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 | 356 |
1 files changed, 203 insertions, 153 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 629a61e8022f..ba8164792016 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -34,25 +34,20 @@ #include <net/flow_offload.h> #include <net/sch_generic.h> #include <net/pkt_cls.h> -#include <net/tc_act/tc_gact.h> -#include <net/tc_act/tc_skbedit.h> #include <linux/mlx5/fs.h> #include <linux/mlx5/device.h> #include <linux/rhashtable.h> #include <linux/refcount.h> #include <linux/completion.h> -#include <net/tc_act/tc_mirred.h> -#include <net/tc_act/tc_vlan.h> -#include <net/tc_act/tc_tunnel_key.h> #include <net/tc_act/tc_pedit.h> #include <net/tc_act/tc_csum.h> -#include <net/tc_act/tc_mpls.h> #include <net/psample.h> #include <net/arp.h> #include <net/ipv6_stubs.h> #include <net/bareudp.h> #include <net/bonding.h> #include "en.h" +#include "en/tc/post_act.h" #include "en_rep.h" #include "en/rep/tc.h" #include "en/rep/neigh.h" @@ -66,7 +61,7 @@ #include "en/mod_hdr.h" #include "en/tc_priv.h" #include "en/tc_tun_encap.h" -#include "esw/sample.h" +#include "en/tc/sample.h" #include "lib/devcom.h" #include "lib/geneve.h" #include "lib/fs_chains.h" @@ -103,7 +98,7 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = { [MARK_TO_REG] = mark_to_reg_ct, [LABELS_TO_REG] = labels_to_reg_ct, [FTEID_TO_REG] = fteid_to_reg_ct, - /* For NIC rules we store the retore metadata directly + /* For NIC rules we store the restore metadata directly * into reg_b that is passed to SW since we don't * jump between steering domains. */ @@ -252,7 +247,7 @@ get_ct_priv(struct mlx5e_priv *priv) } #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) -static struct mlx5_esw_psample * +static struct mlx5e_tc_psample * get_sample_priv(struct mlx5e_priv *priv) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; @@ -263,7 +258,7 @@ get_sample_priv(struct mlx5e_priv *priv) uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); uplink_priv = &uplink_rpriv->uplink_priv; - return uplink_priv->esw_psample; + return uplink_priv->tc_psample; } return NULL; @@ -340,12 +335,12 @@ struct mlx5e_hairpin { struct mlx5_core_dev *func_mdev; struct mlx5e_priv *func_priv; u32 tdn; - u32 tirn; + struct mlx5e_tir direct_tir; int num_channels; struct mlx5e_rqt indir_rqt; - u32 indir_tirn[MLX5E_NUM_INDIR_TIRS]; - struct mlx5e_ttc_table ttc; + struct mlx5e_tir indir_tir[MLX5E_NUM_INDIR_TIRS]; + struct mlx5_ttc_table *ttc; }; struct mlx5e_hairpin_entry { @@ -452,136 +447,131 @@ static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv, static struct mlx5_core_dev *mlx5e_hairpin_get_mdev(struct net *net, int ifindex) { + struct mlx5_core_dev *mdev; struct net_device *netdev; struct mlx5e_priv *priv; - netdev = __dev_get_by_index(net, ifindex); + netdev = dev_get_by_index(net, ifindex); + if (!netdev) + return ERR_PTR(-ENODEV); + priv = netdev_priv(netdev); - return priv->mdev; + mdev = priv->mdev; + dev_put(netdev); + + /* Mirred tc action holds a refcount on the ifindex net_device (see + * net/sched/act_mirred.c:tcf_mirred_get_dev). So, it's okay to continue using mdev + * after dev_put(netdev), while we're in the context of adding a tc flow. + * + * The mdev pointer corresponds to the peer/out net_device of a hairpin. It is then + * stored in a hairpin object, which exists until all flows, that refer to it, get + * removed. + * + * On the other hand, after a hairpin object has been created, the peer net_device may + * be removed/unbound while there are still some hairpin flows that are using it. This + * case is handled by mlx5e_tc_hairpin_update_dead_peer, which is hooked to + * NETDEV_UNREGISTER event of the peer net_device. + */ + return mdev; } static int mlx5e_hairpin_create_transport(struct mlx5e_hairpin *hp) { - u32 in[MLX5_ST_SZ_DW(create_tir_in)] = {}; - void *tirc; + struct mlx5e_tir_builder *builder; int err; + builder = mlx5e_tir_builder_alloc(false); + if (!builder) + return -ENOMEM; + err = mlx5_core_alloc_transport_domain(hp->func_mdev, &hp->tdn); if (err) - goto alloc_tdn_err; - - tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); - - MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_DIRECT); - MLX5_SET(tirc, tirc, inline_rqn, hp->pair->rqn[0]); - MLX5_SET(tirc, tirc, transport_domain, hp->tdn); + goto out; - err = mlx5_core_create_tir(hp->func_mdev, in, &hp->tirn); + mlx5e_tir_builder_build_inline(builder, hp->tdn, hp->pair->rqn[0]); + err = mlx5e_tir_init(&hp->direct_tir, builder, hp->func_mdev, false); if (err) goto create_tir_err; - return 0; +out: + mlx5e_tir_builder_free(builder); + return err; create_tir_err: mlx5_core_dealloc_transport_domain(hp->func_mdev, hp->tdn); -alloc_tdn_err: - return err; + + goto out; } static void mlx5e_hairpin_destroy_transport(struct mlx5e_hairpin *hp) { - mlx5_core_destroy_tir(hp->func_mdev, hp->tirn); + mlx5e_tir_destroy(&hp->direct_tir); mlx5_core_dealloc_transport_domain(hp->func_mdev, hp->tdn); } -static int mlx5e_hairpin_fill_rqt_rqns(struct mlx5e_hairpin *hp, void *rqtc) -{ - struct mlx5e_priv *priv = hp->func_priv; - int i, ix, sz = MLX5E_INDIR_RQT_SIZE; - u32 *indirection_rqt, rqn; - - indirection_rqt = kcalloc(sz, sizeof(*indirection_rqt), GFP_KERNEL); - if (!indirection_rqt) - return -ENOMEM; - - mlx5e_build_default_indir_rqt(indirection_rqt, sz, - hp->num_channels); - - for (i = 0; i < sz; i++) { - ix = i; - if (priv->rss_params.hfunc == ETH_RSS_HASH_XOR) - ix = mlx5e_bits_invert(i, ilog2(sz)); - ix = indirection_rqt[ix]; - rqn = hp->pair->rqn[ix]; - MLX5_SET(rqtc, rqtc, rq_num[i], rqn); - } - - kfree(indirection_rqt); - return 0; -} - static int mlx5e_hairpin_create_indirect_rqt(struct mlx5e_hairpin *hp) { - int inlen, err, sz = MLX5E_INDIR_RQT_SIZE; struct mlx5e_priv *priv = hp->func_priv; struct mlx5_core_dev *mdev = priv->mdev; - void *rqtc; - u32 *in; + struct mlx5e_rss_params_indir *indir; + int err; - inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * sz; - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) + indir = kvmalloc(sizeof(*indir), GFP_KERNEL); + if (!indir) return -ENOMEM; - rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context); - - MLX5_SET(rqtc, rqtc, rqt_actual_size, sz); - MLX5_SET(rqtc, rqtc, rqt_max_size, sz); + mlx5e_rss_params_indir_init_uniform(indir, hp->num_channels); + err = mlx5e_rqt_init_indir(&hp->indir_rqt, mdev, hp->pair->rqn, hp->num_channels, + mlx5e_rx_res_get_current_hash(priv->rx_res).hfunc, + indir); - err = mlx5e_hairpin_fill_rqt_rqns(hp, rqtc); - if (err) - goto out; - - err = mlx5_core_create_rqt(mdev, in, inlen, &hp->indir_rqt.rqtn); - if (!err) - hp->indir_rqt.enabled = true; - -out: - kvfree(in); + kvfree(indir); return err; } static int mlx5e_hairpin_create_indirect_tirs(struct mlx5e_hairpin *hp) { struct mlx5e_priv *priv = hp->func_priv; - u32 in[MLX5_ST_SZ_DW(create_tir_in)]; - int tt, i, err; - void *tirc; + struct mlx5e_rss_params_hash rss_hash; + enum mlx5_traffic_types tt, max_tt; + struct mlx5e_tir_builder *builder; + int err = 0; + + builder = mlx5e_tir_builder_alloc(false); + if (!builder) + return -ENOMEM; + + rss_hash = mlx5e_rx_res_get_current_hash(priv->rx_res); for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { - struct mlx5e_tirc_config ttconfig = mlx5e_tirc_get_default_config(tt); + struct mlx5e_rss_params_traffic_type rss_tt; - memset(in, 0, MLX5_ST_SZ_BYTES(create_tir_in)); - tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); + rss_tt = mlx5e_rss_get_default_tt_config(tt); - MLX5_SET(tirc, tirc, transport_domain, hp->tdn); - MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT); - MLX5_SET(tirc, tirc, indirect_table, hp->indir_rqt.rqtn); - mlx5e_build_indir_tir_ctx_hash(&priv->rss_params, &ttconfig, tirc, false); + mlx5e_tir_builder_build_rqt(builder, hp->tdn, + mlx5e_rqt_get_rqtn(&hp->indir_rqt), + false); + mlx5e_tir_builder_build_rss(builder, &rss_hash, &rss_tt, false); - err = mlx5_core_create_tir(hp->func_mdev, in, - &hp->indir_tirn[tt]); + err = mlx5e_tir_init(&hp->indir_tir[tt], builder, hp->func_mdev, false); if (err) { mlx5_core_warn(hp->func_mdev, "create indirect tirs failed, %d\n", err); goto err_destroy_tirs; } + + mlx5e_tir_builder_clear(builder); } - return 0; -err_destroy_tirs: - for (i = 0; i < tt; i++) - mlx5_core_destroy_tir(hp->func_mdev, hp->indir_tirn[i]); +out: + mlx5e_tir_builder_free(builder); return err; + +err_destroy_tirs: + max_tt = tt; + for (tt = 0; tt < max_tt; tt++) + mlx5e_tir_destroy(&hp->indir_tir[tt]); + + goto out; } static void mlx5e_hairpin_destroy_indirect_tirs(struct mlx5e_hairpin *hp) @@ -589,7 +579,7 @@ static void mlx5e_hairpin_destroy_indirect_tirs(struct mlx5e_hairpin *hp) int tt; for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) - mlx5_core_destroy_tir(hp->func_mdev, hp->indir_tirn[tt]); + mlx5e_tir_destroy(&hp->indir_tir[tt]); } static void mlx5e_hairpin_set_ttc_params(struct mlx5e_hairpin *hp, @@ -600,12 +590,16 @@ static void mlx5e_hairpin_set_ttc_params(struct mlx5e_hairpin *hp, memset(ttc_params, 0, sizeof(*ttc_params)); - ttc_params->any_tt_tirn = hp->tirn; - - for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) - ttc_params->indir_tirn[tt] = hp->indir_tirn[tt]; + ttc_params->ns = mlx5_get_flow_namespace(hp->func_mdev, + MLX5_FLOW_NAMESPACE_KERNEL); + for (tt = 0; tt < MLX5_NUM_TT; tt++) { + ttc_params->dests[tt].type = MLX5_FLOW_DESTINATION_TYPE_TIR; + ttc_params->dests[tt].tir_num = + tt == MLX5_TT_ANY ? + mlx5e_tir_get_tirn(&hp->direct_tir) : + mlx5e_tir_get_tirn(&hp->indir_tir[tt]); + } - ft_attr->max_fte = MLX5E_TTC_TABLE_SIZE; ft_attr->level = MLX5E_TC_TTC_FT_LEVEL; ft_attr->prio = MLX5E_TC_PRIO; } @@ -625,30 +619,31 @@ static int mlx5e_hairpin_rss_init(struct mlx5e_hairpin *hp) goto err_create_indirect_tirs; mlx5e_hairpin_set_ttc_params(hp, &ttc_params); - err = mlx5e_create_ttc_table(priv, &ttc_params, &hp->ttc); - if (err) + hp->ttc = mlx5_create_ttc_table(priv->mdev, &ttc_params); + if (IS_ERR(hp->ttc)) { + err = PTR_ERR(hp->ttc); goto err_create_ttc_table; + } netdev_dbg(priv->netdev, "add hairpin: using %d channels rss ttc table id %x\n", - hp->num_channels, hp->ttc.ft.t->id); + hp->num_channels, + mlx5_get_ttc_flow_table(priv->fs.ttc)->id); return 0; err_create_ttc_table: mlx5e_hairpin_destroy_indirect_tirs(hp); err_create_indirect_tirs: - mlx5e_destroy_rqt(priv, &hp->indir_rqt); + mlx5e_rqt_destroy(&hp->indir_rqt); return err; } static void mlx5e_hairpin_rss_cleanup(struct mlx5e_hairpin *hp) { - struct mlx5e_priv *priv = hp->func_priv; - - mlx5e_destroy_ttc_table(priv, &hp->ttc); + mlx5_destroy_ttc_table(hp->ttc); mlx5e_hairpin_destroy_indirect_tirs(hp); - mlx5e_destroy_rqt(priv, &hp->indir_rqt); + mlx5e_rqt_destroy(&hp->indir_rqt); } static struct mlx5e_hairpin * @@ -666,6 +661,10 @@ mlx5e_hairpin_create(struct mlx5e_priv *priv, struct mlx5_hairpin_params *params func_mdev = priv->mdev; peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex); + if (IS_ERR(peer_mdev)) { + err = PTR_ERR(peer_mdev); + goto create_pair_err; + } pair = mlx5_core_hairpin_create(func_mdev, peer_mdev, params); if (IS_ERR(pair)) { @@ -804,6 +803,11 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, int err; peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex); + if (IS_ERR(peer_mdev)) { + NL_SET_ERR_MSG_MOD(extack, "invalid ifindex of mirred device"); + return PTR_ERR(peer_mdev); + } + if (!MLX5_CAP_GEN(priv->mdev, hairpin) || !MLX5_CAP_GEN(peer_mdev, hairpin)) { NL_SET_ERR_MSG_MOD(extack, "hairpin is not supported"); return -EOPNOTSUPP; @@ -874,16 +878,17 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, } netdev_dbg(priv->netdev, "add hairpin: tirn %x rqn %x peer %s sqn %x prio %d (log) data %d packets %d\n", - hp->tirn, hp->pair->rqn[0], + mlx5e_tir_get_tirn(&hp->direct_tir), hp->pair->rqn[0], dev_name(hp->pair->peer_mdev->device), hp->pair->sqn[0], match_prio, params.log_data_size, params.log_num_packets); attach_flow: if (hpe->hp->num_channels > 1) { flow_flag_set(flow, HAIRPIN_RSS); - flow->attr->nic_attr->hairpin_ft = hpe->hp->ttc.ft.t; + flow->attr->nic_attr->hairpin_ft = + mlx5_get_ttc_flow_table(hpe->hp->ttc); } else { - flow->attr->nic_attr->hairpin_tirn = hpe->hp->tirn; + flow->attr->nic_attr->hairpin_tirn = mlx5e_tir_get_tirn(&hpe->hp->direct_tir); } flow->hpe = hpe; @@ -1027,15 +1032,17 @@ err_ft_get: static int mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, - struct mlx5e_tc_flow_parse_attr *parse_attr, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) { + struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct mlx5_core_dev *dev = priv->mdev; - struct mlx5_fc *counter = NULL; + struct mlx5_fc *counter; int err; + parse_attr = attr->parse_attr; + if (flow_flag_test(flow, HAIRPIN)) { err = mlx5e_hairpin_flow_add(priv, flow, parse_attr, extack); if (err) @@ -1141,7 +1148,8 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw, mod_hdr_acts); #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) } else if (flow_flag_test(flow, SAMPLE)) { - rule = mlx5_esw_sample_offload(get_sample_priv(flow->priv), spec, attr); + rule = mlx5e_tc_sample_offload(get_sample_priv(flow->priv), spec, attr, + mlx5e_tc_get_flow_tun_id(flow)); #endif } else { rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr); @@ -1180,7 +1188,7 @@ void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) if (flow_flag_test(flow, SAMPLE)) { - mlx5_esw_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr); + mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr); return; } #endif @@ -1309,6 +1317,7 @@ bool mlx5e_tc_is_vf_tunnel(struct net_device *out_dev, struct net_device *route_ 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_devcom *devcom = NULL; struct mlx5_core_dev *route_mdev; struct mlx5_eswitch *esw; u16 vhca_id; @@ -1320,7 +1329,24 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro route_mdev = route_priv->mdev; vhca_id = MLX5_CAP_GEN(route_mdev, vhca_id); + if (mlx5_lag_is_active(out_priv->mdev)) { + /* In lag case we may get devices from different eswitch instances. + * If we failed to get vport num, it means, mostly, that we on the wrong + * eswitch. + */ + err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); + if (err != -ENOENT) + return err; + + devcom = out_priv->mdev->priv.devcom; + esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + if (!esw) + return -ENODEV; + } + err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); + if (devcom) + mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); return err; } @@ -1355,9 +1381,9 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, bool vf_tun = false, encap_valid = true; struct net_device *encap_dev = NULL; struct mlx5_esw_flow_attr *esw_attr; - struct mlx5_fc *counter = NULL; struct mlx5e_rep_priv *rpriv; struct mlx5e_priv *out_priv; + struct mlx5_fc *counter; u32 max_prio, max_chain; int err = 0; int out_index; @@ -1544,6 +1570,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, else mlx5e_detach_mod_hdr(priv, flow); } + kfree(attr->sample_attr); kvfree(attr->parse_attr); kvfree(attr->esw_attr->rx_tun_attr); @@ -1553,7 +1580,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, if (flow_flag_test(flow, L3_TO_L2_DECAP)) mlx5e_detach_decap(priv, flow); - kfree(flow->attr->esw_attr->sample); kfree(flow->attr); } @@ -1618,17 +1644,22 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, } } -static int flow_has_tc_fwd_action(struct flow_cls_offload *f) +static bool flow_requires_tunnel_mapping(u32 chain, struct flow_cls_offload *f) { struct flow_rule *rule = flow_cls_offload_flow_rule(f); struct flow_action *flow_action = &rule->action; const struct flow_action_entry *act; int i; + if (chain) + return false; + flow_action_for_each(i, act, flow_action) { switch (act->id) { case FLOW_ACTION_GOTO: return true; + case FLOW_ACTION_SAMPLE: + return true; default: continue; } @@ -1869,7 +1900,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, return -EOPNOTSUPP; needs_mapping = !!flow->attr->chain; - sets_mapping = !flow->attr->chain && flow_has_tc_fwd_action(f); + sets_mapping = flow_requires_tunnel_mapping(flow->attr->chain, f); *match_inner = !needs_mapping; if ((needs_mapping || sets_mapping) && @@ -2442,7 +2473,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_3; } } - /* Currenlty supported only for MPLS over UDP */ + /* Currently supported only for MPLS over UDP */ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS) && !netif_is_bareudp(filter_dev)) { NL_SET_ERR_MSG_MOD(extack, @@ -2696,7 +2727,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, if (s_mask && a_mask) { NL_SET_ERR_MSG_MOD(extack, "can't set and add to the same HW field"); - printk(KERN_WARNING "mlx5: can't set and add to the same HW field (%x)\n", f->field); + netdev_warn(priv->netdev, + "mlx5: can't set and add to the same HW field (%x)\n", + f->field); return -EOPNOTSUPP; } @@ -2735,8 +2768,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, if (first < next_z && next_z < last) { NL_SET_ERR_MSG_MOD(extack, "rewrite of few sub-fields isn't supported"); - printk(KERN_WARNING "mlx5: rewrite of few sub-fields (mask %lx) isn't offloaded\n", - mask); + netdev_warn(priv->netdev, + "mlx5: rewrite of few sub-fields (mask %lx) isn't offloaded\n", + mask); return -EOPNOTSUPP; } @@ -3323,10 +3357,10 @@ static int validate_goto_chain(struct mlx5e_priv *priv, static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct flow_action *flow_action, - struct mlx5e_tc_flow_parse_attr *parse_attr, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) { + struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct pedit_headers_action hdrs[2] = {}; const struct flow_action_entry *act; @@ -3342,8 +3376,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, return -EOPNOTSUPP; nic_attr = attr->nic_attr; - nic_attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; + parse_attr = attr->parse_attr; flow_action_for_each(i, act, flow_action) { switch (act->id) { @@ -3352,10 +3386,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, MLX5_FLOW_CONTEXT_ACTION_COUNT; break; case FLOW_ACTION_DROP: - action |= MLX5_FLOW_CONTEXT_ACTION_DROP; - if (MLX5_CAP_FLOWTABLE(priv->mdev, - flow_table_properties_nic_receive.flow_counter)) - action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; + action |= MLX5_FLOW_CONTEXT_ACTION_DROP | + MLX5_FLOW_CONTEXT_ACTION_COUNT; break; case FLOW_ACTION_MANGLE: case FLOW_ACTION_ADD: @@ -3396,7 +3428,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, "device is not on same HW, can't offload"); netdev_warn(priv->netdev, "device %s not on same HW, can't offload\n", peer_dev->name); - return -EINVAL; + return -EOPNOTSUPP; } } break; @@ -3406,7 +3438,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, if (mark & ~MLX5E_TC_FLOW_ID_MASK) { NL_SET_ERR_MSG_MOD(extack, "Bad flow mark - only 16 bit is supported"); - return -EINVAL; + return -EOPNOTSUPP; } nic_attr->flow_tag = mark; @@ -3703,20 +3735,19 @@ static int verify_uplink_forwarding(struct mlx5e_priv *priv, static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct flow_action *flow_action, struct mlx5e_tc_flow *flow, - struct netlink_ext_ack *extack, - struct net_device *filter_dev) + struct netlink_ext_ack *extack) { struct pedit_headers_action hdrs[2] = {}; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5e_sample_attr sample_attr = {}; const struct ip_tunnel_info *info = NULL; struct mlx5_flow_attr *attr = flow->attr; int ifindexes[MLX5_MAX_FLOW_FWD_VPORTS]; bool ft_flow = mlx5e_is_ft_flow(flow); const struct flow_action_entry *act; struct mlx5_esw_flow_attr *esw_attr; - struct mlx5_sample_attr sample = {}; bool encap = false, decap = false; u32 action = attr->action; int err, i, if_count = 0; @@ -3769,7 +3800,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, "mpls pop supported only as first action"); return -EOPNOTSUPP; } - if (!netif_is_bareudp(filter_dev)) { + if (!netif_is_bareudp(parse_attr->filter_dev)) { NL_SET_ERR_MSG_MOD(extack, "mpls pop supported only on bareudp devices"); return -EOPNOTSUPP; @@ -3918,7 +3949,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, "devices %s %s not on same switch HW, can't offload forwarding\n", priv->netdev->name, out_dev->name); - return -EINVAL; + return -EOPNOTSUPP; } } break; @@ -3987,10 +4018,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, NL_SET_ERR_MSG_MOD(extack, "Sample action with connection tracking is not supported"); return -EOPNOTSUPP; } - sample.rate = act->sample.rate; - sample.group_num = act->sample.psample_group->group_num; + sample_attr.rate = act->sample.rate; + sample_attr.group_num = act->sample.psample_group->group_num; if (act->sample.truncate) - sample.trunc_size = act->sample.trunc_size; + sample_attr.trunc_size = act->sample.trunc_size; flow_flag_set(flow, SAMPLE); break; default: @@ -4075,10 +4106,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, * no errors after parsing. */ if (flow_flag_test(flow, SAMPLE)) { - esw_attr->sample = kzalloc(sizeof(*esw_attr->sample), GFP_KERNEL); - if (!esw_attr->sample) + attr->sample_attr = kzalloc(sizeof(*attr->sample_attr), GFP_KERNEL); + if (!attr->sample_attr) return -ENOMEM; - *esw_attr->sample = sample; + *attr->sample_attr = sample_attr; } return 0; @@ -4271,7 +4302,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, if (err) goto err_free; - err = parse_tc_fdb_actions(priv, &rule->action, flow, extack, filter_dev); + err = parse_tc_fdb_actions(priv, &rule->action, flow, extack); if (err) goto err_free; @@ -4417,11 +4448,11 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv, if (err) goto err_free; - err = parse_tc_nic_actions(priv, &rule->action, parse_attr, flow, extack); + err = parse_tc_nic_actions(priv, &rule->action, flow, extack); if (err) goto err_free; - err = mlx5e_tc_add_nic_flow(priv, parse_attr, flow, extack); + err = mlx5e_tc_add_nic_flow(priv, flow, extack); if (err) goto err_free; @@ -4676,7 +4707,7 @@ static int apply_police_params(struct mlx5e_priv *priv, u64 rate, rate_mbps = max_t(u32, rate, 1); } - err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps); + err = mlx5_esw_qos_modify_vport_rate(esw, vport_num, rate_mbps); if (err) NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware"); @@ -4848,6 +4879,7 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) struct mlx5_core_dev *dev = priv->mdev; struct mapping_ctx *chains_mapping; struct mlx5_chains_attr attr = {}; + u64 mapping_id; int err; mlx5e_mod_hdr_tbl_init(&tc->mod_hdr); @@ -4861,8 +4893,12 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) lockdep_set_class(&tc->ht.mutex, &tc_ht_lock_key); - chains_mapping = mapping_create(sizeof(struct mlx5_mapped_obj), - MLX5E_TC_TABLE_CHAIN_TAG_MASK, true); + mapping_id = mlx5_query_nic_system_image_guid(dev); + + chains_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_CHAIN, + sizeof(struct mlx5_mapped_obj), + MLX5E_TC_TABLE_CHAIN_TAG_MASK, true); + if (IS_ERR(chains_mapping)) { err = PTR_ERR(chains_mapping); goto err_mapping; @@ -4884,8 +4920,9 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) goto err_chains; } + tc->post_act = mlx5e_tc_post_act_init(priv, tc->chains, MLX5_FLOW_NAMESPACE_KERNEL); tc->ct = mlx5_tc_ct_init(priv, tc->chains, &priv->fs.tc.mod_hdr, - MLX5_FLOW_NAMESPACE_KERNEL); + MLX5_FLOW_NAMESPACE_KERNEL, tc->post_act); tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event; err = register_netdevice_notifier_dev_net(priv->netdev, @@ -4901,6 +4938,7 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) err_reg: mlx5_tc_ct_clean(tc->ct); + mlx5e_tc_post_act_destroy(tc->post_act); mlx5_chains_destroy(tc->chains); err_chains: mapping_destroy(chains_mapping); @@ -4939,6 +4977,7 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) mutex_destroy(&tc->t_lock); mlx5_tc_ct_clean(tc->ct); + mlx5e_tc_post_act_destroy(tc->post_act); mapping_destroy(tc->mapping); mlx5_chains_destroy(tc->chains); } @@ -4951,6 +4990,7 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) struct mapping_ctx *mapping; struct mlx5_eswitch *esw; struct mlx5e_priv *priv; + u64 mapping_id; int err = 0; uplink_priv = container_of(tc_ht, struct mlx5_rep_uplink_priv, tc_ht); @@ -4958,17 +4998,24 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) priv = netdev_priv(rpriv->netdev); esw = priv->mdev->priv.eswitch; + uplink_priv->post_act = mlx5e_tc_post_act_init(priv, esw_chains(esw), + MLX5_FLOW_NAMESPACE_FDB); uplink_priv->ct_priv = mlx5_tc_ct_init(netdev_priv(priv->netdev), esw_chains(esw), &esw->offloads.mod_hdr, - MLX5_FLOW_NAMESPACE_FDB); + MLX5_FLOW_NAMESPACE_FDB, + uplink_priv->post_act); #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) - uplink_priv->esw_psample = mlx5_esw_sample_init(netdev_priv(priv->netdev)); + uplink_priv->tc_psample = mlx5e_tc_sample_init(esw, uplink_priv->post_act); #endif - mapping = mapping_create(sizeof(struct tunnel_match_key), - TUNNEL_INFO_BITS_MASK, true); + mapping_id = mlx5_query_nic_system_image_guid(esw->dev); + + mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_TUNNEL, + sizeof(struct tunnel_match_key), + TUNNEL_INFO_BITS_MASK, true); + if (IS_ERR(mapping)) { err = PTR_ERR(mapping); goto err_tun_mapping; @@ -4976,7 +5023,8 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) uplink_priv->tunnel_mapping = mapping; /* 0xFFF is reserved for stack devices slow path table mark */ - mapping = mapping_create(sz_enc_opts, ENC_OPTS_BITS_MASK - 1, true); + mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_TUNNEL_ENC_OPTS, + sz_enc_opts, ENC_OPTS_BITS_MASK - 1, true); if (IS_ERR(mapping)) { err = PTR_ERR(mapping); goto err_enc_opts_mapping; @@ -5005,11 +5053,12 @@ err_enc_opts_mapping: mapping_destroy(uplink_priv->tunnel_mapping); err_tun_mapping: #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) - mlx5_esw_sample_cleanup(uplink_priv->esw_psample); + mlx5e_tc_sample_cleanup(uplink_priv->tc_psample); #endif mlx5_tc_ct_clean(uplink_priv->ct_priv); netdev_warn(priv->netdev, "Failed to initialize tc (eswitch), err: %d", err); + mlx5e_tc_post_act_destroy(uplink_priv->post_act); return err; } @@ -5026,9 +5075,10 @@ void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht) mapping_destroy(uplink_priv->tunnel_mapping); #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) - mlx5_esw_sample_cleanup(uplink_priv->esw_psample); + mlx5e_tc_sample_cleanup(uplink_priv->tc_psample); #endif mlx5_tc_ct_clean(uplink_priv->ct_priv); + mlx5e_tc_post_act_destroy(uplink_priv->post_act); } int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags) |