diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core/eswitch.c')
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 466 |
1 files changed, 352 insertions, 114 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index a44ea7b85614..d0b28251abf2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -39,8 +39,7 @@ #include "lib/eq.h" #include "eswitch.h" #include "fs_core.h" - -#define UPLINK_VPORT 0xFFFF +#include "ecpf.h" enum { MLX5_ACTION_NONE = 0, @@ -52,7 +51,7 @@ enum { struct vport_addr { struct l2addr_node node; u8 action; - u32 vport; + u16 vport; struct mlx5_flow_handle *flow_rule; bool mpfs; /* UC MAC was added to MPFs */ /* A flag indicating that mac was added due to mc promiscuous vport */ @@ -65,11 +64,36 @@ enum { PROMISC_CHANGE = BIT(3), }; +static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw); +static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw); + /* Vport context events */ #define SRIOV_VPORT_EVENTS (UC_ADDR_CHANGE | \ MC_ADDR_CHANGE | \ PROMISC_CHANGE) +/* The vport getter/iterator are only valid after esw->total_vports + * and vport->vport are initialized in mlx5_eswitch_init. + */ +#define mlx5_esw_for_all_vports(esw, i, vport) \ + for ((i) = MLX5_VPORT_PF; \ + (vport) = &(esw)->vports[i], \ + (i) < (esw)->total_vports; (i)++) + +#define mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs) \ + for ((i) = MLX5_VPORT_FIRST_VF; \ + (vport) = &(esw)->vports[i], \ + (i) <= (nvfs); (i)++) + +static struct mlx5_vport *mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, + u16 vport_num) +{ + u16 idx = mlx5_eswitch_vport_num_to_index(esw, vport_num); + + WARN_ON(idx > esw->total_vports - 1); + return &esw->vports[idx]; +} + static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport, u32 events_mask) { @@ -115,7 +139,7 @@ static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport, return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); } -static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport, +static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport, u16 vlan, u8 qos, u8 set_flags) { u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {0}; @@ -152,7 +176,7 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport, /* E-Switch FDB */ static struct mlx5_flow_handle * -__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, +__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u16 vport, bool rx_rule, u8 mac_c[ETH_ALEN], u8 mac_v[ETH_ALEN]) { int match_header = (is_zero_ether_addr(mac_c) ? 0 : @@ -188,7 +212,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, misc_parameters); mc_misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); - MLX5_SET(fte_match_set_misc, mv_misc, source_port, UPLINK_VPORT); + MLX5_SET(fte_match_set_misc, mv_misc, source_port, MLX5_VPORT_UPLINK); MLX5_SET_TO_ONES(fte_match_set_misc, mc_misc, source_port); } @@ -215,7 +239,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, } static struct mlx5_flow_handle * -esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport) +esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u16 vport) { u8 mac_c[ETH_ALEN]; @@ -224,7 +248,7 @@ esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport) } static struct mlx5_flow_handle * -esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport) +esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u16 vport) { u8 mac_c[ETH_ALEN]; u8 mac_v[ETH_ALEN]; @@ -237,7 +261,7 @@ esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport) } static struct mlx5_flow_handle * -esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport) +esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u16 vport) { u8 mac_c[ETH_ALEN]; u8 mac_v[ETH_ALEN]; @@ -247,6 +271,37 @@ esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport) return __esw_fdb_set_vport_rule(esw, vport, true, mac_c, mac_v); } +enum { + LEGACY_VEPA_PRIO = 0, + LEGACY_FDB_PRIO, +}; + +static int esw_create_legacy_vepa_table(struct mlx5_eswitch *esw) +{ + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_namespace *root_ns; + struct mlx5_flow_table *fdb; + int err; + + root_ns = mlx5_get_fdb_sub_ns(dev, 0); + if (!root_ns) { + esw_warn(dev, "Failed to get FDB flow namespace\n"); + return -EOPNOTSUPP; + } + + /* num FTE 2, num FG 2 */ + fdb = mlx5_create_auto_grouped_flow_table(root_ns, LEGACY_VEPA_PRIO, + 2, 2, 0, 0); + if (IS_ERR(fdb)) { + err = PTR_ERR(fdb); + esw_warn(dev, "Failed to create VEPA FDB err %d\n", err); + return err; + } + esw->fdb_table.legacy.vepa_fdb = fdb; + + return 0; +} + static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); @@ -275,8 +330,8 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw) return -ENOMEM; table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size)); - ft_attr.max_fte = table_size; + ft_attr.prio = LEGACY_FDB_PRIO; fdb = mlx5_create_flow_table(root_ns, &ft_attr); if (IS_ERR(fdb)) { err = PTR_ERR(fdb); @@ -335,41 +390,65 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw) esw->fdb_table.legacy.promisc_grp = g; out: - if (err) { - if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.allmulti_grp)) { - mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp); - esw->fdb_table.legacy.allmulti_grp = NULL; - } - if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.addr_grp)) { - mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp); - esw->fdb_table.legacy.addr_grp = NULL; - } - if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.fdb)) { - mlx5_destroy_flow_table(esw->fdb_table.legacy.fdb); - esw->fdb_table.legacy.fdb = NULL; - } - } + if (err) + esw_destroy_legacy_fdb_table(esw); kvfree(flow_group_in); return err; } +static void esw_destroy_legacy_vepa_table(struct mlx5_eswitch *esw) +{ + esw_debug(esw->dev, "Destroy VEPA Table\n"); + if (!esw->fdb_table.legacy.vepa_fdb) + return; + + mlx5_destroy_flow_table(esw->fdb_table.legacy.vepa_fdb); + esw->fdb_table.legacy.vepa_fdb = NULL; +} + static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw) { + esw_debug(esw->dev, "Destroy FDB Table\n"); if (!esw->fdb_table.legacy.fdb) return; - esw_debug(esw->dev, "Destroy FDB Table\n"); - mlx5_destroy_flow_group(esw->fdb_table.legacy.promisc_grp); - mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp); - mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp); + if (esw->fdb_table.legacy.promisc_grp) + mlx5_destroy_flow_group(esw->fdb_table.legacy.promisc_grp); + if (esw->fdb_table.legacy.allmulti_grp) + mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp); + if (esw->fdb_table.legacy.addr_grp) + mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp); mlx5_destroy_flow_table(esw->fdb_table.legacy.fdb); + esw->fdb_table.legacy.fdb = NULL; esw->fdb_table.legacy.addr_grp = NULL; esw->fdb_table.legacy.allmulti_grp = NULL; esw->fdb_table.legacy.promisc_grp = NULL; } +static int esw_create_legacy_table(struct mlx5_eswitch *esw) +{ + int err; + + err = esw_create_legacy_vepa_table(esw); + if (err) + return err; + + err = esw_create_legacy_fdb_table(esw); + if (err) + esw_destroy_legacy_vepa_table(esw); + + return err; +} + +static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) +{ + esw_cleanup_vepa_rules(esw); + esw_destroy_legacy_fdb_table(esw); + esw_destroy_legacy_vepa_table(esw); +} + /* E-Switch vport UC/MC lists management */ typedef int (*vport_addr_action)(struct mlx5_eswitch *esw, struct vport_addr *vaddr); @@ -377,19 +456,19 @@ typedef int (*vport_addr_action)(struct mlx5_eswitch *esw, static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) { u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; int err; - /* Skip mlx5_mpfs_add_mac for PFs, - * it is already done by the PF netdev in mlx5e_execute_l2_action + /* Skip mlx5_mpfs_add_mac for eswitch_managers, + * it is already done by its netdev in mlx5e_execute_l2_action */ - if (!vport) + if (esw->manager_vport == vport) goto fdb_add; err = mlx5_mpfs_add_mac(esw->dev, mac); if (err) { esw_warn(esw->dev, - "Failed to add L2 table mac(%pM) for vport(%d), err(%d)\n", + "Failed to add L2 table mac(%pM) for vport(0x%x), err(%d)\n", mac, vport, err); return err; } @@ -409,13 +488,13 @@ fdb_add: static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) { u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; int err = 0; - /* Skip mlx5_mpfs_del_mac for PFs, - * it is already done by the PF netdev in mlx5e_execute_l2_action + /* Skip mlx5_mpfs_del_mac for eswitch managerss, + * it is already done by its netdev in mlx5e_execute_l2_action */ - if (!vport || !vaddr->mpfs) + if (!vaddr->mpfs || esw->manager_vport == vport) goto fdb_del; err = mlx5_mpfs_del_mac(esw->dev, mac); @@ -438,17 +517,18 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw, struct esw_mc_addr *esw_mc) { u8 *mac = vaddr->node.addr; - u32 vport_idx = 0; + struct mlx5_vport *vport; + u16 i, vport_num; - for (vport_idx = 0; vport_idx < esw->total_vports; vport_idx++) { - struct mlx5_vport *vport = &esw->vports[vport_idx]; + mlx5_esw_for_all_vports(esw, i, vport) { struct hlist_head *vport_hash = vport->mc_list; struct vport_addr *iter_vaddr = l2addr_hash_find(vport_hash, mac, struct vport_addr); + vport_num = vport->vport; if (IS_ERR_OR_NULL(vport->allmulti_rule) || - vaddr->vport == vport_idx) + vaddr->vport == vport_num) continue; switch (vaddr->action) { case MLX5_ACTION_ADD: @@ -460,14 +540,14 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw, if (!iter_vaddr) { esw_warn(esw->dev, "ALL-MULTI: Failed to add MAC(%pM) to vport[%d] DB\n", - mac, vport_idx); + mac, vport_num); continue; } - iter_vaddr->vport = vport_idx; + iter_vaddr->vport = vport_num; iter_vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, - vport_idx); + vport_num); iter_vaddr->mc_promisc = true; break; case MLX5_ACTION_DEL: @@ -485,7 +565,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) struct hlist_head *hash = esw->mc_table; struct esw_mc_addr *esw_mc; u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; if (!esw->fdb_table.legacy.fdb) return 0; @@ -499,7 +579,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) return -ENOMEM; esw_mc->uplink_rule = /* Forward MC MAC to Uplink */ - esw_fdb_set_vport_rule(esw, mac, UPLINK_VPORT); + esw_fdb_set_vport_rule(esw, mac, MLX5_VPORT_UPLINK); /* Add this multicast mac to all the mc promiscuous vports */ update_allmulti_vports(esw, vaddr, esw_mc); @@ -525,7 +605,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) struct hlist_head *hash = esw->mc_table; struct esw_mc_addr *esw_mc; u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; if (!esw->fdb_table.legacy.fdb) return 0; @@ -564,9 +644,9 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) /* Apply vport UC/MC list to HW l2 table and FDB table */ static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw, - u32 vport_num, int list_type) + u16 vport_num, int list_type) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC; vport_addr_action vport_addr_add; vport_addr_action vport_addr_del; @@ -599,9 +679,9 @@ static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw, /* Sync vport UC/MC list from vport context */ static void esw_update_vport_addr_list(struct mlx5_eswitch *esw, - u32 vport_num, int list_type) + u16 vport_num, int list_type) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC; u8 (*mac_list)[ETH_ALEN]; struct l2addr_node *node; @@ -686,9 +766,9 @@ out: /* Sync vport UC/MC list from vport context * Must be called after esw_update_vport_addr_list */ -static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num) +static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u16 vport_num) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); struct l2addr_node *node; struct vport_addr *addr; struct hlist_head *hash; @@ -721,11 +801,11 @@ static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num) } /* Apply vport rx mode to HW FDB table */ -static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num, +static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num, bool promisc, bool mc_promisc) { + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); struct esw_mc_addr *allmulti_addr = &esw->mc_promisc; - struct mlx5_vport *vport = &esw->vports[vport_num]; if (IS_ERR_OR_NULL(vport->allmulti_rule) != mc_promisc) goto promisc; @@ -736,7 +816,7 @@ static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num, if (!allmulti_addr->uplink_rule) allmulti_addr->uplink_rule = esw_fdb_set_vport_allmulti_rule(esw, - UPLINK_VPORT); + MLX5_VPORT_UPLINK); allmulti_addr->refcnt++; } else if (vport->allmulti_rule) { mlx5_del_flow_rules(vport->allmulti_rule); @@ -764,9 +844,9 @@ promisc: } /* Sync vport rx mode from vport context */ -static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num) +static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); int promisc_all = 0; int promisc_uc = 0; int promisc_mc = 0; @@ -1134,13 +1214,6 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, int err = 0; u8 *smac_v; - if (vport->info.spoofchk && !is_valid_ether_addr(vport->info.mac)) { - mlx5_core_warn(esw->dev, - "vport[%d] configure ingress rules failed, illegal mac with spoofchk\n", - vport->vport); - return -EPERM; - } - esw_vport_cleanup_ingress_rules(esw, vport); if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) { @@ -1350,8 +1423,8 @@ static void esw_destroy_tsar(struct mlx5_eswitch *esw) static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num, u32 initial_max_rate, u32 initial_bw_share) { + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; - struct mlx5_vport *vport = &esw->vports[vport_num]; struct mlx5_core_dev *dev = esw->dev; void *vport_elem; int err = 0; @@ -1390,7 +1463,7 @@ static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num, static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); int err = 0; if (!vport->qos.enabled) @@ -1409,8 +1482,8 @@ static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num) static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num, u32 max_rate, u32 bw_share) { + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; - struct mlx5_vport *vport = &esw->vports[vport_num]; struct mlx5_core_dev *dev = esw->dev; void *vport_elem; u32 bitmask = 0; @@ -1466,15 +1539,22 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw, { int vport_num = vport->vport; - if (!vport_num) + if (esw->manager_vport == vport_num) return; mlx5_modify_vport_admin_state(esw->dev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - vport_num, + vport_num, 1, vport->info.link_state); - mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, vport->info.mac); - mlx5_modify_nic_vport_node_guid(esw->dev, vport_num, vport->info.node_guid); + + /* Host PF has its own mac/guid. */ + if (vport_num) { + mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, + vport->info.mac); + mlx5_modify_nic_vport_node_guid(esw->dev, vport_num, + vport->info.node_guid); + } + modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan, vport->info.qos, (vport->info.vlan || vport->info.qos)); @@ -1520,10 +1600,10 @@ static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport) mlx5_fc_destroy(dev, vport->egress.drop_counter); } -static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, +static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, int enable_events) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + u16 vport_num = vport->vport; mutex_lock(&esw->state_lock); WARN_ON(vport->enabled); @@ -1546,8 +1626,11 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, vport->enabled_events = enable_events; vport->enabled = true; - /* only PF is trusted by default */ - if (!vport_num) + /* Esw manager is trusted by default. Host PF (vport 0) is trusted as well + * in smartNIC as it's a vport group manager. + */ + if (esw->manager_vport == vport_num || + (!vport_num && mlx5_core_is_ecpf(esw->dev))) vport->info.trusted = true; esw_vport_change_handle_locked(vport); @@ -1557,9 +1640,10 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, mutex_unlock(&esw->state_lock); } -static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) +static void esw_disable_vport(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + u16 vport_num = vport->vport; if (!vport->enabled) return; @@ -1580,10 +1664,11 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) esw_vport_change_handle_locked(vport); vport->enabled_events = 0; esw_vport_disable_qos(esw, vport_num); - if (vport_num && esw->mode == SRIOV_LEGACY) { + if (esw->manager_vport != vport_num && + esw->mode == SRIOV_LEGACY) { mlx5_modify_vport_admin_state(esw->dev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - vport_num, + vport_num, 1, MLX5_VPORT_ADMIN_STATE_DOWN); esw_vport_disable_egress_acl(esw, vport); esw_vport_disable_ingress_acl(esw, vport); @@ -1602,7 +1687,7 @@ static int eswitch_vport_event(struct notifier_block *nb, u16 vport_num; vport_num = be16_to_cpu(eqe->data.vport_change.vport_num); - vport = &esw->vports[vport_num]; + vport = mlx5_eswitch_get_vport(esw, vport_num); if (vport->enabled) queue_work(esw->work_queue, &vport->vport_change_handler); @@ -1614,6 +1699,8 @@ static int eswitch_vport_event(struct notifier_block *nb, int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { + int vf_nvports = 0, total_nvports = 0; + struct mlx5_vport *vport; int err; int i, enabled_events; @@ -1631,16 +1718,30 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode); + if (mode == SRIOV_OFFLOADS) { + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + err = mlx5_query_host_params_num_vfs(esw->dev, &vf_nvports); + if (err) + return err; + total_nvports = esw->total_vports; + } else { + vf_nvports = nvfs; + total_nvports = nvfs + MLX5_SPECIAL_VPORTS(esw->dev); + } + } + esw->mode = mode; mlx5_lag_update(esw->dev); if (mode == SRIOV_LEGACY) { - err = esw_create_legacy_fdb_table(esw); + err = esw_create_legacy_table(esw); + if (err) + goto abort; } else { mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - err = esw_offloads_init(esw, nvfs + 1); + err = esw_offloads_init(esw, vf_nvports, total_nvports); } if (err) @@ -1655,8 +1756,20 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) * 2. FDB/Eswitch is programmed by user space tools */ enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : 0; - for (i = 0; i <= nvfs; i++) - esw_enable_vport(esw, i, enabled_events); + + /* Enable PF vport */ + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); + esw_enable_vport(esw, vport, enabled_events); + + /* Enable ECPF vports */ + if (mlx5_ecpf_vport_exists(esw->dev)) { + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); + esw_enable_vport(esw, vport, enabled_events); + } + + /* Enable VF vports */ + mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs) + esw_enable_vport(esw, vport, enabled_events); if (mode == SRIOV_LEGACY) { MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE); @@ -1681,8 +1794,8 @@ abort: void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) { struct esw_mc_addr *mc_promisc; + struct mlx5_vport *vport; int old_mode; - int nvports; int i; if (!ESW_ALLOWED(esw) || esw->mode == SRIOV_NONE) @@ -1692,13 +1805,12 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) esw->enabled_vports, esw->mode); mc_promisc = &esw->mc_promisc; - nvports = esw->enabled_vports; if (esw->mode == SRIOV_LEGACY) mlx5_eq_notifier_unregister(esw->dev, &esw->nb); - for (i = 0; i < esw->total_vports; i++) - esw_disable_vport(esw, i); + mlx5_esw_for_all_vports(esw, i, vport) + esw_disable_vport(esw, vport); if (mc_promisc && mc_promisc->uplink_rule) mlx5_del_flow_rules(mc_promisc->uplink_rule); @@ -1706,9 +1818,9 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) esw_destroy_tsar(esw); if (esw->mode == SRIOV_LEGACY) - esw_destroy_legacy_fdb_table(esw); + esw_destroy_legacy_table(esw); else if (esw->mode == SRIOV_OFFLOADS) - esw_offloads_cleanup(esw, nvports); + esw_offloads_cleanup(esw); old_mode = esw->mode; esw->mode = SRIOV_NONE; @@ -1725,10 +1837,10 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) { int total_vports = MLX5_TOTAL_VPORTS(dev); struct mlx5_eswitch *esw; - int vport_num; - int err; + struct mlx5_vport *vport; + int err, i; - if (!MLX5_ESWITCH_MANAGER(dev)) + if (!MLX5_VPORT_MANAGER(dev)) return 0; esw_info(dev, @@ -1742,6 +1854,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) return -ENOMEM; esw->dev = dev; + esw->manager_vport = mlx5_eswitch_manager_vport(dev); esw->work_queue = create_singlethread_workqueue("mlx5_esw_wq"); if (!esw->work_queue) { @@ -1756,6 +1869,8 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) goto abort; } + esw->total_vports = total_vports; + err = esw_offloads_init_reps(esw); if (err) goto abort; @@ -1764,17 +1879,14 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) hash_init(esw->offloads.mod_hdr_tbl); mutex_init(&esw->state_lock); - for (vport_num = 0; vport_num < total_vports; vport_num++) { - struct mlx5_vport *vport = &esw->vports[vport_num]; - - vport->vport = vport_num; + mlx5_esw_for_all_vports(esw, i, vport) { + vport->vport = mlx5_eswitch_index_to_vport_num(esw, i); vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; vport->dev = dev; INIT_WORK(&vport->vport_change_handler, esw_vport_change_handler); } - esw->total_vports = total_vports; esw->enabled_vports = 0; esw->mode = SRIOV_NONE; esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE; @@ -1797,7 +1909,7 @@ abort: void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) { - if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev)) + if (!esw || !MLX5_VPORT_MANAGER(esw->dev)) return; esw_info(esw->dev, "cleanup\n"); @@ -1827,13 +1939,10 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, mutex_lock(&esw->state_lock); evport = &esw->vports[vport]; - if (evport->info.spoofchk && !is_valid_ether_addr(mac)) { + if (evport->info.spoofchk && !is_valid_ether_addr(mac)) mlx5_core_warn(esw->dev, - "MAC invalidation is not allowed when spoofchk is on, vport(%d)\n", + "Set invalid MAC while spoofchk is on, vport(%d)\n", vport); - err = -EPERM; - goto unlock; - } err = mlx5_modify_nic_vport_mac_address(esw->dev, vport, mac); if (err) { @@ -1876,7 +1985,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, err = mlx5_modify_vport_admin_state(esw->dev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - vport, link_state); + vport, 1, link_state); if (err) { mlx5_core_warn(esw->dev, "Failed to set vport %d link state, err = %d", @@ -1979,6 +2088,10 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw, evport = &esw->vports[vport]; pschk = evport->info.spoofchk; evport->info.spoofchk = spoofchk; + if (pschk && !is_valid_ether_addr(evport->info.mac)) + mlx5_core_warn(esw->dev, + "Spoofchk in set while MAC is invalid, vport(%d)\n", + evport->vport); if (evport->enabled && esw->mode == SRIOV_LEGACY) err = esw_vport_ingress_config(esw, evport); if (err) @@ -1988,6 +2101,127 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw, return err; } +static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw) +{ + if (esw->fdb_table.legacy.vepa_uplink_rule) + mlx5_del_flow_rules(esw->fdb_table.legacy.vepa_uplink_rule); + + if (esw->fdb_table.legacy.vepa_star_rule) + mlx5_del_flow_rules(esw->fdb_table.legacy.vepa_star_rule); + + esw->fdb_table.legacy.vepa_uplink_rule = NULL; + esw->fdb_table.legacy.vepa_star_rule = NULL; +} + +static int _mlx5_eswitch_set_vepa_locked(struct mlx5_eswitch *esw, + u8 setting) +{ + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *flow_rule; + struct mlx5_flow_spec *spec; + int err = 0; + void *misc; + + if (!setting) { + esw_cleanup_vepa_rules(esw); + return 0; + } + + if (esw->fdb_table.legacy.vepa_uplink_rule) + return 0; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + /* Uplink rule forward uplink traffic to FDB */ + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); + MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_UPLINK); + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); + MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); + + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; + dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest.ft = esw->fdb_table.legacy.fdb; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + flow_rule = mlx5_add_flow_rules(esw->fdb_table.legacy.vepa_fdb, spec, + &flow_act, &dest, 1); + if (IS_ERR(flow_rule)) { + err = PTR_ERR(flow_rule); + goto out; + } else { + esw->fdb_table.legacy.vepa_uplink_rule = flow_rule; + } + + /* Star rule to forward all traffic to uplink vport */ + memset(spec, 0, sizeof(*spec)); + dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; + dest.vport.num = MLX5_VPORT_UPLINK; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + flow_rule = mlx5_add_flow_rules(esw->fdb_table.legacy.vepa_fdb, spec, + &flow_act, &dest, 1); + if (IS_ERR(flow_rule)) { + err = PTR_ERR(flow_rule); + goto out; + } else { + esw->fdb_table.legacy.vepa_star_rule = flow_rule; + } + +out: + kvfree(spec); + if (err) + esw_cleanup_vepa_rules(esw); + return err; +} + +int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting) +{ + int err = 0; + + if (!esw) + return -EOPNOTSUPP; + + if (!ESW_ALLOWED(esw)) + return -EPERM; + + mutex_lock(&esw->state_lock); + if (esw->mode != SRIOV_LEGACY) { + err = -EOPNOTSUPP; + goto out; + } + + err = _mlx5_eswitch_set_vepa_locked(esw, setting); + +out: + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting) +{ + int err = 0; + + if (!esw) + return -EOPNOTSUPP; + + if (!ESW_ALLOWED(esw)) + return -EPERM; + + mutex_lock(&esw->state_lock); + if (esw->mode != SRIOV_LEGACY) { + err = -EOPNOTSUPP; + goto out; + } + + *setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0; + +out: + mutex_unlock(&esw->state_lock); + return err; +} + int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw, int vport, bool setting) { @@ -2015,8 +2249,7 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw) u32 max_guarantee = 0; int i; - for (i = 0; i < esw->total_vports; i++) { - evport = &esw->vports[i]; + mlx5_esw_for_all_vports(esw, i, evport) { if (!evport->enabled || evport->info.min_rate < max_guarantee) continue; max_guarantee = evport->info.min_rate; @@ -2035,8 +2268,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) int err; int i; - for (i = 0; i < esw->total_vports; i++) { - evport = &esw->vports[i]; + mlx5_esw_for_all_vports(esw, i, evport) { if (!evport->enabled) continue; vport_min_rate = evport->info.min_rate; @@ -2051,7 +2283,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) if (bw_share == evport->qos.bw_share) continue; - err = esw_vport_qos_config(esw, i, vport_max_rate, + err = esw_vport_qos_config(esw, evport->vport, vport_max_rate, bw_share); if (!err) evport->qos.bw_share = bw_share; @@ -2134,7 +2366,7 @@ static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev, !MLX5_CAP_GEN(dev, transmit_discard_vport_down)) return 0; - err = mlx5_query_vport_down_stats(dev, vport_idx, + err = mlx5_query_vport_down_stats(dev, vport_idx, 1, &rx_discard_vport_down, &tx_discard_vport_down); if (err) @@ -2171,8 +2403,7 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw, MLX5_CMD_OP_QUERY_VPORT_COUNTER); MLX5_SET(query_vport_counter_in, in, op_mod, 0); MLX5_SET(query_vport_counter_in, in, vport_number, vport); - if (vport) - MLX5_SET(query_vport_counter_in, in, other_vport, 1); + MLX5_SET(query_vport_counter_in, in, other_vport, 1); memset(out, 0, outlen); err = mlx5_cmd_exec(esw->dev, in, sizeof(in), out, outlen); @@ -2245,3 +2476,10 @@ bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) return false; } + +bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0, + struct mlx5_core_dev *dev1) +{ + return (dev0->priv.eswitch->mode == SRIOV_OFFLOADS && + dev1->priv.eswitch->mode == SRIOV_OFFLOADS); +} |