diff options
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 9 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 296 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 21 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h | 2 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 205 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h | 30 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c | 95 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h | 4 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c | 75 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c | 36 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h | 5 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c | 410 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h | 8 |
14 files changed, 1075 insertions, 122 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index b531d1c226b0..a0e2ca87b8d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2065,6 +2065,7 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw) mlx5_esw_reps_unblock(esw); esw->mode = MLX5_ESWITCH_LEGACY; + mlx5_sd_eswitch_mode_set(esw->dev, MLX5_ESWITCH_LEGACY); mlx5_lag_enable_change(esw->dev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 94a530d19828..fea72b1dedab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -440,6 +440,7 @@ struct mlx5_eswitch { void esw_offloads_disable(struct mlx5_eswitch *esw); int esw_offloads_enable(struct mlx5_eswitch *esw); +int mlx5_esw_offloads_init_deferred_metadata(struct mlx5_eswitch *esw); void esw_offloads_cleanup(struct mlx5_eswitch *esw); int esw_offloads_init(struct mlx5_eswitch *esw); @@ -950,11 +951,16 @@ void esw_vport_change_handle_locked(struct mlx5_vport *vport); bool mlx5_esw_offloads_controller_valid(const struct mlx5_eswitch *esw, u32 controller); +int mlx5_eswitch_offloads_vport_lag_add_one(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw); +void mlx5_eswitch_offloads_vport_lag_del_one(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw); int mlx5_eswitch_offloads_single_fdb_add_one(struct mlx5_eswitch *master_esw, struct mlx5_eswitch *slave_esw, int max_slaves); void mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw, struct mlx5_eswitch *slave_esw); int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw); +void mlx5_eswitch_unload_reps(struct mlx5_eswitch *esw); bool mlx5_eswitch_is_peer(struct mlx5_eswitch *esw, struct mlx5_eswitch *peer_esw); @@ -1059,6 +1065,9 @@ mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw) return 0; } +static inline void +mlx5_eswitch_unload_reps(struct mlx5_eswitch *esw) {} + static inline bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev, bool from_fdb) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 830fc910a080..907ee83a722d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -46,6 +46,7 @@ #include "fs_core.h" #include "lib/mlx5.h" #include "lib/devcom.h" +#include "lib/sd.h" #include "lib/eq.h" #include "lib/fs_chains.h" #include "en_tc.h" @@ -2862,6 +2863,10 @@ static int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num) int rep_type; int err; + if (vport_num != MLX5_VPORT_UPLINK && + mlx5_get_sd(esw->dev) && !mlx5_lag_is_active(esw->dev)) + return 0; + rep = mlx5_eswitch_get_rep(esw, vport_num); for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) { err = __esw_offloads_load_rep(esw, rep, rep_type, @@ -3040,6 +3045,136 @@ static int __esw_set_master_egress_rule(struct mlx5_core_dev *master, return err; } +static int esw_slave_egress_create_resources(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + struct mlx5_flow_table_attr ft_attr = { + .max_fte = 1, .prio = 0, .level = 0, + }; + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_namespace *ns; + struct mlx5_flow_table *acl; + struct mlx5_flow_group *g; + u32 *flow_group_in; + int err = 0; + + if (vport->egress.acl) + return 0; + + xa_init_flags(&vport->egress.offloads.bounce_rules, XA_FLAGS_ALLOC); + ns = mlx5_get_flow_vport_namespace(esw->dev, + MLX5_FLOW_NAMESPACE_ESW_EGRESS, + vport->index); + if (!ns) + return -EINVAL; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) + return -ENOMEM; + + if (vport->vport || mlx5_core_is_ecpf(esw->dev)) + ft_attr.flags = MLX5_FLOW_TABLE_OTHER_VPORT; + + acl = mlx5_create_vport_flow_table(ns, &ft_attr, vport->vport); + if (IS_ERR(acl)) { + err = PTR_ERR(acl); + goto out; + } + + g = mlx5_create_flow_group(acl, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + goto err_table; + } + + vport->egress.acl = acl; + vport->egress.offloads.bounce_grp = g; + vport->egress.type = VPORT_EGRESS_ACL_TYPE_SHARED_FDB; + err = 0; + +err_table: + if (err && !IS_ERR_OR_NULL(acl)) { + mlx5_destroy_flow_table(acl); + vport->egress.acl = NULL; + } +out: + kvfree(flow_group_in); + return err; +} + +static void esw_slave_egress_destroy_resources(struct mlx5_vport *vport) +{ + if (!IS_ERR_OR_NULL(vport->egress.offloads.bounce_grp)) { + mlx5_destroy_flow_group(vport->egress.offloads.bounce_grp); + vport->egress.offloads.bounce_grp = NULL; + } + if (!IS_ERR_OR_NULL(vport->egress.acl)) { + esw_acl_egress_ofld_cleanup(vport); + xa_destroy(&vport->egress.offloads.bounce_rules); + } +} + +static int esw_set_slave_egress_rule(struct mlx5_core_dev *master, + struct mlx5_core_dev *slave) +{ + struct mlx5_eswitch *slave_esw = slave->priv.eswitch; + u16 master_vhca = MLX5_CAP_GEN(master, vhca_id); + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_handle *bounce_rule; + struct mlx5_flow_act flow_act = {}; + struct mlx5_vport *slave_vport; + int err; + + slave_vport = mlx5_eswitch_get_vport(slave_esw, + slave_esw->manager_vport); + if (IS_ERR(slave_vport)) + return PTR_ERR(slave_vport); + + err = esw_slave_egress_create_resources(slave_esw, slave_vport); + if (err) + return err; + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; + dest.vport.num = master->priv.eswitch->manager_vport; + dest.vport.vhca_id = master_vhca; + dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID; + + bounce_rule = mlx5_add_flow_rules(slave_vport->egress.acl, NULL, + &flow_act, &dest, 1); + if (IS_ERR(bounce_rule)) { + err = PTR_ERR(bounce_rule); + goto err_rule; + } + err = xa_insert(&slave_vport->egress.offloads.bounce_rules, + master_vhca, bounce_rule, GFP_KERNEL); + if (err) + goto err_insert; + + return 0; +err_insert: + mlx5_del_flow_rules(bounce_rule); +err_rule: + esw_slave_egress_destroy_resources(slave_vport); + return err; +} + +static void esw_unset_slave_egress_rule(struct mlx5_core_dev *master, + struct mlx5_core_dev *slave) +{ + struct mlx5_eswitch *slave_esw = slave->priv.eswitch; + u16 master_vhca = MLX5_CAP_GEN(master, vhca_id); + struct mlx5_vport *slave_vport; + + slave_vport = mlx5_eswitch_get_vport(slave_esw, + slave_esw->manager_vport); + if (IS_ERR(slave_vport)) + return; + + esw_acl_egress_ofld_bounce_rule_destroy(slave_vport, master_vhca); + esw_slave_egress_destroy_resources(slave_vport); +} + static int esw_master_egress_create_resources(struct mlx5_eswitch *esw, struct mlx5_flow_namespace *egress_ns, struct mlx5_vport *vport, size_t count) @@ -3164,6 +3299,9 @@ static void esw_unset_master_egress_rule(struct mlx5_core_dev *dev, vport = mlx5_eswitch_get_vport(dev->priv.eswitch, dev->priv.eswitch->manager_vport); + if (!vport->egress.acl) + return; + esw_acl_egress_ofld_bounce_rule_destroy(vport, MLX5_CAP_GEN(slave_dev, vhca_id)); if (xa_empty(&vport->egress.offloads.bounce_rules)) { @@ -3182,6 +3320,9 @@ int mlx5_eswitch_offloads_single_fdb_add_one(struct mlx5_eswitch *master_esw, if (err) return err; + if (!mlx5_sd_is_primary(slave_esw->dev)) + return 0; + err = esw_set_master_egress_rule(master_esw->dev, slave_esw->dev, max_slaves); if (err) @@ -3201,6 +3342,18 @@ void mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw, esw_unset_master_egress_rule(master_esw->dev, slave_esw->dev); } +int mlx5_eswitch_offloads_vport_lag_add_one(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw) +{ + return esw_set_slave_egress_rule(master_esw->dev, slave_esw->dev); +} + +void mlx5_eswitch_offloads_vport_lag_del_one(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw) +{ + esw_unset_slave_egress_rule(master_esw->dev, slave_esw->dev); +} + #define ESW_OFFLOADS_DEVCOM_PAIR (0) #define ESW_OFFLOADS_DEVCOM_UNPAIR (1) @@ -3401,7 +3554,7 @@ void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, return; if ((MLX5_VPORT_MANAGER(esw->dev) || mlx5_core_is_ecpf_esw_manager(esw->dev)) && - !mlx5_lag_is_supported(esw->dev)) + (!mlx5_lag_is_supported(esw->dev) && !mlx5_get_sd(esw->dev))) return; xa_init(&esw->paired); @@ -3472,12 +3625,12 @@ u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw) u32 vport_end_ida = (1 << ESW_VPORT_BITS) - 1; /* Reserve 0xf for internal port offload */ u32 max_pf_num = (1 << ESW_PFNUM_BITS) - 2; - u32 pf_num; + int pf_num; int id; /* Only 4 bits of pf_num */ - pf_num = mlx5_get_dev_index(esw->dev); - if (pf_num > max_pf_num) + pf_num = mlx5_sd_pf_num_get(esw->dev); + if (pf_num < 0 || pf_num > max_pf_num) return 0; /* Metadata is 4 bits of PFNUM and 12 bits of unique id */ @@ -3522,6 +3675,7 @@ static void esw_offloads_vport_metadata_cleanup(struct mlx5_eswitch *esw, WARN_ON(vport->metadata != vport->default_metadata); mlx5_esw_match_metadata_free(esw, vport->default_metadata); + vport->default_metadata = 0; } static void esw_offloads_metadata_uninit(struct mlx5_eswitch *esw) @@ -3558,6 +3712,73 @@ metadata_err: return err; } +/* Deferred metadata init for SD devices: allocate vport metadata and + * refresh the ingress ACL for every vport whose ACL was created with + * metadata=0 in esw_create_offloads_acl_tables() / esw_vport_setup(). + * + * No Rep is loaded at this point ==> no Rep net-dev exists, so no need + * to take rtnl lock. + * + * Safe to call multiple times - subsequent calls are no-ops. + */ +int mlx5_esw_offloads_init_deferred_metadata(struct mlx5_eswitch *esw) +{ + struct mlx5_vport *manager, *vport; + unsigned long i; + int err; + + if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) + return 0; + + manager = mlx5_eswitch_get_vport(esw, esw->manager_vport); + if (IS_ERR(manager)) + return PTR_ERR(manager); + + /* Sanity check: skip if metadata was already initialized */ + if (manager->default_metadata) + return 0; + + err = esw_offloads_metadata_init(esw); + if (err) + return err; + + mutex_lock(&esw->state_lock); + /* Manager vport doesn't have a rep/netdev loaded but its ingress ACL + * was programmed with metadata=0 - refresh it explicitly. + */ + err = mlx5_esw_acl_ingress_vport_metadata_update(esw, + esw->manager_vport, + 0); + if (err) + goto err_acl; + + /* UPLINK is never marked enabled but its ACL is programmed in + * esw_create_offloads_acl_tables(); refresh it explicitly. + */ + err = mlx5_esw_acl_ingress_vport_metadata_update(esw, MLX5_VPORT_UPLINK, + 0); + if (err) + goto err_acl; + + mlx5_esw_for_each_vport(esw, i, vport) { + if (!vport || !vport->enabled) + continue; + err = mlx5_esw_acl_ingress_vport_metadata_update(esw, + vport->vport, + 0); + if (err) + goto err_acl; + } + + mutex_unlock(&esw->state_lock); + return 0; + +err_acl: + esw_offloads_metadata_uninit(esw); + mutex_unlock(&esw->state_lock); + return err; +} + int esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw, struct mlx5_vport *vport) @@ -3630,6 +3851,21 @@ static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw) esw_vport_destroy_offloads_acl_tables(esw, vport); } +void mlx5_eswitch_unload_reps(struct mlx5_eswitch *esw) +{ + struct mlx5_eswitch_rep *rep; + unsigned long i; + + if (!esw || esw->mode != MLX5_ESWITCH_OFFLOADS) + return; + + mlx5_esw_for_each_rep(esw, i, rep) { + if (rep->vport == MLX5_VPORT_UPLINK) + continue; + mlx5_esw_offloads_rep_unload(esw, rep->vport); + } +} + int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw) { struct mlx5_eswitch_rep *rep; @@ -3643,11 +3879,23 @@ int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw) if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED) return 0; - ret = __esw_offloads_load_rep(esw, rep, REP_IB, NULL); - if (ret) - return ret; + /* SD secondary devices share the primary's uplink and do not + * have their own uplink representor. Only load VF/SF vports. + */ + if (mlx5_sd_is_primary(esw->dev)) { + ret = __esw_offloads_load_rep(esw, rep, REP_IB, NULL); + if (ret) + return ret; + } mlx5_esw_for_each_rep(esw, i, rep) { + if (!mlx5_sd_is_primary(esw->dev) && + rep->vport == MLX5_VPORT_UPLINK) + continue; + if (rep->vport != MLX5_VPORT_UPLINK && + mlx5_get_sd(esw->dev) && !mlx5_lag_is_active(esw->dev)) + continue; + if (atomic_read(&rep->rep_data[REP_ETH].state) == REP_LOADED) __esw_offloads_load_rep(esw, rep, REP_IB, NULL); } @@ -3892,9 +4140,14 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) if (err) goto err_roce; - err = esw_offloads_metadata_init(esw); - if (err) - goto err_metadata; + /* SD devices defer metadata init until SD is ready and + * mlx5_sd_pf_num_get() can return the correct pf_num. + */ + if (!mlx5_get_sd(esw->dev)) { + err = esw_offloads_metadata_init(esw); + if (err) + goto err_metadata; + } err = esw_set_passing_vport_metadata(esw, true); if (err) @@ -4219,12 +4472,6 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, if (esw_mode_from_devlink(mode, &mlx5_mode)) return -EINVAL; - if (mlx5_mode == MLX5_ESWITCH_OFFLOADS && mlx5_get_sd(esw->dev)) { - NL_SET_ERR_MSG_MOD(extack, - "Can't change E-Switch mode to switchdev when multi-PF netdev (Socket Direct) is configured."); - return -EPERM; - } - /* Avoid try_lock, active/inactive mode change is not restricted */ if (mlx5_devlink_switchdev_active_mode_change(esw, mode)) return 0; @@ -4298,6 +4545,9 @@ unlock: mlx5_esw_unlock(esw); enable_lag: mlx5_lag_enable_change(esw->dev); + /* Shared FDB activation is creating LAG which is changing reps. */ + if (!err) + mlx5_sd_eswitch_mode_set(esw->dev, mlx5_mode); return err; } @@ -4586,13 +4836,25 @@ mlx5_eswitch_register_vport_reps_blocked(struct mlx5_eswitch *esw, static void mlx5_eswitch_reload_reps_blocked(struct mlx5_eswitch *esw) { + struct mlx5_eswitch_rep *uplink; struct mlx5_vport *vport; + bool newly_loaded; unsigned long i; if (esw->mode != MLX5_ESWITCH_OFFLOADS) return; - if (mlx5_esw_offloads_rep_load(esw, MLX5_VPORT_UPLINK)) + uplink = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK); + if (__esw_offloads_load_rep(esw, uplink, REP_ETH, &newly_loaded)) + return; + if (mlx5_sd_is_primary(esw->dev) && + __esw_offloads_load_rep(esw, uplink, REP_IB, NULL)) { + if (newly_loaded) + __esw_offloads_unload_rep(esw, uplink, REP_ETH); + return; + } + + if (mlx5_get_sd(esw->dev) && !mlx5_lag_is_active(esw->dev)) return; mlx5_esw_for_each_vport(esw, i, vport) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 1cd4cd898ec2..8af73393770c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -1217,3 +1217,24 @@ int mlx5_fs_cmd_set_tx_flow_table_root(struct mlx5_core_dev *dev, u32 ft_id, boo return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } + +int mlx5_fs_cmd_query_l2table_silent(struct mlx5_core_dev *dev, u8 *silent_mode) +{ + u32 out[MLX5_ST_SZ_DW(query_l2_table_entry_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_l2_table_entry_in)] = {}; + int err; + + if (!MLX5_CAP_GEN(dev, silent_mode_query)) + return -EOPNOTSUPP; + + MLX5_SET(query_l2_table_entry_in, in, opcode, + MLX5_CMD_OP_QUERY_L2_TABLE_ENTRY); + MLX5_SET(query_l2_table_entry_in, in, silent_mode_query, 1); + + err = mlx5_cmd_exec_inout(dev, query_l2_table_entry, in, out); + if (err) + return err; + + *silent_mode = MLX5_GET(query_l2_table_entry_out, out, silent_mode); + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index 7eb7b3ffe3d8..60280ff7da50 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -124,6 +124,8 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void); int mlx5_fs_cmd_set_l2table_entry_silent(struct mlx5_core_dev *dev, u8 silent_mode); int mlx5_fs_cmd_set_tx_flow_table_root(struct mlx5_core_dev *dev, u32 ft_id, bool disconnect); +int mlx5_fs_cmd_query_l2table_silent(struct mlx5_core_dev *dev, + u8 *silent_mode); static inline bool mlx5_fs_cmd_is_fw_term_table(struct mlx5_flow_table *ft) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index dd3f18f85466..28d16fdc3f06 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -139,9 +139,44 @@ static int mlx5_cmd_modify_lag(struct mlx5_core_dev *dev, struct mlx5_lag *ldev, return mlx5_cmd_exec_in(dev, modify_lag, in); } +static u32 mlx5_lag_dev_group_id(struct mlx5_core_dev *dev) +{ + struct mlx5_lag *ldev = mlx5_lag_dev(dev); + struct lag_func *pf; + int i; + + if (!ldev) + return 0; + + mlx5_lag_for_each(i, 0, ldev, MLX5_LAG_FILTER_ALL) { + pf = mlx5_lag_pf(ldev, i); + if (pf->dev == dev) + return pf->sd_fdb_active ? pf->group_id : 0; + } + return 0; +} + +static int mlx5_lag_is_sw_lag(struct mlx5_core_dev *dev) +{ + return mlx5_lag_is_sd(dev); +} + int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev) { u32 in[MLX5_ST_SZ_DW(create_vport_lag_in)] = {}; + struct mlx5_lag *ldev = mlx5_lag_dev(dev); + int ret; + + if (mlx5_lag_is_sw_lag(dev)) { + if (!ldev) + return -ENODEV; + + mutex_lock(&ldev->lock); + ret = mlx5_lag_create_vport_lag(mlx5_lag_dev(dev), + mlx5_lag_dev_group_id(dev)); + mutex_unlock(&ldev->lock); + return ret; + } MLX5_SET(create_vport_lag_in, in, opcode, MLX5_CMD_OP_CREATE_VPORT_LAG); @@ -152,6 +187,18 @@ EXPORT_SYMBOL(mlx5_cmd_create_vport_lag); int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev) { u32 in[MLX5_ST_SZ_DW(destroy_vport_lag_in)] = {}; + struct mlx5_lag *ldev = mlx5_lag_dev(dev); + + if (mlx5_lag_is_sw_lag(dev)) { + if (!ldev) + return 0; + + mutex_lock(&ldev->lock); + mlx5_lag_destroy_vport_lag(mlx5_lag_dev(dev), + mlx5_lag_dev_group_id(dev)); + mutex_unlock(&ldev->lock); + return 0; + } MLX5_SET(destroy_vport_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_VPORT_LAG); @@ -1265,6 +1312,32 @@ int mlx5_lag_reload_ib_reps_from_locked(struct mlx5_lag *ldev, u32 flags, return mlx5_lag_reload_ib_reps(ldev, flags, filter, cont_on_fail); } +static void mlx5_lag_unload_reps_unlocked(struct mlx5_lag *ldev, u32 filter) +{ + struct lag_func *pf; + int i; + + mlx5_lag_for_each(i, 0, ldev, filter) { + struct mlx5_eswitch *esw; + + pf = mlx5_lag_pf(ldev, i); + esw = pf->dev->priv.eswitch; + mlx5_esw_reps_block(esw); + mlx5_eswitch_unload_reps(esw); + mlx5_esw_reps_unblock(esw); + } +} + +void mlx5_lag_unload_reps_from_locked(struct mlx5_lag *ldev, u32 filter) +{ + /* Same lock dance as mlx5_lag_reload_ib_reps: drop ldev->lock around + * the per-eswitch reps_lock to keep the reps_lock -> ldev->lock order. + */ + mlx5_lag_drop_lock_for_reps(ldev, filter); + mlx5_lag_unload_reps_unlocked(ldev, filter); + mlx5_lag_retake_lock_after_reps(ldev); +} + void mlx5_disable_lag(struct mlx5_lag *ldev) { bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags); @@ -1590,7 +1663,7 @@ struct mlx5_devcom_comp_dev *mlx5_lag_get_devcom_comp(struct mlx5_lag *ldev) static int mlx5_lag_demux_ft_fg_init(struct mlx5_core_dev *dev, struct mlx5_flow_table_attr *ft_attr, - struct mlx5_lag *ldev) + struct lag_func *pf) { #ifdef CONFIG_MLX5_ESWITCH struct mlx5_flow_namespace *ns; @@ -1601,20 +1674,20 @@ static int mlx5_lag_demux_ft_fg_init(struct mlx5_core_dev *dev, if (!ns) return 0; - ldev->lag_demux_ft = mlx5_create_flow_table(ns, ft_attr); - if (IS_ERR(ldev->lag_demux_ft)) - return PTR_ERR(ldev->lag_demux_ft); + pf->lag_demux_ft = mlx5_create_flow_table(ns, ft_attr); + if (IS_ERR(pf->lag_demux_ft)) + return PTR_ERR(pf->lag_demux_ft); fg = mlx5_esw_lag_demux_fg_create(dev->priv.eswitch, - ldev->lag_demux_ft); + pf->lag_demux_ft); if (IS_ERR(fg)) { err = PTR_ERR(fg); - mlx5_destroy_flow_table(ldev->lag_demux_ft); - ldev->lag_demux_ft = NULL; + mlx5_destroy_flow_table(pf->lag_demux_ft); + pf->lag_demux_ft = NULL; return err; } - ldev->lag_demux_fg = fg; + pf->lag_demux_fg = fg; return 0; #else return -EOPNOTSUPP; @@ -1623,7 +1696,7 @@ static int mlx5_lag_demux_ft_fg_init(struct mlx5_core_dev *dev, static int mlx5_lag_demux_fw_init(struct mlx5_core_dev *dev, struct mlx5_flow_table_attr *ft_attr, - struct mlx5_lag *ldev) + struct lag_func *pf) { struct mlx5_flow_namespace *ns; int err; @@ -1632,12 +1705,12 @@ static int mlx5_lag_demux_fw_init(struct mlx5_core_dev *dev, if (!ns) return 0; - ldev->lag_demux_fg = NULL; + pf->lag_demux_fg = NULL; ft_attr->max_fte = 1; - ldev->lag_demux_ft = mlx5_create_lag_demux_flow_table(ns, ft_attr); - if (IS_ERR(ldev->lag_demux_ft)) { - err = PTR_ERR(ldev->lag_demux_ft); - ldev->lag_demux_ft = NULL; + pf->lag_demux_ft = mlx5_create_lag_demux_flow_table(ns, ft_attr); + if (IS_ERR(pf->lag_demux_ft)) { + err = PTR_ERR(pf->lag_demux_ft); + pf->lag_demux_ft = NULL; return err; } @@ -1648,6 +1721,7 @@ int mlx5_lag_demux_init(struct mlx5_core_dev *dev, struct mlx5_flow_table_attr *ft_attr) { struct mlx5_lag *ldev; + struct lag_func *pf; if (!ft_attr) return -EINVAL; @@ -1656,12 +1730,16 @@ int mlx5_lag_demux_init(struct mlx5_core_dev *dev, if (!ldev) return -ENODEV; - xa_init(&ldev->lag_demux_rules); + pf = mlx5_lag_pf_by_dev(ldev, dev); + if (!pf) + return -ENODEV; + + xa_init(&pf->lag_demux_rules); - if (mlx5_get_sd(dev)) - return mlx5_lag_demux_ft_fg_init(dev, ft_attr, ldev); + if (mlx5_lag_is_sw_lag(dev)) + return mlx5_lag_demux_ft_fg_init(dev, ft_attr, pf); - return mlx5_lag_demux_fw_init(dev, ft_attr, ldev); + return mlx5_lag_demux_fw_init(dev, ft_attr, pf); } EXPORT_SYMBOL(mlx5_lag_demux_init); @@ -1670,40 +1748,63 @@ void mlx5_lag_demux_cleanup(struct mlx5_core_dev *dev) struct mlx5_flow_handle *rule; struct mlx5_lag *ldev; unsigned long vport_num; + struct lag_func *pf; ldev = mlx5_lag_dev(dev); if (!ldev) return; - xa_for_each(&ldev->lag_demux_rules, vport_num, rule) + pf = mlx5_lag_pf_by_dev(ldev, dev); + if (!pf) + return; + + xa_for_each(&pf->lag_demux_rules, vport_num, rule) mlx5_del_flow_rules(rule); - xa_destroy(&ldev->lag_demux_rules); + xa_destroy(&pf->lag_demux_rules); - if (ldev->lag_demux_fg) - mlx5_destroy_flow_group(ldev->lag_demux_fg); - if (ldev->lag_demux_ft) - mlx5_destroy_flow_table(ldev->lag_demux_ft); - ldev->lag_demux_fg = NULL; - ldev->lag_demux_ft = NULL; + if (pf->lag_demux_fg) + mlx5_destroy_flow_group(pf->lag_demux_fg); + if (pf->lag_demux_ft) + mlx5_destroy_flow_table(pf->lag_demux_ft); + pf->lag_demux_fg = NULL; + pf->lag_demux_ft = NULL; } EXPORT_SYMBOL(mlx5_lag_demux_cleanup); +static struct lag_func *mlx5_lag_dev_get_master_pf(struct mlx5_lag *ldev, + struct mlx5_core_dev *dev) +{ + u32 filter = mlx5_lag_get_filter(ldev, dev); + int idx; + + idx = mlx5_lag_get_dev_index_by_seq_filter(ldev, MLX5_LAG_P1, filter); + if (idx < 0) + return NULL; + + return mlx5_lag_pf(ldev, idx); +} + int mlx5_lag_demux_rule_add(struct mlx5_core_dev *vport_dev, u16 vport_num, int index) { struct mlx5_flow_handle *rule; + struct lag_func *master; struct mlx5_lag *ldev; int err; ldev = mlx5_lag_dev(vport_dev); - if (!ldev || !ldev->lag_demux_fg) + if (!ldev) + return 0; + + master = mlx5_lag_dev_get_master_pf(ldev, vport_dev); + if (!master || !master->lag_demux_fg) return 0; - if (xa_load(&ldev->lag_demux_rules, index)) + if (xa_load(&master->lag_demux_rules, index)) return 0; rule = mlx5_esw_lag_demux_rule_create(vport_dev->priv.eswitch, - vport_num, ldev->lag_demux_ft); + vport_num, master->lag_demux_ft); if (IS_ERR(rule)) { err = PTR_ERR(rule); mlx5_core_warn(vport_dev, @@ -1712,7 +1813,7 @@ int mlx5_lag_demux_rule_add(struct mlx5_core_dev *vport_dev, u16 vport_num, return err; } - err = xa_err(xa_store(&ldev->lag_demux_rules, index, rule, + err = xa_err(xa_store(&master->lag_demux_rules, index, rule, GFP_KERNEL)); if (err) { mlx5_del_flow_rules(rule); @@ -1728,13 +1829,18 @@ EXPORT_SYMBOL(mlx5_lag_demux_rule_add); void mlx5_lag_demux_rule_del(struct mlx5_core_dev *dev, int index) { struct mlx5_flow_handle *rule; + struct lag_func *master_pf; struct mlx5_lag *ldev; ldev = mlx5_lag_dev(dev); - if (!ldev || !ldev->lag_demux_fg) + if (!ldev) + return; + + master_pf = mlx5_lag_dev_get_master_pf(ldev, dev); + if (!master_pf || !master_pf->lag_demux_fg) return; - rule = xa_erase(&ldev->lag_demux_rules, index); + rule = xa_erase(&master_pf->lag_demux_rules, index); if (rule) mlx5_del_flow_rules(rule); } @@ -2461,13 +2567,26 @@ EXPORT_SYMBOL(mlx5_lag_is_shared_fdb); void mlx5_lag_disable_change(struct mlx5_core_dev *dev) { + struct mlx5_devcom_comp_dev *sd_devcom = mlx5_sd_get_devcom(dev); + struct mlx5_core_dev *primary = dev; struct mlx5_lag *ldev; + struct lag_func *pf; + bool mpesw; + int i; ldev = mlx5_lag_dev(dev); if (!ldev) return; - mlx5_devcom_comp_lock(dev->priv.hca_devcom_comp); + if (sd_devcom) { + mlx5_devcom_comp_lock(sd_devcom); + primary = mlx5_sd_get_primary(dev) ?: dev; + mlx5_devcom_comp_unlock(sd_devcom); + } + mlx5_devcom_comp_lock(primary->priv.hca_devcom_comp); + mpesw = ldev->mode == MLX5_LAG_MODE_MPESW; + if (mpesw) + mlx5_mpesw_sd_devcoms_lock(ldev); mutex_lock(&ldev->lock); ldev->mode_changes_in_progress++; @@ -2479,7 +2598,25 @@ void mlx5_lag_disable_change(struct mlx5_core_dev *dev) } mutex_unlock(&ldev->lock); - mlx5_devcom_comp_unlock(dev->priv.hca_devcom_comp); + if (mpesw) + mlx5_mpesw_sd_devcoms_unlock(ldev); + mlx5_devcom_comp_unlock(primary->priv.hca_devcom_comp); + + if (!sd_devcom) + return; + + /* Teardown SD shared FDB for this device's group if active */ + mlx5_devcom_comp_lock(sd_devcom); + mutex_lock(&ldev->lock); + mlx5_lag_for_each(i, 0, ldev, MLX5_LAG_FILTER_ALL) { + pf = mlx5_lag_pf(ldev, i); + if (pf->dev == dev && pf->sd_fdb_active) { + mlx5_lag_shared_fdb_destroy(ldev, pf->group_id); + break; + } + } + mutex_unlock(&ldev->lock); + mlx5_devcom_comp_unlock(sd_devcom); } void mlx5_lag_enable_change(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h index 0296f752bb4c..e9f0ef83ce1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h @@ -59,6 +59,10 @@ struct lag_func { struct mlx5_nb port_change_nb; u32 group_id; /* SD group ID, 0 = not SD */ bool sd_fdb_active; /* set on all SD group members */ + /* Lag demux resources - only populated on master devices */ + struct mlx5_flow_table *lag_demux_ft; + struct mlx5_flow_group *lag_demux_fg; + struct xarray lag_demux_rules; }; /* Used for collection of netdev event info. */ @@ -95,9 +99,6 @@ struct mlx5_lag { /* Protect lag fields/state changes */ struct mutex lock; struct lag_mpesw lag_mpesw; - struct mlx5_flow_table *lag_demux_ft; - struct mlx5_flow_group *lag_demux_fg; - struct xarray lag_demux_rules; }; static inline struct mlx5_lag * @@ -157,6 +158,14 @@ __mlx5_lag_is_sd(struct mlx5_lag *ldev, struct mlx5_core_dev *dev) } static inline bool +__mlx5_lag_dev_is_port(struct mlx5_lag *ldev, struct mlx5_core_dev *dev) +{ + struct lag_func *pf = mlx5_lag_pf_by_dev(ldev, dev); + + return pf && xa_get_mark(&ldev->pfs, pf->idx, MLX5_LAG_XA_MARK_PORT); +} + +static inline bool __mlx5_lag_is_active(struct mlx5_lag *ldev) { return ldev->mode != MLX5_LAG_MODE_NONE; @@ -174,6 +183,8 @@ int mlx5_lag_shared_fdb_create(struct mlx5_lag *ldev, enum mlx5_lag_mode mode, u32 group_id); void mlx5_lag_shared_fdb_destroy(struct mlx5_lag *ldev, u32 group_id); +int mlx5_lag_create_vport_lag(struct mlx5_lag *ldev, u32 group_id); +int mlx5_lag_destroy_vport_lag(struct mlx5_lag *ldev, u32 group_id); int mlx5_lag_create_single_fdb(struct mlx5_lag *ldev); void mlx5_lag_destroy_single_fdb(struct mlx5_lag *ldev); bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev); @@ -190,6 +201,18 @@ static inline int mlx5_lag_shared_fdb_create(struct mlx5_lag *ldev, static inline void mlx5_lag_shared_fdb_destroy(struct mlx5_lag *ldev, u32 group_id) {} +static inline int mlx5_lag_create_vport_lag(struct mlx5_lag *ldev, + u32 group_id) +{ + return -EOPNOTSUPP; +} + +static inline int mlx5_lag_destroy_vport_lag(struct mlx5_lag *ldev, + u32 group_id) +{ + return -EOPNOTSUPP; +} + static inline int mlx5_lag_create_single_fdb(struct mlx5_lag *ldev) { return -EOPNOTSUPP; @@ -287,6 +310,7 @@ int mlx5_lag_num_devs(struct mlx5_lag *ldev); int mlx5_lag_num_netdevs(struct mlx5_lag *ldev); int mlx5_lag_reload_ib_reps_from_locked(struct mlx5_lag *ldev, u32 flags, u32 filter, bool cont_on_fail); +void mlx5_lag_unload_reps_from_locked(struct mlx5_lag *ldev, u32 filter); int mlx5_ldev_add_mdev(struct mlx5_lag *ldev, struct mlx5_core_dev *dev, u32 group_id); void mlx5_ldev_remove_mdev(struct mlx5_lag *ldev, struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index 2cb44084e239..50bfb450c71e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -15,7 +15,7 @@ static void mlx5_mpesw_metadata_cleanup(struct mlx5_lag *ldev) u32 pf_metadata; int i; - mlx5_ldev_for_each(i, 0, ldev) { + mlx5_lag_for_each(i, 0, ldev, MLX5_LAG_FILTER_ALL) { dev = mlx5_lag_pf(ldev, i)->dev; esw = dev->priv.eswitch; pf_metadata = ldev->lag_mpesw.pf_metadata[i]; @@ -36,7 +36,7 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev) u32 pf_metadata; int i, err; - mlx5_ldev_for_each(i, 0, ldev) { + mlx5_lag_for_each(i, 0, ldev, MLX5_LAG_FILTER_ALL) { dev = mlx5_lag_pf(ldev, i)->dev; esw = dev->priv.eswitch; pf_metadata = mlx5_esw_match_metadata_alloc(esw); @@ -52,7 +52,7 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev) goto err_metadata; } - mlx5_ldev_for_each(i, 0, ldev) { + mlx5_lag_for_each(i, 0, ldev, MLX5_LAG_FILTER_ALL) { dev = mlx5_lag_pf(ldev, i)->dev; mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_MULTIPORT_ESW, (void *)0); @@ -65,6 +65,48 @@ err_metadata: return err; } +static void mlx5_mpesw_restore_sd_fdb(struct mlx5_lag *ldev) +{ + struct lag_func *pf; + int err, i; + + mlx5_ldev_for_each(i, 0, ldev) { + pf = mlx5_lag_pf(ldev, i); + err = mlx5_lag_shared_fdb_create(ldev, NULL, 0, pf->group_id); + if (err) + mlx5_core_warn(pf->dev, + "Failed to restore SD shared FDB (%d)\n", + err); + } +} + +static int mlx5_mpesw_teardown_sd_fdb(struct mlx5_lag *ldev) +{ + struct lag_func *pf; + int i; + + mlx5_ldev_for_each(i, 0, ldev) { + pf = mlx5_lag_pf(ldev, i); + if (!pf->sd_fdb_active) + continue; + mlx5_lag_shared_fdb_destroy(ldev, pf->group_id); + } + return 0; +} + +static bool mlx5_lag_has_sd_group(struct mlx5_lag *ldev) +{ + struct lag_func *pf; + int i; + + mlx5_ldev_for_each(i, 0, ldev) { + pf = mlx5_lag_pf(ldev, i); + if (pf->group_id) + return true; + } + return false; +} + static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev) { int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); @@ -92,10 +134,17 @@ static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev) if (err) return err; + if (mlx5_lag_has_sd_group(ldev)) + mlx5_mpesw_teardown_sd_fdb(ldev); + err = mlx5_lag_shared_fdb_create(ldev, NULL, MLX5_LAG_MODE_MPESW, MLX5_LAG_FILTER_ALL); if (err) { - mlx5_core_warn(dev0, "Failed to create LAG in MPESW mode (%d)\n", err); + mlx5_core_warn(dev0, + "Failed to create LAG in MPESW mode (%d)\n", + err); + if (mlx5_lag_has_sd_group(ldev)) + mlx5_mpesw_restore_sd_fdb(ldev); mlx5_mpesw_metadata_cleanup(ldev); return err; } @@ -105,9 +154,36 @@ static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev) void mlx5_lag_disable_mpesw(struct mlx5_lag *ldev) { - if (ldev->mode == MLX5_LAG_MODE_MPESW) { - mlx5_mpesw_metadata_cleanup(ldev); - mlx5_lag_shared_fdb_destroy(ldev, MLX5_LAG_FILTER_ALL); + if (ldev->mode != MLX5_LAG_MODE_MPESW) + return; + + mlx5_mpesw_metadata_cleanup(ldev); + mlx5_lag_shared_fdb_destroy(ldev, MLX5_LAG_FILTER_ALL); + if (mlx5_lag_has_sd_group(ldev)) + mlx5_mpesw_restore_sd_fdb(ldev); +} + +void mlx5_mpesw_sd_devcoms_lock(struct mlx5_lag *ldev) +{ + struct mlx5_devcom_comp_dev *sd_devcom; + int i; + + mlx5_ldev_for_each(i, 0, ldev) { + sd_devcom = mlx5_sd_get_devcom(mlx5_lag_pf(ldev, i)->dev); + if (sd_devcom) + mlx5_devcom_comp_lock(sd_devcom); + } +} + +void mlx5_mpesw_sd_devcoms_unlock(struct mlx5_lag *ldev) +{ + struct mlx5_devcom_comp_dev *sd_devcom; + int i; + + mlx5_ldev_for_each_reverse(i, MLX5_MAX_PORTS, 0, ldev) { + sd_devcom = mlx5_sd_get_devcom(mlx5_lag_pf(ldev, i)->dev); + if (sd_devcom) + mlx5_devcom_comp_unlock(sd_devcom); } } @@ -122,6 +198,7 @@ static void mlx5_mpesw_work(struct work_struct *work) return; mlx5_devcom_comp_lock(devcom); + mlx5_mpesw_sd_devcoms_lock(ldev); mutex_lock(&ldev->lock); if (ldev->mode_changes_in_progress) { mpesww->result = -EAGAIN; @@ -134,6 +211,7 @@ static void mlx5_mpesw_work(struct work_struct *work) mlx5_lag_disable_mpesw(ldev); unlock: mutex_unlock(&ldev->lock); + mlx5_mpesw_sd_devcoms_unlock(ldev); mlx5_devcom_comp_unlock(devcom); complete(&mpesww->comp); } @@ -199,7 +277,8 @@ bool mlx5_lag_is_mpesw(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev = mlx5_lag_dev(dev); - return ldev && ldev->mode == MLX5_LAG_MODE_MPESW; + return ldev && ldev->mode == MLX5_LAG_MODE_MPESW && + __mlx5_lag_dev_is_port(ldev, dev); } EXPORT_SYMBOL(mlx5_lag_is_mpesw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h index b767dbb4f457..5099723ba0f7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h @@ -33,8 +33,12 @@ void mlx5_lag_mpesw_disable(struct mlx5_core_dev *dev); int mlx5_lag_mpesw_enable(struct mlx5_core_dev *dev); #ifdef CONFIG_MLX5_ESWITCH void mlx5_lag_disable_mpesw(struct mlx5_lag *ldev); +void mlx5_mpesw_sd_devcoms_lock(struct mlx5_lag *ldev); +void mlx5_mpesw_sd_devcoms_unlock(struct mlx5_lag *ldev); #else static inline void mlx5_lag_disable_mpesw(struct mlx5_lag *ldev) {} +static inline void mlx5_mpesw_sd_devcoms_lock(struct mlx5_lag *ldev) {} +static inline void mlx5_mpesw_sd_devcoms_unlock(struct mlx5_lag *ldev) {} #endif /* CONFIG_MLX5_ESWITCH */ #ifdef CONFIG_MLX5_ESWITCH diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c index 1371e14c4c13..113866494d16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c @@ -89,6 +89,76 @@ err: return err; } +int mlx5_lag_create_vport_lag(struct mlx5_lag *ldev, u32 group_id) +{ + u32 filter = group_id ? group_id : MLX5_LAG_FILTER_ALL; + int master_idx = mlx5_lag_get_dev_index_by_seq_filter(ldev, MLX5_LAG_P1, + filter); + struct mlx5_eswitch *master_esw; + struct mlx5_core_dev *dev0; + int i, j; + int err; + + if (master_idx < 0) + return -EINVAL; + + dev0 = mlx5_lag_pf(ldev, master_idx)->dev; + master_esw = dev0->priv.eswitch; + + mlx5_lag_for_each(i, 0, ldev, filter) { + struct mlx5_eswitch *slave_esw; + + if (i == master_idx) + continue; + + slave_esw = mlx5_lag_pf(ldev, i)->dev->priv.eswitch; + err = mlx5_eswitch_offloads_vport_lag_add_one(master_esw, + slave_esw); + if (err) + goto err; + } + + return 0; + +err: + mlx5_lag_for_each_reverse(j, i - 1, 0, ldev, filter) { + struct mlx5_eswitch *slave_esw; + + if (j == master_idx) + continue; + slave_esw = mlx5_lag_pf(ldev, j)->dev->priv.eswitch; + mlx5_eswitch_offloads_vport_lag_del_one(master_esw, slave_esw); + } + return err; +} + +int mlx5_lag_destroy_vport_lag(struct mlx5_lag *ldev, u32 group_id) +{ + u32 filter = group_id ? group_id : MLX5_LAG_FILTER_ALL; + int master_idx = mlx5_lag_get_dev_index_by_seq_filter(ldev, MLX5_LAG_P1, + filter); + struct mlx5_eswitch *master_esw; + struct mlx5_core_dev *dev0; + int i; + + if (master_idx < 0) + return 0; + + dev0 = mlx5_lag_pf(ldev, master_idx)->dev; + master_esw = dev0->priv.eswitch; + + mlx5_lag_for_each(i, 0, ldev, filter) { + struct mlx5_core_dev *dev; + + if (i == master_idx) + continue; + dev = mlx5_lag_pf(ldev, i)->dev; + mlx5_eswitch_offloads_vport_lag_del_one(master_esw, + dev->priv.eswitch); + } + return 0; +} + static void mlx5_lag_destroy_single_fdb_filter(struct mlx5_lag *ldev, u32 filter) { @@ -141,7 +211,7 @@ int mlx5_lag_shared_fdb_create(struct mlx5_lag *ldev, enum mlx5_lag_mode mode, u32 group_id) { - u32 filter = group_id ? group_id : MLX5_LAG_FILTER_PORTS; + u32 filter = group_id ? group_id : MLX5_LAG_FILTER_ALL; int idx = mlx5_lag_get_dev_index_by_seq_filter(ldev, MLX5_LAG_P1, filter); struct mlx5_core_dev *dev0; @@ -209,7 +279,7 @@ err_add_devices: void mlx5_lag_shared_fdb_destroy(struct mlx5_lag *ldev, u32 group_id) { - u32 filter = group_id ? group_id : MLX5_LAG_FILTER_PORTS; + u32 filter = group_id ? group_id : MLX5_LAG_FILTER_ALL; struct lag_func *pf; int err; int i; @@ -226,6 +296,7 @@ void mlx5_lag_shared_fdb_destroy(struct mlx5_lag *ldev, u32 group_id) pf->sd_fdb_active = false; } mlx5_lag_destroy_single_fdb_filter(ldev, group_id); + mlx5_lag_unload_reps_from_locked(ldev, filter); } mlx5_lag_add_devices_filter(ldev, filter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index d40c53193ea8..64f92427602d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -287,9 +287,9 @@ int mlx5_devcom_comp_get_size(struct mlx5_devcom_comp_dev *devcom) return kref_read(&comp->ref); } -int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom, - int event, int rollback_event, - void *event_data) +int mlx5_devcom_locked_send_event(struct mlx5_devcom_comp_dev *devcom, + int event, int rollback_event, + void *event_data) { struct mlx5_devcom_comp_dev *pos; struct mlx5_devcom_comp *comp; @@ -299,24 +299,28 @@ int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom, if (!devcom) return -ENODEV; + lockdep_assert_held_write(&devcom->comp->sem); comp = devcom->comp; - down_write(&comp->sem); list_for_each_entry(pos, &comp->comp_dev_list_head, list) { data = rcu_dereference_protected(pos->data, lockdep_is_held(&comp->sem)); if (pos != devcom && data) { err = comp->handler(event, data, event_data); - if (err) + if (err && rollback_event != DEVCOM_CANT_FAIL) { goto rollback; + } else if (err && rollback_event == DEVCOM_CANT_FAIL) { + WARN_ONCE(1, "devcom component %d event %d failed: %d\n", + comp->id, event, err); + return err; + } } } - up_write(&comp->sem); return 0; rollback: if (list_entry_is_head(pos, &comp->comp_dev_list_head, list)) - goto out; + return err; pos = list_prev_entry(pos, list); list_for_each_entry_from_reverse(pos, &comp->comp_dev_list_head, list) { data = rcu_dereference_protected(pos->data, lockdep_is_held(&comp->sem)); @@ -324,7 +328,23 @@ rollback: if (pos != devcom && data) comp->handler(rollback_event, data, event_data); } -out: + return err; +} + +int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom, + int event, int rollback_event, + void *event_data) +{ + struct mlx5_devcom_comp *comp; + int err; + + if (!devcom) + return -ENODEV; + + comp = devcom->comp; + down_write(&comp->sem); + err = mlx5_devcom_locked_send_event(devcom, event, rollback_event, + event_data); up_write(&comp->sem); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h index 316052a85ca5..7a704fafdbd3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h @@ -46,6 +46,11 @@ mlx5_devcom_register_component(struct mlx5_devcom_dev *devc, void *data); void mlx5_devcom_unregister_component(struct mlx5_devcom_comp_dev *devcom); +#define DEVCOM_CANT_FAIL (INT_MAX) + +int mlx5_devcom_locked_send_event(struct mlx5_devcom_comp_dev *devcom, + int event, int rollback_event, + void *event_data); int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom, int event, int rollback_event, void *event_data); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index 25286ecd724e..ee2fdefa1945 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -5,6 +5,8 @@ #include "../lag/lag.h" #include "mlx5_core.h" #include "lib/mlx5.h" +#include "devlink.h" +#include "eswitch.h" #include "fs_cmd.h" #include <linux/mlx5/eswitch.h> #include <linux/mlx5/vport.h> @@ -22,14 +24,19 @@ struct mlx5_sd { struct dentry *dfs; u8 state; bool primary; + bool fw_silents_secondaries; union { struct { /* primary */ struct mlx5_core_dev *secondaries[MLX5_SD_MAX_GROUP_SZ - 1]; struct mlx5_flow_table *tx_ft; + /* Next index for secondary registration */ + u8 next_secondary_idx; }; struct { /* secondary */ struct mlx5_core_dev *primary_dev; u32 alias_obj_id; + /* TX flow table root in switchdev (silent) config */ + bool tx_root_silent; }; }; }; @@ -82,6 +89,27 @@ bool mlx5_sd_is_primary(struct mlx5_core_dev *dev) return sd->primary; } +int mlx5_sd_pf_num_get(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + int pf_num = mlx5_get_dev_index(dev); + struct mlx5_core_dev *pos; + int i; + + if (!sd) + return pf_num; + + mlx5_devcom_comp_assert_locked(sd->devcom); + if (!mlx5_devcom_comp_is_ready(sd->devcom)) + return -ENODEV; + + mlx5_sd_for_each_dev(i, mlx5_sd_get_primary(dev), pos) + if (pos == dev) + break; + + return pf_num * sd->host_buses + i; +} + struct mlx5_core_dev * mlx5_sd_primary_get_peer(struct mlx5_core_dev *primary, int idx) { @@ -165,7 +193,8 @@ static bool mlx5_sd_caps_supported(struct mlx5_core_dev *dev, u8 host_buses) /* Disconnect secondaries from the network */ if (!MLX5_CAP_GEN(dev, eswitch_manager)) return false; - if (!MLX5_CAP_GEN(dev, silent_mode_set)) + if (!MLX5_CAP_GEN(dev, silent_mode_set) && + !MLX5_CAP_GEN(dev, silent_mode_query)) return false; /* RX steering from primary to secondaries */ @@ -193,10 +222,6 @@ bool mlx5_sd_is_supported(struct mlx5_core_dev *dev) if (!mlx5_core_is_pf(dev)) return false; - /* Block on embedded CPU PFs */ - if (mlx5_core_is_ecpf(dev)) - return false; - err = mlx5_query_nic_vport_sd_group(dev, &sd_group); if (err || !sd_group) return false; @@ -223,10 +248,6 @@ static int sd_init(struct mlx5_core_dev *dev) if (!mlx5_core_is_pf(dev)) return 0; - /* Block on embedded CPU PFs */ - if (mlx5_core_is_ecpf(dev)) - return 0; - err = mlx5_query_nic_vport_sd_group(dev, &sd_group); if (err) return err; @@ -374,62 +395,196 @@ static void sd_lag_cleanup(struct mlx5_core_dev *dev) mutex_unlock(&ldev->lock); } +enum { + SD_PRIMARY_SET, + SD_SECONDARIES_SET, + SD_FW_SILENT_CHECK, +}; + +static int sd_handle_fw_silent_check(struct mlx5_core_dev *dev, + struct mlx5_core_dev *peer) +{ + struct mlx5_sd *peer_sd = mlx5_get_sd(peer); + struct mlx5_sd *sd = mlx5_get_sd(dev); + u8 dev_silent = 0, peer_silent = 0; + int err; + + if (peer_sd->fw_silents_secondaries) { + sd->fw_silents_secondaries = true; + return 0; + } + + err = mlx5_fs_cmd_query_l2table_silent(dev, &dev_silent); + if (err) { + sd_warn(dev, "Failed to query silent mode for dev: %d\n", err); + return err; + } + + err = mlx5_fs_cmd_query_l2table_silent(peer, &peer_silent); + if (err) { + sd_warn(dev, "Failed to query silent mode for peer: %d\n", err); + return err; + } + + if (dev_silent || peer_silent) { + sd->fw_silents_secondaries = true; + peer_sd->fw_silents_secondaries = true; + sd_info(dev, "FW indicates at least one device is silent\n"); + } + return 0; +} + +static int sd_handle_primary_set(struct mlx5_core_dev *dev, + struct mlx5_core_dev *peer) +{ + struct mlx5_sd *peer_sd = mlx5_get_sd(peer); + struct mlx5_sd *sd = mlx5_get_sd(dev); + struct mlx5_core_dev *candidate; + struct mlx5_sd *candidate_sd; + bool dev_should_be_primary; + + /* Peer is the device that being sent to all the other devices in the + * group. Hence, use peer to get the candidate device. + */ + candidate = peer_sd->primary ? peer : peer_sd->primary_dev; + + if (sd->fw_silents_secondaries) { + u8 candidate_silent = 0; + int err; + + err = mlx5_fs_cmd_query_l2table_silent(candidate, + &candidate_silent); + if (err) { + sd_warn(candidate, "Failed to query silent mode for dev: %d\n", + err); + return err; + } + /* Candidate is silent, dev should be primary */ + dev_should_be_primary = candidate_silent; + } else { + /* No FW silent mode, use bus number */ + dev_should_be_primary = + dev->pdev->bus->number < candidate->pdev->bus->number; + } + + if (!dev_should_be_primary) + return 0; + + candidate_sd = mlx5_get_sd(candidate); + + sd->primary = true; + candidate_sd->primary = false; + candidate_sd->primary_dev = dev; + peer_sd->primary = false; + peer_sd->primary_dev = dev; + return 0; +} + +static void sd_handle_secondaries_set(struct mlx5_core_dev *dev, + struct mlx5_core_dev *peer) +{ + struct mlx5_sd *peer_sd = mlx5_get_sd(peer); + struct mlx5_sd *sd = mlx5_get_sd(dev); + u8 idx; + + /* Primary has nothing to register with itself. */ + if (sd->primary) + return; + + /* dev is a secondary device, peer is the primary device. + * Secondary registers itself with the primary. + */ + idx = peer_sd->next_secondary_idx++; + peer_sd->secondaries[idx] = dev; + sd->primary_dev = peer; +} + +static int mlx5_sd_devcom_event(int event, void *my_data, void *event_data) +{ + struct mlx5_core_dev *peer = event_data; + struct mlx5_core_dev *dev = my_data; + + switch (event) { + case SD_FW_SILENT_CHECK: + return sd_handle_fw_silent_check(dev, peer); + case SD_PRIMARY_SET: + return sd_handle_primary_set(dev, peer); + case SD_SECONDARIES_SET: + sd_handle_secondaries_set(dev, peer); + return 0; + } + + return 0; +} + static int sd_register(struct mlx5_core_dev *dev) { - struct mlx5_devcom_comp_dev *devcom, *pos; struct mlx5_devcom_match_attr attr = {}; - struct mlx5_core_dev *peer, *primary; - struct mlx5_sd *sd, *primary_sd; - int err, i; + struct mlx5_devcom_comp_dev *devcom; + struct mlx5_core_dev *primary; + struct mlx5_sd *primary_sd; + struct mlx5_sd *sd; + int err; sd = mlx5_get_sd(dev); attr.key.val = sd->group_id; attr.flags = MLX5_DEVCOM_MATCH_FLAGS_NS; attr.net = mlx5_core_net(dev); - devcom = mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_SD_GROUP, - &attr, NULL, dev); + devcom = mlx5_devcom_register_component(dev->priv.devc, + MLX5_DEVCOM_SD_GROUP, + &attr, mlx5_sd_devcom_event, + dev); if (!devcom) return -EINVAL; sd->devcom = devcom; - if (mlx5_devcom_comp_get_size(devcom) != sd->host_buses) - return 0; - mlx5_devcom_comp_lock(devcom); - mlx5_devcom_comp_set_ready(devcom, true); - mlx5_devcom_comp_unlock(devcom); + if (mlx5_devcom_comp_get_size(devcom) != sd->host_buses || + mlx5_devcom_comp_is_ready(devcom)) + goto out; - if (!mlx5_devcom_for_each_peer_begin(devcom)) { - err = -ENODEV; - goto err_devcom_unreg; + /* If silent mode query is supported, ask each device whether it is + * silent and propagate the result to the whole group. In each group + * only one device is not silent + */ + if (MLX5_CAP_GEN(dev, silent_mode_query)) { + err = mlx5_devcom_locked_send_event(devcom, SD_FW_SILENT_CHECK, + SD_FW_SILENT_CHECK, dev); + if (err) + goto err_devcom_unreg; } - primary = dev; - mlx5_devcom_for_each_peer_entry(devcom, peer, pos) - if (peer->pdev->bus->number < primary->pdev->bus->number) - primary = peer; + /* Send SD_PRIMARY_SET event with this device. + * All peers will receive this event and compare to this device. + * If fw_silents_secondaries is set, choose non-silent device. + * Otherwise use bus number. + */ + sd->primary = true; + err = mlx5_devcom_locked_send_event(devcom, SD_PRIMARY_SET, + SD_PRIMARY_SET, dev); + if (err) + goto err_devcom_unreg; - primary_sd = mlx5_get_sd(primary); - primary_sd->primary = true; - i = 0; - /* loop the secondaries */ - mlx5_devcom_for_each_peer_entry(primary_sd->devcom, peer, pos) { - struct mlx5_sd *peer_sd = mlx5_get_sd(peer); - - primary_sd->secondaries[i++] = peer; - peer_sd->primary = false; - peer_sd->primary_dev = primary; - } + /* Broadcast SD_SECONDARIES_SET. Each non-sender peer's handler runs; + * the primary's handler returns early so only secondaries register. + */ + primary = sd->primary ? dev : sd->primary_dev; + if (!sd->primary) + sd_handle_secondaries_set(dev, primary); + mlx5_devcom_locked_send_event(devcom, SD_SECONDARIES_SET, + DEVCOM_CANT_FAIL, primary); - mlx5_devcom_for_each_peer_end(devcom); + primary_sd = mlx5_get_sd(primary); + if (primary_sd->next_secondary_idx + 1 == sd->host_buses) + mlx5_devcom_comp_set_ready(devcom, true); +out: + mlx5_devcom_comp_unlock(devcom); return 0; err_devcom_unreg: - mlx5_devcom_comp_lock(sd->devcom); - mlx5_devcom_comp_set_ready(sd->devcom, false); - mlx5_devcom_comp_unlock(sd->devcom); - mlx5_devcom_unregister_component(sd->devcom); + mlx5_devcom_comp_unlock(devcom); + mlx5_devcom_unregister_component(devcom); return err; } @@ -513,6 +668,29 @@ static void sd_secondary_destroy_alias_ft(struct mlx5_core_dev *secondary) MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS); } +static int mlx5_sd_secondary_conf_tx_root(struct mlx5_core_dev *secondary, + bool disconnect) +{ + struct mlx5_sd *sd = mlx5_get_sd(secondary); + int err; + + /* Idempotent: skip if TX root is already in the requested state. */ + if (sd->tx_root_silent == disconnect) + return 0; + + if (disconnect) + err = mlx5_fs_cmd_set_tx_flow_table_root(secondary, 0, true); + else + err = mlx5_fs_cmd_set_tx_flow_table_root(secondary, + sd->alias_obj_id, + false); + if (err) + return err; + + sd->tx_root_silent = disconnect; + return 0; +} + static int sd_cmd_set_secondary(struct mlx5_core_dev *secondary, struct mlx5_core_dev *primary, u8 *alias_key) @@ -521,33 +699,42 @@ static int sd_cmd_set_secondary(struct mlx5_core_dev *secondary, struct mlx5_sd *sd = mlx5_get_sd(secondary); int err; - err = mlx5_fs_cmd_set_l2table_entry_silent(secondary, 1); - if (err) - return err; + if (!primary_sd->fw_silents_secondaries) { + err = mlx5_fs_cmd_set_l2table_entry_silent(secondary, 1); + if (err) + return err; + } err = sd_secondary_create_alias_ft(secondary, primary, primary_sd->tx_ft, &sd->alias_obj_id, alias_key); if (err) goto err_unset_silent; - err = mlx5_fs_cmd_set_tx_flow_table_root(secondary, sd->alias_obj_id, false); + err = mlx5_fs_cmd_set_tx_flow_table_root(secondary, sd->alias_obj_id, + false); if (err) goto err_destroy_alias_ft; + sd->tx_root_silent = false; return 0; err_destroy_alias_ft: sd_secondary_destroy_alias_ft(secondary); err_unset_silent: - mlx5_fs_cmd_set_l2table_entry_silent(secondary, 0); + if (!primary_sd->fw_silents_secondaries) + mlx5_fs_cmd_set_l2table_entry_silent(secondary, 0); return err; } static void sd_cmd_unset_secondary(struct mlx5_core_dev *secondary) { - mlx5_fs_cmd_set_tx_flow_table_root(secondary, 0, true); + struct mlx5_sd *primary_sd; + + primary_sd = mlx5_get_sd(mlx5_sd_get_primary(secondary)); + mlx5_sd_secondary_conf_tx_root(secondary, true); sd_secondary_destroy_alias_ft(secondary); - mlx5_fs_cmd_set_l2table_entry_silent(secondary, 0); + if (!primary_sd->fw_silents_secondaries) + mlx5_fs_cmd_set_l2table_entry_silent(secondary, 0); } static void sd_print_group(struct mlx5_core_dev *primary) @@ -672,6 +859,7 @@ err_sd_unregister: peer_sd->primary_dev = NULL; } primary_sd->primary = false; + primary_sd->next_secondary_idx = 0; mlx5_devcom_comp_set_ready(sd->devcom, false); mlx5_devcom_comp_unlock(sd->devcom); sd_unregister(dev); @@ -719,6 +907,7 @@ out_clear_peers: peer_sd->primary_dev = NULL; } primary_sd->primary = false; + primary_sd->next_secondary_idx = 0; out_ready_false: mlx5_devcom_comp_set_ready(sd->devcom, false); out_unlock: @@ -771,6 +960,127 @@ struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev, return &primary_adev->adev; } +#ifdef CONFIG_MLX5_ESWITCH +/* All SD members must have completed esw_offloads_enable (i.e., reached + * mlx5_esw_offloads_devcom_init) and become eswitch-peers of the primary. + * Until then, mlx5_eswitch_is_peer() returns false for the not-yet-paired + * member and shared_fdb_supported_filter would reject. When all PFs transition + * in parallel, only the last one to finish satisfies this gate; the earlier + * ones return 0 silently here. + */ +static bool mlx5_sd_all_paired(struct mlx5_core_dev *primary) +{ + struct mlx5_eswitch *primary_esw = primary->priv.eswitch; + struct mlx5_core_dev *pos; + int i; + + mlx5_sd_for_each_secondary(i, primary, pos) { + if (!mlx5_eswitch_is_peer(primary_esw, pos->priv.eswitch)) + return false; + } + return true; +} + +static void mlx5_sd_activate_shared_fdb(struct mlx5_core_dev *primary) +{ + struct mlx5_sd *sd = mlx5_get_sd(primary); + struct mlx5_core_dev *pos; + struct mlx5_lag *ldev; + struct lag_func *pf; + int err; + int i; + + ldev = mlx5_lag_dev(primary); + if (!ldev) { + sd_warn(primary, "Shared FDB MUST have ldev\n"); + return; + } + + mutex_lock(&ldev->lock); + + if (ldev->mode_changes_in_progress) + goto unlock; + + if (!mlx5_sd_all_paired(primary)) + goto unlock; + + /* Check if SD FDB is already active for this group */ + mlx5_lag_for_each(i, 0, ldev, sd->group_id) { + pf = mlx5_lag_pf(ldev, i); + if (pf->sd_fdb_active) + goto unlock; + break; + } + + if (!mlx5_lag_shared_fdb_supported_filter(ldev, sd->group_id)) { + sd_warn(primary, "Shared FDB not supported\n"); + goto unlock; + } + + /* Initialize vport metadata for all group devices. This is deferred + * from esw_offloads_enable() because mlx5_sd_pf_num_get() requires + * the SD group to be ready. + */ + mlx5_sd_for_each_dev(i, primary, pos) { + struct mlx5_eswitch *esw = pos->priv.eswitch; + + err = mlx5_esw_offloads_init_deferred_metadata(esw); + if (err) { + sd_warn(primary, "Failed to init metadata for %s: %d\n", + dev_name(pos->device), err); + goto unlock; + } + } + + err = mlx5_lag_shared_fdb_create(ldev, NULL, 0, sd->group_id); + if (err) + sd_warn(primary, "Failed to create shared FDB: %d\n", err); + else + sd_info(primary, "Shared FDB created\n"); + +unlock: + mutex_unlock(&ldev->lock); +} + +void mlx5_sd_eswitch_mode_set(struct mlx5_core_dev *dev, u16 mlx5_mode) +{ + struct mlx5_core_dev *primary; + struct mlx5_sd *sd; + int err; + + sd = mlx5_get_sd(dev); + if (!sd || !mlx5_devcom_comp_is_ready(sd->devcom)) + return; + + mlx5_devcom_comp_lock(sd->devcom); + if (!mlx5_devcom_comp_is_ready(sd->devcom)) + goto unlock; + + primary = mlx5_sd_get_primary(dev); + + /* Secondary devices need TX root reconfiguration */ + if (dev != primary) { + bool disconnect = (mlx5_mode == MLX5_ESWITCH_OFFLOADS); + + err = mlx5_sd_secondary_conf_tx_root(dev, disconnect); + if (err) { + sd_warn(dev, "Failed to set TX root: %d\n", err); + goto unlock; + } + } + + /* Try to activate shared FDB when all devices are in switchdev. + * Shared FDB is optional - failure here doesn't fail the transition. + */ + if (mlx5_mode == MLX5_ESWITCH_OFFLOADS) + mlx5_sd_activate_shared_fdb(primary); + +unlock: + mlx5_devcom_comp_unlock(sd->devcom); +} + +#endif /* CONFIG_MLX5_ESWITCH */ + void mlx5_sd_put_adev(struct auxiliary_device *actual_adev, struct auxiliary_device *adev) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h index 011702ff6f02..cb88bf34079a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h @@ -12,6 +12,7 @@ struct mlx5_sd; struct mlx5_core_dev *mlx5_sd_get_primary(struct mlx5_core_dev *dev); bool mlx5_sd_is_primary(struct mlx5_core_dev *dev); +int mlx5_sd_pf_num_get(struct mlx5_core_dev *dev); struct mlx5_core_dev *mlx5_sd_primary_get_peer(struct mlx5_core_dev *primary, int idx); int mlx5_sd_ch_ix_get_dev_ix(struct mlx5_core_dev *dev, int ch_ix); int mlx5_sd_ch_ix_get_vec_ix(struct mlx5_core_dev *dev, int ch_ix); @@ -44,6 +45,13 @@ mlx5_sd_get_devcom(struct mlx5_core_dev *dev) } #endif +#ifdef CONFIG_MLX5_ESWITCH +void mlx5_sd_eswitch_mode_set(struct mlx5_core_dev *dev, u16 mlx5_mode); +#else +static inline void +mlx5_sd_eswitch_mode_set(struct mlx5_core_dev *dev, u16 mlx5_mode) { return; } +#endif + #define mlx5_sd_for_each_dev_from_to(i, primary, ix_from, to, pos) \ for (i = ix_from; \ (pos = mlx5_sd_primary_get_peer(primary, i)) && pos != (to); i++) |