diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core/en_tc.c')
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 1107 |
1 files changed, 263 insertions, 844 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index dd0bfbacad47..0da69b98f38f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -63,6 +63,8 @@ #include "en/mapping.h" #include "en/tc_ct.h" #include "en/mod_hdr.h" +#include "en/tc_priv.h" +#include "en/tc_tun_encap.h" #include "lib/devcom.h" #include "lib/geneve.h" #include "lib/fs_chains.h" @@ -71,90 +73,6 @@ #define nic_chains(priv) ((priv)->fs.tc.chains) #define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto) -#define MLX5E_TC_FLOW_BASE (MLX5E_TC_FLAG_LAST_EXPORTED_BIT + 1) - -enum { - MLX5E_TC_FLOW_FLAG_INGRESS = MLX5E_TC_FLAG_INGRESS_BIT, - MLX5E_TC_FLOW_FLAG_EGRESS = MLX5E_TC_FLAG_EGRESS_BIT, - MLX5E_TC_FLOW_FLAG_ESWITCH = MLX5E_TC_FLAG_ESW_OFFLOAD_BIT, - MLX5E_TC_FLOW_FLAG_FT = MLX5E_TC_FLAG_FT_OFFLOAD_BIT, - MLX5E_TC_FLOW_FLAG_NIC = MLX5E_TC_FLAG_NIC_OFFLOAD_BIT, - MLX5E_TC_FLOW_FLAG_OFFLOADED = MLX5E_TC_FLOW_BASE, - MLX5E_TC_FLOW_FLAG_HAIRPIN = MLX5E_TC_FLOW_BASE + 1, - MLX5E_TC_FLOW_FLAG_HAIRPIN_RSS = MLX5E_TC_FLOW_BASE + 2, - MLX5E_TC_FLOW_FLAG_SLOW = MLX5E_TC_FLOW_BASE + 3, - MLX5E_TC_FLOW_FLAG_DUP = MLX5E_TC_FLOW_BASE + 4, - MLX5E_TC_FLOW_FLAG_NOT_READY = MLX5E_TC_FLOW_BASE + 5, - MLX5E_TC_FLOW_FLAG_DELETED = MLX5E_TC_FLOW_BASE + 6, - MLX5E_TC_FLOW_FLAG_CT = MLX5E_TC_FLOW_BASE + 7, - MLX5E_TC_FLOW_FLAG_L3_TO_L2_DECAP = MLX5E_TC_FLOW_BASE + 8, -}; - -#define MLX5E_TC_MAX_SPLITS 1 - -/* Helper struct for accessing a struct containing list_head array. - * Containing struct - * |- Helper array - * [0] Helper item 0 - * |- list_head item 0 - * |- index (0) - * [1] Helper item 1 - * |- list_head item 1 - * |- index (1) - * To access the containing struct from one of the list_head items: - * 1. Get the helper item from the list_head item using - * helper item = - * container_of(list_head item, helper struct type, list_head field) - * 2. Get the contining struct from the helper item and its index in the array: - * containing struct = - * container_of(helper item, containing struct type, helper field[index]) - */ -struct encap_flow_item { - struct mlx5e_encap_entry *e; /* attached encap instance */ - struct list_head list; - int index; -}; - -struct mlx5e_tc_flow { - struct rhash_head node; - struct mlx5e_priv *priv; - u64 cookie; - unsigned long flags; - struct mlx5_flow_handle *rule[MLX5E_TC_MAX_SPLITS + 1]; - - /* flows sharing the same reformat object - currently mpls decap */ - struct list_head l3_to_l2_reformat; - struct mlx5e_decap_entry *decap_reformat; - - /* Flow can be associated with multiple encap IDs. - * The number of encaps is bounded by the number of supported - * destinations. - */ - struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS]; - struct mlx5e_tc_flow *peer_flow; - struct mlx5e_mod_hdr_handle *mh; /* attached mod header instance */ - struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */ - struct list_head hairpin; /* flows sharing the same hairpin */ - struct list_head peer; /* flows with peer flow */ - struct list_head unready; /* flows not ready to be offloaded (e.g due to missing route) */ - struct net_device *orig_dev; /* netdev adding flow first */ - int tmp_efi_index; - struct list_head tmp_list; /* temporary flow list used by neigh update */ - refcount_t refcnt; - struct rcu_head rcu_head; - struct completion init_done; - int tunnel_id; /* the mapped tunnel id of this flow */ - struct mlx5_flow_attr *attr; -}; - -struct mlx5e_tc_flow_parse_attr { - const struct ip_tunnel_info *tun_info[MLX5_MAX_FLOW_FWD_VPORTS]; - struct net_device *filter_dev; - struct mlx5_flow_spec spec; - struct mlx5e_tc_mod_hdr_acts mod_hdr_acts; - int mirred_ifindex[MLX5_MAX_FLOW_FWD_VPORTS]; - struct ethhdr eth; -}; #define MLX5E_TC_TABLE_NUM_GROUPS 4 #define MLX5E_TC_TABLE_MAX_GROUP_SIZE BIT(18) @@ -165,10 +83,15 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = { .moffset = 0, .mlen = 2, }, + [VPORT_TO_REG] = { + .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_0, + .moffset = 2, + .mlen = 2, + }, [TUNNEL_TO_REG] = { .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_1, .moffset = 1, - .mlen = 3, + .mlen = ((ESW_TUN_OPTS_BITS + ESW_TUN_ID_BITS) / 8), .soffset = MLX5_BYTE_OFF(fte_match_param, misc_parameters_2.metadata_reg_c_1), }, @@ -190,6 +113,14 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = { [NIC_ZONE_RESTORE_TO_REG] = nic_zone_restore_to_reg_ct, }; +/* To avoid false lock dependency warning set the tc_ht lock + * class different than the lock class of the ht being used when deleting + * last flow from a group and then deleting a group, we get into del_sw_flow_group() + * which call rhashtable_destroy on fg->ftes_hash which will take ht->mutex but + * it's different than the ht->mutex here. + */ +static struct lock_class_key tc_ht_lock_key; + static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow); void @@ -239,11 +170,11 @@ mlx5e_tc_match_to_reg_get_match(struct mlx5_flow_spec *spec, } int -mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev, - struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts, - enum mlx5_flow_namespace_type ns, - enum mlx5e_tc_attr_to_reg type, - u32 data) +mlx5e_tc_match_to_reg_set_and_get_id(struct mlx5_core_dev *mdev, + struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts, + enum mlx5_flow_namespace_type ns, + enum mlx5e_tc_attr_to_reg type, + u32 data) { int moffset = mlx5e_tc_attr_to_reg_mappings[type].moffset; int mfield = mlx5e_tc_attr_to_reg_mappings[type].mfield; @@ -267,9 +198,10 @@ mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev, MLX5_SET(set_action_in, modact, offset, moffset * 8); MLX5_SET(set_action_in, modact, length, mlen * 8); MLX5_SET(set_action_in, modact, data, data); + err = mod_hdr_acts->num_actions; mod_hdr_acts->num_actions++; - return 0; + return err; } static struct mlx5_tc_ct_priv * @@ -318,6 +250,41 @@ mlx5_tc_rule_delete(struct mlx5e_priv *priv, mlx5e_del_offloaded_nic_rule(priv, rule, attr); } +int +mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev, + struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts, + enum mlx5_flow_namespace_type ns, + enum mlx5e_tc_attr_to_reg type, + u32 data) +{ + int ret = mlx5e_tc_match_to_reg_set_and_get_id(mdev, mod_hdr_acts, ns, type, data); + + return ret < 0 ? ret : 0; +} + +void mlx5e_tc_match_to_reg_mod_hdr_change(struct mlx5_core_dev *mdev, + struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts, + enum mlx5e_tc_attr_to_reg type, + int act_id, u32 data) +{ + int moffset = mlx5e_tc_attr_to_reg_mappings[type].moffset; + int mfield = mlx5e_tc_attr_to_reg_mappings[type].mfield; + int mlen = mlx5e_tc_attr_to_reg_mappings[type].mlen; + char *modact; + + modact = mod_hdr_acts->actions + (act_id * MLX5_MH_ACT_SZ); + + /* Firmware has 5bit length field and 0 means 32bits */ + if (mlen == 4) + mlen = 0; + + MLX5_SET(set_action_in, modact, action_type, MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, modact, field, mfield); + MLX5_SET(set_action_in, modact, offset, moffset * 8); + MLX5_SET(set_action_in, modact, length, mlen * 8); + MLX5_SET(set_action_in, modact, data, data); +} + struct mlx5e_hairpin { struct mlx5_hairpin *pair; @@ -355,15 +322,14 @@ struct mlx5e_hairpin_entry { static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow); -static struct mlx5e_tc_flow *mlx5e_flow_get(struct mlx5e_tc_flow *flow) +struct mlx5e_tc_flow *mlx5e_flow_get(struct mlx5e_tc_flow *flow) { if (!flow || !refcount_inc_not_zero(&flow->refcnt)) return ERR_PTR(-EINVAL); return flow; } -static void mlx5e_flow_put(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow) +void mlx5e_flow_put(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { if (refcount_dec_and_test(&flow->refcnt)) { mlx5e_tc_del_flow(priv, flow); @@ -371,48 +337,6 @@ static void mlx5e_flow_put(struct mlx5e_priv *priv, } } -static void __flow_flag_set(struct mlx5e_tc_flow *flow, unsigned long flag) -{ - /* Complete all memory stores before setting bit. */ - smp_mb__before_atomic(); - set_bit(flag, &flow->flags); -} - -#define flow_flag_set(flow, flag) __flow_flag_set(flow, MLX5E_TC_FLOW_FLAG_##flag) - -static bool __flow_flag_test_and_set(struct mlx5e_tc_flow *flow, - unsigned long flag) -{ - /* test_and_set_bit() provides all necessary barriers */ - return test_and_set_bit(flag, &flow->flags); -} - -#define flow_flag_test_and_set(flow, flag) \ - __flow_flag_test_and_set(flow, \ - MLX5E_TC_FLOW_FLAG_##flag) - -static void __flow_flag_clear(struct mlx5e_tc_flow *flow, unsigned long flag) -{ - /* Complete all memory stores before clearing bit. */ - smp_mb__before_atomic(); - clear_bit(flag, &flow->flags); -} - -#define flow_flag_clear(flow, flag) __flow_flag_clear(flow, \ - MLX5E_TC_FLOW_FLAG_##flag) - -static bool __flow_flag_test(struct mlx5e_tc_flow *flow, unsigned long flag) -{ - bool ret = test_bit(flag, &flow->flags); - - /* Read fields of flow structure only after checking flags. */ - smp_mb__after_atomic(); - return ret; -} - -#define flow_flag_test(flow, flag) __flow_flag_test(flow, \ - MLX5E_TC_FLOW_FLAG_##flag) - bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow) { return flow_flag_test(flow, ESWITCH); @@ -423,7 +347,7 @@ static bool mlx5e_is_ft_flow(struct mlx5e_tc_flow *flow) return flow_flag_test(flow, FT); } -static bool mlx5e_is_offloaded_flow(struct mlx5e_tc_flow *flow) +bool mlx5e_is_offloaded_flow(struct mlx5e_tc_flow *flow) { return flow_flag_test(flow, OFFLOADED); } @@ -1138,23 +1062,7 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, kfree(flow->attr); } -static void mlx5e_detach_encap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, int out_index); - -static int mlx5e_attach_encap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct net_device *mirred_dev, - int out_index, - struct netlink_ext_ack *extack, - struct net_device **encap_dev, - bool *encap_valid); -static int mlx5e_attach_decap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct netlink_ext_ack *extack); -static void mlx5e_detach_decap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow); - -static struct mlx5_flow_handle * +struct mlx5_flow_handle * mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw, struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *spec, @@ -1189,10 +1097,9 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw, return rule; } -static void -mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, - struct mlx5e_tc_flow *flow, - struct mlx5_flow_attr *attr) +void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr) { flow_flag_clear(flow, OFFLOADED); @@ -1211,7 +1118,7 @@ offload_rule_0: mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr); } -static struct mlx5_flow_handle * +struct mlx5_flow_handle * mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *spec) @@ -1237,9 +1144,8 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, return rule; } -static void -mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, - struct mlx5e_tc_flow *flow) +void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, + struct mlx5e_tc_flow *flow) { struct mlx5_flow_attr *slow_attr; @@ -1307,6 +1213,63 @@ static void remove_unready_flow(struct mlx5e_tc_flow *flow) mutex_unlock(&uplink_priv->unready_flows_lock); } +static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv); + +bool mlx5e_tc_is_vf_tunnel(struct net_device *out_dev, struct net_device *route_dev) +{ + struct mlx5_core_dev *out_mdev, *route_mdev; + struct mlx5e_priv *out_priv, *route_priv; + + out_priv = netdev_priv(out_dev); + out_mdev = out_priv->mdev; + route_priv = netdev_priv(route_dev); + route_mdev = route_priv->mdev; + + if (out_mdev->coredev_type != MLX5_COREDEV_PF || + route_mdev->coredev_type != MLX5_COREDEV_VF) + return false; + + return same_hw_devs(out_priv, route_priv); +} + +int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *route_dev, u16 *vport) +{ + struct mlx5e_priv *out_priv, *route_priv; + struct mlx5_core_dev *route_mdev; + struct mlx5_eswitch *esw; + u16 vhca_id; + int err; + + out_priv = netdev_priv(out_dev); + esw = out_priv->mdev->priv.eswitch; + route_priv = netdev_priv(route_dev); + route_mdev = route_priv->mdev; + + vhca_id = MLX5_CAP_GEN(route_mdev, vhca_id); + err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); + return err; +} + +int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct mlx5e_tc_flow *flow) +{ + struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts = &parse_attr->mod_hdr_acts; + struct mlx5_modify_hdr *mod_hdr; + + mod_hdr = mlx5_modify_header_alloc(priv->mdev, + get_flow_name_space(flow), + mod_hdr_acts->num_actions, + mod_hdr_acts->actions); + if (IS_ERR(mod_hdr)) + return PTR_ERR(mod_hdr); + + WARN_ON(flow->attr->modify_hdr); + flow->attr->modify_hdr = mod_hdr; + + return 0; +} + static int mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, @@ -1316,21 +1279,15 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct net_device *out_dev, *encap_dev = NULL; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; + bool vf_tun = false, encap_valid = true; struct mlx5_esw_flow_attr *esw_attr; struct mlx5_fc *counter = NULL; struct mlx5e_rep_priv *rpriv; struct mlx5e_priv *out_priv; - bool encap_valid = true; u32 max_prio, max_chain; int err = 0; int out_index; - if (!mlx5_chains_prios_supported(esw_chains(esw)) && attr->prio != 1) { - NL_SET_ERR_MSG_MOD(extack, - "E-switch priorities unsupported, upgrade FW"); - return -EOPNOTSUPP; - } - /* We check chain range only for tc flows. * For ft flows, we checked attr->chain was originally 0 and set it to * FDB_FT_CHAIN which is outside tc range. @@ -1340,20 +1297,28 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, if (!mlx5e_is_ft_flow(flow) && attr->chain > max_chain) { NL_SET_ERR_MSG_MOD(extack, "Requested chain is out of supported range"); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto err_out; } max_prio = mlx5_chains_get_prio_range(esw_chains(esw)); if (attr->prio > max_prio) { NL_SET_ERR_MSG_MOD(extack, "Requested priority is out of supported range"); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto err_out; + } + + if (flow_flag_test(flow, TUN_RX)) { + err = mlx5e_attach_decap_route(priv, flow); + if (err) + goto err_out; } if (flow_flag_test(flow, L3_TO_L2_DECAP)) { err = mlx5e_attach_decap(priv, flow, extack); if (err) - return err; + goto err_out; } parse_attr = attr->parse_attr; @@ -1371,8 +1336,11 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, err = mlx5e_attach_encap(priv, flow, out_dev, out_index, extack, &encap_dev, &encap_valid); if (err) - return err; + goto err_out; + if (esw_attr->dests[out_index].flags & + MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE) + vf_tun = true; out_priv = netdev_priv(encap_dev); rpriv = out_priv->ppriv; esw_attr->dests[out_index].rep = rpriv->rep; @@ -1381,20 +1349,27 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, err = mlx5_eswitch_add_vlan_action(esw, attr); if (err) - return err; + goto err_out; if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && !(attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR)) { - err = mlx5e_attach_mod_hdr(priv, flow, parse_attr); - dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts); - if (err) - return err; + if (vf_tun) { + err = mlx5e_tc_add_flow_mod_hdr(priv, parse_attr, flow); + if (err) + goto err_out; + } else { + err = mlx5e_attach_mod_hdr(priv, flow, parse_attr); + if (err) + goto err_out; + } } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { counter = mlx5_fc_create(esw_attr->counter_dev, true); - if (IS_ERR(counter)) - return PTR_ERR(counter); + if (IS_ERR(counter)) { + err = PTR_ERR(counter); + goto err_out; + } attr->counter = counter; } @@ -1408,12 +1383,17 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, else flow->rule[0] = mlx5e_tc_offload_fdb_rules(esw, flow, &parse_attr->spec, attr); - if (IS_ERR(flow->rule[0])) - return PTR_ERR(flow->rule[0]); - else - flow_flag_set(flow, OFFLOADED); + if (IS_ERR(flow->rule[0])) { + err = PTR_ERR(flow->rule[0]); + goto err_out; + } + flow_flag_set(flow, OFFLOADED); return 0; + +err_out: + flow_flag_set(flow, FAILED); + return err; } static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow) @@ -1434,8 +1414,11 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_flow_attr *attr = flow->attr; + struct mlx5_esw_flow_attr *esw_attr; + bool vf_tun = false; int out_index; + esw_attr = attr->esw_attr; mlx5e_put_flow_tunnel_id(flow); if (flow_flag_test(flow, NOT_READY)) @@ -1453,20 +1436,33 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5_eswitch_del_vlan_action(esw, attr); - for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) - if (attr->esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) { + if (flow->decap_route) + mlx5e_detach_decap_route(priv, flow); + + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + if (esw_attr->dests[out_index].flags & + MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE) + vf_tun = true; + if (esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) { mlx5e_detach_encap(priv, flow, out_index); kfree(attr->parse_attr->tun_info[out_index]); } - kvfree(attr->parse_attr); + } mlx5_tc_ct_match_del(get_ct_priv(priv), &flow->attr->ct_attr); - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - mlx5e_detach_mod_hdr(priv, flow); + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { + dealloc_mod_hdr_actions(&attr->parse_attr->mod_hdr_acts); + if (vf_tun && attr->modify_hdr) + mlx5_modify_header_dealloc(priv->mdev, attr->modify_hdr); + else + mlx5e_detach_mod_hdr(priv, flow); + } + kvfree(attr->parse_attr); + kvfree(attr->esw_attr->rx_tun_attr); if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) - mlx5_fc_destroy(attr->esw_attr->counter_dev, attr->counter); + mlx5_fc_destroy(esw_attr->counter_dev, attr->counter); if (flow_flag_test(flow, L3_TO_L2_DECAP)) mlx5e_detach_decap(priv, flow); @@ -1474,141 +1470,13 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, kfree(flow->attr); } -void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, - struct mlx5e_encap_entry *e, - struct list_head *flow_list) -{ - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mlx5_esw_flow_attr *esw_attr; - struct mlx5_flow_handle *rule; - struct mlx5_flow_attr *attr; - struct mlx5_flow_spec *spec; - struct mlx5e_tc_flow *flow; - int err; - - e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - e->encap_size, e->encap_header, - MLX5_FLOW_NAMESPACE_FDB); - if (IS_ERR(e->pkt_reformat)) { - mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %lu\n", - PTR_ERR(e->pkt_reformat)); - return; - } - e->flags |= MLX5_ENCAP_ENTRY_VALID; - mlx5e_rep_queue_neigh_stats_work(priv); - - list_for_each_entry(flow, flow_list, tmp_list) { - bool all_flow_encaps_valid = true; - int i; - - if (!mlx5e_is_offloaded_flow(flow)) - continue; - attr = flow->attr; - esw_attr = attr->esw_attr; - spec = &attr->parse_attr->spec; - - esw_attr->dests[flow->tmp_efi_index].pkt_reformat = e->pkt_reformat; - esw_attr->dests[flow->tmp_efi_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; - /* Flow can be associated with multiple encap entries. - * Before offloading the flow verify that all of them have - * a valid neighbour. - */ - for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) { - if (!(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP)) - continue; - if (!(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP_VALID)) { - all_flow_encaps_valid = false; - break; - } - } - /* Do not offload flows with unresolved neighbors */ - if (!all_flow_encaps_valid) - continue; - /* update from slow path rule to encap rule */ - rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, attr); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - mlx5_core_warn(priv->mdev, "Failed to update cached encapsulation flow, %d\n", - err); - continue; - } - - mlx5e_tc_unoffload_from_slow_path(esw, flow); - flow->rule[0] = rule; - /* was unset when slow path rule removed */ - flow_flag_set(flow, OFFLOADED); - } -} - -void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, - struct mlx5e_encap_entry *e, - struct list_head *flow_list) -{ - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mlx5_esw_flow_attr *esw_attr; - struct mlx5_flow_handle *rule; - struct mlx5_flow_attr *attr; - struct mlx5_flow_spec *spec; - struct mlx5e_tc_flow *flow; - int err; - - list_for_each_entry(flow, flow_list, tmp_list) { - if (!mlx5e_is_offloaded_flow(flow)) - continue; - attr = flow->attr; - esw_attr = attr->esw_attr; - spec = &attr->parse_attr->spec; - - /* update from encap rule to slow path rule */ - rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec); - /* mark the flow's encap dest as non-valid */ - esw_attr->dests[flow->tmp_efi_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID; - - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - mlx5_core_warn(priv->mdev, "Failed to update slow path (encap) flow, %d\n", - err); - continue; - } - - mlx5e_tc_unoffload_fdb_rules(esw, flow, attr); - flow->rule[0] = rule; - /* was unset when fast path rule removed */ - flow_flag_set(flow, OFFLOADED); - } - - /* we know that the encap is valid */ - e->flags &= ~MLX5_ENCAP_ENTRY_VALID; - mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat); -} - -static struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow) +struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow) { return flow->attr->counter; } -/* Takes reference to all flows attached to encap and adds the flows to - * flow_list using 'tmp_list' list_head in mlx5e_tc_flow. - */ -void mlx5e_take_all_encap_flows(struct mlx5e_encap_entry *e, struct list_head *flow_list) -{ - struct encap_flow_item *efi; - struct mlx5e_tc_flow *flow; - - list_for_each_entry(efi, &e->flows, list) { - flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]); - if (IS_ERR(mlx5e_flow_get(flow))) - continue; - wait_for_completion(&flow->init_done); - - flow->tmp_efi_index = efi->index; - list_add(&flow->tmp_list, flow_list); - } -} - /* Iterate over tmp_list of flows attached to flow_list head. */ -void mlx5e_put_encap_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list) +void mlx5e_put_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list) { struct mlx5e_tc_flow *flow, *tmp; @@ -1616,222 +1484,6 @@ void mlx5e_put_encap_flow_list(struct mlx5e_priv *priv, struct list_head *flow_l mlx5e_flow_put(priv, flow); } -static struct mlx5e_encap_entry * -mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, - struct mlx5e_encap_entry *e) -{ - struct mlx5e_encap_entry *next = NULL; - -retry: - rcu_read_lock(); - - /* find encap with non-zero reference counter value */ - for (next = e ? - list_next_or_null_rcu(&nhe->encap_list, - &e->encap_list, - struct mlx5e_encap_entry, - encap_list) : - list_first_or_null_rcu(&nhe->encap_list, - struct mlx5e_encap_entry, - encap_list); - next; - next = list_next_or_null_rcu(&nhe->encap_list, - &next->encap_list, - struct mlx5e_encap_entry, - encap_list)) - if (mlx5e_encap_take(next)) - break; - - rcu_read_unlock(); - - /* release starting encap */ - if (e) - mlx5e_encap_put(netdev_priv(e->out_dev), e); - if (!next) - return next; - - /* wait for encap to be fully initialized */ - wait_for_completion(&next->res_ready); - /* continue searching if encap entry is not in valid state after completion */ - if (!(next->flags & MLX5_ENCAP_ENTRY_VALID)) { - e = next; - goto retry; - } - - return next; -} - -void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) -{ - struct mlx5e_neigh *m_neigh = &nhe->m_neigh; - struct mlx5e_encap_entry *e = NULL; - struct mlx5e_tc_flow *flow; - struct mlx5_fc *counter; - struct neigh_table *tbl; - bool neigh_used = false; - struct neighbour *n; - u64 lastuse; - - if (m_neigh->family == AF_INET) - tbl = &arp_tbl; -#if IS_ENABLED(CONFIG_IPV6) - else if (m_neigh->family == AF_INET6) - tbl = ipv6_stub->nd_tbl; -#endif - else - return; - - /* mlx5e_get_next_valid_encap() releases previous encap before returning - * next one. - */ - while ((e = mlx5e_get_next_valid_encap(nhe, e)) != NULL) { - struct mlx5e_priv *priv = netdev_priv(e->out_dev); - struct encap_flow_item *efi, *tmp; - struct mlx5_eswitch *esw; - LIST_HEAD(flow_list); - - esw = priv->mdev->priv.eswitch; - mutex_lock(&esw->offloads.encap_tbl_lock); - list_for_each_entry_safe(efi, tmp, &e->flows, list) { - flow = container_of(efi, struct mlx5e_tc_flow, - encaps[efi->index]); - if (IS_ERR(mlx5e_flow_get(flow))) - continue; - list_add(&flow->tmp_list, &flow_list); - - if (mlx5e_is_offloaded_flow(flow)) { - counter = mlx5e_tc_get_counter(flow); - lastuse = mlx5_fc_query_lastuse(counter); - if (time_after((unsigned long)lastuse, nhe->reported_lastuse)) { - neigh_used = true; - break; - } - } - } - mutex_unlock(&esw->offloads.encap_tbl_lock); - - mlx5e_put_encap_flow_list(priv, &flow_list); - if (neigh_used) { - /* release current encap before breaking the loop */ - mlx5e_encap_put(priv, e); - break; - } - } - - trace_mlx5e_tc_update_neigh_used_value(nhe, neigh_used); - - if (neigh_used) { - nhe->reported_lastuse = jiffies; - - /* find the relevant neigh according to the cached device and - * dst ip pair - */ - n = neigh_lookup(tbl, &m_neigh->dst_ip, m_neigh->dev); - if (!n) - return; - - neigh_event_send(n, NULL); - neigh_release(n); - } -} - -static void mlx5e_encap_dealloc(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) -{ - WARN_ON(!list_empty(&e->flows)); - - if (e->compl_result > 0) { - mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); - - if (e->flags & MLX5_ENCAP_ENTRY_VALID) - mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat); - } - - kfree(e->tun_info); - kfree(e->encap_header); - kfree_rcu(e, rcu); -} - -static void mlx5e_decap_dealloc(struct mlx5e_priv *priv, - struct mlx5e_decap_entry *d) -{ - WARN_ON(!list_empty(&d->flows)); - - if (!d->compl_result) - mlx5_packet_reformat_dealloc(priv->mdev, d->pkt_reformat); - - kfree_rcu(d, rcu); -} - -void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) -{ - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - - if (!refcount_dec_and_mutex_lock(&e->refcnt, &esw->offloads.encap_tbl_lock)) - return; - hash_del_rcu(&e->encap_hlist); - mutex_unlock(&esw->offloads.encap_tbl_lock); - - mlx5e_encap_dealloc(priv, e); -} - -static void mlx5e_decap_put(struct mlx5e_priv *priv, struct mlx5e_decap_entry *d) -{ - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - - if (!refcount_dec_and_mutex_lock(&d->refcnt, &esw->offloads.decap_tbl_lock)) - return; - hash_del_rcu(&d->hlist); - mutex_unlock(&esw->offloads.decap_tbl_lock); - - mlx5e_decap_dealloc(priv, d); -} - -static void mlx5e_detach_encap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, int out_index) -{ - struct mlx5e_encap_entry *e = flow->encaps[out_index].e; - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - - /* flow wasn't fully initialized */ - if (!e) - return; - - mutex_lock(&esw->offloads.encap_tbl_lock); - list_del(&flow->encaps[out_index].list); - flow->encaps[out_index].e = NULL; - if (!refcount_dec_and_test(&e->refcnt)) { - mutex_unlock(&esw->offloads.encap_tbl_lock); - return; - } - hash_del_rcu(&e->encap_hlist); - mutex_unlock(&esw->offloads.encap_tbl_lock); - - mlx5e_encap_dealloc(priv, e); -} - -static void mlx5e_detach_decap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow) -{ - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mlx5e_decap_entry *d = flow->decap_reformat; - - if (!d) - return; - - mutex_lock(&esw->offloads.decap_tbl_lock); - list_del(&flow->l3_to_l2_reformat); - flow->decap_reformat = NULL; - - if (!refcount_dec_and_test(&d->refcnt)) { - mutex_unlock(&esw->offloads.decap_tbl_lock); - return; - } - hash_del_rcu(&d->hlist); - mutex_unlock(&esw->offloads.decap_tbl_lock); - - mlx5e_decap_dealloc(priv, d); -} - static void __mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow) { struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch; @@ -2089,6 +1741,29 @@ void mlx5e_tc_set_ethertype(struct mlx5_core_dev *mdev, } } +u8 mlx5e_tc_get_ip_version(struct mlx5_flow_spec *spec, bool outer) +{ + void *headers_v; + u16 ethertype; + u8 ip_version; + + if (outer) + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); + else + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, inner_headers); + + ip_version = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_version); + /* Return ip_version converted from ethertype anyway */ + if (!ip_version) { + ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype); + if (ethertype == ETH_P_IP || ethertype == ETH_P_ARP) + ip_version = 4; + else if (ethertype == ETH_P_IPV6) + ip_version = 6; + } + return ip_version; +} + static int parse_tunnel_attr(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *spec, @@ -2097,6 +1772,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, u8 *match_level, bool *match_inner) { + struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(filter_dev); struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct netlink_ext_ack *extack = f->common.extack; bool needs_mapping, sets_mapping; @@ -2134,6 +1810,31 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, */ if (!netif_is_bareudp(filter_dev)) flow->attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP; + err = mlx5e_tc_set_attr_rx_tun(flow, spec); + if (err) + return err; + } else if (tunnel && tunnel->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) { + struct mlx5_flow_spec *tmp_spec; + + tmp_spec = kvzalloc(sizeof(*tmp_spec), GFP_KERNEL); + if (!tmp_spec) { + NL_SET_ERR_MSG_MOD(extack, "Failed to allocate memory for vxlan tmp spec"); + netdev_warn(priv->netdev, "Failed to allocate memory for vxlan tmp spec"); + return -ENOMEM; + } + memcpy(tmp_spec, spec, sizeof(*tmp_spec)); + + err = mlx5e_tc_tun_parse(filter_dev, priv, tmp_spec, f, match_level); + if (err) { + kvfree(tmp_spec); + NL_SET_ERR_MSG_MOD(extack, "Failed to parse tunnel attributes"); + netdev_warn(priv->netdev, "Failed to parse tunnel attributes"); + return err; + } + err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec); + kvfree(tmp_spec); + if (err) + return err; } if (!needs_mapping && !sets_mapping) @@ -3582,35 +3283,6 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, return 0; } -struct encap_key { - const struct ip_tunnel_key *ip_tun_key; - struct mlx5e_tc_tunnel *tc_tunnel; -}; - -static inline int cmp_encap_info(struct encap_key *a, - struct encap_key *b) -{ - return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) || - a->tc_tunnel->tunnel_type != b->tc_tunnel->tunnel_type; -} - -static inline int cmp_decap_info(struct mlx5e_decap_key *a, - struct mlx5e_decap_key *b) -{ - return memcmp(&a->key, &b->key, sizeof(b->key)); -} - -static inline int hash_encap_info(struct encap_key *key) -{ - return jhash(key->ip_tun_key, sizeof(*key->ip_tun_key), - key->tc_tunnel->tunnel_type); -} - -static inline int hash_decap_info(struct mlx5e_decap_key *key) -{ - return jhash(&key->key, sizeof(key->key), 0); -} - static bool is_merged_eswitch_vfs(struct mlx5e_priv *priv, struct net_device *peer_netdev) { @@ -3624,277 +3296,6 @@ static bool is_merged_eswitch_vfs(struct mlx5e_priv *priv, same_hw_devs(priv, peer_priv)); } -bool mlx5e_encap_take(struct mlx5e_encap_entry *e) -{ - return refcount_inc_not_zero(&e->refcnt); -} - -static bool mlx5e_decap_take(struct mlx5e_decap_entry *e) -{ - return refcount_inc_not_zero(&e->refcnt); -} - -static struct mlx5e_encap_entry * -mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key, - uintptr_t hash_key) -{ - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mlx5e_encap_entry *e; - struct encap_key e_key; - - hash_for_each_possible_rcu(esw->offloads.encap_tbl, e, - encap_hlist, hash_key) { - e_key.ip_tun_key = &e->tun_info->key; - e_key.tc_tunnel = e->tunnel; - if (!cmp_encap_info(&e_key, key) && - mlx5e_encap_take(e)) - return e; - } - - return NULL; -} - -static struct mlx5e_decap_entry * -mlx5e_decap_get(struct mlx5e_priv *priv, struct mlx5e_decap_key *key, - uintptr_t hash_key) -{ - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mlx5e_decap_key r_key; - struct mlx5e_decap_entry *e; - - hash_for_each_possible_rcu(esw->offloads.decap_tbl, e, - hlist, hash_key) { - r_key = e->key; - if (!cmp_decap_info(&r_key, key) && - mlx5e_decap_take(e)) - return e; - } - return NULL; -} - -static struct ip_tunnel_info *dup_tun_info(const struct ip_tunnel_info *tun_info) -{ - size_t tun_size = sizeof(*tun_info) + tun_info->options_len; - - return kmemdup(tun_info, tun_size, GFP_KERNEL); -} - -static bool is_duplicated_encap_entry(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - int out_index, - struct mlx5e_encap_entry *e, - struct netlink_ext_ack *extack) -{ - int i; - - for (i = 0; i < out_index; i++) { - if (flow->encaps[i].e != e) - continue; - NL_SET_ERR_MSG_MOD(extack, "can't duplicate encap action"); - netdev_err(priv->netdev, "can't duplicate encap action\n"); - return true; - } - - return false; -} - -static int mlx5e_attach_encap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct net_device *mirred_dev, - int out_index, - struct netlink_ext_ack *extack, - struct net_device **encap_dev, - bool *encap_valid) -{ - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mlx5e_tc_flow_parse_attr *parse_attr; - struct mlx5_flow_attr *attr = flow->attr; - const struct ip_tunnel_info *tun_info; - struct encap_key key; - struct mlx5e_encap_entry *e; - unsigned short family; - uintptr_t hash_key; - int err = 0; - - parse_attr = attr->parse_attr; - tun_info = parse_attr->tun_info[out_index]; - family = ip_tunnel_info_af(tun_info); - key.ip_tun_key = &tun_info->key; - key.tc_tunnel = mlx5e_get_tc_tun(mirred_dev); - if (!key.tc_tunnel) { - NL_SET_ERR_MSG_MOD(extack, "Unsupported tunnel"); - return -EOPNOTSUPP; - } - - hash_key = hash_encap_info(&key); - - mutex_lock(&esw->offloads.encap_tbl_lock); - e = mlx5e_encap_get(priv, &key, hash_key); - - /* must verify if encap is valid or not */ - if (e) { - /* Check that entry was not already attached to this flow */ - if (is_duplicated_encap_entry(priv, flow, out_index, e, extack)) { - err = -EOPNOTSUPP; - goto out_err; - } - - mutex_unlock(&esw->offloads.encap_tbl_lock); - wait_for_completion(&e->res_ready); - - /* Protect against concurrent neigh update. */ - mutex_lock(&esw->offloads.encap_tbl_lock); - if (e->compl_result < 0) { - err = -EREMOTEIO; - goto out_err; - } - goto attach_flow; - } - - e = kzalloc(sizeof(*e), GFP_KERNEL); - if (!e) { - err = -ENOMEM; - goto out_err; - } - - refcount_set(&e->refcnt, 1); - init_completion(&e->res_ready); - - tun_info = dup_tun_info(tun_info); - if (!tun_info) { - err = -ENOMEM; - goto out_err_init; - } - e->tun_info = tun_info; - err = mlx5e_tc_tun_init_encap_attr(mirred_dev, priv, e, extack); - if (err) - goto out_err_init; - - INIT_LIST_HEAD(&e->flows); - hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key); - mutex_unlock(&esw->offloads.encap_tbl_lock); - - if (family == AF_INET) - err = mlx5e_tc_tun_create_header_ipv4(priv, mirred_dev, e); - else if (family == AF_INET6) - err = mlx5e_tc_tun_create_header_ipv6(priv, mirred_dev, e); - - /* Protect against concurrent neigh update. */ - mutex_lock(&esw->offloads.encap_tbl_lock); - complete_all(&e->res_ready); - if (err) { - e->compl_result = err; - goto out_err; - } - e->compl_result = 1; - -attach_flow: - flow->encaps[out_index].e = e; - list_add(&flow->encaps[out_index].list, &e->flows); - flow->encaps[out_index].index = out_index; - *encap_dev = e->out_dev; - if (e->flags & MLX5_ENCAP_ENTRY_VALID) { - attr->esw_attr->dests[out_index].pkt_reformat = e->pkt_reformat; - attr->esw_attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; - *encap_valid = true; - } else { - *encap_valid = false; - } - mutex_unlock(&esw->offloads.encap_tbl_lock); - - return err; - -out_err: - mutex_unlock(&esw->offloads.encap_tbl_lock); - if (e) - mlx5e_encap_put(priv, e); - return err; - -out_err_init: - mutex_unlock(&esw->offloads.encap_tbl_lock); - kfree(tun_info); - kfree(e); - return err; -} - -static int mlx5e_attach_decap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct netlink_ext_ack *extack) -{ - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mlx5_esw_flow_attr *attr = flow->attr->esw_attr; - struct mlx5e_tc_flow_parse_attr *parse_attr; - struct mlx5e_decap_entry *d; - struct mlx5e_decap_key key; - uintptr_t hash_key; - int err = 0; - - parse_attr = flow->attr->parse_attr; - if (sizeof(parse_attr->eth) > MLX5_CAP_ESW(priv->mdev, max_encap_header_size)) { - NL_SET_ERR_MSG_MOD(extack, - "encap header larger than max supported"); - return -EOPNOTSUPP; - } - - key.key = parse_attr->eth; - hash_key = hash_decap_info(&key); - mutex_lock(&esw->offloads.decap_tbl_lock); - d = mlx5e_decap_get(priv, &key, hash_key); - if (d) { - mutex_unlock(&esw->offloads.decap_tbl_lock); - wait_for_completion(&d->res_ready); - mutex_lock(&esw->offloads.decap_tbl_lock); - if (d->compl_result) { - err = -EREMOTEIO; - goto out_free; - } - goto found; - } - - d = kzalloc(sizeof(*d), GFP_KERNEL); - if (!d) { - err = -ENOMEM; - goto out_err; - } - - d->key = key; - refcount_set(&d->refcnt, 1); - init_completion(&d->res_ready); - INIT_LIST_HEAD(&d->flows); - hash_add_rcu(esw->offloads.decap_tbl, &d->hlist, hash_key); - mutex_unlock(&esw->offloads.decap_tbl_lock); - - d->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2, - sizeof(parse_attr->eth), - &parse_attr->eth, - MLX5_FLOW_NAMESPACE_FDB); - if (IS_ERR(d->pkt_reformat)) { - err = PTR_ERR(d->pkt_reformat); - d->compl_result = err; - } - mutex_lock(&esw->offloads.decap_tbl_lock); - complete_all(&d->res_ready); - if (err) - goto out_free; - -found: - flow->decap_reformat = d; - attr->decap_pkt_reformat = d->pkt_reformat; - list_add(&flow->l3_to_l2_reformat, &d->flows); - mutex_unlock(&esw->offloads.decap_tbl_lock); - return 0; - -out_free: - mutex_unlock(&esw->offloads.decap_tbl_lock); - mlx5e_decap_put(priv, d); - return err; - -out_err: - mutex_unlock(&esw->offloads.decap_tbl_lock); - return err; -} - static int parse_tc_vlan_action(struct mlx5e_priv *priv, const struct flow_action_entry *act, struct mlx5_esw_flow_attr *attr, @@ -4247,7 +3648,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (encap) { parse_attr->mirred_ifindex[esw_attr->out_count] = out_dev->ifindex; - parse_attr->tun_info[esw_attr->out_count] = dup_tun_info(info); + parse_attr->tun_info[esw_attr->out_count] = + mlx5e_dup_tun_info(info); if (!parse_attr->tun_info[esw_attr->out_count]) return -ENOMEM; encap = false; @@ -4384,6 +3786,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, } } + /* always set IP version for indirect table handling */ + attr->ip_version = mlx5e_tc_get_ip_version(&parse_attr->spec, true); + if (MLX5_CAP_GEN(esw->dev, prio_tag_required) && action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) { /* For prio tag mode, replace vlan pop with rewrite vlan prio @@ -4664,7 +4069,6 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, return flow; err_free: - dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts); mlx5e_flow_put(priv, flow); out: return ERR_PTR(err); @@ -4809,6 +4213,7 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv, return 0; err_free: + flow_flag_set(flow, FAILED); dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts); mlx5e_flow_put(priv, flow); out: @@ -5040,7 +4445,7 @@ static int apply_police_params(struct mlx5e_priv *priv, u64 rate, */ if (rate) { rate = (rate * BITS_PER_BYTE) + 500000; - rate_mbps = max_t(u32, do_div(rate, 1000000), 1); + rate_mbps = max_t(u64, do_div(rate, 1000000), 1); } err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps); @@ -5221,6 +4626,8 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) if (err) return err; + lockdep_set_class(&tc->ht.mutex, &tc_ht_lock_key); + if (MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ignore_flow_level)) { attr.flags = MLX5_CHAINS_AND_PRIOS_SUPPORTED | MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED; @@ -5328,7 +4735,8 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) } uplink_priv->tunnel_mapping = mapping; - mapping = mapping_create(sz_enc_opts, ENC_OPTS_BITS_MASK, true); + /* 0xFFF is reserved for stack devices slow path table mark */ + mapping = mapping_create(sz_enc_opts, ENC_OPTS_BITS_MASK - 1, true); if (IS_ERR(mapping)) { err = PTR_ERR(mapping); goto err_enc_opts_mapping; @@ -5339,8 +4747,18 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) if (err) goto err_ht_init; - return err; + lockdep_set_class(&tc_ht->mutex, &tc_ht_lock_key); + + uplink_priv->encap = mlx5e_tc_tun_init(priv); + if (IS_ERR(uplink_priv->encap)) { + err = PTR_ERR(uplink_priv->encap); + goto err_register_fib_notifier; + } + return 0; + +err_register_fib_notifier: + rhashtable_destroy(tc_ht); err_ht_init: mapping_destroy(uplink_priv->tunnel_enc_opts_mapping); err_enc_opts_mapping: @@ -5357,10 +4775,11 @@ void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht) { struct mlx5_rep_uplink_priv *uplink_priv; - rhashtable_free_and_destroy(tc_ht, _mlx5e_tc_del_flow, NULL); - uplink_priv = container_of(tc_ht, struct mlx5_rep_uplink_priv, tc_ht); + rhashtable_free_and_destroy(tc_ht, _mlx5e_tc_del_flow, NULL); + mlx5e_tc_tun_cleanup(uplink_priv->encap); + mapping_destroy(uplink_priv->tunnel_enc_opts_mapping); mapping_destroy(uplink_priv->tunnel_mapping); @@ -5460,7 +4879,7 @@ bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, tc_skb_ext->chain = chain; zone_restore_id = (reg_b >> REG_MAPPING_SHIFT(NIC_ZONE_RESTORE_TO_REG)) & - ZONE_RESTORE_MAX; + ESW_ZONE_ID_MASK; if (!mlx5e_tc_ct_restore_flow(tc->ct, skb, zone_restore_id)) |