4_event_work(struct work_struct *work) { struct mlxsw_sp_fib_event_work *fib_work = @@ -5849,12 +6117,6 @@ static void mlxsw_sp_router_fib4_event_work(struct work_struct *work) mlxsw_sp_router_fib4_del(mlxsw_sp, &fib_work->fen_info); fib_info_put(fib_work->fen_info.fi); break; - case FIB_EVENT_RULE_ADD: - /* if we get here, a rule was added that we do not support. - * just do the fib_abort - */ - mlxsw_sp_router_fib_abort(mlxsw_sp); - break; case FIB_EVENT_NH_ADD: /* fall through */ case FIB_EVENT_NH_DEL: mlxsw_sp_nexthop4_event(mlxsw_sp, fib_work->event, @@ -5879,24 +6141,21 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: /* fall through */ - case FIB_EVENT_ENTRY_APPEND: /* fall through */ case FIB_EVENT_ENTRY_ADD: replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE; err = mlxsw_sp_router_fib6_add(mlxsw_sp, - fib_work->fen6_info.rt, replace); + fib_work->fib6_work.rt_arr, + fib_work->fib6_work.nrt6, + replace); if (err) mlxsw_sp_router_fib_abort(mlxsw_sp); - mlxsw_sp_rt6_release(fib_work->fen6_info.rt); + mlxsw_sp_router_fib6_work_fini(&fib_work->fib6_work); break; case FIB_EVENT_ENTRY_DEL: - mlxsw_sp_router_fib6_del(mlxsw_sp, fib_work->fen6_info.rt); - mlxsw_sp_rt6_release(fib_work->fen6_info.rt); - break; - case FIB_EVENT_RULE_ADD: - /* if we get here, a rule was added that we do not support. - * just do the fib_abort - */ - mlxsw_sp_router_fib_abort(mlxsw_sp); + mlxsw_sp_router_fib6_del(mlxsw_sp, + fib_work->fib6_work.rt_arr, + fib_work->fib6_work.nrt6); + mlxsw_sp_router_fib6_work_fini(&fib_work->fib6_work); break; } rtnl_unlock(); @@ -5939,12 +6198,6 @@ static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work) &fib_work->ven_info); dev_put(fib_work->ven_info.dev); break; - case FIB_EVENT_RULE_ADD: - /* if we get here, a rule was added that we do not support. - * just do the fib_abort - */ - mlxsw_sp_router_fib_abort(mlxsw_sp); - break; } rtnl_unlock(); kfree(fib_work); @@ -5979,22 +6232,26 @@ static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work, } } -static void mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work, - struct fib_notifier_info *info) +static int mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work, + struct fib_notifier_info *info) { struct fib6_entry_notifier_info *fen6_info; + int err; switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: /* fall through */ - case FIB_EVENT_ENTRY_APPEND: /* fall through */ case FIB_EVENT_ENTRY_ADD: /* fall through */ case FIB_EVENT_ENTRY_DEL: fen6_info = container_of(info, struct fib6_entry_notifier_info, info); - fib_work->fen6_info = *fen6_info; - fib6_info_hold(fib_work->fen6_info.rt); + err = mlxsw_sp_router_fib6_work_init(&fib_work->fib6_work, + fen6_info); + if (err) + return err; break; } + + return 0; } static void @@ -6035,6 +6292,10 @@ static int mlxsw_sp_router_fib_rule_event(unsigned long event, fr_info = container_of(info, struct fib_rule_notifier_info, info); rule = fr_info->rule; + /* Rule only affects locally generated traffic */ + if (rule->iifindex == mlxsw_sp_net(mlxsw_sp)->loopback_dev->ifindex) + return 0; + switch (info->family) { case AF_INET: if (!fib4_rule_default(rule) && !rule->l3mdev) @@ -6069,8 +6330,7 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, struct mlxsw_sp_router *router; int err; - if (!net_eq(info->net, &init_net) || - (info->family != AF_INET && info->family != AF_INET6 && + if ((info->family != AF_INET && info->family != AF_INET6 && info->family != RTNL_FAMILY_IPMR && info->family != RTNL_FAMILY_IP6MR)) return NOTIFY_DONE; @@ -6082,14 +6342,36 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, case FIB_EVENT_RULE_DEL: err = mlxsw_sp_router_fib_rule_event(event, info, router->mlxsw_sp); - if (!err || info->extack) - return notifier_from_errno(err); - break; + return notifier_from_errno(err); case FIB_EVENT_ENTRY_ADD: + case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_APPEND: /* fall through */ if (router->aborted) { NL_SET_ERR_MSG_MOD(info->extack, "FIB offload was aborted. Not configuring route"); return notifier_from_errno(-EINVAL); } + if (info->family == AF_INET) { + struct fib_entry_notifier_info *fen_info = ptr; + + if (fen_info->fi->fib_nh_is_v6) { + NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported"); + return notifier_from_errno(-EINVAL); + } + if (fen_info->fi->nh) { + NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported"); + return notifier_from_errno(-EINVAL); + } + } else if (info->family == AF_INET6) { + struct fib6_entry_notifier_info *fen6_info; + + fen6_info = container_of(info, + struct fib6_entry_notifier_info, + info); + if (fen6_info->rt->nh) { + NL_SET_ERR_MSG_MOD(info->extack, "IPv6 route with nexthop objects is not supported"); + return notifier_from_errno(-EINVAL); + } + } break; } @@ -6107,7 +6389,9 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, break; case AF_INET6: INIT_WORK(&fib_work->work, mlxsw_sp_router_fib6_event_work); - mlxsw_sp_router_fib6_event(fib_work, info); + err = mlxsw_sp_router_fib6_event(fib_work, info); + if (err) + goto err_fib_event; break; case RTNL_FAMILY_IP6MR: case RTNL_FAMILY_IPMR: @@ -6119,6 +6403,10 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, mlxsw_core_schedule_work(&fib_work->work); return NOTIFY_DONE; + +err_fib_event: + kfree(fib_work); + return NOTIFY_BAD; } struct mlxsw_sp_rif * @@ -6781,7 +7069,7 @@ static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp, /* A RIF is not created for macvlan netdevs. Their MAC is used to * populate the FDB */ - if (netif_is_macvlan(dev)) + if (netif_is_macvlan(dev) || netif_is_l3_master(dev)) return 0; for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { @@ -7763,9 +8051,10 @@ static void mlxsw_sp_mp_hash_field_set(char *recr2_pl, int field) mlxsw_reg_recr2_outer_header_fields_enable_set(recr2_pl, field, true); } -static void mlxsw_sp_mp4_hash_init(char *recr2_pl) +static void mlxsw_sp_mp4_hash_init(struct mlxsw_sp *mlxsw_sp, char *recr2_pl) { - bool only_l3 = !init_net.ipv4.sysctl_fib_multipath_hash_policy; + struct net *net = mlxsw_sp_net(mlxsw_sp); + bool only_l3 = !net->ipv4.sysctl_fib_multipath_hash_policy; mlxsw_sp_mp_hash_header_set(recr2_pl, MLXSW_REG_RECR2_IPV4_EN_NOT_TCP_NOT_UDP); @@ -7780,9 +8069,9 @@ static void mlxsw_sp_mp4_hash_init(char *recr2_pl) mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_TCP_UDP_DPORT); } -static void mlxsw_sp_mp6_hash_init(char *recr2_pl) +static void mlxsw_sp_mp6_hash_init(struct mlxsw_sp *mlxsw_sp, char *recr2_pl) { - bool only_l3 = !ip6_multipath_hash_policy(&init_net); + bool only_l3 = !ip6_multipath_hash_policy(mlxsw_sp_net(mlxsw_sp)); mlxsw_sp_mp_hash_header_set(recr2_pl, MLXSW_REG_RECR2_IPV6_EN_NOT_TCP_NOT_UDP); @@ -7808,10 +8097,10 @@ static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp) char recr2_pl[MLXSW_REG_RECR2_LEN]; u32 seed; - get_random_bytes(&seed, sizeof(seed)); + seed = jhash(mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac), 0); mlxsw_reg_recr2_pack(recr2_pl, seed); - mlxsw_sp_mp4_hash_init(recr2_pl); - mlxsw_sp_mp6_hash_init(recr2_pl); + mlxsw_sp_mp4_hash_init(mlxsw_sp, recr2_pl); + mlxsw_sp_mp6_hash_init(mlxsw_sp, recr2_pl); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(recr2), recr2_pl); } @@ -7842,7 +8131,8 @@ static int mlxsw_sp_dscp_init(struct mlxsw_sp *mlxsw_sp) static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) { - bool usp = init_net.ipv4.sysctl_ip_fwd_update_priority; + struct net *net = mlxsw_sp_net(mlxsw_sp); + bool usp = net->ipv4.sysctl_ip_fwd_update_priority; char rgcr_pl[MLXSW_REG_RGCR_LEN]; u64 max_rifs; int err; @@ -7868,7 +8158,8 @@ static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); } -int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) +int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, + struct netlink_ext_ack *extack) { struct mlxsw_sp_router *router; int err; @@ -7944,8 +8235,9 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) goto err_dscp_init; mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event; - err = register_fib_notifier(&mlxsw_sp->router->fib_nb, - mlxsw_sp_router_fib_dump_flush); + err = register_fib_notifier(mlxsw_sp_net(mlxsw_sp), + &mlxsw_sp->router->fib_nb, + mlxsw_sp_router_fib_dump_flush, extack); if (err) goto err_register_fib_notifier; @@ -7984,7 +8276,8 @@ err_register_inetaddr_notifier: void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) { - unregister_fib_notifier(&mlxsw_sp->router->fib_nb); + unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), + &mlxsw_sp->router->fib_nb); unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); mlxsw_sp_neigh_fini(mlxsw_sp); mlxsw_sp_vrs_fini(mlxsw_sp); |
