diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox')
121 files changed, 3226 insertions, 1459 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 277738c50c56..61286b0d9b0c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1374,16 +1374,13 @@ static int mlx4_mf_bond(struct mlx4_dev *dev) int nvfs; struct mlx4_slaves_pport slaves_port1; struct mlx4_slaves_pport slaves_port2; - DECLARE_BITMAP(slaves_port_1_2, MLX4_MFUNC_MAX); slaves_port1 = mlx4_phys_to_slaves_pport(dev, 1); slaves_port2 = mlx4_phys_to_slaves_pport(dev, 2); - bitmap_and(slaves_port_1_2, - slaves_port1.slaves, slaves_port2.slaves, - dev->persist->num_vfs + 1); /* only single port vfs are allowed */ - if (bitmap_weight(slaves_port_1_2, dev->persist->num_vfs + 1) > 1) { + if (bitmap_weight_and(slaves_port1.slaves, slaves_port2.slaves, + dev->persist->num_vfs + 1) > 1) { mlx4_warn(dev, "HA mode unsupported for dual ported VFs\n"); return -EINVAL; } @@ -3027,13 +3024,43 @@ no_msi: } } +static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port, + enum devlink_port_type port_type) +{ + struct mlx4_port_info *info = container_of(devlink_port, + struct mlx4_port_info, + devlink_port); + enum mlx4_port_type mlx4_port_type; + + switch (port_type) { + case DEVLINK_PORT_TYPE_AUTO: + mlx4_port_type = MLX4_PORT_TYPE_AUTO; + break; + case DEVLINK_PORT_TYPE_ETH: + mlx4_port_type = MLX4_PORT_TYPE_ETH; + break; + case DEVLINK_PORT_TYPE_IB: + mlx4_port_type = MLX4_PORT_TYPE_IB; + break; + default: + return -EOPNOTSUPP; + } + + return __set_port_type(info, mlx4_port_type); +} + +static const struct devlink_port_ops mlx4_devlink_port_ops = { + .port_type_set = mlx4_devlink_port_type_set, +}; + static int mlx4_init_port_info(struct mlx4_dev *dev, int port) { struct devlink *devlink = priv_to_devlink(mlx4_priv(dev)); struct mlx4_port_info *info = &mlx4_priv(dev)->port[port]; int err; - err = devl_port_register(devlink, &info->devlink_port, port); + err = devl_port_register_with_ops(devlink, &info->devlink_port, port, + &mlx4_devlink_port_ops); if (err) return err; @@ -3877,31 +3904,6 @@ err_disable_pdev: return err; } -static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port, - enum devlink_port_type port_type) -{ - struct mlx4_port_info *info = container_of(devlink_port, - struct mlx4_port_info, - devlink_port); - enum mlx4_port_type mlx4_port_type; - - switch (port_type) { - case DEVLINK_PORT_TYPE_AUTO: - mlx4_port_type = MLX4_PORT_TYPE_AUTO; - break; - case DEVLINK_PORT_TYPE_ETH: - mlx4_port_type = MLX4_PORT_TYPE_ETH; - break; - case DEVLINK_PORT_TYPE_IB: - mlx4_port_type = MLX4_PORT_TYPE_IB; - break; - default: - return -EOPNOTSUPP; - } - - return __set_port_type(info, mlx4_port_type); -} - static void mlx4_devlink_param_load_driverinit_values(struct devlink *devlink) { struct mlx4_priv *priv = devlink_priv(devlink); @@ -3986,7 +3988,6 @@ static int mlx4_devlink_reload_up(struct devlink *devlink, enum devlink_reload_a } static const struct devlink_ops mlx4_devlink_ops = { - .port_type_set = mlx4_devlink_port_type_set, .reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT), .reload_down = mlx4_devlink_reload_down, .reload_up = mlx4_devlink_reload_up, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index ddf1e352f51d..35f00700a4d6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -75,7 +75,8 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += esw/acl/helper.o \ esw/acl/egress_lgcy.o esw/acl/egress_ofld.o \ esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o -mlx5_core-$(CONFIG_MLX5_BRIDGE) += esw/bridge.o esw/bridge_mcast.o en/rep/bridge.o +mlx5_core-$(CONFIG_MLX5_BRIDGE) += esw/bridge.o esw/bridge_mcast.o esw/bridge_debugfs.o \ + en/rep/bridge.o mlx5_core-$(CONFIG_THERMAL) += thermal.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index bb95b40d25eb..2138f28a2931 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -246,6 +246,7 @@ void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev) debugfs_create_u32("fw_pages_total", 0400, pages, &dev->priv.fw_pages); debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.page_counters[MLX5_VF]); + debugfs_create_u32("fw_pages_ec_vfs", 0400, pages, &dev->priv.page_counters[MLX5_EC_VF]); debugfs_create_u32("fw_pages_sfs", 0400, pages, &dev->priv.page_counters[MLX5_SF]); debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.page_counters[MLX5_HOST_PF]); debugfs_create_u32("fw_pages_alloc_failed", 0400, pages, &dev->priv.fw_pages_alloc_failed); @@ -513,11 +514,11 @@ EXPORT_SYMBOL(mlx5_debug_qp_add); void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp) { - if (!mlx5_debugfs_root) + if (!mlx5_debugfs_root || !qp->dbg) return; - if (qp->dbg) - rem_res_tree(qp->dbg); + rem_res_tree(qp->dbg); + qp->dbg = NULL; } EXPORT_SYMBOL(mlx5_debug_qp_remove); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 1b33533b15de..edb06fb9bbc5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -151,12 +151,6 @@ static bool is_ib_rep_supported(struct mlx5_core_dev *dev) if (!is_eth_rep_supported(dev)) return false; - if (!MLX5_ESWITCH_MANAGER(dev)) - return false; - - if (!is_mdev_switchdev_mode(dev)) - return false; - if (mlx5_core_mp_enabled(dev)) return false; @@ -323,6 +317,18 @@ static void del_adev(struct auxiliary_device *adev) auxiliary_device_uninit(adev); } +void mlx5_dev_set_lightweight(struct mlx5_core_dev *dev) +{ + mutex_lock(&mlx5_intf_mutex); + dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV; + mutex_unlock(&mlx5_intf_mutex); +} + +bool mlx5_dev_is_lightweight(struct mlx5_core_dev *dev) +{ + return dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV; +} + int mlx5_attach_device(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; @@ -457,6 +463,10 @@ static int add_drivers(struct mlx5_core_dev *dev) if (priv->adev[i]) continue; + if (mlx5_adev_devices[i].is_enabled && + !(mlx5_adev_devices[i].is_enabled(dev))) + continue; + if (mlx5_adev_devices[i].is_supported) is_supported = mlx5_adev_devices[i].is_supported(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 4b607785d694..3d82ec890666 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -7,7 +7,6 @@ #include "fw_reset.h" #include "fs_core.h" #include "eswitch.h" -#include "lag/lag.h" #include "esw/qos.h" #include "sf/dev/dev.h" #include "sf/sf.h" @@ -142,6 +141,13 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, bool sf_dev_allocated; int ret = 0; + if (mlx5_dev_is_lightweight(dev)) { + if (action != DEVLINK_RELOAD_ACTION_DRIVER_REINIT) + return -EOPNOTSUPP; + mlx5_unload_one_light(dev); + return 0; + } + sf_dev_allocated = mlx5_sf_dev_allocated(dev); if (sf_dev_allocated) { /* Reload results in deleting SF device which further results in @@ -162,9 +168,8 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, return -EOPNOTSUPP; } - if (pci_num_vf(pdev)) { + if (mlx5_core_is_pf(dev) && pci_num_vf(pdev)) NL_SET_ERR_MSG_MOD(extack, "reload while VFs are present is unfavorable"); - } switch (action) { case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: @@ -195,6 +200,10 @@ static int mlx5_devlink_reload_up(struct devlink *devlink, enum devlink_reload_a *actions_performed = BIT(action); switch (action) { case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: + if (mlx5_dev_is_lightweight(dev)) { + mlx5_fw_reporters_create(dev); + return mlx5_init_one_devl_locked(dev); + } ret = mlx5_load_one_devl_locked(dev, false); break; case DEVLINK_RELOAD_ACTION_FW_ACTIVATE: @@ -311,8 +320,6 @@ static const struct devlink_ops mlx5_devlink_ops = { .eswitch_inline_mode_get = mlx5_devlink_eswitch_inline_mode_get, .eswitch_encap_mode_set = mlx5_devlink_eswitch_encap_mode_set, .eswitch_encap_mode_get = mlx5_devlink_eswitch_encap_mode_get, - .port_function_hw_addr_get = mlx5_devlink_port_function_hw_addr_get, - .port_function_hw_addr_set = mlx5_devlink_port_function_hw_addr_set, .rate_leaf_tx_share_set = mlx5_esw_devlink_rate_leaf_tx_share_set, .rate_leaf_tx_max_set = mlx5_esw_devlink_rate_leaf_tx_max_set, .rate_node_tx_share_set = mlx5_esw_devlink_rate_node_tx_share_set, @@ -320,16 +327,9 @@ static const struct devlink_ops mlx5_devlink_ops = { .rate_node_new = mlx5_esw_devlink_rate_node_new, .rate_node_del = mlx5_esw_devlink_rate_node_del, .rate_leaf_parent_set = mlx5_esw_devlink_rate_parent_set, - .port_fn_roce_get = mlx5_devlink_port_fn_roce_get, - .port_fn_roce_set = mlx5_devlink_port_fn_roce_set, - .port_fn_migratable_get = mlx5_devlink_port_fn_migratable_get, - .port_fn_migratable_set = mlx5_devlink_port_fn_migratable_set, #endif #ifdef CONFIG_MLX5_SF_MANAGER .port_new = mlx5_devlink_sf_port_new, - .port_del = mlx5_devlink_sf_port_del, - .port_fn_state_get = mlx5_devlink_sf_port_fn_state_get, - .port_fn_state_set = mlx5_devlink_sf_port_fn_state_set, #endif .flash_update = mlx5_devlink_flash_update, .info_get = mlx5_devlink_info_get, @@ -437,54 +437,6 @@ static int mlx5_devlink_large_group_num_validate(struct devlink *devlink, u32 id return 0; } - -static int mlx5_devlink_esw_multiport_set(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) -{ - struct mlx5_core_dev *dev = devlink_priv(devlink); - - if (!MLX5_ESWITCH_MANAGER(dev)) - return -EOPNOTSUPP; - - if (ctx->val.vbool) - return mlx5_lag_mpesw_enable(dev); - - mlx5_lag_mpesw_disable(dev); - return 0; -} - -static int mlx5_devlink_esw_multiport_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) -{ - struct mlx5_core_dev *dev = devlink_priv(devlink); - - if (!MLX5_ESWITCH_MANAGER(dev)) - return -EOPNOTSUPP; - - ctx->val.vbool = mlx5_lag_is_mpesw(dev); - return 0; -} - -static int mlx5_devlink_esw_multiport_validate(struct devlink *devlink, u32 id, - union devlink_param_value val, - struct netlink_ext_ack *extack) -{ - struct mlx5_core_dev *dev = devlink_priv(devlink); - - if (!MLX5_ESWITCH_MANAGER(dev)) { - NL_SET_ERR_MSG_MOD(extack, "E-Switch is unsupported"); - return -EOPNOTSUPP; - } - - if (mlx5_eswitch_mode(dev) != MLX5_ESWITCH_OFFLOADS) { - NL_SET_ERR_MSG_MOD(extack, - "E-Switch must be in switchdev mode"); - return -EBUSY; - } - - return 0; -} - #endif static int mlx5_devlink_eq_depth_validate(struct devlink *devlink, u32 id, @@ -558,12 +510,6 @@ static const struct devlink_param mlx5_devlink_params[] = { BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), NULL, NULL, mlx5_devlink_large_group_num_validate), - DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_ESW_MULTIPORT, - "esw_multiport", DEVLINK_PARAM_TYPE_BOOL, - BIT(DEVLINK_PARAM_CMODE_RUNTIME), - mlx5_devlink_esw_multiport_get, - mlx5_devlink_esw_multiport_set, - mlx5_devlink_esw_multiport_validate), #endif DEVLINK_PARAM_GENERIC(IO_EQ_SIZE, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), NULL, NULL, mlx5_devlink_eq_depth_validate), @@ -576,7 +522,7 @@ static void mlx5_devlink_set_params_init_values(struct devlink *devlink) struct mlx5_core_dev *dev = devlink_priv(devlink); union devlink_param_value value; - value.vbool = MLX5_CAP_GEN(dev, roce); + value.vbool = MLX5_CAP_GEN(dev, roce) && !mlx5_dev_is_lightweight(dev); devl_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, value); @@ -626,7 +572,7 @@ static int mlx5_devlink_eth_params_register(struct devlink *devlink) if (err) return err; - value.vbool = true; + value.vbool = !mlx5_dev_is_lightweight(dev); devl_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH, value); @@ -666,6 +612,7 @@ static const struct devlink_param mlx5_devlink_rdma_params[] = { static int mlx5_devlink_rdma_params_register(struct devlink *devlink) { + struct mlx5_core_dev *dev = devlink_priv(devlink); union devlink_param_value value; int err; @@ -677,7 +624,7 @@ static int mlx5_devlink_rdma_params_register(struct devlink *devlink) if (err) return err; - value.vbool = true; + value.vbool = !mlx5_dev_is_lightweight(dev); devl_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, value); @@ -712,7 +659,7 @@ static int mlx5_devlink_vnet_params_register(struct devlink *devlink) if (err) return err; - value.vbool = true; + value.vbool = !mlx5_dev_is_lightweight(dev); devl_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET, value); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c index 9114661cd967..e869c65d8e90 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c @@ -2,6 +2,7 @@ /* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. */ #include "reporter_vnic.h" +#include "en_stats.h" #include "devlink.h" #define VNIC_ENV_GET64(vnic_env_stats, c) \ @@ -36,45 +37,72 @@ int mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev, if (err) return err; - err = devlink_fmsg_u64_pair_put(fmsg, "total_error_queues", - VNIC_ENV_GET64(&vnic, total_error_queues)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "send_queue_priority_update_flow", - VNIC_ENV_GET64(&vnic, send_queue_priority_update_flow)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "comp_eq_overrun", - VNIC_ENV_GET64(&vnic, comp_eq_overrun)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "async_eq_overrun", - VNIC_ENV_GET64(&vnic, async_eq_overrun)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "cq_overrun", - VNIC_ENV_GET64(&vnic, cq_overrun)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "invalid_command", - VNIC_ENV_GET64(&vnic, invalid_command)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "quota_exceeded_command", - VNIC_ENV_GET64(&vnic, quota_exceeded_command)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "nic_receive_steering_discard", - VNIC_ENV_GET64(&vnic, nic_receive_steering_discard)); - if (err) - return err; + if (MLX5_CAP_GEN(dev, vnic_env_queue_counters)) { + err = devlink_fmsg_u32_pair_put(fmsg, "total_error_queues", + VNIC_ENV_GET(&vnic, total_error_queues)); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "send_queue_priority_update_flow", + VNIC_ENV_GET(&vnic, + send_queue_priority_update_flow)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, eq_overrun_count)) { + err = devlink_fmsg_u32_pair_put(fmsg, "comp_eq_overrun", + VNIC_ENV_GET(&vnic, comp_eq_overrun)); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "async_eq_overrun", + VNIC_ENV_GET(&vnic, async_eq_overrun)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, vnic_env_cq_overrun)) { + err = devlink_fmsg_u32_pair_put(fmsg, "cq_overrun", + VNIC_ENV_GET(&vnic, cq_overrun)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, invalid_command_count)) { + err = devlink_fmsg_u32_pair_put(fmsg, "invalid_command", + VNIC_ENV_GET(&vnic, invalid_command)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, quota_exceeded_count)) { + err = devlink_fmsg_u32_pair_put(fmsg, "quota_exceeded_command", + VNIC_ENV_GET(&vnic, quota_exceeded_command)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, nic_receive_steering_discard)) { + err = devlink_fmsg_u64_pair_put(fmsg, "nic_receive_steering_discard", + VNIC_ENV_GET64(&vnic, + nic_receive_steering_discard)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, vnic_env_cnt_steering_fail)) { + err = devlink_fmsg_u64_pair_put(fmsg, "generated_pkt_steering_fail", + VNIC_ENV_GET64(&vnic, + generated_pkt_steering_fail)); + if (err) + return err; + + err = devlink_fmsg_u64_pair_put(fmsg, "handled_pkt_steering_fail", + VNIC_ENV_GET64(&vnic, handled_pkt_steering_fail)); + if (err) + return err; + } err = devlink_fmsg_obj_nest_end(fmsg); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 8e999f238194..b1807bfb815f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -165,15 +165,6 @@ struct page_pool; #define MLX5E_MAX_KLM_PER_WQE(mdev) \ MLX5E_KLM_ENTRIES_PER_WQE(MLX5_SEND_WQE_BB * mlx5e_get_max_sq_aligned_wqebbs(mdev)) -#define MLX5E_MSG_LEVEL NETIF_MSG_LINK - -#define mlx5e_dbg(mlevel, priv, format, ...) \ -do { \ - if (NETIF_MSG_##mlevel & (priv)->msglevel) \ - netdev_warn(priv->netdev, format, \ - ##__VA_ARGS__); \ -} while (0) - #define mlx5e_state_dereference(priv, p) \ rcu_dereference_protected((p), lockdep_is_held(&(priv)->state_lock)) @@ -594,13 +585,6 @@ struct mlx5e_mpw_info { #define MLX5E_MAX_RX_FRAGS 4 -/* a single cache unit is capable to serve one napi call (for non-striding rq) - * or a MPWQE (for striding rq). - */ -#define MLX5E_CACHE_UNIT (MLX5_MPWRQ_MAX_PAGES_PER_WQE > NAPI_POLL_WEIGHT ? \ - MLX5_MPWRQ_MAX_PAGES_PER_WQE : NAPI_POLL_WEIGHT) -#define MLX5E_CACHE_SIZE (4 * roundup_pow_of_two(MLX5E_CACHE_UNIT)) - struct mlx5e_rq; typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq*, struct mlx5_cqe64*); typedef struct sk_buff * @@ -887,7 +871,6 @@ struct mlx5e_priv { #endif /* priv data path fields - end */ - u32 msglevel; unsigned long state; struct mutex state_lock; /* Protects Interface state */ struct mlx5e_rq drop_rq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c index 03cb79adf912..be83ad9db82a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c @@ -594,7 +594,7 @@ int mlx5e_fs_tt_redirect_any_create(struct mlx5e_flow_steering *fs) err = fs_any_create_table(fs); if (err) - return err; + goto err_free_any; err = fs_any_enable(fs); if (err) @@ -606,8 +606,8 @@ int mlx5e_fs_tt_redirect_any_create(struct mlx5e_flow_steering *fs) err_destroy_table: fs_any_destroy_table(fs_any); - - kfree(fs_any); +err_free_any: mlx5e_fs_set_any(fs, NULL); + kfree(fs_any); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index 7e8e96cc5cd0..8e25f4ef5ccc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -65,12 +65,13 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv, MLX5_GET(bufferx_reg, buffer, xoff_threshold) * port_buff_cell_sz; total_used += port_buffer->buffer[i].size; - mlx5e_dbg(HW, priv, "buffer %d: size=%d, xon=%d, xoff=%d, epsb=%d, lossy=%d\n", i, - port_buffer->buffer[i].size, - port_buffer->buffer[i].xon, - port_buffer->buffer[i].xoff, - port_buffer->buffer[i].epsb, - port_buffer->buffer[i].lossy); + netdev_dbg(priv->netdev, "buffer %d: size=%d, xon=%d, xoff=%d, epsb=%d, lossy=%d\n", + i, + port_buffer->buffer[i].size, + port_buffer->buffer[i].xon, + port_buffer->buffer[i].xoff, + port_buffer->buffer[i].epsb, + port_buffer->buffer[i].lossy); } port_buffer->internal_buffers_size = 0; @@ -87,11 +88,11 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv, port_buffer->internal_buffers_size - port_buffer->headroom_size; - mlx5e_dbg(HW, priv, - "total buffer size=%u, headroom buffer size=%u, internal buffers size=%u, spare buffer size=%u\n", - port_buffer->port_buffer_size, port_buffer->headroom_size, - port_buffer->internal_buffers_size, - port_buffer->spare_buffer_size); + netdev_dbg(priv->netdev, + "total buffer size=%u, headroom buffer size=%u, internal buffers size=%u, spare buffer size=%u\n", + port_buffer->port_buffer_size, port_buffer->headroom_size, + port_buffer->internal_buffers_size, + port_buffer->spare_buffer_size); out: kfree(out); return err; @@ -352,7 +353,7 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu) xoff = (301 + 216 * priv->dcbx.cable_len / 100) * speed / 1000 + 272 * mtu / 100; - mlx5e_dbg(HW, priv, "%s: xoff=%d\n", __func__, xoff); + netdev_dbg(priv->netdev, "%s: xoff=%d\n", __func__, xoff); return xoff; } @@ -484,6 +485,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, u8 *prio2buffer) { u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz; + struct net_device *netdev = priv->netdev; struct mlx5e_port_buffer port_buffer; u32 xoff = calculate_xoff(priv, mtu); bool update_prio2buffer = false; @@ -495,7 +497,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, int err; int i; - mlx5e_dbg(HW, priv, "%s: change=%x\n", __func__, change); + netdev_dbg(netdev, "%s: change=%x\n", __func__, change); max_mtu = max_t(unsigned int, priv->netdev->max_mtu, MINIMUM_MAX_MTU); err = mlx5e_port_query_buffer(priv, &port_buffer); @@ -510,8 +512,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, } if (change & MLX5E_PORT_BUFFER_PFC) { - mlx5e_dbg(HW, priv, "%s: requested PFC per priority bitmask: 0x%x\n", - __func__, pfc->pfc_en); + netdev_dbg(netdev, "%s: requested PFC per priority bitmask: 0x%x\n", + __func__, pfc->pfc_en); err = mlx5e_port_query_priority2buffer(priv->mdev, buffer); if (err) return err; @@ -526,8 +528,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (change & MLX5E_PORT_BUFFER_PRIO2BUFFER) { update_prio2buffer = true; for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) - mlx5e_dbg(HW, priv, "%s: requested to map prio[%d] to buffer %d\n", - __func__, i, prio2buffer[i]); + netdev_dbg(priv->netdev, "%s: requested to map prio[%d] to buffer %d\n", + __func__, i, prio2buffer[i]); err = fill_pfc_en(priv->mdev, &curr_pfc_en); if (err) @@ -541,10 +543,10 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (change & MLX5E_PORT_BUFFER_SIZE) { for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { - mlx5e_dbg(HW, priv, "%s: buffer[%d]=%d\n", __func__, i, buffer_size[i]); + netdev_dbg(priv->netdev, "%s: buffer[%d]=%d\n", __func__, i, buffer_size[i]); if (!port_buffer.buffer[i].lossy && !buffer_size[i]) { - mlx5e_dbg(HW, priv, "%s: lossless buffer[%d] size cannot be zero\n", - __func__, i); + netdev_dbg(priv->netdev, "%s: lossless buffer[%d] size cannot be zero\n", + __func__, i); return -EINVAL; } @@ -552,7 +554,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, total_used += buffer_size[i]; } - mlx5e_dbg(HW, priv, "%s: total buffer requested=%d\n", __func__, total_used); + netdev_dbg(priv->netdev, "%s: total buffer requested=%d\n", __func__, total_used); if (total_used > port_buffer.headroom_size && (total_used - port_buffer.headroom_size) > diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 3cbebfba582b..b0b429a0321e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -729,8 +729,10 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params, c = kvzalloc_node(sizeof(*c), GFP_KERNEL, dev_to_node(mlx5_core_dma_dev(mdev))); cparams = kvzalloc(sizeof(*cparams), GFP_KERNEL); - if (!c || !cparams) - return -ENOMEM; + if (!c || !cparams) { + err = -ENOMEM; + goto err_free; + } c->priv = priv; c->mdev = priv->mdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 2842195ee548..1874c2f0587f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -379,6 +379,12 @@ int mlx5e_htb_setup_tc(struct mlx5e_priv *priv, struct tc_htb_qopt_offload *htb_ if (!htb && htb_qopt->command != TC_HTB_CREATE) return -EINVAL; + if (htb_qopt->prio) { + NL_SET_ERR_MSG_MOD(htb_qopt->extack, + "prio parameter is not supported by device with HTB offload enabled."); + return -EOPNOTSUPP; + } + switch (htb_qopt->command) { case TC_HTB_CREATE: if (!mlx5_qos_is_supported(priv->mdev)) { @@ -515,4 +521,3 @@ int mlx5e_mqprio_rl_get_node_hw_id(struct mlx5e_mqprio_rl *rl, int tc, u32 *hw_i *hw_id = rl->leaves_id[tc]; return 0; } - diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index fd191925ab4b..560800246573 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -136,7 +136,6 @@ static int mlx5_esw_bridge_port_changeupper(struct notifier_block *nb, void *ptr struct mlx5_eswitch *esw = br_offloads->esw; u16 vport_num, esw_owner_vhca_id; struct netlink_ext_ack *extack; - int ifindex = upper->ifindex; int err = 0; if (!netif_is_bridge_master(upper)) @@ -150,15 +149,15 @@ static int mlx5_esw_bridge_port_changeupper(struct notifier_block *nb, void *ptr if (mlx5_esw_bridge_is_local(dev, rep, esw)) err = info->linking ? - mlx5_esw_bridge_vport_link(ifindex, vport_num, esw_owner_vhca_id, + mlx5_esw_bridge_vport_link(upper, vport_num, esw_owner_vhca_id, br_offloads, extack) : - mlx5_esw_bridge_vport_unlink(ifindex, vport_num, esw_owner_vhca_id, + mlx5_esw_bridge_vport_unlink(upper, vport_num, esw_owner_vhca_id, br_offloads, extack); else if (mlx5_esw_bridge_dev_same_hw(rep, esw)) err = info->linking ? - mlx5_esw_bridge_vport_peer_link(ifindex, vport_num, esw_owner_vhca_id, + mlx5_esw_bridge_vport_peer_link(upper, vport_num, esw_owner_vhca_id, br_offloads, extack) : - mlx5_esw_bridge_vport_peer_unlink(ifindex, vport_num, esw_owner_vhca_id, + mlx5_esw_bridge_vport_peer_unlink(upper, vport_num, esw_owner_vhca_id, br_offloads, extack); return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c index 92d3952dfa8b..feeb41693c17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c @@ -17,8 +17,10 @@ tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state, if (err) return err; - if (mlx5e_is_eswitch_flow(parse_state->flow)) + if (mlx5e_is_eswitch_flow(parse_state->flow)) { attr->esw_attr->split_count = attr->esw_attr->out_count; + parse_state->if_count = 0; + } attr->flags |= MLX5_ATTR_FLAG_CT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c index 291193f7120d..f63402c48028 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c @@ -294,6 +294,7 @@ parse_mirred_ovs_master(struct mlx5e_tc_act_parse_state *parse_state, if (err) return err; + parse_state->if_count = 0; esw_attr->out_count++; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c index 3b272bbf4c53..368a95fa77d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c @@ -98,8 +98,10 @@ tc_act_parse_pedit(struct mlx5e_tc_act_parse_state *parse_state, attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - if (ns_type == MLX5_FLOW_NAMESPACE_FDB) + if (ns_type == MLX5_FLOW_NAMESPACE_FDB) { esw_attr->split_count = esw_attr->out_count; + parse_state->if_count = 0; + } return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c index ad09a8a5f36e..2d1d4a04501b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c @@ -66,6 +66,7 @@ tc_act_parse_redirect_ingress(struct mlx5e_tc_act_parse_state *parse_state, if (err) return err; + parse_state->if_count = 0; esw_attr->out_count++; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c index c8a3eaf189f6..a13c5e707b83 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c @@ -166,6 +166,7 @@ tc_act_parse_vlan(struct mlx5e_tc_act_parse_state *parse_state, return err; esw_attr->split_count = esw_attr->out_count; + parse_state->if_count = 0; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c index 310b99230760..f17575b09788 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c @@ -65,8 +65,10 @@ tc_act_parse_vlan_mangle(struct mlx5e_tc_act_parse_state *parse_state, if (err) return err; - if (ns_type == MLX5_FLOW_NAMESPACE_FDB) + if (ns_type == MLX5_FLOW_NAMESPACE_FDB) { attr->esw_attr->split_count = attr->esw_attr->out_count; + parse_state->if_count = 0; + } return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c index 07c1895a2b23..7aa926e542d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c @@ -25,8 +25,8 @@ struct mlx5e_tc_act_stats { static const struct rhashtable_params act_counters_ht_params = { .head_offset = offsetof(struct mlx5e_tc_act_stats, hash), - .key_offset = 0, - .key_len = offsetof(struct mlx5e_tc_act_stats, counter), + .key_offset = offsetof(struct mlx5e_tc_act_stats, tc_act_cookie), + .key_len = sizeof_field(struct mlx5e_tc_act_stats, tc_act_cookie), .automatic_shrinking = true, }; @@ -169,14 +169,11 @@ mlx5e_tc_act_stats_fill_stats(struct mlx5e_tc_act_stats_handle *handle, { struct rhashtable *ht = &handle->ht; struct mlx5e_tc_act_stats *item; - struct mlx5e_tc_act_stats key; u64 pkts, bytes, lastused; int err = 0; - key.tc_act_cookie = fl_act->cookie; - rcu_read_lock(); - item = rhashtable_lookup(ht, &key, act_counters_ht_params); + item = rhashtable_lookup(ht, &fl_act->cookie, act_counters_ht_params); if (!item) { rcu_read_unlock(); err = -ENOENT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c index 0290e0dea539..4e923a2874ae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c @@ -112,10 +112,8 @@ mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *po int err; handle = kzalloc(sizeof(*handle), GFP_KERNEL); - if (!handle) { - kfree(handle); + if (!handle) return ERR_PTR(-ENOMEM); - } post_attr->chain = 0; post_attr->prio = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index a254e728ac95..fadfa8b50beb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -1545,7 +1545,8 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, attr->ct_attr.ct_action |= act->ct.action; /* So we can have clear + ct */ attr->ct_attr.zone = act->ct.zone; - attr->ct_attr.nf_ft = act->ct.flow_table; + if (!(act->ct.action & TCA_CT_ACT_CLEAR)) + attr->ct_attr.nf_ft = act->ct.flow_table; attr->ct_attr.act_miss_cookie = act->miss_cookie; return 0; @@ -1990,6 +1991,9 @@ mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *att if (!priv) return -EOPNOTSUPP; + if (attr->ct_attr.offloaded) + return 0; + if (attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR) { err = mlx5_tc_ct_entry_set_registers(priv, &attr->parse_attr->mod_hdr_acts, 0, 0, 0, 0); @@ -1999,11 +2003,15 @@ mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *att attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; } - if (!attr->ct_attr.nf_ft) /* means only ct clear action, and not ct_clear,ct() */ + if (!attr->ct_attr.nf_ft) { /* means only ct clear action, and not ct_clear,ct() */ + attr->ct_attr.offloaded = true; return 0; + } mutex_lock(&priv->control_lock); err = __mlx5_tc_ct_flow_offload(priv, attr); + if (!err) + attr->ct_attr.offloaded = true; mutex_unlock(&priv->control_lock); return err; @@ -2021,7 +2029,7 @@ void mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr) { - if (!attr->ct_attr.ft) /* no ct action, return */ + if (!attr->ct_attr.offloaded) /* no ct action, return */ return; if (!attr->ct_attr.nf_ft) /* means only ct clear action, and not ct_clear,ct() */ return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 8e9316fa46d4..b66c5f98067f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -29,6 +29,7 @@ struct mlx5_ct_attr { u32 ct_labels_id; u32 act_miss_mapping; u64 act_miss_cookie; + bool offloaded; struct mlx5_ct_ft *ft; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index ba2b1f24ff14..6cc23af66b5b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -94,13 +94,13 @@ struct mlx5e_tc_flow { * destinations. */ struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS]; - struct mlx5e_tc_flow *peer_flow; struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */ struct list_head hairpin; /* flows sharing the same hairpin */ - struct list_head peer; /* flows with peer flow */ + struct list_head peer[MLX5_MAX_PORTS]; /* flows with peer flow */ struct list_head unready; /* flows not ready to be offloaded (e.g * due to missing route) */ + struct list_head peer_flows; /* flows on peer */ struct net_device *orig_dev; /* netdev adding flow first */ int tmp_entry_index; struct list_head tmp_list; /* temporary flow list used by neigh update */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index f0c3464f037f..1730f6a716ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -1030,9 +1030,6 @@ int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv, int out_index; int err = 0; - if (!mlx5e_is_eswitch_flow(flow)) - return 0; - parse_attr = attr->parse_attr; esw_attr = attr->esw_attr; *vf_tun = false; @@ -1464,10 +1461,12 @@ static void mlx5e_invalidate_encap(struct mlx5e_priv *priv, attr = mlx5e_tc_get_encap_attr(flow); esw_attr = attr->esw_attr; - if (flow_flag_test(flow, SLOW)) + if (flow_flag_test(flow, SLOW)) { mlx5e_tc_unoffload_from_slow_path(esw, flow); - else + } else { mlx5e_tc_unoffload_fdb_rules(esw, flow, flow->attr); + mlx5e_tc_unoffload_flow_post_acts(flow); + } mlx5e_tc_detach_mod_hdr(priv, flow, attr); attr->modify_hdr = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index f0e6095809fa..40589cebb773 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -662,8 +662,7 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, /* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE) * as we know this is a page_pool page. */ - page_pool_put_defragged_page(page->pp, - page, -1, true); + page_pool_recycle_direct(page->pp, page); } while (++n < num); break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index 9e8e6184f9e4..ecfe93a479da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -84,6 +84,8 @@ enum mlx5e_xdp_xmit_mode { * MLX5E_XDP_XMIT_MODE_XSK: * none. */ +#define MLX5E_XDP_FIFO_ENTRIES2DS_MAX_RATIO 4 + union mlx5e_xdp_info { enum mlx5e_xdp_xmit_mode mode; union { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index d97e6df66f45..b8dd74453655 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -323,8 +323,11 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, net_prefetch(mxbuf->xdp.data); prog = rcu_dereference(rq->xdp_prog); - if (likely(prog && mlx5e_xdp_handle(rq, prog, mxbuf))) + if (likely(prog && mlx5e_xdp_handle(rq, prog, mxbuf))) { + if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))) + wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); return NULL; /* page/packet was consumed by XDP */ + } /* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse * will be handled by mlx5e_free_rx_wqe. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h index c964644ee866..bac4717548c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h @@ -125,7 +125,7 @@ static inline bool mlx5e_accel_tx_begin(struct net_device *dev, #ifdef CONFIG_MLX5_EN_TLS /* May send WQEs. */ - if (mlx5e_ktls_skb_offloaded(skb)) + if (tls_is_skb_tx_device_offloaded(skb)) if (unlikely(!mlx5e_ktls_handle_tx_skb(dev, sq, skb, &state->tls))) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c index 88a5aed9d678..c7d191f66ad1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c @@ -190,6 +190,7 @@ static int accel_fs_tcp_create_groups(struct mlx5e_flow_table *ft, in = kvzalloc(inlen, GFP_KERNEL); if (!in || !ft->g) { kfree(ft->g); + ft->g = NULL; kvfree(in); return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index dbe87bf89c0d..832d36be4a17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -808,9 +808,9 @@ static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upsp } if (upspec->sport) { - MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria, udp_dport, + MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria, udp_sport, upspec->sport_mask); - MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, udp_dport, upspec->sport); + MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, udp_sport, upspec->sport); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index eab5bc718771..8d995e304869 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -58,7 +58,9 @@ static int mlx5e_ipsec_remove_trailer(struct sk_buff *skb, struct xfrm_state *x) trailer_len = alen + plen + 2; - pskb_trim(skb, skb->len - trailer_len); + ret = pskb_trim(skb, skb->len - trailer_len); + if (unlikely(ret)) + return ret; if (skb->protocol == htons(ETH_P_IP)) { ipv4hdr->tot_len = htons(ntohs(ipv4hdr->tot_len) - trailer_len); ip_send_check(ipv4hdr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c index cf704f106b7c..984fa04bd331 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c @@ -188,7 +188,6 @@ static void mlx5e_tls_debugfs_init(struct mlx5e_tls *tls, int mlx5e_ktls_init(struct mlx5e_priv *priv) { - struct mlx5_crypto_dek_pool *dek_pool; struct mlx5e_tls *tls; if (!mlx5e_is_ktls_device(priv->mdev)) @@ -199,12 +198,6 @@ int mlx5e_ktls_init(struct mlx5e_priv *priv) return -ENOMEM; tls->mdev = priv->mdev; - dek_pool = mlx5_crypto_dek_pool_create(priv->mdev, MLX5_ACCEL_OBJ_TLS_KEY); - if (IS_ERR(dek_pool)) { - kfree(tls); - return PTR_ERR(dek_pool); - } - tls->dek_pool = dek_pool; priv->tls = tls; mlx5e_tls_debugfs_init(tls, priv->dfs_root); @@ -222,7 +215,6 @@ void mlx5e_ktls_cleanup(struct mlx5e_priv *priv) debugfs_remove_recursive(tls->debugfs.dfs); tls->debugfs.dfs = NULL; - mlx5_crypto_dek_pool_destroy(tls->dek_pool); kfree(priv->tls); priv->tls = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index 0e4c0a093293..d61be26a4df1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -846,7 +846,7 @@ bool mlx5e_ktls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq, tls_ctx = tls_get_ctx(skb->sk); tls_netdev = rcu_dereference_bh(tls_ctx->netdev); /* Don't WARN on NULL: if tls_device_down is running in parallel, - * netdev might become NULL, even if tls_is_sk_tx_device_offloaded was + * netdev might become NULL, even if tls_is_skb_tx_device_offloaded was * true. Rather continue processing this packet. */ if (WARN_ON_ONCE(tls_netdev && tls_netdev != netdev)) @@ -908,28 +908,51 @@ static void mlx5e_tls_tx_debugfs_init(struct mlx5e_tls *tls, int mlx5e_ktls_init_tx(struct mlx5e_priv *priv) { + struct mlx5_crypto_dek_pool *dek_pool; struct mlx5e_tls *tls = priv->tls; + int err; + + if (!mlx5e_is_ktls_device(priv->mdev)) + return 0; + + /* DEK pool could be used by either or both of TX and RX. But we have to + * put the creation here to avoid syndrome when doing devlink reload. + */ + dek_pool = mlx5_crypto_dek_pool_create(priv->mdev, MLX5_ACCEL_OBJ_TLS_KEY); + if (IS_ERR(dek_pool)) + return PTR_ERR(dek_pool); + tls->dek_pool = dek_pool; if (!mlx5e_is_ktls_tx(priv->mdev)) return 0; priv->tls->tx_pool = mlx5e_tls_tx_pool_init(priv->mdev, &priv->tls->sw_stats); - if (!priv->tls->tx_pool) - return -ENOMEM; + if (!priv->tls->tx_pool) { + err = -ENOMEM; + goto err_tx_pool_init; + } mlx5e_tls_tx_debugfs_init(tls, tls->debugfs.dfs); return 0; + +err_tx_pool_init: + mlx5_crypto_dek_pool_destroy(dek_pool); + return err; } void mlx5e_ktls_cleanup_tx(struct mlx5e_priv *priv) { if (!mlx5e_is_ktls_tx(priv->mdev)) - return; + goto dek_pool_destroy; debugfs_remove_recursive(priv->tls->debugfs.dfs_tx); priv->tls->debugfs.dfs_tx = NULL; mlx5e_tls_tx_pool_cleanup(priv->tls->tx_pool); priv->tls->tx_pool = NULL; + +dek_pool_destroy: + if (mlx5e_is_ktls_device(priv->mdev)) + mlx5_crypto_dek_pool_destroy(priv->tls->dek_pool); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h index 2dd78dd4ad65..f87b65c560ea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h @@ -49,11 +49,6 @@ mlx5e_ktls_rx_pending_resync_list(struct mlx5e_channel *c, int budget) return budget && test_bit(MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC, &c->async_icosq.state); } -static inline bool mlx5e_ktls_skb_offloaded(struct sk_buff *skb) -{ - return skb->sk && tls_is_sk_tx_device_offloaded(skb->sk); -} - static inline void mlx5e_ktls_handle_tx_wqe(struct mlx5_wqe_ctrl_seg *cseg, struct mlx5e_accel_tx_tls_state *state) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index 6b7b563f844a..592b165530ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -349,15 +349,6 @@ static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, sa->macsec_rule = NULL; } -static struct mlx5e_priv *macsec_netdev_priv(const struct net_device *dev) -{ -#if IS_ENABLED(CONFIG_VLAN_8021Q) - if (is_vlan_dev(dev)) - return netdev_priv(vlan_dev_priv(dev)->real_dev); -#endif - return netdev_priv(dev); -} - static int mlx5e_macsec_init_sa(struct macsec_context *ctx, struct mlx5e_macsec_sa *sa, bool encrypt, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c index 7fc901a6ec5f..414e28584881 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c @@ -161,6 +161,7 @@ static int macsec_fs_tx_create_crypto_table_groups(struct mlx5e_flow_table *ft) if (!in) { kfree(ft->g); + ft->g = NULL; return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index bed0c2d043e7..5aa51d74f8b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -135,6 +135,16 @@ static void arfs_del_rules(struct mlx5e_flow_steering *fs); int mlx5e_arfs_disable(struct mlx5e_flow_steering *fs) { + /* Moving to switchdev mode, fs->arfs is freed by mlx5e_nic_profile + * cleanup_rx callback and it is not recreated when + * mlx5e_uplink_rep_profile is loaded as mlx5e_create_flow_steering() + * is not called by the uplink_rep profile init_rx callback. Thus, if + * ntuple is set, moving to switchdev flow will enter this function + * with fs->arfs nullified. + */ + if (!mlx5e_fs_get_arfs(fs)) + return 0; + arfs_del_rules(fs); return arfs_disable(fs); @@ -570,10 +580,10 @@ static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv, if (IS_ERR(rule)) { err = PTR_ERR(rule); priv->channel_stats[arfs_rule->rxq]->rq.arfs_err++; - mlx5e_dbg(HW, priv, - "%s: add rule(filter id=%d, rq idx=%d, ip proto=0x%x) failed,err=%d\n", - __func__, arfs_rule->filter_id, arfs_rule->rxq, - tuple->ip_proto, err); + netdev_dbg(priv->netdev, + "%s: add rule(filter id=%d, rq idx=%d, ip proto=0x%x) failed,err=%d\n", + __func__, arfs_rule->filter_id, arfs_rule->rxq, + tuple->ip_proto, err); } out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index ebee52a8361a..8705cffc747f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -275,10 +275,10 @@ static int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets memcpy(priv->dcbx.tc_tsa, ets->tc_tsa, sizeof(ets->tc_tsa)); for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { - mlx5e_dbg(HW, priv, "%s: prio_%d <=> tc_%d\n", - __func__, i, ets->prio_tc[i]); - mlx5e_dbg(HW, priv, "%s: tc_%d <=> tx_bw_%d%%, group_%d\n", - __func__, i, tc_tx_bw[i], tc_group[i]); + netdev_dbg(priv->netdev, "%s: prio_%d <=> tc_%d\n", + __func__, i, ets->prio_tc[i]); + netdev_dbg(priv->netdev, "%s: tc_%d <=> tx_bw_%d%%, group_%d\n", + __func__, i, tc_tx_bw[i], tc_group[i]); } return err; @@ -399,9 +399,9 @@ static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev, } if (!ret) { - mlx5e_dbg(HW, priv, - "%s: PFC per priority bit mask: 0x%x\n", - __func__, pfc->pfc_en); + netdev_dbg(dev, + "%s: PFC per priority bit mask: 0x%x\n", + __func__, pfc->pfc_en); } return ret; } @@ -611,8 +611,8 @@ static int mlx5e_dcbnl_ieee_setmaxrate(struct net_device *netdev, } for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { - mlx5e_dbg(HW, priv, "%s: tc_%d <=> max_bw %d Gbps\n", - __func__, i, max_bw_value[i]); + netdev_dbg(netdev, "%s: tc_%d <=> max_bw %d Gbps\n", + __func__, i, max_bw_value[i]); } return mlx5_modify_port_ets_rate_limit(mdev, max_bw_value, max_bw_unit); @@ -640,10 +640,10 @@ static u8 mlx5e_dcbnl_setall(struct net_device *netdev) ets.tc_rx_bw[i] = cee_cfg->pg_bw_pct[i]; ets.tc_tsa[i] = IEEE_8021QAZ_TSA_ETS; ets.prio_tc[i] = cee_cfg->prio_to_pg_map[i]; - mlx5e_dbg(HW, priv, - "%s: Priority group %d: tx_bw %d, rx_bw %d, prio_tc %d\n", - __func__, i, ets.tc_tx_bw[i], ets.tc_rx_bw[i], - ets.prio_tc[i]); + netdev_dbg(netdev, + "%s: Priority group %d: tx_bw %d, rx_bw %d, prio_tc %d\n", + __func__, i, ets.tc_tx_bw[i], ets.tc_rx_bw[i], + ets.prio_tc[i]); } err = mlx5e_dbcnl_validate_ets(netdev, &ets, true); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 1f5a2110d31f..27861b68ced5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1689,16 +1689,6 @@ static int mlx5e_set_fecparam(struct net_device *netdev, return 0; } -static u32 mlx5e_get_msglevel(struct net_device *dev) -{ - return ((struct mlx5e_priv *)netdev_priv(dev))->msglevel; -} - -static void mlx5e_set_msglevel(struct net_device *dev, u32 val) -{ - ((struct mlx5e_priv *)netdev_priv(dev))->msglevel = val; -} - static int mlx5e_set_phys_id(struct net_device *dev, enum ethtool_phys_id_state state) { @@ -1952,9 +1942,9 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val if (err) return err; - mlx5e_dbg(DRV, priv, "MLX5E: RxCqeCmprss was turned %s\n", - MLX5E_GET_PFLAG(&priv->channels.params, - MLX5E_PFLAG_RX_CQE_COMPRESS) ? "ON" : "OFF"); + netdev_dbg(priv->netdev, "MLX5E: RxCqeCmprss was turned %s\n", + MLX5E_GET_PFLAG(&priv->channels.params, + MLX5E_PFLAG_RX_CQE_COMPRESS) ? "ON" : "OFF"); return 0; } @@ -2444,8 +2434,6 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .get_priv_flags = mlx5e_get_priv_flags, .set_priv_flags = mlx5e_set_priv_flags, .self_test = mlx5e_self_test, - .get_msglevel = mlx5e_get_msglevel, - .set_msglevel = mlx5e_set_msglevel, .get_fec_stats = mlx5e_get_fec_stats, .get_fecparam = mlx5e_get_fecparam, .set_fecparam = mlx5e_set_fecparam, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 33bfe4d7338b..934b0d5ce1b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -283,7 +283,7 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_flow_steering *fs, if (IS_ERR(*rule_p)) { err = PTR_ERR(*rule_p); *rule_p = NULL; - fs_err(fs, "%s: add rule failed\n", __func__); + fs_err(fs, "add rule failed\n"); } return err; @@ -395,8 +395,7 @@ int mlx5e_add_vlan_trap(struct mlx5e_flow_steering *fs, int trap_id, int tir_num if (IS_ERR(rule)) { err = PTR_ERR(rule); fs->vlan->trap_rule = NULL; - fs_err(fs, "%s: add VLAN trap rule failed, err %d\n", - __func__, err); + fs_err(fs, "add VLAN trap rule failed, err %d\n", err); return err; } fs->vlan->trap_rule = rule; @@ -421,8 +420,7 @@ int mlx5e_add_mac_trap(struct mlx5e_flow_steering *fs, int trap_id, int tir_num) if (IS_ERR(rule)) { err = PTR_ERR(rule); fs->l2.trap_rule = NULL; - fs_err(fs, "%s: add MAC trap rule failed, err %d\n", - __func__, err); + fs_err(fs, "add MAC trap rule failed, err %d\n", err); return err; } fs->l2.trap_rule = rule; @@ -763,7 +761,7 @@ static int mlx5e_add_promisc_rule(struct mlx5e_flow_steering *fs) if (IS_ERR(*rule_p)) { err = PTR_ERR(*rule_p); *rule_p = NULL; - fs_err(fs, "%s: add promiscuous rule failed\n", __func__); + fs_err(fs, "add promiscuous rule failed\n"); } kvfree(spec); return err; @@ -995,7 +993,7 @@ static int mlx5e_add_l2_flow_rule(struct mlx5e_flow_steering *fs, ai->rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(ai->rule)) { - fs_err(fs, "%s: add l2 rule(mac:%pM) failed\n", __func__, mv_dmac); + fs_err(fs, "add l2 rule(mac:%pM) failed\n", mv_dmac); err = PTR_ERR(ai->rule); ai->rule = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index a5bdf78955d7..f7b494125eee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1036,7 +1036,23 @@ static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_s return err; } -static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state) +static void mlx5e_flush_rq_cq(struct mlx5e_rq *rq) +{ + struct mlx5_cqwq *cqwq = &rq->cq.wq; + struct mlx5_cqe64 *cqe; + + if (test_bit(MLX5E_RQ_STATE_MINI_CQE_ENHANCED, &rq->state)) { + while ((cqe = mlx5_cqwq_get_cqe_enahnced_comp(cqwq))) + mlx5_cqwq_pop(cqwq); + } else { + while ((cqe = mlx5_cqwq_get_cqe(cqwq))) + mlx5_cqwq_pop(cqwq); + } + + mlx5_cqwq_update_db_record(cqwq); +} + +int mlx5e_flush_rq(struct mlx5e_rq *rq, int curr_state) { struct net_device *dev = rq->netdev; int err; @@ -1046,6 +1062,10 @@ static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state) netdev_err(dev, "Failed to move rq 0x%x to reset\n", rq->rqn); return err; } + + mlx5e_free_rx_descs(rq); + mlx5e_flush_rq_cq(rq); + err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY); if (err) { netdev_err(dev, "Failed to move rq 0x%x to ready\n", rq->rqn); @@ -1055,13 +1075,6 @@ static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state) return 0; } -int mlx5e_flush_rq(struct mlx5e_rq *rq, int curr_state) -{ - mlx5e_free_rx_descs(rq); - - return mlx5e_rq_to_ready(rq, curr_state); -} - static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd) { struct mlx5_core_dev *mdev = rq->mdev; @@ -1285,11 +1298,13 @@ static int mlx5e_alloc_xdpsq_fifo(struct mlx5e_xdpsq *sq, int numa) { struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo; int wq_sz = mlx5_wq_cyc_get_size(&sq->wq); - int entries = wq_sz * MLX5_SEND_WQEBB_NUM_DS * 2; /* upper bound for maximum num of - * entries of all xmit_modes. - */ + int entries; size_t size; + /* upper bound for maximum num of entries of all xmit_modes. */ + entries = roundup_pow_of_two(wq_sz * MLX5_SEND_WQEBB_NUM_DS * + MLX5E_XDP_FIFO_ENTRIES2DS_MAX_RATIO); + size = array_size(sizeof(*xdpi_fifo->xi), entries); xdpi_fifo->xi = kvzalloc_node(size, GFP_KERNEL, numa); if (!xdpi_fifo->xi) @@ -2402,7 +2417,7 @@ static int mlx5e_channel_stats_alloc(struct mlx5e_priv *priv, int ix, int cpu) /* Asymmetric dynamic memory allocation. * Freed in mlx5e_priv_arrays_free, not on channel closure. */ - mlx5e_dbg(DRV, priv, "Creating channel stats %d\n", ix); + netdev_dbg(priv->netdev, "Creating channel stats %d\n", ix); priv->channel_stats[ix] = kvzalloc_node(sizeof(**priv->channel_stats), GFP_KERNEL, cpu_to_node(cpu)); if (!priv->channel_stats[ix]) @@ -2780,7 +2795,7 @@ int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv) if (MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_TX_PORT_TS)) num_txqs += ntc; - mlx5e_dbg(DRV, priv, "Setting num_txqs %d\n", num_txqs); + netdev_dbg(priv->netdev, "Setting num_txqs %d\n", num_txqs); err = netif_set_real_num_tx_queues(priv->netdev, num_txqs); if (err) netdev_warn(priv->netdev, "netif_set_real_num_tx_queues failed, %d\n", err); @@ -5253,6 +5268,7 @@ void mlx5e_destroy_q_counters(struct mlx5e_priv *priv) static int mlx5e_nic_init(struct mlx5_core_dev *mdev, struct net_device *netdev) { + const bool take_rtnl = netdev->reg_state == NETREG_REGISTERED; struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_flow_steering *fs; int err; @@ -5281,9 +5297,19 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, mlx5_core_err(mdev, "TLS initialization failed, %d\n", err); mlx5e_health_create_reporters(priv); + + /* If netdev is already registered (e.g. move from uplink to nic profile), + * RTNL lock must be held before triggering netdev notifiers. + */ + if (take_rtnl) + rtnl_lock(); + /* update XDP supported features */ mlx5e_set_xdp_feature(netdev); + if (take_rtnl) + rtnl_unlock(); + return 0; } @@ -5586,7 +5612,6 @@ int mlx5e_priv_init(struct mlx5e_priv *priv, /* priv init */ priv->mdev = mdev; priv->netdev = netdev; - priv->msglevel = MLX5E_MSG_LEVEL; priv->max_nch = nch; priv->max_opened_tc = 1; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 3e7041bd5705..99b3843396f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -374,7 +374,9 @@ static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) { struct mlx5e_rep_sq *rep_sq, *tmp; + struct mlx5e_rep_sq_peer *sq_peer; struct mlx5e_rep_priv *rpriv; + unsigned long i; if (esw->mode != MLX5_ESWITCH_OFFLOADS) return; @@ -382,31 +384,78 @@ static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw, rpriv = mlx5e_rep_to_rep_priv(rep); list_for_each_entry_safe(rep_sq, tmp, &rpriv->vport_sqs_list, list) { mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule); - if (rep_sq->send_to_vport_rule_peer) - mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule_peer); + xa_for_each(&rep_sq->sq_peer, i, sq_peer) { + if (sq_peer->rule) + mlx5_eswitch_del_send_to_vport_rule(sq_peer->rule); + + xa_erase(&rep_sq->sq_peer, i); + kfree(sq_peer); + } + + xa_destroy(&rep_sq->sq_peer); list_del(&rep_sq->list); kfree(rep_sq); } } +static int mlx5e_sqs2vport_add_peers_rules(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep, + struct mlx5_devcom *devcom, + struct mlx5e_rep_sq *rep_sq, int i) +{ + struct mlx5_eswitch *peer_esw = NULL; + struct mlx5_flow_handle *flow_rule; + int tmp; + + mlx5_devcom_for_each_peer_entry(devcom, MLX5_DEVCOM_ESW_OFFLOADS, + peer_esw, tmp) { + u16 peer_rule_idx = MLX5_CAP_GEN(peer_esw->dev, vhca_id); + struct mlx5e_rep_sq_peer *sq_peer; + int err; + + sq_peer = kzalloc(sizeof(*sq_peer), GFP_KERNEL); + if (!sq_peer) + return -ENOMEM; + + flow_rule = mlx5_eswitch_add_send_to_vport_rule(peer_esw, esw, + rep, rep_sq->sqn); + if (IS_ERR(flow_rule)) { + kfree(sq_peer); + return PTR_ERR(flow_rule); + } + + sq_peer->rule = flow_rule; + sq_peer->peer = peer_esw; + err = xa_insert(&rep_sq->sq_peer, peer_rule_idx, sq_peer, GFP_KERNEL); + if (err) { + kfree(sq_peer); + mlx5_eswitch_del_send_to_vport_rule(flow_rule); + return err; + } + } + + return 0; +} + static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep, u32 *sqns_array, int sqns_num) { - struct mlx5_eswitch *peer_esw = NULL; struct mlx5_flow_handle *flow_rule; struct mlx5e_rep_priv *rpriv; struct mlx5e_rep_sq *rep_sq; + struct mlx5_devcom *devcom; + bool devcom_locked = false; int err; int i; if (esw->mode != MLX5_ESWITCH_OFFLOADS) return 0; + devcom = esw->dev->priv.devcom; rpriv = mlx5e_rep_to_rep_priv(rep); - if (mlx5_devcom_is_paired(esw->dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS)) - peer_esw = mlx5_devcom_get_peer_data(esw->dev->priv.devcom, - MLX5_DEVCOM_ESW_OFFLOADS); + if (mlx5_devcom_comp_is_ready(devcom, MLX5_DEVCOM_ESW_OFFLOADS) && + mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) + devcom_locked = true; for (i = 0; i < sqns_num; i++) { rep_sq = kzalloc(sizeof(*rep_sq), GFP_KERNEL); @@ -426,31 +475,30 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, rep_sq->send_to_vport_rule = flow_rule; rep_sq->sqn = sqns_array[i]; - if (peer_esw) { - flow_rule = mlx5_eswitch_add_send_to_vport_rule(peer_esw, esw, - rep, sqns_array[i]); - if (IS_ERR(flow_rule)) { - err = PTR_ERR(flow_rule); + xa_init(&rep_sq->sq_peer); + if (devcom_locked) { + err = mlx5e_sqs2vport_add_peers_rules(esw, rep, devcom, rep_sq, i); + if (err) { mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule); + xa_destroy(&rep_sq->sq_peer); kfree(rep_sq); goto out_err; } - rep_sq->send_to_vport_rule_peer = flow_rule; } list_add(&rep_sq->list, &rpriv->vport_sqs_list); } - if (peer_esw) - mlx5_devcom_release_peer_data(esw->dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS); + if (devcom_locked) + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); return 0; out_err: mlx5e_sqs2vport_stop(esw, rep); - if (peer_esw) - mlx5_devcom_release_peer_data(esw->dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS); + if (devcom_locked) + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); return err; } @@ -964,7 +1012,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) err = mlx5e_open_drop_rq(priv, &priv->drop_rq); if (err) { mlx5_core_err(mdev, "open drop rq failed, %d\n", err); - return err; + goto err_rx_res_free; } err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0, @@ -998,6 +1046,7 @@ err_destroy_rx_res: mlx5e_rx_res_destroy(priv->rx_res); err_close_drop_rq: mlx5e_close_drop_rq(&priv->drop_rq); +err_rx_res_free: mlx5e_rx_res_free(priv->rx_res); priv->rx_res = NULL; err_free_fs: @@ -1111,6 +1160,10 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) return err; } + err = mlx5e_rep_neigh_init(rpriv); + if (err) + goto err_neigh_init; + if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { err = mlx5e_init_uplink_rep_tx(rpriv); if (err) @@ -1127,6 +1180,8 @@ err_ht_init: if (rpriv->rep->vport == MLX5_VPORT_UPLINK) mlx5e_cleanup_uplink_rep_tx(rpriv); err_init_tx: + mlx5e_rep_neigh_cleanup(rpriv); +err_neigh_init: mlx5e_destroy_tises(priv); return err; } @@ -1140,22 +1195,17 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) if (rpriv->rep->vport == MLX5_VPORT_UPLINK) mlx5e_cleanup_uplink_rep_tx(rpriv); + mlx5e_rep_neigh_cleanup(rpriv); mlx5e_destroy_tises(priv); } static void mlx5e_rep_enable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; - mlx5e_set_netdev_mtu_boundaries(priv); - mlx5e_rep_neigh_init(rpriv); } static void mlx5e_rep_disable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; - - mlx5e_rep_neigh_cleanup(rpriv); } static int mlx5e_update_rep_rx(struct mlx5e_priv *priv) @@ -1205,7 +1255,6 @@ static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; u16 max_mtu; @@ -1227,7 +1276,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) mlx5_notifier_register(mdev, &priv->events_nb); mlx5e_dcbnl_initialize(priv); mlx5e_dcbnl_init_app(priv); - mlx5e_rep_neigh_init(rpriv); mlx5e_rep_bridge_init(priv); netdev->wanted_features |= NETIF_F_HW_TC; @@ -1242,7 +1290,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_core_dev *mdev = priv->mdev; rtnl_lock(); @@ -1252,7 +1299,6 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) rtnl_unlock(); mlx5e_rep_bridge_cleanup(priv); - mlx5e_rep_neigh_cleanup(rpriv); mlx5e_dcbnl_delete_app(priv); mlx5_notifier_unregister(mdev, &priv->events_nb); mlx5e_rep_tc_disable(priv); @@ -1530,17 +1576,24 @@ static void *mlx5e_vport_rep_get_proto_dev(struct mlx5_eswitch_rep *rep) return rpriv->netdev; } -static void mlx5e_vport_rep_event_unpair(struct mlx5_eswitch_rep *rep) +static void mlx5e_vport_rep_event_unpair(struct mlx5_eswitch_rep *rep, + struct mlx5_eswitch *peer_esw) { + u16 i = MLX5_CAP_GEN(peer_esw->dev, vhca_id); struct mlx5e_rep_priv *rpriv; struct mlx5e_rep_sq *rep_sq; + WARN_ON_ONCE(!peer_esw); rpriv = mlx5e_rep_to_rep_priv(rep); list_for_each_entry(rep_sq, &rpriv->vport_sqs_list, list) { - if (!rep_sq->send_to_vport_rule_peer) + struct mlx5e_rep_sq_peer *sq_peer = xa_load(&rep_sq->sq_peer, i); + + if (!sq_peer || sq_peer->peer != peer_esw) continue; - mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule_peer); - rep_sq->send_to_vport_rule_peer = NULL; + + mlx5_eswitch_del_send_to_vport_rule(sq_peer->rule); + xa_erase(&rep_sq->sq_peer, i); + kfree(sq_peer); } } @@ -1548,24 +1601,52 @@ static int mlx5e_vport_rep_event_pair(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep, struct mlx5_eswitch *peer_esw) { + u16 i = MLX5_CAP_GEN(peer_esw->dev, vhca_id); struct mlx5_flow_handle *flow_rule; + struct mlx5e_rep_sq_peer *sq_peer; struct mlx5e_rep_priv *rpriv; struct mlx5e_rep_sq *rep_sq; + int err; rpriv = mlx5e_rep_to_rep_priv(rep); list_for_each_entry(rep_sq, &rpriv->vport_sqs_list, list) { - if (rep_sq->send_to_vport_rule_peer) + sq_peer = xa_load(&rep_sq->sq_peer, i); + + if (sq_peer && sq_peer->peer) continue; - flow_rule = mlx5_eswitch_add_send_to_vport_rule(peer_esw, esw, rep, rep_sq->sqn); - if (IS_ERR(flow_rule)) + + flow_rule = mlx5_eswitch_add_send_to_vport_rule(peer_esw, esw, rep, + rep_sq->sqn); + if (IS_ERR(flow_rule)) { + err = PTR_ERR(flow_rule); goto err_out; - rep_sq->send_to_vport_rule_peer = flow_rule; + } + + if (sq_peer) { + sq_peer->rule = flow_rule; + sq_peer->peer = peer_esw; + continue; + } + sq_peer = kzalloc(sizeof(*sq_peer), GFP_KERNEL); + if (!sq_peer) { + err = -ENOMEM; + goto err_sq_alloc; + } + err = xa_insert(&rep_sq->sq_peer, i, sq_peer, GFP_KERNEL); + if (err) + goto err_xa; + sq_peer->rule = flow_rule; + sq_peer->peer = peer_esw; } return 0; +err_xa: + kfree(sq_peer); +err_sq_alloc: + mlx5_eswitch_del_send_to_vport_rule(flow_rule); err_out: - mlx5e_vport_rep_event_unpair(rep); - return PTR_ERR(flow_rule); + mlx5e_vport_rep_event_unpair(rep, peer_esw); + return err; } static int mlx5e_vport_rep_event(struct mlx5_eswitch *esw, @@ -1578,7 +1659,7 @@ static int mlx5e_vport_rep_event(struct mlx5_eswitch *esw, if (event == MLX5_SWITCHDEV_EVENT_PAIR) err = mlx5e_vport_rep_event_pair(esw, rep, data); else if (event == MLX5_SWITCHDEV_EVENT_UNPAIR) - mlx5e_vport_rep_event_unpair(rep); + mlx5e_vport_rep_event_unpair(rep, data); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 80b7f5079a5a..70640fa1ad7b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -225,9 +225,14 @@ struct mlx5e_encap_entry { struct rcu_head rcu; }; +struct mlx5e_rep_sq_peer { + struct mlx5_flow_handle *rule; + void *peer; +}; + struct mlx5e_rep_sq { struct mlx5_flow_handle *send_to_vport_rule; - struct mlx5_flow_handle *send_to_vport_rule_peer; + struct xarray sq_peer; u32 sqn; struct list_head list; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 69634829558e..41d37159e027 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -390,10 +390,18 @@ static void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix) { struct mlx5e_wqe_frag_info *wi = get_frag(rq, ix); - if (rq->xsk_pool) + if (rq->xsk_pool) { mlx5e_xsk_free_rx_wqe(wi); - else + } else { mlx5e_free_rx_wqe(rq, wi); + + /* Avoid a second release of the wqe pages: dealloc is called + * for the same missing wqes on regular RQ flush and on regular + * RQ close. This happens when XSK RQs come into play. + */ + for (int i = 0; i < rq->wqe.info.num_frags; i++, wi++) + wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); + } } static void mlx5e_xsk_free_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk) @@ -491,9 +499,7 @@ mlx5e_add_skb_shared_info_frag(struct mlx5e_rq *rq, struct skb_shared_info *sinf } frag = &sinfo->frags[sinfo->nr_frags++]; - __skb_frag_set_page(frag, frag_page->page); - skb_frag_off_set(frag, frag_offset); - skb_frag_size_set(frag, len); + skb_frag_fill_page_desc(frag, frag_page->page, frag_offset, len); if (page_is_pfmemalloc(frag_page->page)) xdp_buff_set_frag_pfmemalloc(xdp); @@ -1745,11 +1751,11 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi prog = rcu_dereference(rq->xdp_prog); if (prog && mlx5e_xdp_handle(rq, prog, &mxbuf)) { - if (test_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { + if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { struct mlx5e_wqe_frag_info *pwi; for (pwi = head_wi; pwi < wi; pwi++) - pwi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); + pwi->frag_page->frags++; } return NULL; /* page/packet was consumed by XDP */ } @@ -1819,12 +1825,8 @@ static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) rq, wi, cqe, cqe_bcnt); if (!skb) { /* probably for XDP */ - if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { - /* do not return page to cache, - * it will be returned on XDP_TX completion. - */ - wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); - } + if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) + wi->frag_page->frags++; goto wq_cyc_pop; } @@ -1870,12 +1872,8 @@ static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) rq, wi, cqe, cqe_bcnt); if (!skb) { /* probably for XDP */ - if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { - /* do not return page to cache, - * it will be returned on XDP_TX completion. - */ - wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); - } + if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) + wi->frag_page->frags++; goto wq_cyc_pop; } @@ -2054,12 +2052,12 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w if (prog) { if (mlx5e_xdp_handle(rq, prog, &mxbuf)) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { - int i; + struct mlx5e_frag_page *pfp; + + for (pfp = head_page; pfp < frag_page; pfp++) + pfp->frags++; - for (i = 0; i < sinfo->nr_frags; i++) - /* non-atomic */ - __set_bit(page_idx + i, wi->skip_release_bitmap); - return NULL; + wi->linear_page.frags++; } mlx5e_page_release_fragmented(rq, &wi->linear_page); return NULL; /* page/packet was consumed by XDP */ @@ -2157,7 +2155,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, cqe_bcnt, &mxbuf); if (mlx5e_xdp_handle(rq, prog, &mxbuf)) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) - __set_bit(page_idx, wi->skip_release_bitmap); /* non-atomic */ + frag_page->frags++; return NULL; /* page/packet was consumed by XDP */ } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index f1d9596905c6..4d77055abd4b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -30,7 +30,7 @@ * SOFTWARE. */ -#include "lib/mlx5.h" +#include "lib/events.h" #include "en.h" #include "en_accel/ktls.h" #include "en_accel/en_accel.h" @@ -748,11 +748,22 @@ static const struct counter_desc vport_stats_desc[] = { VPORT_COUNTER_OFF(transmitted_ib_multicast.octets) }, }; +static const struct counter_desc vport_loopback_stats_desc[] = { + { "vport_loopback_packets", + VPORT_COUNTER_OFF(local_loopback.packets) }, + { "vport_loopback_bytes", + VPORT_COUNTER_OFF(local_loopback.octets) }, +}; + #define NUM_VPORT_COUNTERS ARRAY_SIZE(vport_stats_desc) +#define NUM_VPORT_LOOPBACK_COUNTERS(dev) \ + (MLX5_CAP_GEN(dev, vport_counter_local_loopback) ? \ + ARRAY_SIZE(vport_loopback_stats_desc) : 0) static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(vport) { - return NUM_VPORT_COUNTERS; + return NUM_VPORT_COUNTERS + + NUM_VPORT_LOOPBACK_COUNTERS(priv->mdev); } static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vport) @@ -761,6 +772,11 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vport) for (i = 0; i < NUM_VPORT_COUNTERS; i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, vport_stats_desc[i].format); + + for (i = 0; i < NUM_VPORT_LOOPBACK_COUNTERS(priv->mdev); i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + vport_loopback_stats_desc[i].format); + return idx; } @@ -771,6 +787,11 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vport) for (i = 0; i < NUM_VPORT_COUNTERS; i++) data[idx++] = MLX5E_READ_CTR64_BE(priv->stats.vport.query_vport_out, vport_stats_desc, i); + + for (i = 0; i < NUM_VPORT_LOOPBACK_COUNTERS(priv->mdev); i++) + data[idx++] = MLX5E_READ_CTR64_BE(priv->stats.vport.query_vport_out, + vport_loopback_stats_desc, i); + return idx; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index b9b1da751a3b..4b22a91482ce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1639,7 +1639,8 @@ static void remove_unready_flow(struct mlx5e_tc_flow *flow) uplink_priv = &rpriv->uplink_priv; mutex_lock(&uplink_priv->unready_flows_lock); - unready_flow_del(flow); + if (flow_flag_test(flow, NOT_READY)) + unready_flow_del(flow); mutex_unlock(&uplink_priv->unready_flows_lock); } @@ -1667,8 +1668,11 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro { struct mlx5e_priv *out_priv, *route_priv; struct mlx5_core_dev *route_mdev; + struct mlx5_devcom *devcom; struct mlx5_eswitch *esw; u16 vhca_id; + int err; + int i; out_priv = netdev_priv(out_dev); esw = out_priv->mdev->priv.eswitch; @@ -1676,28 +1680,25 @@ 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)) { - struct mlx5_devcom *devcom; - int err; - - /* 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; - - rcu_read_lock(); - devcom = out_priv->mdev->priv.devcom; - esw = mlx5_devcom_get_peer_data_rcu(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - err = esw ? mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport) : -ENODEV; - rcu_read_unlock(); + err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); + if (!err) + return err; + if (!mlx5_lag_is_active(out_priv->mdev)) return err; + + rcu_read_lock(); + devcom = out_priv->mdev->priv.devcom; + err = -ENODEV; + mlx5_devcom_for_each_peer_entry_rcu(devcom, MLX5_DEVCOM_ESW_OFFLOADS, + esw, i) { + err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); + if (!err) + break; } + rcu_read_unlock(); - return mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); + return err; } static int @@ -1724,6 +1725,19 @@ verify_attr_actions(u32 actions, struct netlink_ext_ack *extack) return 0; } +static bool +has_encap_dests(struct mlx5_flow_attr *attr) +{ + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + int out_index; + + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) + if (esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) + return true; + + return false; +} + static int post_process_attr(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, @@ -1736,9 +1750,11 @@ post_process_attr(struct mlx5e_tc_flow *flow, if (err) goto err_out; - err = mlx5e_tc_tun_encap_dests_set(flow->priv, flow, attr, extack, &vf_tun); - if (err) - goto err_out; + if (mlx5e_is_eswitch_flow(flow) && has_encap_dests(attr)) { + err = mlx5e_tc_tun_encap_dests_set(flow->priv, flow, attr, extack, &vf_tun); + if (err) + goto err_out; + } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr); @@ -1927,13 +1943,10 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_flow_attr *attr = flow->attr; - struct mlx5_esw_flow_attr *esw_attr; - esw_attr = attr->esw_attr; mlx5e_put_flow_tunnel_id(flow); - if (flow_flag_test(flow, NOT_READY)) - remove_unready_flow(flow); + remove_unready_flow(flow); if (mlx5e_is_offloaded_flow(flow)) { if (flow_flag_test(flow, SLOW)) @@ -1951,12 +1964,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5_tc_ct_match_del(get_ct_priv(priv), &flow->attr->ct_attr); - if (esw_attr->int_port) - mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->int_port); - - if (esw_attr->dest_int_port) - mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->dest_int_port); - if (flow_flag_test(flow, L3_TO_L2_DECAP)) mlx5e_detach_decap(priv, flow); @@ -1987,47 +1994,59 @@ void mlx5e_put_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list) mlx5e_flow_put(priv, flow); } -static void __mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow) +static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow, + int peer_index) { struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch; + struct mlx5e_tc_flow *peer_flow; + struct mlx5e_tc_flow *tmp; if (!flow_flag_test(flow, ESWITCH) || !flow_flag_test(flow, DUP)) return; mutex_lock(&esw->offloads.peer_mutex); - list_del(&flow->peer); + list_del(&flow->peer[peer_index]); mutex_unlock(&esw->offloads.peer_mutex); - flow_flag_clear(flow, DUP); - - if (refcount_dec_and_test(&flow->peer_flow->refcnt)) { - mlx5e_tc_del_fdb_flow(flow->peer_flow->priv, flow->peer_flow); - kfree(flow->peer_flow); + list_for_each_entry_safe(peer_flow, tmp, &flow->peer_flows, peer_flows) { + if (peer_index != mlx5_get_dev_index(peer_flow->priv->mdev)) + continue; + if (refcount_dec_and_test(&peer_flow->refcnt)) { + mlx5e_tc_del_fdb_flow(peer_flow->priv, peer_flow); + list_del(&peer_flow->peer_flows); + kfree(peer_flow); + } } - flow->peer_flow = NULL; + if (list_empty(&flow->peer_flows)) + flow_flag_clear(flow, DUP); } -static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow) +static void mlx5e_tc_del_fdb_peers_flow(struct mlx5e_tc_flow *flow) { - struct mlx5_core_dev *dev = flow->priv->mdev; - struct mlx5_devcom *devcom = dev->priv.devcom; - struct mlx5_eswitch *peer_esw; - - peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - if (!peer_esw) - return; + int i; - __mlx5e_tc_del_fdb_peer_flow(flow); - mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + for (i = 0; i < MLX5_MAX_PORTS; i++) { + if (i == mlx5_get_dev_index(flow->priv->mdev)) + continue; + mlx5e_tc_del_fdb_peer_flow(flow, i); + } } static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { if (mlx5e_is_eswitch_flow(flow)) { - mlx5e_tc_del_fdb_peer_flow(flow); + struct mlx5_devcom *devcom = flow->priv->mdev->priv.devcom; + + if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) { + mlx5e_tc_del_fdb_flow(priv, flow); + return; + } + + mlx5e_tc_del_fdb_peers_flow(flow); + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); mlx5e_tc_del_fdb_flow(priv, flow); } else { mlx5e_tc_del_nic_flow(priv, flow); @@ -2503,6 +2522,12 @@ static int mlx5e_flower_parse_meta(struct net_device *filter_dev, return 0; flow_rule_match_meta(rule, &match); + + if (match.mask->l2_miss) { + NL_SET_ERR_MSG_MOD(f->common.extack, "Can't match on \"l2_miss\""); + return -EOPNOTSUPP; + } + if (!match.mask->ingress_ifindex) return 0; @@ -3914,6 +3939,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, } i_split = i + 1; + parse_state->if_count = 0; list_add(&attr->list, &flow->attrs); } @@ -4198,8 +4224,8 @@ static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow) flow_flag_test(flow, INGRESS); bool act_is_encap = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT); - bool esw_paired = mlx5_devcom_is_paired(esw_attr->in_mdev->priv.devcom, - MLX5_DEVCOM_ESW_OFFLOADS); + bool esw_paired = mlx5_devcom_comp_is_ready(esw_attr->in_mdev->priv.devcom, + MLX5_DEVCOM_ESW_OFFLOADS); if (!esw_paired) return false; @@ -4235,6 +4261,7 @@ static void mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) { struct mlx5_core_dev *counter_dev = get_flow_counter_dev(flow); + struct mlx5_esw_flow_attr *esw_attr; if (!attr) return; @@ -4252,6 +4279,18 @@ mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *a mlx5e_tc_detach_mod_hdr(flow->priv, flow, attr); } + if (mlx5e_is_eswitch_flow(flow)) { + esw_attr = attr->esw_attr; + + if (esw_attr->int_port) + mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(flow->priv), + esw_attr->int_port); + + if (esw_attr->dest_int_port) + mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(flow->priv), + esw_attr->dest_int_port); + } + mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), attr); free_branch_attr(flow, attr->branch_true); @@ -4290,6 +4329,7 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size, INIT_LIST_HEAD(&flow->hairpin); INIT_LIST_HEAD(&flow->l3_to_l2_reformat); INIT_LIST_HEAD(&flow->attrs); + INIT_LIST_HEAD(&flow->peer_flows); refcount_set(&flow->refcnt, 1); init_completion(&flow->init_done); init_completion(&flow->del_hw_done); @@ -4398,22 +4438,19 @@ out: static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f, struct mlx5e_tc_flow *flow, - unsigned long flow_flags) + unsigned long flow_flags, + struct mlx5_eswitch *peer_esw) { struct mlx5e_priv *priv = flow->priv, *peer_priv; - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch, *peer_esw; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr *attr = flow->attr->esw_attr; - struct mlx5_devcom *devcom = priv->mdev->priv.devcom; struct mlx5e_tc_flow_parse_attr *parse_attr; + int i = mlx5_get_dev_index(peer_esw->dev); struct mlx5e_rep_priv *peer_urpriv; struct mlx5e_tc_flow *peer_flow; struct mlx5_core_dev *in_mdev; int err = 0; - peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - if (!peer_esw) - return -ENODEV; - peer_urpriv = mlx5_eswitch_get_uplink_priv(peer_esw, REP_ETH); peer_priv = netdev_priv(peer_urpriv->netdev); @@ -4438,14 +4475,13 @@ static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f, goto out; } - flow->peer_flow = peer_flow; + list_add_tail(&peer_flow->peer_flows, &flow->peer_flows); flow_flag_set(flow, DUP); mutex_lock(&esw->offloads.peer_mutex); - list_add_tail(&flow->peer, &esw->offloads.peer_flows); + list_add_tail(&flow->peer[i], &esw->offloads.peer_flows[i]); mutex_unlock(&esw->offloads.peer_mutex); out: - mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); return err; } @@ -4456,30 +4492,48 @@ mlx5e_add_fdb_flow(struct mlx5e_priv *priv, struct net_device *filter_dev, struct mlx5e_tc_flow **__flow) { + struct mlx5_devcom *devcom = priv->mdev->priv.devcom; struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *in_rep = rpriv->rep; struct mlx5_core_dev *in_mdev = priv->mdev; + struct mlx5_eswitch *peer_esw; struct mlx5e_tc_flow *flow; int err; + int i; flow = __mlx5e_add_fdb_flow(priv, f, flow_flags, filter_dev, in_rep, in_mdev); if (IS_ERR(flow)) return PTR_ERR(flow); - if (is_peer_flow_needed(flow)) { - err = mlx5e_tc_add_fdb_peer_flow(f, flow, flow_flags); - if (err) { - mlx5e_tc_del_fdb_flow(priv, flow); - goto out; - } + if (!is_peer_flow_needed(flow)) { + *__flow = flow; + return 0; } - *__flow = flow; + if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) { + err = -ENODEV; + goto clean_flow; + } + mlx5_devcom_for_each_peer_entry(devcom, + MLX5_DEVCOM_ESW_OFFLOADS, + peer_esw, i) { + err = mlx5e_tc_add_fdb_peer_flow(f, flow, flow_flags, peer_esw); + if (err) + goto peer_clean; + } + + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + + *__flow = flow; return 0; -out: +peer_clean: + mlx5e_tc_del_fdb_peers_flow(flow); + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); +clean_flow: + mlx5e_tc_del_fdb_flow(priv, flow); return err; } @@ -4697,7 +4751,6 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, { struct mlx5_devcom *devcom = priv->mdev->priv.devcom; struct rhashtable *tc_ht = get_tc_ht(priv, flags); - struct mlx5_eswitch *peer_esw; struct mlx5e_tc_flow *flow; struct mlx5_fc *counter; u64 lastuse = 0; @@ -4732,23 +4785,29 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, /* Under multipath it's possible for one rule to be currently * un-offloaded while the other rule is offloaded. */ - peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - if (!peer_esw) + if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) goto out; - if (flow_flag_test(flow, DUP) && - flow_flag_test(flow->peer_flow, OFFLOADED)) { - u64 bytes2; - u64 packets2; - u64 lastuse2; + if (flow_flag_test(flow, DUP)) { + struct mlx5e_tc_flow *peer_flow; - if (flow_flag_test(flow, USE_ACT_STATS)) { - f->use_act_stats = true; - } else { - counter = mlx5e_tc_get_counter(flow->peer_flow); + list_for_each_entry(peer_flow, &flow->peer_flows, peer_flows) { + u64 packets2; + u64 lastuse2; + u64 bytes2; + + if (!flow_flag_test(peer_flow, OFFLOADED)) + continue; + if (flow_flag_test(flow, USE_ACT_STATS)) { + f->use_act_stats = true; + break; + } + + counter = mlx5e_tc_get_counter(peer_flow); if (!counter) goto no_peer_counter; - mlx5_fc_query_cached(counter, &bytes2, &packets2, &lastuse2); + mlx5_fc_query_cached(counter, &bytes2, &packets2, + &lastuse2); bytes += bytes2; packets += packets2; @@ -4757,7 +4816,7 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, } no_peer_counter: - mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); out: flow_stats_update(&f->stats, bytes, packets, 0, lastuse, FLOW_ACTION_HW_STATS_DELAYED); @@ -5275,9 +5334,14 @@ int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags) void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw) { struct mlx5e_tc_flow *flow, *tmp; + int i; - list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows, peer) - __mlx5e_tc_del_fdb_peer_flow(flow); + for (i = 0; i < MLX5_MAX_PORTS; i++) { + if (i == mlx5_get_dev_index(esw->dev)) + continue; + list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows[i], peer[i]) + mlx5e_tc_del_fdb_peers_flow(flow); + } } void mlx5e_tc_reoffload_flows_work(struct work_struct *work) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index fbb2d963fb7e..a7d9b7cb4297 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -207,7 +207,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) } ch_stats->aff_change++; aff_change = true; - if (budget && work_done == budget) + if (work_done == budget) work_done--; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c index 2e504c7461c6..24b1ca4e4ff8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c @@ -15,13 +15,27 @@ static void esw_acl_egress_ofld_fwd2vport_destroy(struct mlx5_vport *vport) vport->egress.offloads.fwd_rule = NULL; } -static void esw_acl_egress_ofld_bounce_rule_destroy(struct mlx5_vport *vport) +void esw_acl_egress_ofld_bounce_rule_destroy(struct mlx5_vport *vport, int rule_index) { - if (!vport->egress.offloads.bounce_rule) + struct mlx5_flow_handle *bounce_rule = + xa_load(&vport->egress.offloads.bounce_rules, rule_index); + + if (!bounce_rule) return; - mlx5_del_flow_rules(vport->egress.offloads.bounce_rule); - vport->egress.offloads.bounce_rule = NULL; + mlx5_del_flow_rules(bounce_rule); + xa_erase(&vport->egress.offloads.bounce_rules, rule_index); +} + +static void esw_acl_egress_ofld_bounce_rules_destroy(struct mlx5_vport *vport) +{ + struct mlx5_flow_handle *bounce_rule; + unsigned long i; + + xa_for_each(&vport->egress.offloads.bounce_rules, i, bounce_rule) { + mlx5_del_flow_rules(bounce_rule); + xa_erase(&vport->egress.offloads.bounce_rules, i); + } } static int esw_acl_egress_ofld_fwd2vport_create(struct mlx5_eswitch *esw, @@ -96,7 +110,7 @@ static void esw_acl_egress_ofld_rules_destroy(struct mlx5_vport *vport) { esw_acl_egress_vlan_destroy(vport); esw_acl_egress_ofld_fwd2vport_destroy(vport); - esw_acl_egress_ofld_bounce_rule_destroy(vport); + esw_acl_egress_ofld_bounce_rules_destroy(vport); } static int esw_acl_egress_ofld_groups_create(struct mlx5_eswitch *esw, @@ -194,6 +208,7 @@ int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport vport->egress.acl = NULL; return err; } + vport->egress.type = VPORT_EGRESS_ACL_TYPE_DEFAULT; err = esw_acl_egress_ofld_groups_create(esw, vport); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c index 45b839116212..d599e50af346 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c @@ -35,7 +35,8 @@ esw_acl_table_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport, int ns, } ft_attr.max_fte = size; - ft_attr.flags = MLX5_FLOW_TABLE_OTHER_VPORT; + if (vport_num || mlx5_core_is_ecpf(esw->dev)) + ft_attr.flags = MLX5_FLOW_TABLE_OTHER_VPORT; acl = mlx5_create_vport_flow_table(root_ns, &ft_attr, vport_num); if (IS_ERR(acl)) { err = PTR_ERR(acl); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h index c9f8469e9a47..536b04e83618 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h @@ -10,6 +10,7 @@ /* Eswitch acl egress external APIs */ int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport); void esw_acl_egress_ofld_cleanup(struct mlx5_vport *vport); +void esw_acl_egress_ofld_bounce_rule_destroy(struct mlx5_vport *vport, int rule_index); int mlx5_esw_acl_egress_vport_bond(struct mlx5_eswitch *esw, u16 active_vport_num, u16 passive_vport_num); int mlx5_esw_acl_egress_vport_unbond(struct mlx5_eswitch *esw, u16 vport_num); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index 1ba03e219111..f4fe1daa4afd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -647,22 +647,35 @@ mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr, } static struct mlx5_flow_handle * -mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, const unsigned char *addr, +mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, u16 esw_owner_vhca_id, + const unsigned char *addr, struct mlx5_esw_bridge_vlan *vlan, u32 counter_id, struct mlx5_esw_bridge *bridge) { struct mlx5_devcom *devcom = bridge->br_offloads->esw->dev->priv.devcom; + struct mlx5_eswitch *tmp, *peer_esw = NULL; static struct mlx5_flow_handle *handle; - struct mlx5_eswitch *peer_esw; + int i; - peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - if (!peer_esw) + if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) return ERR_PTR(-ENODEV); + mlx5_devcom_for_each_peer_entry(devcom, + MLX5_DEVCOM_ESW_OFFLOADS, + tmp, i) { + if (mlx5_esw_is_owner(tmp, vport_num, esw_owner_vhca_id)) { + peer_esw = tmp; + break; + } + } + if (!peer_esw) { + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + return ERR_PTR(-ENODEV); + } + handle = mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id, bridge, peer_esw); - - mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); return handle; } @@ -821,7 +834,7 @@ mlx5_esw_bridge_egress_miss_flow_create(struct mlx5_flow_table *egress_ft, return handle; } -static struct mlx5_esw_bridge *mlx5_esw_bridge_create(int ifindex, +static struct mlx5_esw_bridge *mlx5_esw_bridge_create(struct net_device *br_netdev, struct mlx5_esw_bridge_offloads *br_offloads) { struct mlx5_esw_bridge *bridge; @@ -845,11 +858,12 @@ static struct mlx5_esw_bridge *mlx5_esw_bridge_create(int ifindex, goto err_mdb_ht; INIT_LIST_HEAD(&bridge->fdb_list); - bridge->ifindex = ifindex; + bridge->ifindex = br_netdev->ifindex; bridge->refcnt = 1; bridge->ageing_time = clock_t_to_jiffies(BR_DEFAULT_AGEING_TIME); bridge->vlan_proto = ETH_P_8021Q; list_add(&bridge->list, &br_offloads->bridges); + mlx5_esw_bridge_debugfs_init(br_netdev, bridge); return bridge; @@ -873,6 +887,7 @@ static void mlx5_esw_bridge_put(struct mlx5_esw_bridge_offloads *br_offloads, if (--bridge->refcnt) return; + mlx5_esw_bridge_debugfs_cleanup(bridge); mlx5_esw_bridge_egress_table_cleanup(bridge); mlx5_esw_bridge_mcast_disable(bridge); list_del(&bridge->list); @@ -885,14 +900,14 @@ static void mlx5_esw_bridge_put(struct mlx5_esw_bridge_offloads *br_offloads, } static struct mlx5_esw_bridge * -mlx5_esw_bridge_lookup(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads) +mlx5_esw_bridge_lookup(struct net_device *br_netdev, struct mlx5_esw_bridge_offloads *br_offloads) { struct mlx5_esw_bridge *bridge; ASSERT_RTNL(); list_for_each_entry(bridge, &br_offloads->bridges, list) { - if (bridge->ifindex == ifindex) { + if (bridge->ifindex == br_netdev->ifindex) { mlx5_esw_bridge_get(bridge); return bridge; } @@ -905,7 +920,7 @@ mlx5_esw_bridge_lookup(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads return ERR_PTR(err); } - bridge = mlx5_esw_bridge_create(ifindex, br_offloads); + bridge = mlx5_esw_bridge_create(br_netdev, br_offloads); if (IS_ERR(bridge) && list_empty(&br_offloads->bridges)) mlx5_esw_bridge_ingress_table_cleanup(br_offloads); return bridge; @@ -1369,8 +1384,9 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_ow entry->ingress_counter = counter; handle = peer ? - mlx5_esw_bridge_ingress_flow_peer_create(vport_num, addr, vlan, - mlx5_fc_id(counter), bridge) : + mlx5_esw_bridge_ingress_flow_peer_create(vport_num, esw_owner_vhca_id, + addr, vlan, mlx5_fc_id(counter), + bridge) : mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan, mlx5_fc_id(counter), bridge); if (IS_ERR(handle)) { @@ -1587,15 +1603,15 @@ static int mlx5_esw_bridge_vport_cleanup(struct mlx5_esw_bridge_offloads *br_off return 0; } -static int mlx5_esw_bridge_vport_link_with_flags(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, - u16 flags, +static int mlx5_esw_bridge_vport_link_with_flags(struct net_device *br_netdev, u16 vport_num, + u16 esw_owner_vhca_id, u16 flags, struct mlx5_esw_bridge_offloads *br_offloads, struct netlink_ext_ack *extack) { struct mlx5_esw_bridge *bridge; int err; - bridge = mlx5_esw_bridge_lookup(ifindex, br_offloads); + bridge = mlx5_esw_bridge_lookup(br_netdev, br_offloads); if (IS_ERR(bridge)) { NL_SET_ERR_MSG_MOD(extack, "Error checking for existing bridge with same ifindex"); return PTR_ERR(bridge); @@ -1613,15 +1629,16 @@ err_vport: return err; } -int mlx5_esw_bridge_vport_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, +int mlx5_esw_bridge_vport_link(struct net_device *br_netdev, u16 vport_num, u16 esw_owner_vhca_id, struct mlx5_esw_bridge_offloads *br_offloads, struct netlink_ext_ack *extack) { - return mlx5_esw_bridge_vport_link_with_flags(ifindex, vport_num, esw_owner_vhca_id, 0, + return mlx5_esw_bridge_vport_link_with_flags(br_netdev, vport_num, esw_owner_vhca_id, 0, br_offloads, extack); } -int mlx5_esw_bridge_vport_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, +int mlx5_esw_bridge_vport_unlink(struct net_device *br_netdev, u16 vport_num, + u16 esw_owner_vhca_id, struct mlx5_esw_bridge_offloads *br_offloads, struct netlink_ext_ack *extack) { @@ -1633,7 +1650,7 @@ int mlx5_esw_bridge_vport_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_ NL_SET_ERR_MSG_MOD(extack, "Port is not attached to any bridge"); return -EINVAL; } - if (port->bridge->ifindex != ifindex) { + if (port->bridge->ifindex != br_netdev->ifindex) { NL_SET_ERR_MSG_MOD(extack, "Port is attached to another bridge"); return -EINVAL; } @@ -1644,23 +1661,25 @@ int mlx5_esw_bridge_vport_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_ return err; } -int mlx5_esw_bridge_vport_peer_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, +int mlx5_esw_bridge_vport_peer_link(struct net_device *br_netdev, u16 vport_num, + u16 esw_owner_vhca_id, struct mlx5_esw_bridge_offloads *br_offloads, struct netlink_ext_ack *extack) { if (!MLX5_CAP_ESW(br_offloads->esw->dev, merged_eswitch)) return 0; - return mlx5_esw_bridge_vport_link_with_flags(ifindex, vport_num, esw_owner_vhca_id, + return mlx5_esw_bridge_vport_link_with_flags(br_netdev, vport_num, esw_owner_vhca_id, MLX5_ESW_BRIDGE_PORT_FLAG_PEER, br_offloads, extack); } -int mlx5_esw_bridge_vport_peer_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, +int mlx5_esw_bridge_vport_peer_unlink(struct net_device *br_netdev, u16 vport_num, + u16 esw_owner_vhca_id, struct mlx5_esw_bridge_offloads *br_offloads, struct netlink_ext_ack *extack) { - return mlx5_esw_bridge_vport_unlink(ifindex, vport_num, esw_owner_vhca_id, br_offloads, + return mlx5_esw_bridge_vport_unlink(br_netdev, vport_num, esw_owner_vhca_id, br_offloads, extack); } @@ -1887,6 +1906,7 @@ struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw) xa_init(&br_offloads->ports); br_offloads->esw = esw; esw->br_offloads = br_offloads; + mlx5_esw_bridge_debugfs_offloads_init(br_offloads); return br_offloads; } @@ -1902,6 +1922,7 @@ void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw) mlx5_esw_bridge_flush(br_offloads); WARN_ON(!xa_empty(&br_offloads->ports)); + mlx5_esw_bridge_debugfs_offloads_cleanup(br_offloads); esw->br_offloads = NULL; kvfree(br_offloads); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h index a9dd18c73d6a..c2c7c70d99eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h @@ -10,6 +10,7 @@ #include <linux/xarray.h> #include "eswitch.h" +struct dentry; struct mlx5_flow_table; struct mlx5_flow_group; @@ -17,6 +18,7 @@ struct mlx5_esw_bridge_offloads { struct mlx5_eswitch *esw; struct list_head bridges; struct xarray ports; + struct dentry *debugfs_root; struct notifier_block netdev_nb; struct notifier_block nb_blk; @@ -43,16 +45,18 @@ struct mlx5_esw_bridge_offloads { struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw); void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw); -int mlx5_esw_bridge_vport_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, +int mlx5_esw_bridge_vport_link(struct net_device *br_netdev, u16 vport_num, u16 esw_owner_vhca_id, struct mlx5_esw_bridge_offloads *br_offloads, struct netlink_ext_ack *extack); -int mlx5_esw_bridge_vport_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, +int mlx5_esw_bridge_vport_unlink(struct net_device *br_netdev, u16 vport_num, u16 esw_owner_vhca_id, struct mlx5_esw_bridge_offloads *br_offloads, struct netlink_ext_ack *extack); -int mlx5_esw_bridge_vport_peer_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, +int mlx5_esw_bridge_vport_peer_link(struct net_device *br_netdev, u16 vport_num, + u16 esw_owner_vhca_id, struct mlx5_esw_bridge_offloads *br_offloads, struct netlink_ext_ack *extack); -int mlx5_esw_bridge_vport_peer_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id, +int mlx5_esw_bridge_vport_peer_unlink(struct net_device *br_netdev, u16 vport_num, + u16 esw_owner_vhca_id, struct mlx5_esw_bridge_offloads *br_offloads, struct netlink_ext_ack *extack); void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_debugfs.c new file mode 100644 index 000000000000..dbd7cbe6cbf3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_debugfs.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include <linux/debugfs.h> +#include "bridge.h" +#include "bridge_priv.h" + +static void *mlx5_esw_bridge_debugfs_start(struct seq_file *seq, loff_t *pos); +static void *mlx5_esw_bridge_debugfs_next(struct seq_file *seq, void *v, loff_t *pos); +static void mlx5_esw_bridge_debugfs_stop(struct seq_file *seq, void *v); +static int mlx5_esw_bridge_debugfs_show(struct seq_file *seq, void *v); + +static const struct seq_operations mlx5_esw_bridge_debugfs_sops = { + .start = mlx5_esw_bridge_debugfs_start, + .next = mlx5_esw_bridge_debugfs_next, + .stop = mlx5_esw_bridge_debugfs_stop, + .show = mlx5_esw_bridge_debugfs_show, +}; +DEFINE_SEQ_ATTRIBUTE(mlx5_esw_bridge_debugfs); + +static void *mlx5_esw_bridge_debugfs_start(struct seq_file *seq, loff_t *pos) +{ + struct mlx5_esw_bridge *bridge = seq->private; + + rtnl_lock(); + return *pos ? seq_list_start(&bridge->fdb_list, *pos - 1) : SEQ_START_TOKEN; +} + +static void *mlx5_esw_bridge_debugfs_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct mlx5_esw_bridge *bridge = seq->private; + + return seq_list_next(v == SEQ_START_TOKEN ? &bridge->fdb_list : v, &bridge->fdb_list, pos); +} + +static void mlx5_esw_bridge_debugfs_stop(struct seq_file *seq, void *v) +{ + rtnl_unlock(); +} + +static int mlx5_esw_bridge_debugfs_show(struct seq_file *seq, void *v) +{ + struct mlx5_esw_bridge_fdb_entry *entry; + u64 packets, bytes, lastuse; + + if (v == SEQ_START_TOKEN) { + seq_printf(seq, "%-16s %-17s %4s %20s %20s %20s %5s\n", + "DEV", "MAC", "VLAN", "PACKETS", "BYTES", "LASTUSE", "FLAGS"); + return 0; + } + + entry = list_entry(v, struct mlx5_esw_bridge_fdb_entry, list); + mlx5_fc_query_cached_raw(entry->ingress_counter, &bytes, &packets, &lastuse); + seq_printf(seq, "%-16s %-17pM %4d %20llu %20llu %20llu %#5x\n", + entry->dev->name, entry->key.addr, entry->key.vid, packets, bytes, lastuse, + entry->flags); + return 0; +} + +void mlx5_esw_bridge_debugfs_init(struct net_device *br_netdev, struct mlx5_esw_bridge *bridge) +{ + if (!bridge->br_offloads->debugfs_root) + return; + + bridge->debugfs_dir = debugfs_create_dir(br_netdev->name, + bridge->br_offloads->debugfs_root); + debugfs_create_file("fdb", 0400, bridge->debugfs_dir, bridge, + &mlx5_esw_bridge_debugfs_fops); +} + +void mlx5_esw_bridge_debugfs_cleanup(struct mlx5_esw_bridge *bridge) +{ + debugfs_remove_recursive(bridge->debugfs_dir); + bridge->debugfs_dir = NULL; +} + +void mlx5_esw_bridge_debugfs_offloads_init(struct mlx5_esw_bridge_offloads *br_offloads) +{ + if (!br_offloads->esw->debugfs_root) + return; + + br_offloads->debugfs_root = debugfs_create_dir("bridge", br_offloads->esw->debugfs_root); +} + +void mlx5_esw_bridge_debugfs_offloads_cleanup(struct mlx5_esw_bridge_offloads *br_offloads) +{ + debugfs_remove_recursive(br_offloads->debugfs_root); + br_offloads->debugfs_root = NULL; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c index 2eae594a5e80..2455f8b93c1e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c @@ -540,16 +540,29 @@ static struct mlx5_flow_handle * mlx5_esw_bridge_mcast_filter_flow_peer_create(struct mlx5_esw_bridge_port *port) { struct mlx5_devcom *devcom = port->bridge->br_offloads->esw->dev->priv.devcom; + struct mlx5_eswitch *tmp, *peer_esw = NULL; static struct mlx5_flow_handle *handle; - struct mlx5_eswitch *peer_esw; + int i; - peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - if (!peer_esw) + if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) return ERR_PTR(-ENODEV); + mlx5_devcom_for_each_peer_entry(devcom, + MLX5_DEVCOM_ESW_OFFLOADS, + tmp, i) { + if (mlx5_esw_is_owner(tmp, port->vport_num, port->esw_owner_vhca_id)) { + peer_esw = tmp; + break; + } + } + if (!peer_esw) { + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + return ERR_PTR(-ENODEV); + } + handle = mlx5_esw_bridge_mcast_flow_with_esw_create(port, peer_esw); - mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); return handle; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h index c9595801bdb4..4911cc32161b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h @@ -199,6 +199,7 @@ struct mlx5_esw_bridge { int refcnt; struct list_head list; struct mlx5_esw_bridge_offloads *br_offloads; + struct dentry *debugfs_dir; struct list_head fdb_list; struct rhashtable fdb_ht; @@ -241,4 +242,9 @@ void mlx5_esw_bridge_port_mdb_vlan_flush(struct mlx5_esw_bridge_port *port, struct mlx5_esw_bridge_vlan *vlan); void mlx5_esw_bridge_mdb_flush(struct mlx5_esw_bridge *bridge); +void mlx5_esw_bridge_debugfs_offloads_init(struct mlx5_esw_bridge_offloads *br_offloads); +void mlx5_esw_bridge_debugfs_offloads_cleanup(struct mlx5_esw_bridge_offloads *br_offloads); +void mlx5_esw_bridge_debugfs_init(struct net_device *br_netdev, struct mlx5_esw_bridge *bridge); +void mlx5_esw_bridge_debugfs_cleanup(struct mlx5_esw_bridge *bridge); + #endif /* _MLX5_ESW_BRIDGE_PRIVATE_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index 084a910bb4e7..2170539461fa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -18,23 +18,21 @@ static bool mlx5_esw_devlink_port_supported(struct mlx5_eswitch *esw, u16 vport_ { return vport_num == MLX5_VPORT_UPLINK || (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF) || - mlx5_eswitch_is_vf_vport(esw, vport_num); + mlx5_eswitch_is_vf_vport(esw, vport_num) || + mlx5_core_is_ec_vf_vport(esw->dev, vport_num); } -static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 vport_num) +static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *esw, + u16 vport_num, + struct devlink_port *dl_port) { struct mlx5_core_dev *dev = esw->dev; struct devlink_port_attrs attrs = {}; struct netdev_phys_item_id ppid = {}; - struct devlink_port *dl_port; u32 controller_num = 0; bool external; u16 pfnum; - dl_port = kzalloc(sizeof(*dl_port), GFP_KERNEL); - if (!dl_port) - return NULL; - mlx5_esw_get_port_parent_id(dev, &ppid); pfnum = mlx5_get_dev_index(dev); external = mlx5_core_is_ecpf_esw_manager(dev); @@ -56,15 +54,57 @@ static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 dl_port->attrs.switch_id.id_len = ppid.id_len; devlink_port_attrs_pci_vf_set(dl_port, controller_num, pfnum, vport_num - 1, external); + } else if (mlx5_core_is_ec_vf_vport(esw->dev, vport_num)) { + memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len); + dl_port->attrs.switch_id.id_len = ppid.id_len; + devlink_port_attrs_pci_vf_set(dl_port, 0, pfnum, + vport_num - 1, false); } - return dl_port; } -static void mlx5_esw_dl_port_free(struct devlink_port *dl_port) +int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num) +{ + struct devlink_port *dl_port; + struct mlx5_vport *vport; + + if (!mlx5_esw_devlink_port_supported(esw, vport_num)) + return 0; + + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + dl_port = kzalloc(sizeof(*dl_port), GFP_KERNEL); + if (!dl_port) + return -ENOMEM; + + mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(esw, vport_num, dl_port); + + vport->dl_port = dl_port; + return 0; +} + +void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num) { - kfree(dl_port); + struct mlx5_vport *vport; + + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport) || !vport->dl_port) + return; + + kfree(vport->dl_port); + vport->dl_port = NULL; } +static const struct devlink_port_ops mlx5_esw_dl_port_ops = { + .port_fn_hw_addr_get = mlx5_devlink_port_fn_hw_addr_get, + .port_fn_hw_addr_set = mlx5_devlink_port_fn_hw_addr_set, + .port_fn_roce_get = mlx5_devlink_port_fn_roce_get, + .port_fn_roce_set = mlx5_devlink_port_fn_roce_set, + .port_fn_migratable_get = mlx5_devlink_port_fn_migratable_get, + .port_fn_migratable_set = mlx5_devlink_port_fn_migratable_set, +}; + int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num) { struct mlx5_core_dev *dev = esw->dev; @@ -74,34 +114,29 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_ struct devlink *devlink; int err; - if (!mlx5_esw_devlink_port_supported(esw, vport_num)) - return 0; - vport = mlx5_eswitch_get_vport(esw, vport_num); if (IS_ERR(vport)) return PTR_ERR(vport); - dl_port = mlx5_esw_dl_port_alloc(esw, vport_num); + dl_port = vport->dl_port; if (!dl_port) - return -ENOMEM; + return 0; devlink = priv_to_devlink(dev); dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num); - err = devl_port_register(devlink, dl_port, dl_port_index); + err = devl_port_register_with_ops(devlink, dl_port, dl_port_index, + &mlx5_esw_dl_port_ops); if (err) - goto reg_err; + return err; err = devl_rate_leaf_create(dl_port, vport, NULL); if (err) goto rate_err; - vport->dl_port = dl_port; return 0; rate_err: devl_port_unregister(dl_port); -reg_err: - mlx5_esw_dl_port_free(dl_port); return err; } @@ -109,11 +144,8 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vpo { struct mlx5_vport *vport; - if (!mlx5_esw_devlink_port_supported(esw, vport_num)) - return; - vport = mlx5_eswitch_get_vport(esw, vport_num); - if (IS_ERR(vport)) + if (IS_ERR(vport) || !vport->dl_port) return; if (vport->dl_port->devlink_rate) { @@ -122,8 +154,6 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vpo } devl_port_unregister(vport->dl_port); - mlx5_esw_dl_port_free(vport->dl_port); - vport->dl_port = NULL; } struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num) @@ -134,6 +164,20 @@ struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u1 return IS_ERR(vport) ? ERR_CAST(vport) : vport->dl_port; } +static const struct devlink_port_ops mlx5_esw_dl_sf_port_ops = { +#ifdef CONFIG_MLX5_SF_MANAGER + .port_del = mlx5_devlink_sf_port_del, +#endif + .port_fn_hw_addr_get = mlx5_devlink_port_fn_hw_addr_get, + .port_fn_hw_addr_set = mlx5_devlink_port_fn_hw_addr_set, + .port_fn_roce_get = mlx5_devlink_port_fn_roce_get, + .port_fn_roce_set = mlx5_devlink_port_fn_roce_set, +#ifdef CONFIG_MLX5_SF_MANAGER + .port_fn_state_get = mlx5_devlink_sf_port_fn_state_get, + .port_fn_state_set = mlx5_devlink_sf_port_fn_state_set, +#endif +}; + int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_port *dl_port, u16 vport_num, u32 controller, u32 sfnum) { @@ -156,7 +200,8 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p devlink_port_attrs_pci_sf_set(dl_port, controller, pfnum, sfnum, !!controller); devlink = priv_to_devlink(dev); dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num); - err = devl_port_register(devlink, dl_port, dl_port_index); + err = devl_port_register_with_ops(devlink, dl_port, dl_port_index, + &mlx5_esw_dl_sf_port_ops); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c index fabe49a35a5c..255bc8b749f9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c @@ -285,9 +285,8 @@ static int _mlx5_eswitch_set_vepa_locked(struct mlx5_eswitch *esw, if (IS_ERR(flow_rule)) { err = PTR_ERR(flow_rule); goto out; - } else { - esw->fdb_table.legacy.vepa_uplink_rule = flow_rule; } + esw->fdb_table.legacy.vepa_uplink_rule = flow_rule; /* Star rule to forward all traffic to uplink vport */ memset(&dest, 0, sizeof(dest)); @@ -299,9 +298,8 @@ static int _mlx5_eswitch_set_vepa_locked(struct mlx5_eswitch *esw, if (IS_ERR(flow_rule)) { err = PTR_ERR(flow_rule); goto out; - } else { - esw->fdb_table.legacy.vepa_star_rule = flow_rule; } + esw->fdb_table.legacy.vepa_star_rule = flow_rule; out: kvfree(spec); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 901c53751b0a..6e9b1b183190 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -31,6 +31,7 @@ */ #include <linux/etherdevice.h> +#include <linux/debugfs.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/mlx5_ifc.h> #include <linux/mlx5/vport.h> @@ -41,6 +42,7 @@ #include "esw/qos.h" #include "mlx5_core.h" #include "lib/eq.h" +#include "lag/lag.h" #include "eswitch.h" #include "fs_core.h" #include "devlink.h" @@ -92,7 +94,7 @@ mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num) { struct mlx5_vport *vport; - if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager)) + if (!esw) return ERR_PTR(-EPERM); vport = xa_load(&esw->vports, vport_num); @@ -113,7 +115,8 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport, opcode, MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT); MLX5_SET(modify_nic_vport_context_in, in, field_select.change_event, 1); MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport); - MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1); + if (vport || mlx5_core_is_ecpf(dev)) + MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1); nic_vport_ctx = MLX5_ADDR_OF(modify_nic_vport_context_in, in, nic_vport_context); @@ -309,11 +312,12 @@ static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) fdb_add: /* SRIOV is enabled: Forward UC MAC to vport */ - if (esw->fdb_table.legacy.fdb && esw->mode == MLX5_ESWITCH_LEGACY) + if (esw->fdb_table.legacy.fdb && esw->mode == MLX5_ESWITCH_LEGACY) { vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, vport); - esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM fr(%p)\n", - vport, mac, vaddr->flow_rule); + esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM fr(%p)\n", + vport, mac, vaddr->flow_rule); + } return 0; } @@ -710,6 +714,9 @@ void esw_vport_change_handle_locked(struct mlx5_vport *vport) struct mlx5_eswitch *esw = dev->priv.eswitch; u8 mac[ETH_ALEN]; + if (!MLX5_CAP_GEN(dev, log_max_l2_table)) + return; + mlx5_query_nic_vport_mac_address(dev, vport->vport, true, mac); esw_debug(dev, "vport[%d] Context Changed: perm mac: %pM\n", vport->vport, mac); @@ -800,6 +807,9 @@ static int mlx5_esw_vport_caps_get(struct mlx5_eswitch *esw, struct mlx5_vport * hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability); vport->info.roce_enabled = MLX5_GET(cmd_hca_cap, hca_caps, roce); + if (!MLX5_CAP_GEN_MAX(esw->dev, hca_cap_2)) + goto out_free; + memset(query_ctx, 0, query_out_sz); err = mlx5_vport_get_other_func_cap(esw->dev, vport->vport, query_ctx, MLX5_CAP_GENERAL_2); @@ -946,7 +956,8 @@ void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, u16 vport_num) vport->enabled = false; /* Disable events from this vport */ - arm_vport_context_events_cmd(esw->dev, vport->vport, 0); + if (MLX5_CAP_GEN(esw->dev, log_max_l2_table)) + arm_vport_context_events_cmd(esw->dev, vport->vport, 0); if (!mlx5_esw_is_manager_vport(esw, vport->vport) && MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) @@ -1045,6 +1056,18 @@ static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw) } } +static void mlx5_eswitch_clear_ec_vf_vports_info(struct mlx5_eswitch *esw) +{ + struct mlx5_vport *vport; + unsigned long i; + + mlx5_esw_for_each_ec_vf_vport(esw, i, vport, esw->esw_funcs.num_ec_vfs) { + memset(&vport->qos, 0, sizeof(vport->qos)); + memset(&vport->info, 0, sizeof(vport->info)); + vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; + } +} + /* Public E-Switch API */ int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num, enum mlx5_eswitch_vport_event enabled_events) @@ -1055,7 +1078,7 @@ int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num, if (err) return err; - err = esw_offloads_load_rep(esw, vport_num); + err = mlx5_esw_offloads_load_rep(esw, vport_num); if (err) goto err_rep; @@ -1068,10 +1091,35 @@ err_rep: void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num) { - esw_offloads_unload_rep(esw, vport_num); + mlx5_esw_offloads_unload_rep(esw, vport_num); mlx5_esw_vport_disable(esw, vport_num); } +static int mlx5_eswitch_load_pf_vf_vport(struct mlx5_eswitch *esw, u16 vport_num, + enum mlx5_eswitch_vport_event enabled_events) +{ + int err; + + err = mlx5_esw_offloads_init_pf_vf_rep(esw, vport_num); + if (err) + return err; + + err = mlx5_eswitch_load_vport(esw, vport_num, enabled_events); + if (err) + goto err_load; + return 0; + +err_load: + mlx5_esw_offloads_cleanup_pf_vf_rep(esw, vport_num); + return err; +} + +static void mlx5_eswitch_unload_pf_vf_vport(struct mlx5_eswitch *esw, u16 vport_num) +{ + mlx5_eswitch_unload_vport(esw, vport_num); + mlx5_esw_offloads_cleanup_pf_vf_rep(esw, vport_num); +} + void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs) { struct mlx5_vport *vport; @@ -1080,7 +1128,20 @@ void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs) mlx5_esw_for_each_vf_vport(esw, i, vport, num_vfs) { if (!vport->enabled) continue; - mlx5_eswitch_unload_vport(esw, vport->vport); + mlx5_eswitch_unload_pf_vf_vport(esw, vport->vport); + } +} + +static void mlx5_eswitch_unload_ec_vf_vports(struct mlx5_eswitch *esw, + u16 num_ec_vfs) +{ + struct mlx5_vport *vport; + unsigned long i; + + mlx5_esw_for_each_ec_vf_vport(esw, i, vport, num_ec_vfs) { + if (!vport->enabled) + continue; + mlx5_eswitch_unload_pf_vf_vport(esw, vport->vport); } } @@ -1092,7 +1153,7 @@ int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs, int err; mlx5_esw_for_each_vf_vport(esw, i, vport, num_vfs) { - err = mlx5_eswitch_load_vport(esw, vport->vport, enabled_events); + err = mlx5_eswitch_load_pf_vf_vport(esw, vport->vport, enabled_events); if (err) goto vf_err; } @@ -1104,6 +1165,26 @@ vf_err: return err; } +static int mlx5_eswitch_load_ec_vf_vports(struct mlx5_eswitch *esw, u16 num_ec_vfs, + enum mlx5_eswitch_vport_event enabled_events) +{ + struct mlx5_vport *vport; + unsigned long i; + int err; + + mlx5_esw_for_each_ec_vf_vport(esw, i, vport, num_ec_vfs) { + err = mlx5_eswitch_load_pf_vf_vport(esw, vport->vport, enabled_events); + if (err) + goto vf_err; + } + + return 0; + +vf_err: + mlx5_eswitch_unload_ec_vf_vports(esw, num_ec_vfs); + return err; +} + static int host_pf_enable_hca(struct mlx5_core_dev *dev) { if (!mlx5_core_is_ecpf(dev)) @@ -1131,12 +1212,19 @@ int mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, enum mlx5_eswitch_vport_event enabled_events) { + bool pf_needed; int ret; + pf_needed = mlx5_core_is_ecpf_esw_manager(esw->dev) || + esw->mode == MLX5_ESWITCH_LEGACY; + /* Enable PF vport */ - ret = mlx5_eswitch_load_vport(esw, MLX5_VPORT_PF, enabled_events); - if (ret) - return ret; + if (pf_needed) { + ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_PF, + enabled_events); + if (ret) + return ret; + } /* Enable external host PF HCA */ ret = host_pf_enable_hca(esw->dev); @@ -1145,9 +1233,15 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, /* Enable ECPF vport */ if (mlx5_ecpf_vport_exists(esw->dev)) { - ret = mlx5_eswitch_load_vport(esw, MLX5_VPORT_ECPF, enabled_events); + ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_ECPF, enabled_events); if (ret) goto ecpf_err; + if (mlx5_core_ec_sriov_enabled(esw->dev)) { + ret = mlx5_eswitch_load_ec_vf_vports(esw, esw->esw_funcs.num_ec_vfs, + enabled_events); + if (ret) + goto ec_vf_err; + } } /* Enable VF vports */ @@ -1158,12 +1252,16 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, return 0; vf_err: + if (mlx5_core_ec_sriov_enabled(esw->dev)) + mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_ec_vfs); +ec_vf_err: if (mlx5_ecpf_vport_exists(esw->dev)) - mlx5_eswitch_unload_vport(esw, MLX5_VPORT_ECPF); + mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF); ecpf_err: host_pf_disable_hca(esw->dev); pf_hca_err: - mlx5_eswitch_unload_vport(esw, MLX5_VPORT_PF); + if (pf_needed) + mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_PF); return ret; } @@ -1174,11 +1272,17 @@ void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw) { mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs); - if (mlx5_ecpf_vport_exists(esw->dev)) - mlx5_eswitch_unload_vport(esw, MLX5_VPORT_ECPF); + if (mlx5_ecpf_vport_exists(esw->dev)) { + if (mlx5_core_ec_sriov_enabled(esw->dev)) + mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_vfs); + mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF); + } host_pf_disable_hca(esw->dev); - mlx5_eswitch_unload_vport(esw, MLX5_VPORT_PF); + + if (mlx5_core_is_ecpf_esw_manager(esw->dev) || + esw->mode == MLX5_ESWITCH_LEGACY) + mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_PF); } static void mlx5_eswitch_get_devlink_param(struct mlx5_eswitch *esw) @@ -1219,6 +1323,9 @@ mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, int num_vfs) esw->esw_funcs.num_vfs = MLX5_GET(query_esw_functions_out, out, host_params_context.host_num_of_vfs); + if (mlx5_core_ec_sriov_enabled(esw->dev)) + esw->esw_funcs.num_ec_vfs = num_vfs; + kvfree(out); } @@ -1326,9 +1433,9 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs) mlx5_eswitch_event_handlers_register(esw); - esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), active vports(%d)\n", + esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n", esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", - esw->esw_funcs.num_vfs, esw->enabled_vports); + esw->esw_funcs.num_vfs, esw->esw_funcs.num_ec_vfs, esw->enabled_vports); mlx5_esw_mode_change_notify(esw, esw->mode); @@ -1350,7 +1457,7 @@ abort: int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) { bool toggle_lag; - int ret; + int ret = 0; if (!mlx5_esw_allowed(esw)) return 0; @@ -1370,10 +1477,21 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) vport_events = (esw->mode == MLX5_ESWITCH_LEGACY) ? MLX5_LEGACY_SRIOV_VPORT_EVENTS : MLX5_VPORT_UC_ADDR_CHANGE; - ret = mlx5_eswitch_load_vf_vports(esw, num_vfs, vport_events); - if (!ret) - esw->esw_funcs.num_vfs = num_vfs; + /* If this is the ECPF the number of host VFs is managed via the + * eswitch function change event handler, and any num_vfs provided + * here are intended to be EC VFs. + */ + if (!mlx5_core_is_ecpf(esw->dev)) { + ret = mlx5_eswitch_load_vf_vports(esw, num_vfs, vport_events); + if (!ret) + esw->esw_funcs.num_vfs = num_vfs; + } else if (mlx5_core_ec_sriov_enabled(esw->dev)) { + ret = mlx5_eswitch_load_ec_vf_vports(esw, num_vfs, vport_events); + if (!ret) + esw->esw_funcs.num_ec_vfs = num_vfs; + } } + up_write(&esw->mode_lock); if (toggle_lag) @@ -1393,16 +1511,22 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) /* If driver is unloaded, this function is called twice by remove_one() * and mlx5_unload(). Prevent the second call. */ - if (!esw->esw_funcs.num_vfs && !clear_vf) + if (!esw->esw_funcs.num_vfs && !esw->esw_funcs.num_ec_vfs && !clear_vf) goto unlock; - esw_info(esw->dev, "Unload vfs: mode(%s), nvfs(%d), active vports(%d)\n", + esw_info(esw->dev, "Unload vfs: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n", esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", - esw->esw_funcs.num_vfs, esw->enabled_vports); - - mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs); - if (clear_vf) - mlx5_eswitch_clear_vf_vports_info(esw); + esw->esw_funcs.num_vfs, esw->esw_funcs.num_ec_vfs, esw->enabled_vports); + + if (!mlx5_core_is_ecpf(esw->dev)) { + mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs); + if (clear_vf) + mlx5_eswitch_clear_vf_vports_info(esw); + } else if (mlx5_core_ec_sriov_enabled(esw->dev)) { + mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_ec_vfs); + if (clear_vf) + mlx5_eswitch_clear_ec_vf_vports_info(esw); + } if (esw->mode == MLX5_ESWITCH_OFFLOADS) { struct devlink *devlink = priv_to_devlink(esw->dev); @@ -1413,7 +1537,10 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) if (esw->mode == MLX5_ESWITCH_LEGACY) mlx5_eswitch_disable_locked(esw); - esw->esw_funcs.num_vfs = 0; + if (!mlx5_core_is_ecpf(esw->dev)) + esw->esw_funcs.num_vfs = 0; + else + esw->esw_funcs.num_ec_vfs = 0; unlock: up_write(&esw->mode_lock); @@ -1433,9 +1560,9 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw) mlx5_eswitch_event_handlers_unregister(esw); - esw_info(esw->dev, "Disable: mode(%s), nvfs(%d), active vports(%d)\n", + esw_info(esw->dev, "Disable: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n", esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", - esw->esw_funcs.num_vfs, esw->enabled_vports); + esw->esw_funcs.num_vfs, esw->esw_funcs.num_ec_vfs, esw->enabled_vports); if (esw->fdb_table.flags & MLX5_ESW_FDB_CREATED) { esw->fdb_table.flags &= ~MLX5_ESW_FDB_CREATED; @@ -1595,7 +1722,19 @@ static int mlx5_esw_vports_init(struct mlx5_eswitch *esw) idx++; } - if (mlx5_ecpf_vport_exists(dev)) { + if (mlx5_core_ec_sriov_enabled(esw->dev)) { + int ec_vf_base_num = mlx5_core_ec_vf_vport_base(dev); + + for (i = 0; i < mlx5_core_max_ec_vfs(esw->dev); i++) { + err = mlx5_esw_vport_alloc(esw, idx, ec_vf_base_num + i); + if (err) + goto err; + idx++; + } + } + + if (mlx5_ecpf_vport_exists(dev) || + mlx5_core_is_ecpf_esw_manager(dev)) { err = mlx5_esw_vport_alloc(esw, idx, MLX5_VPORT_ECPF); if (err) goto err; @@ -1611,22 +1750,60 @@ err: return err; } +static int mlx5_devlink_esw_multiport_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + + if (!MLX5_ESWITCH_MANAGER(dev)) + return -EOPNOTSUPP; + + if (ctx->val.vbool) + return mlx5_lag_mpesw_enable(dev); + + mlx5_lag_mpesw_disable(dev); + return 0; +} + +static int mlx5_devlink_esw_multiport_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + + ctx->val.vbool = mlx5_lag_is_mpesw(dev); + return 0; +} + +static const struct devlink_param mlx5_eswitch_params[] = { + DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_ESW_MULTIPORT, + "esw_multiport", DEVLINK_PARAM_TYPE_BOOL, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + mlx5_devlink_esw_multiport_get, + mlx5_devlink_esw_multiport_set, NULL), +}; + int mlx5_eswitch_init(struct mlx5_core_dev *dev) { struct mlx5_eswitch *esw; int err; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_VPORT_MANAGER(dev) && !MLX5_ESWITCH_MANAGER(dev)) return 0; esw = kzalloc(sizeof(*esw), GFP_KERNEL); if (!esw) return -ENOMEM; + err = devl_params_register(priv_to_devlink(dev), mlx5_eswitch_params, + ARRAY_SIZE(mlx5_eswitch_params)); + if (err) + goto free_esw; + esw->dev = dev; esw->manager_vport = mlx5_eswitch_manager_vport(dev); esw->first_host_vport = mlx5_eswitch_first_host_vport_num(dev); + esw->debugfs_root = debugfs_create_dir("esw", mlx5_debugfs_get_dev_root(dev)); esw->work_queue = create_singlethread_workqueue("mlx5_esw_wq"); if (!esw->work_queue) { err = -ENOMEM; @@ -1680,13 +1857,17 @@ reps_err: abort: if (esw->work_queue) destroy_workqueue(esw->work_queue); + debugfs_remove_recursive(esw->debugfs_root); + devl_params_unregister(priv_to_devlink(dev), mlx5_eswitch_params, + ARRAY_SIZE(mlx5_eswitch_params)); +free_esw: kfree(esw); return err; } void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) { - if (!esw || !MLX5_VPORT_MANAGER(esw->dev)) + if (!esw) return; esw_info(esw->dev, "cleanup\n"); @@ -1703,6 +1884,9 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) mutex_destroy(&esw->offloads.decap_tbl_lock); esw_offloads_cleanup(esw); mlx5_esw_vports_cleanup(esw); + debugfs_remove_recursive(esw->debugfs_root); + devl_params_unregister(priv_to_devlink(esw->dev), mlx5_eswitch_params, + ARRAY_SIZE(mlx5_eswitch_params)); kfree(esw); } @@ -1763,12 +1947,6 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, static bool mlx5_esw_check_port_type(struct mlx5_eswitch *esw, u16 vport_num, xa_mark_t mark) { - struct mlx5_vport *vport; - - vport = mlx5_eswitch_get_vport(esw, vport_num); - if (IS_ERR(vport)) - return false; - return xa_get_mark(&esw->vports, vport_num, mark); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index add6cfa432a5..56d9a261a5c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -123,8 +123,14 @@ struct vport_ingress { } offloads; }; +enum vport_egress_acl_type { + VPORT_EGRESS_ACL_TYPE_DEFAULT, + VPORT_EGRESS_ACL_TYPE_SHARED_FDB, +}; + struct vport_egress { struct mlx5_flow_table *acl; + enum vport_egress_acl_type type; struct mlx5_flow_handle *allowed_vlan; struct mlx5_flow_group *vlan_grp; union { @@ -136,7 +142,7 @@ struct vport_egress { struct { struct mlx5_flow_group *fwd_grp; struct mlx5_flow_handle *fwd_rule; - struct mlx5_flow_handle *bounce_rule; + struct xarray bounce_rules; struct mlx5_flow_group *bounce_grp; } offloads; }; @@ -218,7 +224,7 @@ struct mlx5_eswitch_fdb { struct mlx5_flow_group *send_to_vport_grp; struct mlx5_flow_group *send_to_vport_meta_grp; struct mlx5_flow_group *peer_miss_grp; - struct mlx5_flow_handle **peer_miss_rules; + struct mlx5_flow_handle **peer_miss_rules[MLX5_MAX_PORTS]; struct mlx5_flow_group *miss_grp; struct mlx5_flow_handle **send_to_vport_meta_rules; struct mlx5_flow_handle *miss_rule_uni; @@ -249,7 +255,7 @@ struct mlx5_esw_offload { struct mlx5_flow_group *vport_rx_drop_group; struct mlx5_flow_handle *vport_rx_drop_rule; struct xarray vport_reps; - struct list_head peer_flows; + struct list_head peer_flows[MLX5_MAX_PORTS]; struct mutex peer_mutex; struct mutex encap_tbl_lock; /* protects encap_tbl */ DECLARE_HASHTABLE(encap_tbl, 8); @@ -283,6 +289,7 @@ struct mlx5_host_work { struct mlx5_esw_functions { struct mlx5_nb nb; u16 num_vfs; + u16 num_ec_vfs; }; enum { @@ -297,6 +304,8 @@ enum { MLX5_ESW_FDB_CREATED = BIT(0), }; +struct dentry; + struct mlx5_eswitch { struct mlx5_core_dev *dev; struct mlx5_nb nb; @@ -305,6 +314,7 @@ struct mlx5_eswitch { struct hlist_head mc_table[MLX5_L2_ADDR_HASH_SIZE]; struct esw_mc_addr mc_promisc; /* end of legacy */ + struct dentry *debugfs_root; struct workqueue_struct *work_queue; struct xarray vports; u32 flags; @@ -337,12 +347,13 @@ struct mlx5_eswitch { int mode; u16 manager_vport; u16 first_host_vport; + u8 num_peers; struct mlx5_esw_functions esw_funcs; struct { u32 large_group_num; } params; struct blocking_notifier_head n_head; - bool paired[MLX5_MAX_PORTS]; + struct xarray paired; }; void esw_offloads_disable(struct mlx5_eswitch *esw); @@ -506,12 +517,12 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, struct netlink_ext_ack *extack); int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, enum devlink_eswitch_encap_mode *encap); -int mlx5_devlink_port_function_hw_addr_get(struct devlink_port *port, - u8 *hw_addr, int *hw_addr_len, - struct netlink_ext_ack *extack); -int mlx5_devlink_port_function_hw_addr_set(struct devlink_port *port, - const u8 *hw_addr, int hw_addr_len, - struct netlink_ext_ack *extack); +int mlx5_devlink_port_fn_hw_addr_get(struct devlink_port *port, + u8 *hw_addr, int *hw_addr_len, + struct netlink_ext_ack *extack); +int mlx5_devlink_port_fn_hw_addr_set(struct devlink_port *port, + const u8 *hw_addr, int hw_addr_len, + struct netlink_ext_ack *extack); int mlx5_devlink_port_fn_roce_get(struct devlink_port *port, bool *is_enabled, struct netlink_ext_ack *extack); int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable, @@ -578,6 +589,13 @@ mlx5_esw_is_manager_vport(const struct mlx5_eswitch *esw, u16 vport_num) return esw->manager_vport == vport_num; } +static inline bool mlx5_esw_is_owner(struct mlx5_eswitch *esw, u16 vport_num, + u16 esw_owner_vhca_id) +{ + return esw_owner_vhca_id == MLX5_CAP_GEN(esw->dev, vhca_id) || + (vport_num == MLX5_VPORT_UPLINK && mlx5_lag_is_master(esw->dev)); +} + static inline u16 mlx5_eswitch_first_host_vport_num(struct mlx5_core_dev *dev) { return mlx5_core_is_ecpf_esw_manager(dev) ? @@ -640,6 +658,19 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw); #define mlx5_esw_for_each_host_func_vport(esw, index, vport, last) \ mlx5_esw_for_each_vport_marked(esw, index, vport, last, MLX5_ESW_VPT_HOST_FN) +/* This macro should only be used if EC SRIOV is enabled. + * + * Because there were no more marks available on the xarray this uses a + * for_each_range approach. The range is only valid when EC SRIOV is enabled + */ +#define mlx5_esw_for_each_ec_vf_vport(esw, index, vport, last) \ + xa_for_each_range(&((esw)->vports), \ + index, \ + vport, \ + MLX5_CAP_GEN_2((esw->dev), ec_vf_vport_base), \ + MLX5_CAP_GEN_2((esw->dev), ec_vf_vport_base) +\ + (last) - 1) + struct mlx5_eswitch *mlx5_devlink_eswitch_get(struct devlink *devlink); struct mlx5_vport *__must_check mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num); @@ -686,8 +717,18 @@ mlx5_esw_vporttbl_put(struct mlx5_eswitch *esw, struct mlx5_vport_tbl_attr *attr struct mlx5_flow_handle * esw_add_restore_rule(struct mlx5_eswitch *esw, u32 tag); -int esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num); -void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num); +void mlx5_esw_set_flow_group_source_port(struct mlx5_eswitch *esw, + u32 *flow_group_in, + int match_params); + +void mlx5_esw_set_spec_source_port(struct mlx5_eswitch *esw, + u16 vport, + struct mlx5_flow_spec *spec); + +int mlx5_esw_offloads_init_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num); +void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num); +int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num); +void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num); int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num); void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num); @@ -700,6 +741,8 @@ int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs, enum mlx5_eswitch_vport_event enabled_events); void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs); +int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num); +void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num); int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num); void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vport_num); struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num); @@ -740,9 +783,9 @@ 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_config_single_fdb(struct mlx5_eswitch *master_esw, - struct mlx5_eswitch *slave_esw); -void mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_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_reps(struct mlx5_eswitch *esw); @@ -757,6 +800,13 @@ static inline int mlx5_eswitch_num_vfs(struct mlx5_eswitch *esw) return 0; } +static inline int mlx5_eswitch_get_npeers(struct mlx5_eswitch *esw) +{ + if (mlx5_esw_allowed(esw)) + return esw->num_peers; + return 0; +} + static inline struct mlx5_flow_table * mlx5_eswitch_get_slow_fdb(struct mlx5_eswitch *esw) { @@ -794,16 +844,18 @@ mlx5_esw_vport_to_devlink_port_index(const struct mlx5_core_dev *dev, } static inline int -mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw, - struct mlx5_eswitch *slave_esw) +mlx5_eswitch_offloads_single_fdb_add_one(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw, int max_slaves) { return 0; } static inline void -mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw, +mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw, struct mlx5_eswitch *slave_esw) {} +static inline int mlx5_eswitch_get_npeers(struct mlx5_eswitch *esw) { return 0; } + static inline int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 8d19c20d3447..1ad5a72dcc3f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -55,13 +55,6 @@ #define mlx5_esw_for_each_rep(esw, i, rep) \ xa_for_each(&((esw)->offloads.vport_reps), i, rep) -#define mlx5_esw_for_each_sf_rep(esw, i, rep) \ - xa_for_each_marked(&((esw)->offloads.vport_reps), i, rep, MLX5_ESW_VPT_SF) - -#define mlx5_esw_for_each_vf_rep(esw, index, rep) \ - mlx5_esw_for_each_entry_marked(&((esw)->offloads.vport_reps), index, \ - rep, (esw)->esw_funcs.num_vfs, MLX5_ESW_VPT_VF) - /* There are two match-all miss flows, one for unicast dst mac and * one for multicast. */ @@ -838,6 +831,7 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, struct mlx5_flow_handle *flow_rule; struct mlx5_flow_spec *spec; void *misc; + u16 vport; spec = kvzalloc(sizeof(*spec), GFP_KERNEL); if (!spec) { @@ -847,20 +841,43 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn); - /* source vport is the esw manager */ - MLX5_SET(fte_match_set_misc, misc, source_port, from_esw->manager_vport); - if (MLX5_CAP_ESW(on_esw->dev, merged_eswitch)) - MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id, - MLX5_CAP_GEN(from_esw->dev, vhca_id)); misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn); - MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); - if (MLX5_CAP_ESW(on_esw->dev, merged_eswitch)) - MLX5_SET_TO_ONES(fte_match_set_misc, misc, - source_eswitch_owner_vhca_id); spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; + + /* source vport is the esw manager */ + vport = from_esw->manager_vport; + + if (mlx5_eswitch_vport_match_metadata_enabled(on_esw)) { + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2); + MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_for_match(from_esw, vport)); + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2); + MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2; + } else { + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); + MLX5_SET(fte_match_set_misc, misc, source_port, vport); + + if (MLX5_CAP_ESW(on_esw->dev, merged_eswitch)) + MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id, + MLX5_CAP_GEN(from_esw->dev, vhca_id)); + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); + MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); + + if (MLX5_CAP_ESW(on_esw->dev, merged_eswitch)) + MLX5_SET_TO_ONES(fte_match_set_misc, misc, + source_eswitch_owner_vhca_id); + + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; + } + dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; dest.vport.num = rep->vport; dest.vport.vhca_id = MLX5_CAP_GEN(rep->esw->dev, vhca_id); @@ -1052,6 +1069,9 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, void *misc; int err; + if (!MLX5_VPORT_MANAGER(esw->dev) && !mlx5_core_is_ecpf_esw_manager(esw->dev)) + return 0; + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); if (!spec) return -ENOMEM; @@ -1108,11 +1128,32 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, flows[vport->index] = flow; } - esw->fdb_table.offloads.peer_miss_rules = flows; + if (mlx5_core_ec_sriov_enabled(esw->dev)) { + mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) { + if (i >= mlx5_core_max_ec_vfs(peer_dev)) + break; + esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch, + spec, vport->vport); + flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, + spec, &flow_act, &dest, 1); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto add_ec_vf_flow_err; + } + flows[vport->index] = flow; + } + } + esw->fdb_table.offloads.peer_miss_rules[mlx5_get_dev_index(peer_dev)] = flows; kvfree(spec); return 0; +add_ec_vf_flow_err: + mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) { + if (!flows[vport->index]) + continue; + mlx5_del_flow_rules(flows[vport->index]); + } add_vf_flow_err: mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) { if (!flows[vport->index]) @@ -1136,13 +1177,28 @@ alloc_flows_err: return err; } -static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw) +static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw, + struct mlx5_core_dev *peer_dev) { + u16 peer_index = mlx5_get_dev_index(peer_dev); struct mlx5_flow_handle **flows; struct mlx5_vport *vport; unsigned long i; - flows = esw->fdb_table.offloads.peer_miss_rules; + flows = esw->fdb_table.offloads.peer_miss_rules[peer_index]; + if (!flows) + return; + + if (mlx5_core_ec_sriov_enabled(esw->dev)) { + mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) { + /* The flow for a particular vport could be NULL if the other ECPF + * has fewer or no VFs enabled + */ + if (!flows[vport->index]) + continue; + mlx5_del_flow_rules(flows[vport->index]); + } + } mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) mlx5_del_flow_rules(flows[vport->index]); @@ -1156,7 +1212,9 @@ static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw) vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); mlx5_del_flow_rules(flows[vport->index]); } + kvfree(flows); + esw->fdb_table.offloads.peer_miss_rules[peer_index] = NULL; } static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw) @@ -1269,8 +1327,10 @@ esw_add_restore_rule(struct mlx5_eswitch *esw, u32 tag) #define MAX_PF_SQ 256 #define MAX_SQ_NVPORTS 32 -static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw, - u32 *flow_group_in) +void +mlx5_esw_set_flow_group_source_port(struct mlx5_eswitch *esw, + u32 *flow_group_in, + int match_params) { void *match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, @@ -1279,7 +1339,7 @@ static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw, if (mlx5_eswitch_vport_match_metadata_enabled(esw)) { MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, - MLX5_MATCH_MISC_PARAMETERS_2); + MLX5_MATCH_MISC_PARAMETERS_2 | match_params); MLX5_SET(fte_match_param, match_criteria, misc_parameters_2.metadata_reg_c_0, @@ -1287,7 +1347,7 @@ static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw, } else { MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, - MLX5_MATCH_MISC_PARAMETERS); + MLX5_MATCH_MISC_PARAMETERS | match_params); MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_port); @@ -1376,7 +1436,6 @@ esw_chains_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *miss_fdb) esw_init_chains_offload_flags(esw, &attr.flags); attr.ns = MLX5_FLOW_NAMESPACE_FDB; - attr.fs_base_prio = FDB_TC_OFFLOAD; attr.max_grp_num = esw->params.large_group_num; attr.default_ft = miss_fdb; attr.mapping = esw->offloads.reg_c0_obj_pool; @@ -1463,14 +1522,13 @@ esw_create_send_to_vport_group(struct mlx5_eswitch *esw, memset(flow_group_in, 0, inlen); - MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, - MLX5_MATCH_MISC_PARAMETERS); + mlx5_esw_set_flow_group_source_port(esw, flow_group_in, MLX5_MATCH_MISC_PARAMETERS); match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria); - MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_sqn); - MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_port); - if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) { + + if (!mlx5_eswitch_vport_match_metadata_enabled(esw) && + MLX5_CAP_ESW(esw->dev, merged_eswitch)) { MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_eswitch_owner_vhca_id); MLX5_SET(create_flow_group_in, flow_group_in, @@ -1548,6 +1606,7 @@ esw_create_peer_esw_miss_group(struct mlx5_eswitch *esw, u32 *flow_group_in, int *ix) { + int max_peer_ports = (esw->total_vports - 1) * (MLX5_MAX_PORTS - 1); int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5_flow_group *g; void *match_criteria; @@ -1558,7 +1617,7 @@ esw_create_peer_esw_miss_group(struct mlx5_eswitch *esw, memset(flow_group_in, 0, inlen); - esw_set_flow_group_source_port(esw, flow_group_in); + mlx5_esw_set_flow_group_source_port(esw, flow_group_in, 0); if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) { match_criteria = MLX5_ADDR_OF(create_flow_group_in, @@ -1574,8 +1633,8 @@ esw_create_peer_esw_miss_group(struct mlx5_eswitch *esw, MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, *ix); MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, - *ix + esw->total_vports - 1); - *ix += esw->total_vports; + *ix + max_peer_ports); + *ix += max_peer_ports + 1; g = mlx5_create_flow_group(fdb, flow_group_in); if (IS_ERR(g)) { @@ -1677,7 +1736,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) * total vports of the peer (currently is also uses esw->total_vports). */ table_size = MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ) + - esw->total_vports * 2 + MLX5_ESW_MISS_FLOWS; + esw->total_vports * MLX5_MAX_PORTS + MLX5_ESW_MISS_FLOWS; /* create the slow path fdb with encap set, so further table instances * can be created at run time while VFs are probed if the FW allows that. @@ -1844,8 +1903,7 @@ static int esw_create_vport_rx_group(struct mlx5_eswitch *esw) if (!flow_group_in) return -ENOMEM; - /* create vport rx group */ - esw_set_flow_group_source_port(esw, flow_group_in); + mlx5_esw_set_flow_group_source_port(esw, flow_group_in, 0); MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, nvports - 1); @@ -1915,21 +1973,13 @@ static void esw_destroy_vport_rx_drop_group(struct mlx5_eswitch *esw) mlx5_destroy_flow_group(esw->offloads.vport_rx_drop_group); } -struct mlx5_flow_handle * -mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, u16 vport, - struct mlx5_flow_destination *dest) +void +mlx5_esw_set_spec_source_port(struct mlx5_eswitch *esw, + u16 vport, + struct mlx5_flow_spec *spec) { - struct mlx5_flow_act flow_act = {0}; - struct mlx5_flow_handle *flow_rule; - struct mlx5_flow_spec *spec; void *misc; - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) { - flow_rule = ERR_PTR(-ENOMEM); - goto out; - } - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) { misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2); MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0, @@ -1949,6 +1999,23 @@ mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, u16 vport, spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; } +} + +struct mlx5_flow_handle * +mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, u16 vport, + struct mlx5_flow_destination *dest) +{ + struct mlx5_flow_act flow_act = {0}; + struct mlx5_flow_handle *flow_rule; + struct mlx5_flow_spec *spec; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) { + flow_rule = ERR_PTR(-ENOMEM); + goto out; + } + + mlx5_esw_set_spec_source_port(esw, vport, spec); flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec, @@ -2142,6 +2209,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw, "Failed setting eswitch to offloads"); esw->mode = MLX5_ESWITCH_LEGACY; mlx5_rescan_drivers(esw->dev); + return err; } if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) { if (mlx5_eswitch_inline_mode_get(esw, @@ -2151,19 +2219,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw, "Inline mode is different between vports"); } } - return err; -} - -static void mlx5_esw_offloads_rep_mark_set(struct mlx5_eswitch *esw, - struct mlx5_eswitch_rep *rep, - xa_mark_t mark) -{ - bool mark_set; - - /* Copy the mark from vport to its rep */ - mark_set = xa_get_mark(&esw->vports, rep->vport, mark); - if (mark_set) - xa_set_mark(&esw->offloads.vport_reps, rep->vport, mark); + return 0; } static int mlx5_esw_offloads_rep_init(struct mlx5_eswitch *esw, const struct mlx5_vport *vport) @@ -2185,9 +2241,6 @@ static int mlx5_esw_offloads_rep_init(struct mlx5_eswitch *esw, const struct mlx if (err) goto insert_err; - mlx5_esw_offloads_rep_mark_set(esw, rep, MLX5_ESW_VPT_HOST_FN); - mlx5_esw_offloads_rep_mark_set(esw, rep, MLX5_ESW_VPT_VF); - mlx5_esw_offloads_rep_mark_set(esw, rep, MLX5_ESW_VPT_SF); return 0; insert_err: @@ -2328,37 +2381,13 @@ static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw, esw->offloads.rep_ops[rep_type]->unload(rep); } -static void __unload_reps_sf_vport(struct mlx5_eswitch *esw, u8 rep_type) -{ - struct mlx5_eswitch_rep *rep; - unsigned long i; - - mlx5_esw_for_each_sf_rep(esw, i, rep) - __esw_offloads_unload_rep(esw, rep, rep_type); -} - static void __unload_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type) { struct mlx5_eswitch_rep *rep; unsigned long i; - __unload_reps_sf_vport(esw, rep_type); - - mlx5_esw_for_each_vf_rep(esw, i, rep) - __esw_offloads_unload_rep(esw, rep, rep_type); - - if (mlx5_ecpf_vport_exists(esw->dev)) { - rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF); - __esw_offloads_unload_rep(esw, rep, rep_type); - } - - if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { - rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF); + mlx5_esw_for_each_rep(esw, i, rep) __esw_offloads_unload_rep(esw, rep, rep_type); - } - - rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK); - __esw_offloads_unload_rep(esw, rep, rep_type); } int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num) @@ -2395,7 +2424,23 @@ void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num) __esw_offloads_unload_rep(esw, rep, rep_type); } -int esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num) +int mlx5_esw_offloads_init_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num) +{ + if (esw->mode != MLX5_ESWITCH_OFFLOADS) + return 0; + + return mlx5_esw_offloads_pf_vf_devlink_port_init(esw, vport_num); +} + +void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num) +{ + if (esw->mode != MLX5_ESWITCH_OFFLOADS) + return; + + mlx5_esw_offloads_pf_vf_devlink_port_cleanup(esw, vport_num); +} + +int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num) { int err; @@ -2419,7 +2464,7 @@ load_err: return err; } -void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num) +void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num) { if (esw->mode != MLX5_ESWITCH_OFFLOADS) return; @@ -2476,6 +2521,7 @@ static int __esw_set_master_egress_rule(struct mlx5_core_dev *master, struct mlx5_vport *vport, struct mlx5_flow_table *acl) { + u16 slave_index = MLX5_CAP_GEN(slave, vhca_id); struct mlx5_flow_handle *flow_rule = NULL; struct mlx5_flow_destination dest = {}; struct mlx5_flow_act flow_act = {}; @@ -2491,8 +2537,7 @@ static int __esw_set_master_egress_rule(struct mlx5_core_dev *master, misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_UPLINK); - MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id, - MLX5_CAP_GEN(slave, vhca_id)); + MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id, slave_index); misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); @@ -2507,49 +2552,43 @@ static int __esw_set_master_egress_rule(struct mlx5_core_dev *master, flow_rule = mlx5_add_flow_rules(acl, spec, &flow_act, &dest, 1); - if (IS_ERR(flow_rule)) + if (IS_ERR(flow_rule)) { err = PTR_ERR(flow_rule); - else - vport->egress.offloads.bounce_rule = flow_rule; + } else { + err = xa_insert(&vport->egress.offloads.bounce_rules, + slave_index, flow_rule, GFP_KERNEL); + if (err) + mlx5_del_flow_rules(flow_rule); + } kvfree(spec); return err; } -static int esw_set_master_egress_rule(struct mlx5_core_dev *master, - struct mlx5_core_dev *slave) +static int esw_master_egress_create_resources(struct mlx5_eswitch *esw, + struct mlx5_flow_namespace *egress_ns, + struct mlx5_vport *vport, size_t count) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - struct mlx5_eswitch *esw = master->priv.eswitch; struct mlx5_flow_table_attr ft_attr = { - .max_fte = 1, .prio = 0, .level = 0, - .flags = MLX5_FLOW_TABLE_OTHER_VPORT, + .max_fte = count, .prio = 0, .level = 0, }; - struct mlx5_flow_namespace *egress_ns; struct mlx5_flow_table *acl; struct mlx5_flow_group *g; - struct mlx5_vport *vport; void *match_criteria; u32 *flow_group_in; int err; - vport = mlx5_eswitch_get_vport(esw, esw->manager_vport); - if (IS_ERR(vport)) - return PTR_ERR(vport); - - egress_ns = mlx5_get_flow_vport_acl_namespace(master, - MLX5_FLOW_NAMESPACE_ESW_EGRESS, - vport->index); - if (!egress_ns) - return -EINVAL; - if (vport->egress.acl) - return -EINVAL; + return 0; 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(egress_ns, &ft_attr, vport->vport); if (IS_ERR(acl)) { err = PTR_ERR(acl); @@ -2568,7 +2607,7 @@ static int esw_set_master_egress_rule(struct mlx5_core_dev *master, MLX5_SET(create_flow_group_in, flow_group_in, source_eswitch_owner_vhca_id_valid, 1); MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, count); g = mlx5_create_flow_group(acl, flow_group_in); if (IS_ERR(g)) { @@ -2576,19 +2615,15 @@ static int esw_set_master_egress_rule(struct mlx5_core_dev *master, goto err_group; } - err = __esw_set_master_egress_rule(master, slave, vport, acl); - if (err) - goto err_rule; - vport->egress.acl = acl; vport->egress.offloads.bounce_grp = g; + vport->egress.type = VPORT_EGRESS_ACL_TYPE_SHARED_FDB; + xa_init_flags(&vport->egress.offloads.bounce_rules, XA_FLAGS_ALLOC); kvfree(flow_group_in); return 0; -err_rule: - mlx5_destroy_flow_group(g); err_group: mlx5_destroy_flow_table(acl); out: @@ -2596,18 +2631,74 @@ out: return err; } -static void esw_unset_master_egress_rule(struct mlx5_core_dev *dev) +static void esw_master_egress_destroy_resources(struct mlx5_vport *vport) +{ + if (!xa_empty(&vport->egress.offloads.bounce_rules)) + return; + mlx5_destroy_flow_group(vport->egress.offloads.bounce_grp); + vport->egress.offloads.bounce_grp = NULL; + mlx5_destroy_flow_table(vport->egress.acl); + vport->egress.acl = NULL; +} + +static int esw_set_master_egress_rule(struct mlx5_core_dev *master, + struct mlx5_core_dev *slave, size_t count) +{ + struct mlx5_eswitch *esw = master->priv.eswitch; + u16 slave_index = MLX5_CAP_GEN(slave, vhca_id); + struct mlx5_flow_namespace *egress_ns; + struct mlx5_vport *vport; + int err; + + vport = mlx5_eswitch_get_vport(esw, esw->manager_vport); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + egress_ns = mlx5_get_flow_vport_acl_namespace(master, + MLX5_FLOW_NAMESPACE_ESW_EGRESS, + vport->index); + if (!egress_ns) + return -EINVAL; + + if (vport->egress.acl && vport->egress.type != VPORT_EGRESS_ACL_TYPE_SHARED_FDB) + return 0; + + err = esw_master_egress_create_resources(esw, egress_ns, vport, count); + if (err) + return err; + + if (xa_load(&vport->egress.offloads.bounce_rules, slave_index)) + return -EINVAL; + + err = __esw_set_master_egress_rule(master, slave, vport, vport->egress.acl); + if (err) + goto err_rule; + + return 0; + +err_rule: + esw_master_egress_destroy_resources(vport); + return err; +} + +static void esw_unset_master_egress_rule(struct mlx5_core_dev *dev, + struct mlx5_core_dev *slave_dev) { struct mlx5_vport *vport; vport = mlx5_eswitch_get_vport(dev->priv.eswitch, dev->priv.eswitch->manager_vport); - esw_acl_egress_ofld_cleanup(vport); + esw_acl_egress_ofld_bounce_rule_destroy(vport, MLX5_CAP_GEN(slave_dev, vhca_id)); + + if (xa_empty(&vport->egress.offloads.bounce_rules)) { + esw_acl_egress_ofld_cleanup(vport); + xa_destroy(&vport->egress.offloads.bounce_rules); + } } -int mlx5_eswitch_offloads_config_single_fdb(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) { int err; @@ -2617,7 +2708,7 @@ int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw, return err; err = esw_set_master_egress_rule(master_esw->dev, - slave_esw->dev); + slave_esw->dev, max_slaves); if (err) goto err_acl; @@ -2625,21 +2716,21 @@ int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw, err_acl: esw_set_slave_root_fdb(NULL, slave_esw->dev); - return err; } -void mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw, +void mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw, struct mlx5_eswitch *slave_esw) { - esw_unset_master_egress_rule(master_esw->dev); esw_set_slave_root_fdb(NULL, slave_esw->dev); + esw_unset_master_egress_rule(master_esw->dev, slave_esw->dev); } #define ESW_OFFLOADS_DEVCOM_PAIR (0) #define ESW_OFFLOADS_DEVCOM_UNPAIR (1) -static void mlx5_esw_offloads_rep_event_unpair(struct mlx5_eswitch *esw) +static void mlx5_esw_offloads_rep_event_unpair(struct mlx5_eswitch *esw, + struct mlx5_eswitch *peer_esw) { const struct mlx5_eswitch_rep_ops *ops; struct mlx5_eswitch_rep *rep; @@ -2652,18 +2743,19 @@ static void mlx5_esw_offloads_rep_event_unpair(struct mlx5_eswitch *esw) ops = esw->offloads.rep_ops[rep_type]; if (atomic_read(&rep->rep_data[rep_type].state) == REP_LOADED && ops->event) - ops->event(esw, rep, MLX5_SWITCHDEV_EVENT_UNPAIR, NULL); + ops->event(esw, rep, MLX5_SWITCHDEV_EVENT_UNPAIR, peer_esw); } } } -static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw) +static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw, + struct mlx5_eswitch *peer_esw) { #if IS_ENABLED(CONFIG_MLX5_CLS_ACT) mlx5e_tc_clean_fdb_peer_flows(esw); #endif - mlx5_esw_offloads_rep_event_unpair(esw); - esw_del_fdb_peer_miss_rules(esw); + mlx5_esw_offloads_rep_event_unpair(esw, peer_esw); + esw_del_fdb_peer_miss_rules(esw, peer_esw->dev); } static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw, @@ -2694,7 +2786,7 @@ static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw, return 0; err_out: - mlx5_esw_offloads_unpair(esw); + mlx5_esw_offloads_unpair(esw, peer_esw); return err; } @@ -2702,6 +2794,8 @@ static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw, struct mlx5_eswitch *peer_esw, bool pair) { + u16 peer_vhca_id = MLX5_CAP_GEN(peer_esw->dev, vhca_id); + u16 vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id); struct mlx5_flow_root_namespace *peer_ns; struct mlx5_flow_root_namespace *ns; int err; @@ -2710,18 +2804,18 @@ static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw, ns = esw->dev->priv.steering->fdb_root_ns; if (pair) { - err = mlx5_flow_namespace_set_peer(ns, peer_ns); + err = mlx5_flow_namespace_set_peer(ns, peer_ns, peer_vhca_id); if (err) return err; - err = mlx5_flow_namespace_set_peer(peer_ns, ns); + err = mlx5_flow_namespace_set_peer(peer_ns, ns, vhca_id); if (err) { - mlx5_flow_namespace_set_peer(ns, NULL); + mlx5_flow_namespace_set_peer(ns, NULL, peer_vhca_id); return err; } } else { - mlx5_flow_namespace_set_peer(ns, NULL); - mlx5_flow_namespace_set_peer(peer_ns, NULL); + mlx5_flow_namespace_set_peer(ns, NULL, peer_vhca_id); + mlx5_flow_namespace_set_peer(peer_ns, NULL, vhca_id); } return 0; @@ -2734,15 +2828,21 @@ static int mlx5_esw_offloads_devcom_event(int event, struct mlx5_eswitch *esw = my_data; struct mlx5_devcom *devcom = esw->dev->priv.devcom; struct mlx5_eswitch *peer_esw = event_data; + u16 esw_i, peer_esw_i; + bool esw_paired; int err; + peer_esw_i = MLX5_CAP_GEN(peer_esw->dev, vhca_id); + esw_i = MLX5_CAP_GEN(esw->dev, vhca_id); + esw_paired = !!xa_load(&esw->paired, peer_esw_i); + switch (event) { case ESW_OFFLOADS_DEVCOM_PAIR: if (mlx5_eswitch_vport_match_metadata_enabled(esw) != mlx5_eswitch_vport_match_metadata_enabled(peer_esw)) break; - if (esw->paired[mlx5_get_dev_index(peer_esw->dev)]) + if (esw_paired) break; err = mlx5_esw_offloads_set_ns_peer(esw, peer_esw, true); @@ -2756,28 +2856,43 @@ static int mlx5_esw_offloads_devcom_event(int event, if (err) goto err_pair; - esw->paired[mlx5_get_dev_index(peer_esw->dev)] = true; - peer_esw->paired[mlx5_get_dev_index(esw->dev)] = true; - mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, true); + err = xa_insert(&esw->paired, peer_esw_i, peer_esw, GFP_KERNEL); + if (err) + goto err_xa; + + err = xa_insert(&peer_esw->paired, esw_i, esw, GFP_KERNEL); + if (err) + goto err_peer_xa; + + esw->num_peers++; + peer_esw->num_peers++; + mlx5_devcom_comp_set_ready(devcom, MLX5_DEVCOM_ESW_OFFLOADS, true); break; case ESW_OFFLOADS_DEVCOM_UNPAIR: - if (!esw->paired[mlx5_get_dev_index(peer_esw->dev)]) + if (!esw_paired) break; - mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false); - esw->paired[mlx5_get_dev_index(peer_esw->dev)] = false; - peer_esw->paired[mlx5_get_dev_index(esw->dev)] = false; - mlx5_esw_offloads_unpair(peer_esw); - mlx5_esw_offloads_unpair(esw); + peer_esw->num_peers--; + esw->num_peers--; + if (!esw->num_peers && !peer_esw->num_peers) + mlx5_devcom_comp_set_ready(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false); + xa_erase(&peer_esw->paired, esw_i); + xa_erase(&esw->paired, peer_esw_i); + mlx5_esw_offloads_unpair(peer_esw, esw); + mlx5_esw_offloads_unpair(esw, peer_esw); mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false); break; } return 0; +err_peer_xa: + xa_erase(&esw->paired, peer_esw_i); +err_xa: + mlx5_esw_offloads_unpair(peer_esw, esw); err_pair: - mlx5_esw_offloads_unpair(esw); + mlx5_esw_offloads_unpair(esw, peer_esw); err_peer: mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false); err_out: @@ -2789,24 +2904,29 @@ err_out: void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw) { struct mlx5_devcom *devcom = esw->dev->priv.devcom; + int i; - INIT_LIST_HEAD(&esw->offloads.peer_flows); + for (i = 0; i < MLX5_MAX_PORTS; i++) + INIT_LIST_HEAD(&esw->offloads.peer_flows[i]); mutex_init(&esw->offloads.peer_mutex); if (!MLX5_CAP_ESW(esw->dev, merged_eswitch)) return; - if (!mlx5_is_lag_supported(esw->dev)) + if (!mlx5_lag_is_supported(esw->dev)) return; + xa_init(&esw->paired); mlx5_devcom_register_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS, mlx5_esw_offloads_devcom_event, esw); + esw->num_peers = 0; mlx5_devcom_send_event(devcom, MLX5_DEVCOM_ESW_OFFLOADS, - ESW_OFFLOADS_DEVCOM_PAIR, esw); + ESW_OFFLOADS_DEVCOM_PAIR, + ESW_OFFLOADS_DEVCOM_UNPAIR, esw); } void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) @@ -2816,13 +2936,15 @@ void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) if (!MLX5_CAP_ESW(esw->dev, merged_eswitch)) return; - if (!mlx5_is_lag_supported(esw->dev)) + if (!mlx5_lag_is_supported(esw->dev)) return; mlx5_devcom_send_event(devcom, MLX5_DEVCOM_ESW_OFFLOADS, + ESW_OFFLOADS_DEVCOM_UNPAIR, ESW_OFFLOADS_DEVCOM_UNPAIR, esw); mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + xa_destroy(&esw->paired); } bool mlx5_esw_vport_match_metadata_supported(const struct mlx5_eswitch *esw) @@ -2834,9 +2956,6 @@ bool mlx5_esw_vport_match_metadata_supported(const struct mlx5_eswitch *esw) MLX5_FDB_TO_VPORT_REG_C_0)) return false; - if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source)) - return false; - return true; } @@ -2973,26 +3092,47 @@ esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw, esw_acl_ingress_ofld_cleanup(esw, vport); } -static int esw_create_uplink_offloads_acl_tables(struct mlx5_eswitch *esw) +static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw) { - struct mlx5_vport *vport; + struct mlx5_vport *uplink, *manager; + int ret; - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK); - if (IS_ERR(vport)) - return PTR_ERR(vport); + uplink = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK); + if (IS_ERR(uplink)) + return PTR_ERR(uplink); + + ret = esw_vport_create_offloads_acl_tables(esw, uplink); + if (ret) + return ret; - return esw_vport_create_offloads_acl_tables(esw, vport); + manager = mlx5_eswitch_get_vport(esw, esw->manager_vport); + if (IS_ERR(manager)) { + ret = PTR_ERR(manager); + goto err_manager; + } + + ret = esw_vport_create_offloads_acl_tables(esw, manager); + if (ret) + goto err_manager; + + return 0; + +err_manager: + esw_vport_destroy_offloads_acl_tables(esw, uplink); + return ret; } -static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw) +static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw) { struct mlx5_vport *vport; - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK); - if (IS_ERR(vport)) - return; + vport = mlx5_eswitch_get_vport(esw, esw->manager_vport); + if (!IS_ERR(vport)) + esw_vport_destroy_offloads_acl_tables(esw, vport); - esw_vport_destroy_offloads_acl_tables(esw, vport); + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK); + if (!IS_ERR(vport)) + esw_vport_destroy_offloads_acl_tables(esw, vport); } int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw) @@ -3037,7 +3177,7 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw) } esw->fdb_table.offloads.indir = indir; - err = esw_create_uplink_offloads_acl_tables(esw); + err = esw_create_offloads_acl_tables(esw); if (err) goto create_acl_err; @@ -3078,7 +3218,7 @@ create_fdb_err: create_restore_err: esw_destroy_offloads_table(esw); create_offloads_err: - esw_destroy_uplink_offloads_acl_tables(esw); + esw_destroy_offloads_acl_tables(esw); create_acl_err: mlx5_esw_indir_table_destroy(esw->fdb_table.offloads.indir); create_indir_err: @@ -3094,7 +3234,7 @@ static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw) esw_destroy_offloads_fdb_tables(esw); esw_destroy_restore_table(esw); esw_destroy_offloads_table(esw); - esw_destroy_uplink_offloads_acl_tables(esw); + esw_destroy_offloads_acl_tables(esw); mlx5_esw_indir_table_destroy(esw->fdb_table.offloads.indir); mutex_destroy(&esw->fdb_table.offloads.vports.lock); } @@ -3247,9 +3387,12 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) /* Representor will control the vport link state */ mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) vport->info.link_state = MLX5_VPORT_ADMIN_STATE_DOWN; + if (mlx5_core_ec_sriov_enabled(esw->dev)) + mlx5_esw_for_each_ec_vf_vport(esw, i, vport, esw->esw_funcs.num_ec_vfs) + vport->info.link_state = MLX5_VPORT_ADMIN_STATE_DOWN; /* Uplink vport rep must load first. */ - err = esw_offloads_load_rep(esw, MLX5_VPORT_UPLINK); + err = mlx5_esw_offloads_load_rep(esw, MLX5_VPORT_UPLINK); if (err) goto err_uplink; @@ -3260,7 +3403,7 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) return 0; err_vports: - esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK); + mlx5_esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK); err_uplink: esw_offloads_steering_cleanup(esw); err_steering_init: @@ -3285,7 +3428,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, /* If changing from switchdev to legacy mode without sriov enabled, * no need to create legacy fdb. */ - if (!mlx5_sriov_is_enabled(esw->dev)) + if (!mlx5_core_is_pf(esw->dev) || !mlx5_sriov_is_enabled(esw->dev)) return 0; err = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_IGNORE_NUM_VFS); @@ -3298,7 +3441,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, void esw_offloads_disable(struct mlx5_eswitch *esw) { mlx5_eswitch_disable_pf_vf_vports(esw); - esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK); + mlx5_esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK); esw_set_passing_vport_metadata(esw, false); esw_offloads_steering_cleanup(esw); mapping_destroy(esw->offloads.reg_c0_obj_pool); @@ -3484,8 +3627,27 @@ static int mlx5_esw_vports_inline_set(struct mlx5_eswitch *esw, u8 mlx5_mode, goto revert_inline_mode; } } + if (mlx5_core_ec_sriov_enabled(esw->dev)) { + mlx5_esw_for_each_ec_vf_vport(esw, i, vport, esw->esw_funcs.num_ec_vfs) { + err = mlx5_modify_nic_vport_min_inline(dev, vport->vport, mlx5_mode); + if (err) { + err_vport_num = vport->vport; + NL_SET_ERR_MSG_MOD(extack, + "Failed to set min inline on vport"); + goto revert_ec_vf_inline_mode; + } + } + } return 0; +revert_ec_vf_inline_mode: + mlx5_esw_for_each_ec_vf_vport(esw, i, vport, esw->esw_funcs.num_ec_vfs) { + if (vport->vport == err_vport_num) + break; + mlx5_modify_nic_vport_min_inline(dev, + vport->vport, + esw->offloads.inline_mode); + } revert_inline_mode: mlx5_esw_for_each_host_func_vport(esw, i, vport, esw->esw_funcs.num_vfs) { if (vport->vport == err_vport_num) @@ -3835,9 +3997,6 @@ static int mlx5_esw_query_vport_vhca_id(struct mlx5_eswitch *esw, u16 vport_num, int err; *vhca_id = 0; - if (mlx5_esw_is_manager_vport(esw, vport_num) || - !MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) - return -EPERM; query_ctx = kzalloc(query_out_sz, GFP_KERNEL); if (!query_ctx) @@ -3926,9 +4085,9 @@ is_port_function_supported(struct mlx5_eswitch *esw, u16 vport_num) mlx5_esw_is_sf_vport(esw, vport_num); } -int mlx5_devlink_port_function_hw_addr_get(struct devlink_port *port, - u8 *hw_addr, int *hw_addr_len, - struct netlink_ext_ack *extack) +int mlx5_devlink_port_fn_hw_addr_get(struct devlink_port *port, + u8 *hw_addr, int *hw_addr_len, + struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw; struct mlx5_vport *vport; @@ -3955,9 +4114,9 @@ int mlx5_devlink_port_function_hw_addr_get(struct devlink_port *port, return 0; } -int mlx5_devlink_port_function_hw_addr_set(struct devlink_port *port, - const u8 *hw_addr, int hw_addr_len, - struct netlink_ext_ack *extack) +int mlx5_devlink_port_fn_hw_addr_set(struct devlink_port *port, + const u8 *hw_addr, int hw_addr_len, + struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw; u16 vport_num; @@ -4073,7 +4232,7 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable, } hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability); - MLX5_SET(cmd_hca_cap_2, hca_caps, migratable, 1); + MLX5_SET(cmd_hca_cap_2, hca_caps, migratable, enable); err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport->vport, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE2); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index 718cf09c28ce..3ec892d51f57 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -5,7 +5,7 @@ #include "mlx5_core.h" #include "lib/eq.h" -#include "lib/mlx5.h" +#include "lib/events.h" struct mlx5_event_nb { struct mlx5_nb nb; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index ec83e6483d1a..244cfd470903 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -139,7 +139,8 @@ static void mlx5_cmd_stub_modify_header_dealloc(struct mlx5_flow_root_namespace } static int mlx5_cmd_stub_set_peer(struct mlx5_flow_root_namespace *ns, - struct mlx5_flow_root_namespace *peer_ns) + struct mlx5_flow_root_namespace *peer_ns, + u16 peer_vhca_id) { return 0; } @@ -243,16 +244,30 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, ft->type == FS_FT_FDB && mlx5_lag_is_shared_fdb(dev) && mlx5_lag_is_master(dev)) { - err = mlx5_cmd_set_slave_root_fdb(dev, - mlx5_lag_get_peer_mdev(dev), - !disconnect, (!disconnect) ? - ft->id : 0); - if (err && !disconnect) { - MLX5_SET(set_flow_table_root_in, in, op_mod, 0); - MLX5_SET(set_flow_table_root_in, in, table_id, - ns->root_ft->id); - mlx5_cmd_exec_in(dev, set_flow_table_root, in); + struct mlx5_core_dev *peer_dev; + int i, j; + + mlx5_lag_for_each_peer_mdev(dev, peer_dev, i) { + err = mlx5_cmd_set_slave_root_fdb(dev, peer_dev, !disconnect, + (!disconnect) ? ft->id : 0); + if (err && !disconnect) { + mlx5_lag_for_each_peer_mdev(dev, peer_dev, j) { + if (j < i) + mlx5_cmd_set_slave_root_fdb(dev, peer_dev, 1, + ns->root_ft->id); + else + break; + } + + MLX5_SET(set_flow_table_root_in, in, op_mod, 0); + MLX5_SET(set_flow_table_root_in, in, table_id, + ns->root_ft->id); + mlx5_cmd_exec_in(dev, set_flow_table_root, in); + } + if (err) + break; } + } return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index 8ef4254b9ea1..7790ae5531e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -93,7 +93,8 @@ struct mlx5_flow_cmds { struct mlx5_modify_hdr *modify_hdr); int (*set_peer)(struct mlx5_flow_root_namespace *ns, - struct mlx5_flow_root_namespace *peer_ns); + struct mlx5_flow_root_namespace *peer_ns, + u16 peer_vhca_id); int (*create_ns)(struct mlx5_flow_root_namespace *ns); int (*destroy_ns)(struct mlx5_flow_root_namespace *ns); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 19da02c41616..6b069fa411c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -889,7 +889,7 @@ static struct mlx5_flow_table *find_closest_ft_recursive(struct fs_node *root, struct fs_node *iter = list_entry(start, struct fs_node, list); struct mlx5_flow_table *ft = NULL; - if (!root || root->type == FS_TYPE_PRIO_CHAINS) + if (!root) return NULL; list_for_each_advance_continue(iter, &root->children, reverse) { @@ -905,20 +905,42 @@ static struct mlx5_flow_table *find_closest_ft_recursive(struct fs_node *root, return ft; } -/* If reverse is false then return the first flow table in next priority of - * prio in the tree, else return the last flow table in the previous priority - * of prio in the tree. +static struct fs_node *find_prio_chains_parent(struct fs_node *parent, + struct fs_node **child) +{ + struct fs_node *node = NULL; + + while (parent && parent->type != FS_TYPE_PRIO_CHAINS) { + node = parent; + parent = parent->parent; + } + + if (child) + *child = node; + + return parent; +} + +/* If reverse is false then return the first flow table next to the passed node + * in the tree, else return the last flow table before the node in the tree. + * If skip is true, skip the flow tables in the same prio_chains prio. */ -static struct mlx5_flow_table *find_closest_ft(struct fs_prio *prio, bool reverse) +static struct mlx5_flow_table *find_closest_ft(struct fs_node *node, bool reverse, + bool skip) { + struct fs_node *prio_chains_parent = NULL; struct mlx5_flow_table *ft = NULL; struct fs_node *curr_node; struct fs_node *parent; - parent = prio->node.parent; - curr_node = &prio->node; + if (skip) + prio_chains_parent = find_prio_chains_parent(node, NULL); + parent = node->parent; + curr_node = node; while (!ft && parent) { - ft = find_closest_ft_recursive(parent, &curr_node->list, reverse); + if (parent != prio_chains_parent) + ft = find_closest_ft_recursive(parent, &curr_node->list, + reverse); curr_node = parent; parent = curr_node->parent; } @@ -926,15 +948,15 @@ static struct mlx5_flow_table *find_closest_ft(struct fs_prio *prio, bool revers } /* Assuming all the tree is locked by mutex chain lock */ -static struct mlx5_flow_table *find_next_chained_ft(struct fs_prio *prio) +static struct mlx5_flow_table *find_next_chained_ft(struct fs_node *node) { - return find_closest_ft(prio, false); + return find_closest_ft(node, false, true); } /* Assuming all the tree is locked by mutex chain lock */ -static struct mlx5_flow_table *find_prev_chained_ft(struct fs_prio *prio) +static struct mlx5_flow_table *find_prev_chained_ft(struct fs_node *node) { - return find_closest_ft(prio, true); + return find_closest_ft(node, true, true); } static struct mlx5_flow_table *find_next_fwd_ft(struct mlx5_flow_table *ft, @@ -946,7 +968,7 @@ static struct mlx5_flow_table *find_next_fwd_ft(struct mlx5_flow_table *ft, next_ns = flow_act->action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS; fs_get_obj(prio, next_ns ? ft->ns->node.parent : ft->node.parent); - return find_next_chained_ft(prio); + return find_next_chained_ft(&prio->node); } static int connect_fts_in_prio(struct mlx5_core_dev *dev, @@ -970,21 +992,55 @@ static int connect_fts_in_prio(struct mlx5_core_dev *dev, return 0; } +static struct mlx5_flow_table *find_closet_ft_prio_chains(struct fs_node *node, + struct fs_node *parent, + struct fs_node **child, + bool reverse) +{ + struct mlx5_flow_table *ft; + + ft = find_closest_ft(node, reverse, false); + + if (ft && parent == find_prio_chains_parent(&ft->node, child)) + return ft; + + return NULL; +} + /* Connect flow tables from previous priority of prio to ft */ static int connect_prev_fts(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, struct fs_prio *prio) { + struct fs_node *prio_parent, *parent = NULL, *child, *node; struct mlx5_flow_table *prev_ft; + int err = 0; + + prio_parent = find_prio_chains_parent(&prio->node, &child); + + /* return directly if not under the first sub ns of prio_chains prio */ + if (prio_parent && !list_is_first(&child->list, &prio_parent->children)) + return 0; - prev_ft = find_prev_chained_ft(prio); - if (prev_ft) { + prev_ft = find_prev_chained_ft(&prio->node); + while (prev_ft) { struct fs_prio *prev_prio; fs_get_obj(prev_prio, prev_ft->node.parent); - return connect_fts_in_prio(dev, prev_prio, ft); + err = connect_fts_in_prio(dev, prev_prio, ft); + if (err) + break; + + if (!parent) { + parent = find_prio_chains_parent(&prev_prio->node, &child); + if (!parent) + break; + } + + node = child; + prev_ft = find_closet_ft_prio_chains(node, parent, &child, true); } - return 0; + return err; } static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio @@ -1123,7 +1179,7 @@ static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table if (err) return err; - next_ft = first_ft ? first_ft : find_next_chained_ft(prio); + next_ft = first_ft ? first_ft : find_next_chained_ft(&prio->node); err = connect_fwd_rules(dev, ft, next_ft); if (err) return err; @@ -1198,7 +1254,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table); next_ft = unmanaged ? ft_attr->next_ft : - find_next_chained_ft(fs_prio); + find_next_chained_ft(&fs_prio->node); ft->def_miss_action = ns->def_miss_action; ft->ns = ns; err = root->cmds->create_flow_table(root, ft, ft_attr, next_ft); @@ -2195,13 +2251,20 @@ EXPORT_SYMBOL(mlx5_del_flow_rules); /* Assuming prio->node.children(flow tables) is sorted by level */ static struct mlx5_flow_table *find_next_ft(struct mlx5_flow_table *ft) { + struct fs_node *prio_parent, *child; struct fs_prio *prio; fs_get_obj(prio, ft->node.parent); if (!list_is_last(&ft->node.list, &prio->node.children)) return list_next_entry(ft, node.list); - return find_next_chained_ft(prio); + + prio_parent = find_prio_chains_parent(&prio->node, &child); + + if (prio_parent && list_is_first(&child->list, &prio_parent->children)) + return find_closest_ft(&prio->node, false, false); + + return find_next_chained_ft(&prio->node); } static int update_root_ft_destroy(struct mlx5_flow_table *ft) @@ -3620,7 +3683,8 @@ void mlx5_destroy_match_definer(struct mlx5_core_dev *dev, } int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, - struct mlx5_flow_root_namespace *peer_ns) + struct mlx5_flow_root_namespace *peer_ns, + u16 peer_vhca_id) { if (peer_ns && ns->mode != peer_ns->mode) { mlx5_core_err(ns->dev, @@ -3628,7 +3692,7 @@ int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, return -EINVAL; } - return ns->cmds->set_peer(ns, peer_ns); + return ns->cmds->set_peer(ns, peer_ns, peer_vhca_id); } /* This function should be called only at init stage of the namespace. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index b043190e50a8..4aed1768b85f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -302,7 +302,8 @@ void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev, const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void); int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, - struct mlx5_flow_root_namespace *peer_ns); + struct mlx5_flow_root_namespace *peer_ns, + u16 peer_vhca_id); int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns, enum mlx5_flow_steering_mode mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 7bb7be01225a..fb2035a5ec99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -196,14 +196,11 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } - if (MLX5_CAP_GEN(dev, vport_group_manager) && - MLX5_ESWITCH_MANAGER(dev)) { + if (MLX5_ESWITCH_MANAGER(dev)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE); if (err) return err; - } - if (MLX5_ESWITCH_MANAGER(dev)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 50022e7565f1..99dcbd006357 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -21,6 +21,7 @@ struct mlx5_fw_reset { struct workqueue_struct *wq; struct work_struct fw_live_patch_work; struct work_struct reset_request_work; + struct work_struct reset_unload_work; struct work_struct reset_reload_work; struct work_struct reset_now_work; struct work_struct reset_abort_work; @@ -30,6 +31,26 @@ struct mlx5_fw_reset { int ret; }; +enum { + MLX5_FW_RST_STATE_IDLE = 0, + MLX5_FW_RST_STATE_TOGGLE_REQ = 4, +}; + +enum { + MLX5_RST_STATE_BIT_NUM = 12, + MLX5_RST_ACK_BIT_NUM = 22, +}; + +static u8 mlx5_get_fw_rst_state(struct mlx5_core_dev *dev) +{ + return (ioread32be(&dev->iseg->initializing) >> MLX5_RST_STATE_BIT_NUM) & 0xF; +} + +static void mlx5_set_fw_rst_ack(struct mlx5_core_dev *dev) +{ + iowrite32be(BIT(MLX5_RST_ACK_BIT_NUM), &dev->iseg->initializing); +} + static int mlx5_fw_reset_enable_remote_dev_reset_set(struct devlink *devlink, u32 id, struct devlink_param_gset_ctx *ctx) { @@ -155,7 +176,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev) return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL0, 0, 0, false); } -static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev) +static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unloaded) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; @@ -163,7 +184,8 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev) if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) { complete(&fw_reset->done); } else { - mlx5_unload_one(dev, false); + if (!unloaded) + mlx5_unload_one(dev, false); if (mlx5_health_wait_pci_up(dev)) mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n"); else @@ -204,7 +226,7 @@ static void mlx5_sync_reset_reload_work(struct work_struct *work) mlx5_sync_reset_clear_reset_requested(dev, false); mlx5_enter_error_state(dev, true); - mlx5_fw_reset_complete_reload(dev); + mlx5_fw_reset_complete_reload(dev, false); } #define MLX5_RESET_POLL_INTERVAL (HZ / 10) @@ -276,6 +298,44 @@ static void mlx5_fw_live_patch_event(struct work_struct *work) mlx5_core_err(dev, "Failed to reload FW tracer\n"); } +static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id) +{ + struct pci_bus *bridge_bus = dev->pdev->bus; + struct pci_dev *sdev; + u16 sdev_id; + int err; + + /* Check that all functions under the pci bridge are PFs of + * this device otherwise fail this function. + */ + list_for_each_entry(sdev, &bridge_bus->devices, bus_list) { + err = pci_read_config_word(sdev, PCI_DEVICE_ID, &sdev_id); + if (err) + return err; + if (sdev_id != dev_id) { + mlx5_core_warn(dev, "unrecognized dev_id (0x%x)\n", sdev_id); + return -EPERM; + } + } + return 0; +} + +static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev) +{ + u16 dev_id; + int err; + + if (!MLX5_CAP_GEN(dev, fast_teardown)) { + mlx5_core_warn(dev, "fast teardown is not supported by firmware\n"); + return false; + } + + err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id); + if (err) + return false; + return (!mlx5_check_dev_ids(dev, dev_id)); +} + static void mlx5_sync_reset_request_event(struct work_struct *work) { struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset, @@ -283,7 +343,8 @@ static void mlx5_sync_reset_request_event(struct work_struct *work) struct mlx5_core_dev *dev = fw_reset->dev; int err; - if (test_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, &fw_reset->reset_flags)) { + if (test_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, &fw_reset->reset_flags) || + !mlx5_is_reset_now_capable(dev)) { err = mlx5_fw_reset_set_reset_sync_nack(dev); mlx5_core_warn(dev, "PCI Sync FW Update Reset Nack %s", err ? "Failed" : "Sent"); @@ -303,26 +364,17 @@ static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) { struct pci_bus *bridge_bus = dev->pdev->bus; struct pci_dev *bridge = bridge_bus->self; - u16 reg16, dev_id, sdev_id; unsigned long timeout; struct pci_dev *sdev; + u16 reg16, dev_id; int cap, err; - u32 reg32; - /* Check that all functions under the pci bridge are PFs of - * this device otherwise fail this function. - */ err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id); if (err) return err; - list_for_each_entry(sdev, &bridge_bus->devices, bus_list) { - err = pci_read_config_word(sdev, PCI_DEVICE_ID, &sdev_id); - if (err) - return err; - if (sdev_id != dev_id) - return -EPERM; - } - + err = mlx5_check_dev_ids(dev, dev_id); + if (err) + return err; cap = pci_find_capability(bridge, PCI_CAP_ID_EXP); if (!cap) return -EOPNOTSUPP; @@ -332,25 +384,17 @@ static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) pci_cfg_access_lock(sdev); } /* PCI link toggle */ - err = pci_read_config_word(bridge, cap + PCI_EXP_LNKCTL, ®16); - if (err) - return err; - reg16 |= PCI_EXP_LNKCTL_LD; - err = pci_write_config_word(bridge, cap + PCI_EXP_LNKCTL, reg16); + err = pcie_capability_set_word(bridge, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_LD); if (err) return err; msleep(500); - reg16 &= ~PCI_EXP_LNKCTL_LD; - err = pci_write_config_word(bridge, cap + PCI_EXP_LNKCTL, reg16); + err = pcie_capability_clear_word(bridge, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_LD); if (err) return err; /* Check link */ - err = pci_read_config_dword(bridge, cap + PCI_EXP_LNKCAP, ®32); - if (err) - return err; - if (!(reg32 & PCI_EXP_LNKCAP_DLLLARC)) { - mlx5_core_warn(dev, "No PCI link reporting capability (0x%08x)\n", reg32); + if (!bridge->link_active_reporting) { + mlx5_core_warn(dev, "No PCI link reporting capability\n"); msleep(1000); goto restore; } @@ -427,7 +471,70 @@ static void mlx5_sync_reset_now_event(struct work_struct *work) mlx5_enter_error_state(dev, true); done: fw_reset->ret = err; - mlx5_fw_reset_complete_reload(dev); + mlx5_fw_reset_complete_reload(dev, false); +} + +static void mlx5_sync_reset_unload_event(struct work_struct *work) +{ + struct mlx5_fw_reset *fw_reset; + struct mlx5_core_dev *dev; + unsigned long timeout; + bool reset_action; + u8 rst_state; + int err; + + fw_reset = container_of(work, struct mlx5_fw_reset, reset_unload_work); + dev = fw_reset->dev; + + if (mlx5_sync_reset_clear_reset_requested(dev, false)) + return; + + mlx5_core_warn(dev, "Sync Reset Unload. Function is forced down.\n"); + + err = mlx5_cmd_fast_teardown_hca(dev); + if (err) + mlx5_core_warn(dev, "Fast teardown failed, unloading, err %d\n", err); + else + mlx5_enter_error_state(dev, true); + + if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) + mlx5_unload_one_devl_locked(dev, false); + else + mlx5_unload_one(dev, false); + + mlx5_set_fw_rst_ack(dev); + mlx5_core_warn(dev, "Sync Reset Unload done, device reset expected\n"); + + reset_action = false; + timeout = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, RESET_UNLOAD)); + do { + rst_state = mlx5_get_fw_rst_state(dev); + if (rst_state == MLX5_FW_RST_STATE_TOGGLE_REQ || + rst_state == MLX5_FW_RST_STATE_IDLE) { + reset_action = true; + break; + } + msleep(20); + } while (!time_after(jiffies, timeout)); + + if (!reset_action) { + mlx5_core_err(dev, "Got timeout waiting for sync reset action, state = %u\n", + rst_state); + fw_reset->ret = -ETIMEDOUT; + goto done; + } + + mlx5_core_warn(dev, "Sync Reset, got reset action. rst_state = %u\n", rst_state); + if (rst_state == MLX5_FW_RST_STATE_TOGGLE_REQ) { + err = mlx5_pci_link_toggle(dev); + if (err) { + mlx5_core_warn(dev, "mlx5_pci_link_toggle failed, err %d\n", err); + fw_reset->ret = err; + } + } + +done: + mlx5_fw_reset_complete_reload(dev, true); } static void mlx5_sync_reset_abort_event(struct work_struct *work) @@ -452,6 +559,9 @@ static void mlx5_sync_reset_events_handle(struct mlx5_fw_reset *fw_reset, struct case MLX5_SYNC_RST_STATE_RESET_REQUEST: queue_work(fw_reset->wq, &fw_reset->reset_request_work); break; + case MLX5_SYNC_RST_STATE_RESET_UNLOAD: + queue_work(fw_reset->wq, &fw_reset->reset_unload_work); + break; case MLX5_SYNC_RST_STATE_RESET_NOW: queue_work(fw_reset->wq, &fw_reset->reset_now_work); break; @@ -486,10 +596,13 @@ static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long acti int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev) { unsigned long pci_sync_update_timeout = mlx5_tout_ms(dev, PCI_SYNC_UPDATE); - unsigned long timeout = msecs_to_jiffies(pci_sync_update_timeout); struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + unsigned long timeout; int err; + if (MLX5_CAP_GEN(dev, pci_sync_for_fw_update_with_driver_unload)) + pci_sync_update_timeout += mlx5_tout_ms(dev, RESET_UNLOAD); + timeout = msecs_to_jiffies(pci_sync_update_timeout); if (!wait_for_completion_timeout(&fw_reset->done, timeout)) { mlx5_core_warn(dev, "FW sync reset timeout after %lu seconds\n", pci_sync_update_timeout / 1000); @@ -526,6 +639,7 @@ void mlx5_drain_fw_reset(struct mlx5_core_dev *dev) set_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags); cancel_work_sync(&fw_reset->fw_live_patch_work); cancel_work_sync(&fw_reset->reset_request_work); + cancel_work_sync(&fw_reset->reset_unload_work); cancel_work_sync(&fw_reset->reset_reload_work); cancel_work_sync(&fw_reset->reset_now_work); cancel_work_sync(&fw_reset->reset_abort_work); @@ -564,6 +678,7 @@ int mlx5_fw_reset_init(struct mlx5_core_dev *dev) INIT_WORK(&fw_reset->fw_live_patch_work, mlx5_fw_live_patch_event); INIT_WORK(&fw_reset->reset_request_work, mlx5_sync_reset_request_event); + INIT_WORK(&fw_reset->reset_unload_work, mlx5_sync_reset_unload_event); INIT_WORK(&fw_reset->reset_reload_work, mlx5_sync_reset_reload_work); INIT_WORK(&fw_reset->reset_now_work, mlx5_sync_reset_now_event); INIT_WORK(&fw_reset->reset_abort_work, mlx5_sync_reset_abort_event); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 871c32dda66e..187cb2c464f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -39,6 +39,7 @@ #include "mlx5_core.h" #include "lib/eq.h" #include "lib/mlx5.h" +#include "lib/events.h" #include "lib/pci_vsc.h" #include "lib/tout.h" #include "diag/fw_tracer.h" @@ -719,7 +720,7 @@ static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = { #define MLX5_FW_REPORTER_VF_GRACEFUL_PERIOD 30000 #define MLX5_FW_REPORTER_DEFAULT_GRACEFUL_PERIOD MLX5_FW_REPORTER_VF_GRACEFUL_PERIOD -static void mlx5_fw_reporters_create(struct mlx5_core_dev *dev) +void mlx5_fw_reporters_create(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; struct devlink *devlink = priv_to_devlink(dev); @@ -735,17 +736,17 @@ static void mlx5_fw_reporters_create(struct mlx5_core_dev *dev) } health->fw_reporter = - devlink_health_reporter_create(devlink, &mlx5_fw_reporter_ops, - 0, dev); + devl_health_reporter_create(devlink, &mlx5_fw_reporter_ops, + 0, dev); if (IS_ERR(health->fw_reporter)) mlx5_core_warn(dev, "Failed to create fw reporter, err = %ld\n", PTR_ERR(health->fw_reporter)); health->fw_fatal_reporter = - devlink_health_reporter_create(devlink, - &mlx5_fw_fatal_reporter_ops, - grace_period, - dev); + devl_health_reporter_create(devlink, + &mlx5_fw_fatal_reporter_ops, + grace_period, + dev); if (IS_ERR(health->fw_fatal_reporter)) mlx5_core_warn(dev, "Failed to create fw fatal reporter, err = %ld\n", PTR_ERR(health->fw_fatal_reporter)); @@ -777,7 +778,8 @@ void mlx5_trigger_health_work(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; - queue_work(health->wq, &health->fatal_report_work); + if (!mlx5_dev_is_lightweight(dev)) + queue_work(health->wq, &health->fatal_report_work); } #define MLX5_MSEC_PER_HOUR (MSEC_PER_SEC * 60 * 60) @@ -905,10 +907,15 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev) int mlx5_health_init(struct mlx5_core_dev *dev) { + struct devlink *devlink = priv_to_devlink(dev); struct mlx5_core_health *health; char *name; - mlx5_fw_reporters_create(dev); + if (!mlx5_dev_is_lightweight(dev)) { + devl_lock(devlink); + mlx5_fw_reporters_create(dev); + devl_unlock(devlink); + } mlx5_reporter_vnic_create(dev); health = &dev->priv.health; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 5d331b940f4d..f0a074b2fcdf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -512,8 +512,11 @@ static void mlx5_lag_set_port_sel_mode_offloads(struct mlx5_lag *ldev, return; if (MLX5_CAP_PORT_SELECTION(dev0->dev, port_select_flow_table) && - tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH) + tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH) { + if (ldev->ports > 2) + ldev->buckets = MLX5_LAG_MAX_HASH_BUCKETS; set_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, flags); + } } static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode, @@ -550,6 +553,29 @@ char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags) } } +static int mlx5_lag_create_single_fdb(struct mlx5_lag *ldev) +{ + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_eswitch *master_esw = dev0->priv.eswitch; + int err; + int i; + + for (i = MLX5_LAG_P1 + 1; i < ldev->ports; i++) { + struct mlx5_eswitch *slave_esw = ldev->pf[i].dev->priv.eswitch; + + err = mlx5_eswitch_offloads_single_fdb_add_one(master_esw, + slave_esw, ldev->ports); + if (err) + goto err; + } + return 0; +err: + for (; i > MLX5_LAG_P1; i--) + mlx5_eswitch_offloads_single_fdb_del_one(master_esw, + ldev->pf[i].dev->priv.eswitch); + return err; +} + static int mlx5_create_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker, enum mlx5_lag_mode mode, @@ -557,7 +583,6 @@ static int mlx5_create_lag(struct mlx5_lag *ldev, { bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags); struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; - struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {}; int err; @@ -575,8 +600,7 @@ static int mlx5_create_lag(struct mlx5_lag *ldev, } if (shared_fdb) { - err = mlx5_eswitch_offloads_config_single_fdb(dev0->priv.eswitch, - dev1->priv.eswitch); + err = mlx5_lag_create_single_fdb(ldev); if (err) mlx5_core_err(dev0, "Can't enable single FDB mode\n"); else @@ -647,19 +671,21 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, int mlx5_deactivate_lag(struct mlx5_lag *ldev) { struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; - struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; + struct mlx5_eswitch *master_esw = dev0->priv.eswitch; u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {}; bool roce_lag = __mlx5_lag_is_roce(ldev); unsigned long flags = ldev->mode_flags; int err; + int i; ldev->mode = MLX5_LAG_MODE_NONE; ldev->mode_flags = 0; mlx5_lag_mp_reset(ldev); if (test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags)) { - mlx5_eswitch_offloads_destroy_single_fdb(dev0->priv.eswitch, - dev1->priv.eswitch); + for (i = MLX5_LAG_P1 + 1; i < ldev->ports; i++) + mlx5_eswitch_offloads_single_fdb_del_one(master_esw, + ldev->pf[i].dev->priv.eswitch); clear_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags); } @@ -685,7 +711,7 @@ int mlx5_deactivate_lag(struct mlx5_lag *ldev) return 0; } -#define MLX5_LAG_OFFLOADS_SUPPORTED_PORTS 2 +#define MLX5_LAG_OFFLOADS_SUPPORTED_PORTS 4 bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) { #ifdef CONFIG_MLX5_ESWITCH @@ -711,7 +737,7 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) if (mlx5_eswitch_mode(ldev->pf[i].dev) != mode) return false; - if (mode == MLX5_ESWITCH_OFFLOADS && ldev->ports != MLX5_LAG_OFFLOADS_SUPPORTED_PORTS) + if (mode == MLX5_ESWITCH_OFFLOADS && ldev->ports > MLX5_LAG_OFFLOADS_SUPPORTED_PORTS) return false; #else for (i = 0; i < ldev->ports; i++) @@ -759,7 +785,6 @@ void mlx5_disable_lag(struct mlx5_lag *ldev) { bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags); struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; - struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; bool roce_lag; int err; int i; @@ -784,28 +809,35 @@ void mlx5_disable_lag(struct mlx5_lag *ldev) if (shared_fdb || roce_lag) mlx5_lag_add_devices(ldev); - if (shared_fdb) { - if (!(dev0->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) - mlx5_eswitch_reload_reps(dev0->priv.eswitch); - if (!(dev1->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) - mlx5_eswitch_reload_reps(dev1->priv.eswitch); - } + if (shared_fdb) + for (i = 0; i < ldev->ports; i++) + if (!(ldev->pf[i].dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) + mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); } -bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev) +static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev) { - struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; - struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; - - if (is_mdev_switchdev_mode(dev0) && - is_mdev_switchdev_mode(dev1) && - mlx5_eswitch_vport_match_metadata_enabled(dev0->priv.eswitch) && - mlx5_eswitch_vport_match_metadata_enabled(dev1->priv.eswitch) && - mlx5_devcom_is_paired(dev0->priv.devcom, - MLX5_DEVCOM_ESW_OFFLOADS) && - MLX5_CAP_GEN(dev1, lag_native_fdb_selection) && - MLX5_CAP_ESW(dev1, root_ft_on_other_esw) && - MLX5_CAP_ESW(dev0, esw_shared_ingress_acl)) + struct mlx5_core_dev *dev; + int i; + + for (i = MLX5_LAG_P1 + 1; i < ldev->ports; i++) { + dev = ldev->pf[i].dev; + if (is_mdev_switchdev_mode(dev) && + mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) && + MLX5_CAP_GEN(dev, lag_native_fdb_selection) && + MLX5_CAP_ESW(dev, root_ft_on_other_esw) && + mlx5_eswitch_get_npeers(dev->priv.eswitch) == + MLX5_CAP_GEN(dev, num_lag_ports) - 1) + continue; + return false; + } + + dev = ldev->pf[MLX5_LAG_P1].dev; + if (is_mdev_switchdev_mode(dev) && + mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) && + mlx5_devcom_comp_is_ready(dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS) && + MLX5_CAP_ESW(dev, esw_shared_ingress_acl) && + mlx5_eswitch_get_npeers(dev->priv.eswitch) == MLX5_CAP_GEN(dev, num_lag_ports) - 1) return true; return false; @@ -842,7 +874,6 @@ static bool mlx5_lag_should_disable_lag(struct mlx5_lag *ldev, bool do_bond) static void mlx5_do_bond(struct mlx5_lag *ldev) { struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; - struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; struct lag_tracker tracker = { }; bool do_bond, roce_lag; int err; @@ -883,20 +914,24 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) for (i = 1; i < ldev->ports; i++) mlx5_nic_vport_enable_roce(ldev->pf[i].dev); } else if (shared_fdb) { + int i; + dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); - err = mlx5_eswitch_reload_reps(dev0->priv.eswitch); - if (!err) - err = mlx5_eswitch_reload_reps(dev1->priv.eswitch); + for (i = 0; i < ldev->ports; i++) { + err = mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); + if (err) + break; + } if (err) { dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); mlx5_deactivate_lag(ldev); mlx5_lag_add_devices(ldev); - mlx5_eswitch_reload_reps(dev0->priv.eswitch); - mlx5_eswitch_reload_reps(dev1->priv.eswitch); + for (i = 0; i < ldev->ports; i++) + mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); mlx5_core_err(dev0, "Failed to enable lag\n"); return; } @@ -1233,14 +1268,21 @@ recheck: mlx5_ldev_put(ldev); } +bool mlx5_lag_is_supported(struct mlx5_core_dev *dev) +{ + if (!MLX5_CAP_GEN(dev, vport_group_manager) || + !MLX5_CAP_GEN(dev, lag_master) || + MLX5_CAP_GEN(dev, num_lag_ports) < 2 || + MLX5_CAP_GEN(dev, num_lag_ports) > MLX5_MAX_PORTS) + return false; + return true; +} + void mlx5_lag_add_mdev(struct mlx5_core_dev *dev) { int err; - if (!MLX5_CAP_GEN(dev, vport_group_manager) || - !MLX5_CAP_GEN(dev, lag_master) || - (MLX5_CAP_GEN(dev, num_lag_ports) > MLX5_MAX_PORTS || - MLX5_CAP_GEN(dev, num_lag_ports) <= 1)) + if (!mlx5_lag_is_supported(dev)) return; recheck: @@ -1496,26 +1538,37 @@ u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_lag_get_num_ports); -struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev) +struct mlx5_core_dev *mlx5_lag_get_next_peer_mdev(struct mlx5_core_dev *dev, int *i) { struct mlx5_core_dev *peer_dev = NULL; struct mlx5_lag *ldev; unsigned long flags; + int idx; spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); if (!ldev) goto unlock; - peer_dev = ldev->pf[MLX5_LAG_P1].dev == dev ? - ldev->pf[MLX5_LAG_P2].dev : - ldev->pf[MLX5_LAG_P1].dev; + if (*i == ldev->ports) + goto unlock; + for (idx = *i; idx < ldev->ports; idx++) + if (ldev->pf[idx].dev != dev) + break; + + if (idx == ldev->ports) { + *i = idx; + goto unlock; + } + *i = idx + 1; + + peer_dev = ldev->pf[idx].dev; unlock: spin_unlock_irqrestore(&lag_lock, flags); return peer_dev; } -EXPORT_SYMBOL(mlx5_lag_get_peer_mdev); +EXPORT_SYMBOL(mlx5_lag_get_next_peer_mdev); int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, u64 *values, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h index bc1f1dd3e283..a061b1873e27 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h @@ -74,15 +74,7 @@ struct mlx5_lag { struct lag_mpesw lag_mpesw; }; -static inline bool mlx5_is_lag_supported(struct mlx5_core_dev *dev) -{ - if (!MLX5_CAP_GEN(dev, vport_group_manager) || - !MLX5_CAP_GEN(dev, lag_master) || - MLX5_CAP_GEN(dev, num_lag_ports) < 2 || - MLX5_CAP_GEN(dev, num_lag_ports) > MLX5_MAX_PORTS) - return false; - return true; -} +bool mlx5_lag_is_supported(struct mlx5_core_dev *dev); static inline struct mlx5_lag * mlx5_lag_dev(struct mlx5_core_dev *dev) @@ -111,7 +103,6 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, bool shared_fdb); int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev, struct net_device *ndev); -bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev); char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags); void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index d85a8dfc153d..b1aa494c76ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -7,13 +7,14 @@ #include "lag/mp.h" #include "mlx5_core.h" #include "eswitch.h" -#include "lib/mlx5.h" +#include "lib/events.h" static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev) { return ldev->mode == MLX5_LAG_MODE_MULTIPATH; } +#define MLX5_LAG_MULTIPATH_OFFLOADS_SUPPORTED_PORTS 2 static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev) { if (!mlx5_lag_is_ready(ldev)) @@ -22,6 +23,9 @@ static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev) if (__mlx5_lag_is_active(ldev) && !__mlx5_lag_is_multipath(ldev)) return false; + if (ldev->ports > MLX5_LAG_MULTIPATH_OFFLOADS_SUPPORTED_PORTS) + return false; + return mlx5_esw_multipath_prereq(ldev->pf[MLX5_LAG_P1].dev, ldev->pf[MLX5_LAG_P2].dev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index 0c0ef600f643..4bf15391525c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -6,7 +6,7 @@ #include "lag/lag.h" #include "eswitch.h" #include "esw/acl/ofld.h" -#include "lib/mlx5.h" +#include "lib/events.h" static void mlx5_mpesw_metadata_cleanup(struct mlx5_lag *ldev) { @@ -65,6 +65,7 @@ err_metadata: return err; } +#define MLX5_LAG_MPESW_OFFLOADS_SUPPORTED_PORTS 2 static int enable_mpesw(struct mlx5_lag *ldev) { struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; @@ -74,6 +75,9 @@ static int enable_mpesw(struct mlx5_lag *ldev) if (ldev->mode != MLX5_LAG_MODE_NONE) return -EINVAL; + if (ldev->ports > MLX5_LAG_MPESW_OFFLOADS_SUPPORTED_PORTS) + return -EOPNOTSUPP; + if (mlx5_eswitch_mode(dev0) != MLX5_ESWITCH_OFFLOADS || !MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table) || !MLX5_CAP_GEN(dev0, create_lag_when_not_master_up) || diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c index d3a3fe4ce670..7d9bbb494d95 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -574,7 +574,7 @@ static int __mlx5_lag_modify_definers_destinations(struct mlx5_lag *ldev, for (i = 0; i < ldev->ports; i++) { for (j = 0; j < ldev->buckets; j++) { idx = i * ldev->buckets + j; - if (ldev->v2p_map[i] == ports[i]) + if (ldev->v2p_map[idx] == ports[idx]) continue; dest.vport.vhca_id = MLX5_CAP_GEN(ldev->pf[ports[idx] - 1].dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 932fbc843c69..aa29f09e8356 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -32,6 +32,7 @@ #include <linux/clocksource.h> #include <linux/highmem.h> +#include <linux/log2.h> #include <linux/ptp_clock_kernel.h> #include <rdma/mlx5-abi.h> #include "lib/eq.h" @@ -39,10 +40,6 @@ #include "clock.h" enum { - MLX5_CYCLES_SHIFT = 31 -}; - -enum { MLX5_PIN_MODE_IN = 0x0, MLX5_PIN_MODE_OUT = 0x1, }; @@ -93,17 +90,48 @@ static bool mlx5_modify_mtutc_allowed(struct mlx5_core_dev *mdev) return MLX5_CAP_MCAM_FEATURE(mdev, ptpcyc2realtime_modify); } -static bool mlx5_is_mtutc_time_adj_cap(struct mlx5_core_dev *mdev, s64 delta) +static u32 mlx5_ptp_shift_constant(u32 dev_freq_khz) { - s64 min = MLX5_MTUTC_OPERATION_ADJUST_TIME_MIN; - s64 max = MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX; + /* Optimal shift constant leads to corrections above just 1 scaled ppm. + * + * Two sets of equations are needed to derive the optimal shift + * constant for the cyclecounter. + * + * dev_freq_khz * 1000 / 2^shift_constant = 1 scaled_ppm + * ppb = scaled_ppm * 1000 / 2^16 + * + * Using the two equations together + * + * dev_freq_khz * 1000 / 1 scaled_ppm = 2^shift_constant + * dev_freq_khz * 2^16 / 1 ppb = 2^shift_constant + * dev_freq_khz = 2^(shift_constant - 16) + * + * then yields + * + * shift_constant = ilog2(dev_freq_khz) + 16 + */ - if (MLX5_CAP_MCAM_FEATURE(mdev, mtutc_time_adjustment_extended_range)) { - min = MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MIN; - max = MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX; - } + return min(ilog2(dev_freq_khz) + 16, + ilog2((U32_MAX / NSEC_PER_MSEC) * dev_freq_khz)); +} + +static s32 mlx5_ptp_getmaxphase(struct ptp_clock_info *ptp) +{ + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info); + struct mlx5_core_dev *mdev; + + mdev = container_of(clock, struct mlx5_core_dev, clock); + + return MLX5_CAP_MCAM_FEATURE(mdev, mtutc_time_adjustment_extended_range) ? + MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX : + MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX; +} + +static bool mlx5_is_mtutc_time_adj_cap(struct mlx5_core_dev *mdev, s64 delta) +{ + s64 max = mlx5_ptp_getmaxphase(&mdev->clock.ptp_info); - if (delta < min || delta > max) + if (delta < -max || delta > max) return false; return true; @@ -221,10 +249,15 @@ static void mlx5_timestamp_overflow(struct work_struct *work) clock = container_of(timer, struct mlx5_clock, timer); mdev = container_of(clock, struct mlx5_core_dev, clock); + if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + goto out; + write_seqlock_irqsave(&clock->lock, flags); timecounter_read(&timer->tc); mlx5_update_clock_info_page(mdev); write_sequnlock_irqrestore(&clock->lock, flags); + +out: schedule_delayed_work(&timer->overflow_work, timer->overflow_period); } @@ -351,14 +384,6 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta) { - struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info); - struct mlx5_core_dev *mdev; - - mdev = container_of(clock, struct mlx5_core_dev, clock); - - if (!mlx5_is_mtutc_time_adj_cap(mdev, delta)) - return -ERANGE; - return mlx5_ptp_adjtime(ptp, delta); } @@ -734,6 +759,7 @@ static const struct ptp_clock_info mlx5_ptp_clock_info = { .pps = 0, .adjfine = mlx5_ptp_adjfine, .adjphase = mlx5_ptp_adjphase, + .getmaxphase = mlx5_ptp_getmaxphase, .adjtime = mlx5_ptp_adjtime, .gettimex64 = mlx5_ptp_gettimex, .settime64 = mlx5_ptp_settime, @@ -905,7 +931,7 @@ static void mlx5_timecounter_init(struct mlx5_core_dev *mdev) dev_freq = MLX5_CAP_GEN(mdev, device_frequency_khz); timer->cycles.read = read_internal_timer; - timer->cycles.shift = MLX5_CYCLES_SHIFT; + timer->cycles.shift = mlx5_ptp_shift_constant(dev_freq); timer->cycles.mult = clocksource_khz2mult(dev_freq, timer->cycles.shift); timer->nominal_c_mult = timer->cycles.mult; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index b7d779d08d83..78c94b22bdc0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -19,7 +19,7 @@ struct mlx5_devcom_component { mlx5_devcom_event_handler_t handler; struct rw_semaphore sem; - bool paired; + bool ready; }; struct mlx5_devcom_list { @@ -75,13 +75,14 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) if (!mlx5_core_is_pf(dev)) return NULL; - if (MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_DEVCOM_PORTS_SUPPORTED) + if (MLX5_CAP_GEN(dev, num_lag_ports) > MLX5_DEVCOM_PORTS_SUPPORTED) return NULL; mlx5_dev_list_lock(); sguid0 = mlx5_query_nic_system_image_guid(dev); list_for_each_entry(iter, &devcom_list, list) { - struct mlx5_core_dev *tmp_dev = NULL; + /* There is at least one device in iter */ + struct mlx5_core_dev *tmp_dev; idx = -1; for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) { @@ -193,7 +194,7 @@ void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom, int mlx5_devcom_send_event(struct mlx5_devcom *devcom, enum mlx5_devcom_components id, - int event, + int event, int rollback_event, void *event_data) { struct mlx5_devcom_component *comp; @@ -210,84 +211,134 @@ int mlx5_devcom_send_event(struct mlx5_devcom *devcom, if (i != devcom->idx && data) { err = comp->handler(event, data, event_data); - break; + if (err) + goto rollback; } } up_write(&comp->sem); + return 0; + +rollback: + while (i--) { + void *data = rcu_dereference_protected(comp->device[i].data, + lockdep_is_held(&comp->sem)); + + if (i != devcom->idx && data) + comp->handler(rollback_event, data, event_data); + } + + up_write(&comp->sem); return err; } -void mlx5_devcom_set_paired(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, - bool paired) +void mlx5_devcom_comp_set_ready(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id, + bool ready) { struct mlx5_devcom_component *comp; comp = &devcom->priv->components[id]; WARN_ON(!rwsem_is_locked(&comp->sem)); - WRITE_ONCE(comp->paired, paired); + WRITE_ONCE(comp->ready, ready); } -bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id) +bool mlx5_devcom_comp_is_ready(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id) { if (IS_ERR_OR_NULL(devcom)) return false; - return READ_ONCE(devcom->priv->components[id].paired); + return READ_ONCE(devcom->priv->components[id].ready); } -void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id) +bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id) { struct mlx5_devcom_component *comp; - int i; if (IS_ERR_OR_NULL(devcom)) - return NULL; + return false; comp = &devcom->priv->components[id]; down_read(&comp->sem); - if (!READ_ONCE(comp->paired)) { + if (!READ_ONCE(comp->ready)) { up_read(&comp->sem); - return NULL; + return false; } - for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) - if (i != devcom->idx) - break; + return true; +} + +void mlx5_devcom_for_each_peer_end(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id) +{ + struct mlx5_devcom_component *comp = &devcom->priv->components[id]; - return rcu_dereference_protected(comp->device[i].data, lockdep_is_held(&comp->sem)); + up_read(&comp->sem); } -void *mlx5_devcom_get_peer_data_rcu(struct mlx5_devcom *devcom, enum mlx5_devcom_components id) +void *mlx5_devcom_get_next_peer_data(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id, + int *i) { struct mlx5_devcom_component *comp; - int i; + void *ret; + int idx; - if (IS_ERR_OR_NULL(devcom)) - return NULL; + comp = &devcom->priv->components[id]; - for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) - if (i != devcom->idx) - break; + if (*i == MLX5_DEVCOM_PORTS_SUPPORTED) + return NULL; + for (idx = *i; idx < MLX5_DEVCOM_PORTS_SUPPORTED; idx++) { + if (idx != devcom->idx) { + ret = rcu_dereference_protected(comp->device[idx].data, + lockdep_is_held(&comp->sem)); + if (ret) + break; + } + } - comp = &devcom->priv->components[id]; - /* This can change concurrently, however 'data' pointer will remain - * valid for the duration of RCU read section. - */ - if (!READ_ONCE(comp->paired)) + if (idx == MLX5_DEVCOM_PORTS_SUPPORTED) { + *i = idx; return NULL; + } + *i = idx + 1; - return rcu_dereference(comp->device[i].data); + return ret; } -void mlx5_devcom_release_peer_data(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id) +void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id, + int *i) { - struct mlx5_devcom_component *comp = &devcom->priv->components[id]; + struct mlx5_devcom_component *comp; + void *ret; + int idx; - up_read(&comp->sem); + comp = &devcom->priv->components[id]; + + if (*i == MLX5_DEVCOM_PORTS_SUPPORTED) + return NULL; + for (idx = *i; idx < MLX5_DEVCOM_PORTS_SUPPORTED; idx++) { + if (idx != devcom->idx) { + /* This can change concurrently, however 'data' pointer will remain + * valid for the duration of RCU read section. + */ + if (!READ_ONCE(comp->ready)) + return NULL; + ret = rcu_dereference(comp->device[idx].data); + if (ret) + break; + } + } + + if (idx == MLX5_DEVCOM_PORTS_SUPPORTED) { + *i = idx; + return NULL; + } + *i = idx + 1; + + return ret; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h index 9a496f4722da..d953a01b8eaa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h @@ -6,7 +6,7 @@ #include <linux/mlx5/driver.h> -#define MLX5_DEVCOM_PORTS_SUPPORTED 2 +#define MLX5_DEVCOM_PORTS_SUPPORTED 4 enum mlx5_devcom_components { MLX5_DEVCOM_ESW_OFFLOADS, @@ -30,20 +30,33 @@ void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom, int mlx5_devcom_send_event(struct mlx5_devcom *devcom, enum mlx5_devcom_components id, - int event, + int event, int rollback_event, void *event_data); -void mlx5_devcom_set_paired(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, - bool paired); -bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id); +void mlx5_devcom_comp_set_ready(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id, + bool ready); +bool mlx5_devcom_comp_is_ready(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id); -void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id); -void *mlx5_devcom_get_peer_data_rcu(struct mlx5_devcom *devcom, enum mlx5_devcom_components id); -void mlx5_devcom_release_peer_data(struct mlx5_devcom *devcom, +bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id); +void mlx5_devcom_for_each_peer_end(struct mlx5_devcom *devcom, enum mlx5_devcom_components id); +void *mlx5_devcom_get_next_peer_data(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id, int *i); -#endif +#define mlx5_devcom_for_each_peer_entry(devcom, id, data, i) \ + for (i = 0, data = mlx5_devcom_get_next_peer_data(devcom, id, &i); \ + data; \ + data = mlx5_devcom_get_next_peer_data(devcom, id, &i)) + +void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id, int *i); +#define mlx5_devcom_for_each_peer_entry_rcu(devcom, id, data, i) \ + for (i = 0, data = mlx5_devcom_get_next_peer_data_rcu(devcom, id, &i); \ + data; \ + data = mlx5_devcom_get_next_peer_data_rcu(devcom, id, &i)) + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/events.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/events.h new file mode 100644 index 000000000000..a0f7faea317b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/events.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __LIB_EVENTS_H__ +#define __LIB_EVENTS_H__ + +#include "mlx5_core.h" + +#define PORT_MODULE_EVENT_MODULE_STATUS_MASK 0xF +#define PORT_MODULE_EVENT_ERROR_TYPE_MASK 0xF + +enum port_module_event_status_type { + MLX5_MODULE_STATUS_PLUGGED = 0x1, + MLX5_MODULE_STATUS_UNPLUGGED = 0x2, + MLX5_MODULE_STATUS_ERROR = 0x3, + MLX5_MODULE_STATUS_DISABLED = 0x4, + MLX5_MODULE_STATUS_NUM, +}; + +enum port_module_event_error_type { + MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED = 0x0, + MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX = 0x1, + MLX5_MODULE_EVENT_ERROR_BUS_STUCK = 0x2, + MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT = 0x3, + MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST = 0x4, + MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER = 0x5, + MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE = 0x6, + MLX5_MODULE_EVENT_ERROR_BAD_CABLE = 0x7, + MLX5_MODULE_EVENT_ERROR_PCIE_POWER_SLOT_EXCEEDED = 0xc, + MLX5_MODULE_EVENT_ERROR_NUM, +}; + +struct mlx5_pme_stats { + u64 status_counters[MLX5_MODULE_STATUS_NUM]; + u64 error_counters[MLX5_MODULE_EVENT_ERROR_NUM]; +}; + +void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats); +int mlx5_notifier_call_chain(struct mlx5_events *events, unsigned int event, void *data); +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c index db9df9798ffa..a80ecb672f33 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c @@ -178,7 +178,7 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains, if (!mlx5_chains_ignore_flow_level_supported(chains) || (chain == 0 && prio == 1 && level == 0)) { ft_attr.level = chains->fs_base_level; - ft_attr.prio = chains->fs_base_prio; + ft_attr.prio = chains->fs_base_prio + prio - 1; ns = (chains->ns == MLX5_FLOW_NAMESPACE_FDB) ? mlx5_get_fdb_sub_ns(chains->dev, chain) : mlx5_get_flow_namespace(chains->dev, chains->ns); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h index ccf12f7db6f0..2b5826a785c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h @@ -45,40 +45,6 @@ int mlx5_crdump_enable(struct mlx5_core_dev *dev); void mlx5_crdump_disable(struct mlx5_core_dev *dev); int mlx5_crdump_collect(struct mlx5_core_dev *dev, u32 *cr_data); -/* TODO move to lib/events.h */ - -#define PORT_MODULE_EVENT_MODULE_STATUS_MASK 0xF -#define PORT_MODULE_EVENT_ERROR_TYPE_MASK 0xF - -enum port_module_event_status_type { - MLX5_MODULE_STATUS_PLUGGED = 0x1, - MLX5_MODULE_STATUS_UNPLUGGED = 0x2, - MLX5_MODULE_STATUS_ERROR = 0x3, - MLX5_MODULE_STATUS_DISABLED = 0x4, - MLX5_MODULE_STATUS_NUM, -}; - -enum port_module_event_error_type { - MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED = 0x0, - MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX = 0x1, - MLX5_MODULE_EVENT_ERROR_BUS_STUCK = 0x2, - MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT = 0x3, - MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST = 0x4, - MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER = 0x5, - MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE = 0x6, - MLX5_MODULE_EVENT_ERROR_BAD_CABLE = 0x7, - MLX5_MODULE_EVENT_ERROR_PCIE_POWER_SLOT_EXCEEDED = 0xc, - MLX5_MODULE_EVENT_ERROR_NUM, -}; - -struct mlx5_pme_stats { - u64 status_counters[MLX5_MODULE_STATUS_NUM]; - u64 error_counters[MLX5_MODULE_EVENT_ERROR_NUM]; -}; - -void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats); -int mlx5_notifier_call_chain(struct mlx5_events *events, unsigned int event, void *data); - static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev) { return devlink_net(priv_to_devlink(dev)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c index 8ff16318e32d..4450091e181a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -99,7 +99,7 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev) int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table); struct mlx5_mpfs *mpfs; - if (!MLX5_ESWITCH_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev) || l2table_size == 1) return 0; mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c index 696e45e2bd06..e223e0e46433 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c @@ -24,7 +24,8 @@ static const u32 tout_def_sw_val[MAX_TIMEOUT_TYPES] = { [MLX5_TO_TEARDOWN_MS] = 3000, [MLX5_TO_FSM_REACTIVATE_MS] = 5000, [MLX5_TO_RECLAIM_PAGES_MS] = 5000, - [MLX5_TO_RECLAIM_VFS_PAGES_MS] = 120000 + [MLX5_TO_RECLAIM_VFS_PAGES_MS] = 120000, + [MLX5_TO_RESET_UNLOAD_MS] = 300000 }; static void tout_set(struct mlx5_core_dev *dev, u64 val, enum mlx5_timeouts_types type) @@ -118,7 +119,8 @@ u64 _mlx5_tout_ms(struct mlx5_core_dev *dev, enum mlx5_timeouts_types type) #define MLX5_TIMEOUT_FILL(fld, reg_out, dev, to_type, to_extra) \ ({ \ u64 fw_to = MLX5_TIMEOUT_QUERY(fld, reg_out); \ - tout_set(dev, fw_to + (to_extra), to_type); \ + if (fw_to) \ + tout_set(dev, fw_to + (to_extra), to_type); \ fw_to; \ }) @@ -146,6 +148,7 @@ static int tout_query_dtor(struct mlx5_core_dev *dev) MLX5_TIMEOUT_FILL(fsm_reactivate_to, out, dev, MLX5_TO_FSM_REACTIVATE_MS, 0); MLX5_TIMEOUT_FILL(reclaim_pages_to, out, dev, MLX5_TO_RECLAIM_PAGES_MS, 0); MLX5_TIMEOUT_FILL(reclaim_vfs_pages_to, out, dev, MLX5_TO_RECLAIM_VFS_PAGES_MS, 0); + MLX5_TIMEOUT_FILL(reset_unload_to, out, dev, MLX5_TO_RESET_UNLOAD_MS, 0); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h index bc9e9aeda847..99e0a05526fe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h @@ -26,6 +26,7 @@ enum mlx5_timeouts_types { MLX5_TO_FSM_REACTIVATE_MS, MLX5_TO_RECLAIM_PAGES_MS, MLX5_TO_RECLAIM_VFS_PAGES_MS, + MLX5_TO_RESET_UNLOAD_MS, MAX_TIMEOUT_TYPES }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index d6ee016deae1..72ae560a1c68 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -619,6 +619,9 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) if (MLX5_CAP_GEN_MAX(dev, pci_sync_for_fw_update_event)) MLX5_SET(cmd_hca_cap, set_hca_cap, pci_sync_for_fw_update_event, 1); + if (MLX5_CAP_GEN_MAX(dev, pci_sync_for_fw_update_with_driver_unload)) + MLX5_SET(cmd_hca_cap, set_hca_cap, + pci_sync_for_fw_update_with_driver_unload, 1); if (MLX5_CAP_GEN_MAX(dev, num_vhca_ports)) MLX5_SET(cmd_hca_cap, @@ -1118,7 +1121,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_devcom_unregister_device(dev->priv.devcom); } -static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot, u64 timeout) +static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeout) { int err; @@ -1183,28 +1186,56 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot, u64 timeout goto reclaim_boot_pages; } + return 0; + +reclaim_boot_pages: + mlx5_reclaim_startup_pages(dev); +err_disable_hca: + mlx5_core_disable_hca(dev, 0); +stop_health_poll: + mlx5_stop_health_poll(dev, boot); +err_cmd_cleanup: + mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); + mlx5_cmd_cleanup(dev); + + return err; +} + +static void mlx5_function_disable(struct mlx5_core_dev *dev, bool boot) +{ + mlx5_reclaim_startup_pages(dev); + mlx5_core_disable_hca(dev, 0); + mlx5_stop_health_poll(dev, boot); + mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); + mlx5_cmd_cleanup(dev); +} + +static int mlx5_function_open(struct mlx5_core_dev *dev) +{ + int err; + err = set_hca_ctrl(dev); if (err) { mlx5_core_err(dev, "set_hca_ctrl failed\n"); - goto reclaim_boot_pages; + return err; } err = set_hca_cap(dev); if (err) { mlx5_core_err(dev, "set_hca_cap failed\n"); - goto reclaim_boot_pages; + return err; } err = mlx5_satisfy_startup_pages(dev, 0); if (err) { mlx5_core_err(dev, "failed to allocate init pages\n"); - goto reclaim_boot_pages; + return err; } err = mlx5_cmd_init_hca(dev, sw_owner_id); if (err) { mlx5_core_err(dev, "init hca failed\n"); - goto reclaim_boot_pages; + return err; } mlx5_set_driver_version(dev); @@ -1212,26 +1243,13 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot, u64 timeout err = mlx5_query_hca_caps(dev); if (err) { mlx5_core_err(dev, "query hca failed\n"); - goto reclaim_boot_pages; + return err; } mlx5_start_health_fw_log_up(dev); - return 0; - -reclaim_boot_pages: - mlx5_reclaim_startup_pages(dev); -err_disable_hca: - mlx5_core_disable_hca(dev, 0); -stop_health_poll: - mlx5_stop_health_poll(dev, boot); -err_cmd_cleanup: - mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); - mlx5_cmd_cleanup(dev); - - return err; } -static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot) +static int mlx5_function_close(struct mlx5_core_dev *dev) { int err; @@ -1240,15 +1258,33 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot) mlx5_core_err(dev, "tear_down_hca failed, skip cleanup\n"); return err; } - mlx5_reclaim_startup_pages(dev); - mlx5_core_disable_hca(dev, 0); - mlx5_stop_health_poll(dev, boot); - mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); - mlx5_cmd_cleanup(dev); return 0; } +static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot, u64 timeout) +{ + int err; + + err = mlx5_function_enable(dev, boot, timeout); + if (err) + return err; + + err = mlx5_function_open(dev); + if (err) + mlx5_function_disable(dev, boot); + return err; +} + +static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot) +{ + int err = mlx5_function_close(dev); + + if (!err) + mlx5_function_disable(dev, boot); + return err; +} + static int mlx5_load(struct mlx5_core_dev *dev) { int err; @@ -1391,12 +1427,11 @@ static void mlx5_unload(struct mlx5_core_dev *dev) mlx5_put_uars_page(dev, dev->priv.uar); } -int mlx5_init_one(struct mlx5_core_dev *dev) +int mlx5_init_one_devl_locked(struct mlx5_core_dev *dev) { - struct devlink *devlink = priv_to_devlink(dev); + bool light_probe = mlx5_dev_is_lightweight(dev); int err = 0; - devl_lock(devlink); mutex_lock(&dev->intf_state_mutex); dev->state = MLX5_DEVICE_STATE_UP; @@ -1410,9 +1445,14 @@ int mlx5_init_one(struct mlx5_core_dev *dev) goto function_teardown; } - err = mlx5_devlink_params_register(priv_to_devlink(dev)); - if (err) - goto err_devlink_params_reg; + /* In case of light_probe, mlx5_devlink is already registered. + * Hence, don't register devlink again. + */ + if (!light_probe) { + err = mlx5_devlink_params_register(priv_to_devlink(dev)); + if (err) + goto err_devlink_params_reg; + } err = mlx5_load(dev); if (err) @@ -1425,14 +1465,14 @@ int mlx5_init_one(struct mlx5_core_dev *dev) goto err_register; mutex_unlock(&dev->intf_state_mutex); - devl_unlock(devlink); return 0; err_register: clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state); mlx5_unload(dev); err_load: - mlx5_devlink_params_unregister(priv_to_devlink(dev)); + if (!light_probe) + mlx5_devlink_params_unregister(priv_to_devlink(dev)); err_devlink_params_reg: mlx5_cleanup_once(dev); function_teardown: @@ -1440,6 +1480,16 @@ function_teardown: err_function: dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; mutex_unlock(&dev->intf_state_mutex); + return err; +} + +int mlx5_init_one(struct mlx5_core_dev *dev) +{ + struct devlink *devlink = priv_to_devlink(dev); + int err; + + devl_lock(devlink); + err = mlx5_init_one_devl_locked(dev); devl_unlock(devlink); return err; } @@ -1456,6 +1506,7 @@ void mlx5_uninit_one(struct mlx5_core_dev *dev) if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { mlx5_core_warn(dev, "%s: interface is down, NOP\n", __func__); + mlx5_devlink_params_unregister(priv_to_devlink(dev)); mlx5_cleanup_once(dev); goto out; } @@ -1557,6 +1608,100 @@ void mlx5_unload_one(struct mlx5_core_dev *dev, bool suspend) devl_unlock(devlink); } +/* In case of light probe, we don't need a full query of hca_caps, but only the bellow caps. + * A full query of hca_caps will be done when the device will reload. + */ +static int mlx5_query_hca_caps_light(struct mlx5_core_dev *dev) +{ + int err; + + err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL); + if (err) + return err; + + if (MLX5_CAP_GEN(dev, eth_net_offloads)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, nic_flow_table) || + MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_FLOW_TABLE); + if (err) + return err; + } + + if (MLX5_CAP_GEN_64(dev, general_obj_types) & + MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q) { + err = mlx5_core_get_caps(dev, MLX5_CAP_VDPA_EMULATION); + if (err) + return err; + } + + return 0; +} + +int mlx5_init_one_light(struct mlx5_core_dev *dev) +{ + struct devlink *devlink = priv_to_devlink(dev); + int err; + + dev->state = MLX5_DEVICE_STATE_UP; + err = mlx5_function_enable(dev, true, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT)); + if (err) { + mlx5_core_warn(dev, "mlx5_function_enable err=%d\n", err); + goto out; + } + + err = mlx5_query_hca_caps_light(dev); + if (err) { + mlx5_core_warn(dev, "mlx5_query_hca_caps_light err=%d\n", err); + goto query_hca_caps_err; + } + + devl_lock(devlink); + err = mlx5_devlink_params_register(priv_to_devlink(dev)); + devl_unlock(devlink); + if (err) { + mlx5_core_warn(dev, "mlx5_devlink_param_reg err = %d\n", err); + goto query_hca_caps_err; + } + + return 0; + +query_hca_caps_err: + mlx5_function_disable(dev, true); +out: + dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; + return err; +} + +void mlx5_uninit_one_light(struct mlx5_core_dev *dev) +{ + struct devlink *devlink = priv_to_devlink(dev); + + devl_lock(devlink); + mlx5_devlink_params_unregister(priv_to_devlink(dev)); + devl_unlock(devlink); + if (dev->state != MLX5_DEVICE_STATE_UP) + return; + mlx5_function_disable(dev, true); +} + +/* xxx_light() function are used in order to configure the device without full + * init (light init). e.g.: There isn't a point in reload a device to light state. + * Hence, mlx5_load_one_light() isn't needed. + */ + +void mlx5_unload_one_light(struct mlx5_core_dev *dev) +{ + if (dev->state != MLX5_DEVICE_STATE_UP) + return; + mlx5_function_disable(dev, false); + dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; +} + static const int types[] = { MLX5_CAP_GENERAL, MLX5_CAP_GENERAL_2, @@ -1809,7 +1954,7 @@ static void remove_one(struct pci_dev *pdev) mlx5_drain_fw_reset(dev); mlx5_drain_health_wq(dev); devlink_unregister(devlink); - mlx5_sriov_disable(pdev); + mlx5_sriov_disable(pdev, false); mlx5_thermal_uninit(dev); mlx5_crdump_disable(dev); mlx5_uninit_one(dev); @@ -1844,7 +1989,7 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, mlx5_enter_error_state(dev, false); mlx5_error_sw_reset(dev); - mlx5_unload_one(dev, true); + mlx5_unload_one(dev, false); mlx5_drain_health_wq(dev); mlx5_pci_disable_device(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 229520405d4a..682d3dc00dd1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -195,7 +195,7 @@ void mlx5_sriov_cleanup(struct mlx5_core_dev *dev); int mlx5_sriov_attach(struct mlx5_core_dev *dev); void mlx5_sriov_detach(struct mlx5_core_dev *dev); int mlx5_core_sriov_configure(struct pci_dev *dev, int num_vfs); -void mlx5_sriov_disable(struct pci_dev *pdev); +void mlx5_sriov_disable(struct pci_dev *pdev, bool num_vf_change); int mlx5_core_sriov_set_msix_vec_count(struct pci_dev *vf, int msix_vec_count); int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id); int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id); @@ -240,11 +240,14 @@ int mlx5_attach_device(struct mlx5_core_dev *dev); void mlx5_detach_device(struct mlx5_core_dev *dev, bool suspend); int mlx5_register_device(struct mlx5_core_dev *dev); void mlx5_unregister_device(struct mlx5_core_dev *dev); +void mlx5_dev_set_lightweight(struct mlx5_core_dev *dev); +bool mlx5_dev_is_lightweight(struct mlx5_core_dev *dev); struct mlx5_core_dev *mlx5_get_next_phys_dev_lag(struct mlx5_core_dev *dev); void mlx5_dev_list_lock(void); void mlx5_dev_list_unlock(void); int mlx5_dev_list_trylock(void); +void mlx5_fw_reporters_create(struct mlx5_core_dev *dev); int mlx5_query_mtpps(struct mlx5_core_dev *dev, u32 *mtpps, u32 mtpps_size); int mlx5_set_mtpps(struct mlx5_core_dev *mdev, u32 *mtpps, u32 mtpps_size); int mlx5_query_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 *arm, u8 *mode); @@ -307,16 +310,20 @@ static inline bool mlx5_core_is_sf(const struct mlx5_core_dev *dev) int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx); void mlx5_mdev_uninit(struct mlx5_core_dev *dev); int mlx5_init_one(struct mlx5_core_dev *dev); +int mlx5_init_one_devl_locked(struct mlx5_core_dev *dev); void mlx5_uninit_one(struct mlx5_core_dev *dev); void mlx5_unload_one(struct mlx5_core_dev *dev, bool suspend); void mlx5_unload_one_devl_locked(struct mlx5_core_dev *dev, bool suspend); int mlx5_load_one(struct mlx5_core_dev *dev, bool recovery); int mlx5_load_one_devl_locked(struct mlx5_core_dev *dev, bool recovery); +int mlx5_init_one_light(struct mlx5_core_dev *dev); +void mlx5_uninit_one_light(struct mlx5_core_dev *dev); +void mlx5_unload_one_light(struct mlx5_core_dev *dev); -int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap, u16 function_id, +int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap, u16 vport, u16 opmod); -#define mlx5_vport_get_other_func_general_cap(dev, fid, out) \ - mlx5_vport_get_other_func_cap(dev, fid, out, MLX5_CAP_GENERAL) +#define mlx5_vport_get_other_func_general_cap(dev, vport, out) \ + mlx5_vport_get_other_func_cap(dev, vport, out, MLX5_CAP_GENERAL) void mlx5_events_work_enqueue(struct mlx5_core_dev *dev, struct work_struct *work); static inline u32 mlx5_sriov_get_vf_total_msix(struct pci_dev *pdev) @@ -331,4 +338,31 @@ bool mlx5_rdma_supported(struct mlx5_core_dev *dev); bool mlx5_vnet_supported(struct mlx5_core_dev *dev); bool mlx5_same_hw_devs(struct mlx5_core_dev *dev, struct mlx5_core_dev *peer_dev); +static inline u16 mlx5_core_ec_vf_vport_base(const struct mlx5_core_dev *dev) +{ + return MLX5_CAP_GEN_2(dev, ec_vf_vport_base); +} + +static inline u16 mlx5_core_ec_sriov_enabled(const struct mlx5_core_dev *dev) +{ + return mlx5_core_is_ecpf(dev) && mlx5_core_ec_vf_vport_base(dev); +} + +static inline bool mlx5_core_is_ec_vf_vport(const struct mlx5_core_dev *dev, u16 vport_num) +{ + int base_vport = mlx5_core_ec_vf_vport_base(dev); + int max_vport = base_vport + mlx5_core_max_ec_vfs(dev); + + if (!mlx5_core_ec_sriov_enabled(dev)) + return false; + + return (vport_num >= base_vport && vport_num < max_vport); +} + +static inline int mlx5_vport_to_func_id(const struct mlx5_core_dev *dev, u16 vport, bool ec_vf_func) +{ + return ec_vf_func ? vport - mlx5_core_ec_vf_vport_base(dev) + 1 + : vport; +} + #endif /* __MLX5_CORE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 95dc67fb3001..dcf58efac159 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -79,7 +79,13 @@ static u16 func_id_to_type(struct mlx5_core_dev *dev, u16 func_id, bool ec_funct if (!func_id) return mlx5_core_is_ecpf(dev) && !ec_function ? MLX5_HOST_PF : MLX5_PF; - return func_id <= mlx5_core_max_vfs(dev) ? MLX5_VF : MLX5_SF; + if (func_id <= max(mlx5_core_max_vfs(dev), mlx5_core_max_ec_vfs(dev))) { + if (ec_function) + return MLX5_EC_VF; + else + return MLX5_VF; + } + return MLX5_SF; } static u32 mlx5_get_ec_function(u32 function) @@ -730,6 +736,9 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) WARN(dev->priv.page_counters[MLX5_HOST_PF], "External host PF FW pages counter is %d after reclaiming all pages\n", dev->priv.page_counters[MLX5_HOST_PF]); + WARN(dev->priv.page_counters[MLX5_EC_VF], + "EC VFs FW pages counter is %d after reclaiming all pages\n", + dev->priv.page_counters[MLX5_EC_VF]); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 98412bd5a696..cba2a4afb5fd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -41,6 +41,15 @@ struct mlx5_irq_table { struct mlx5_irq_pool *sf_comp_pool; }; +static int mlx5_core_func_to_vport(const struct mlx5_core_dev *dev, + int func, + bool ec_vf_func) +{ + if (!ec_vf_func) + return func; + return mlx5_core_ec_vf_vport_base(dev) + func - 1; +} + /** * mlx5_get_default_msix_vec_count - Get the default number of MSI-X vectors * to be ssigned to each VF. @@ -79,6 +88,8 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in); void *hca_cap = NULL, *query_cap = NULL, *cap; int num_vf_msix, min_msix, max_msix; + bool ec_vf_function; + int vport; int ret; num_vf_msix = MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix); @@ -104,7 +115,9 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, goto out; } - ret = mlx5_vport_get_other_func_general_cap(dev, function_id, query_cap); + ec_vf_function = mlx5_core_ec_sriov_enabled(dev); + vport = mlx5_core_func_to_vport(dev, function_id, ec_vf_function); + ret = mlx5_vport_get_other_func_general_cap(dev, vport, query_cap); if (ret) goto out; @@ -115,6 +128,7 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, MLX5_SET(set_hca_cap_in, hca_cap, opcode, MLX5_CMD_OP_SET_HCA_CAP); MLX5_SET(set_hca_cap_in, hca_cap, other_function, 1); + MLX5_SET(set_hca_cap_in, hca_cap, ec_vf_function, ec_vf_function); MLX5_SET(set_hca_cap_in, hca_cap, function_id, function_id); MLX5_SET(set_hca_cap_in, hca_cap, op_mod, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c index 540cf05f6373..a42f6cd99b74 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c @@ -30,9 +30,8 @@ static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev) struct mlx5_flow_spec *spec; struct mlx5_flow_table *ft; struct mlx5_flow_group *fg; - void *match_criteria; + struct mlx5_eswitch *esw; u32 *flow_group_in; - void *misc; int err; if (!(MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) && @@ -63,12 +62,8 @@ static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev) goto free; } - MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, - MLX5_MATCH_MISC_PARAMETERS); - match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, - match_criteria); - MLX5_SET_TO_ONES(fte_match_param, match_criteria, - misc_parameters.source_port); + esw = dev->priv.eswitch; + mlx5_esw_set_flow_group_source_port(esw, flow_group_in, 0); fg = mlx5_create_flow_group(ft, flow_group_in); if (IS_ERR(fg)) { @@ -77,14 +72,7 @@ static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev) goto destroy_flow_table; } - spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; - misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, - misc_parameters); - MLX5_SET(fte_match_set_misc, misc, source_port, - dev->priv.eswitch->manager_vport); - misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, - misc_parameters); - MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); + mlx5_esw_set_spec_source_port(esw, esw->manager_vport, spec); flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW; flow_rule = mlx5_add_flow_rules(ft, spec, &flow_act, NULL, 0); @@ -115,7 +103,7 @@ free: static void mlx5_rdma_del_roce_addr(struct mlx5_core_dev *dev) { - mlx5_core_roce_gid_set(dev, 0, 0, 0, + mlx5_core_roce_gid_set(dev, 0, MLX5_ROCE_VERSION_2, 0, NULL, NULL, false, 0, 1); } @@ -135,7 +123,7 @@ static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev) mlx5_rdma_make_default_gid(dev, &gid); return mlx5_core_roce_gid_set(dev, 0, - MLX5_ROCE_VERSION_1, + MLX5_ROCE_VERSION_2, 0, gid.raw, mac, false, 0, 1); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index 0692363cf80e..8fe82f1191bb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -3,6 +3,7 @@ #include <linux/mlx5/driver.h> #include <linux/mlx5/device.h> +#include <linux/mlx5/eswitch.h> #include "mlx5_core.h" #include "dev.h" #include "devlink.h" @@ -28,6 +29,10 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia mdev->priv.adev_idx = adev->id; sf_dev->mdev = mdev; + /* Only local SFs do light probe */ + if (MLX5_ESWITCH_MANAGER(sf_dev->parent_mdev)) + mlx5_dev_set_lightweight(mdev); + err = mlx5_mdev_init(mdev, MLX5_SF_PROF); if (err) { mlx5_core_warn(mdev, "mlx5_mdev_init on err=%d\n", err); @@ -41,7 +46,10 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia goto remap_err; } - err = mlx5_init_one(mdev); + if (MLX5_ESWITCH_MANAGER(sf_dev->parent_mdev)) + err = mlx5_init_one_light(mdev); + else + err = mlx5_init_one(mdev); if (err) { mlx5_core_warn(mdev, "mlx5_init_one err=%d\n", err); goto init_one_err; @@ -65,7 +73,10 @@ static void mlx5_sf_dev_remove(struct auxiliary_device *adev) mlx5_drain_health_wq(sf_dev->mdev); devlink_unregister(devlink); - mlx5_uninit_one(sf_dev->mdev); + if (mlx5_dev_is_lightweight(sf_dev->mdev)) + mlx5_uninit_one_light(sf_dev->mdev); + else + mlx5_uninit_one(sf_dev->mdev); iounmap(sf_dev->mdev->iseg); mlx5_mdev_uninit(sf_dev->mdev); mlx5_devlink_free(devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index 7d955a4d9f14..6a3fa30b2bf2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -28,7 +28,6 @@ struct mlx5_sf_table { struct mutex sf_state_lock; /* Serializes sf state among user cmds & vhca event handler. */ struct notifier_block esw_nb; struct notifier_block vhca_nb; - u8 ecpu: 1; }; static struct mlx5_sf * @@ -283,7 +282,7 @@ out: static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table, const struct devlink_port_new_attrs *new_attr, struct netlink_ext_ack *extack, - unsigned int *new_port_index) + struct devlink_port **dl_port) { struct mlx5_eswitch *esw = dev->priv.eswitch; struct mlx5_sf *sf; @@ -297,7 +296,7 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table, new_attr->controller, new_attr->sfnum); if (err) goto esw_err; - *new_port_index = sf->port_index; + *dl_port = &sf->dl_port; trace_mlx5_sf_add(dev, sf->port_index, sf->controller, sf->hw_fn_id, new_attr->sfnum); return 0; @@ -339,7 +338,7 @@ mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_ int mlx5_devlink_sf_port_new(struct devlink *devlink, const struct devlink_port_new_attrs *new_attr, struct netlink_ext_ack *extack, - unsigned int *new_port_index) + struct devlink_port **dl_port) { struct mlx5_core_dev *dev = devlink_priv(devlink); struct mlx5_sf_table *table; @@ -355,7 +354,7 @@ int mlx5_devlink_sf_port_new(struct devlink *devlink, "Port add is only supported in eswitch switchdev mode or SF ports are disabled."); return -EOPNOTSUPP; } - err = mlx5_sf_add(dev, table, new_attr, extack, new_port_index); + err = mlx5_sf_add(dev, table, new_attr, extack, dl_port); mlx5_sf_table_put(table); return err; } @@ -379,7 +378,8 @@ static void mlx5_sf_dealloc(struct mlx5_sf_table *table, struct mlx5_sf *sf) } } -int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index, +int mlx5_devlink_sf_port_del(struct devlink *devlink, + struct devlink_port *dl_port, struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); @@ -394,7 +394,7 @@ int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index, "Port del is only supported in eswitch switchdev mode or SF ports are disabled."); return -EOPNOTSUPP; } - sf = mlx5_sf_lookup_by_index(table, port_index); + sf = mlx5_sf_lookup_by_index(table, dl_port->index); if (!sf) { err = -ENODEV; goto sf_err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h index 3a480e06ecc0..860f9ddb7107 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h @@ -21,8 +21,9 @@ void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev); int mlx5_devlink_sf_port_new(struct devlink *devlink, const struct devlink_port_new_attrs *add_attr, struct netlink_ext_ack *extack, - unsigned int *new_port_index); -int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index, + struct devlink_port **dl_port); +int mlx5_devlink_sf_port_del(struct devlink *devlink, + struct devlink_port *dl_port, struct netlink_ext_ack *extack); int mlx5_devlink_sf_port_fn_state_get(struct devlink_port *dl_port, enum devlink_port_fn_state *state, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 20d7662c10fb..a2fc937d5461 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -37,7 +37,7 @@ #include "mlx5_irq.h" #include "eswitch.h" -static int sriov_restore_guids(struct mlx5_core_dev *dev, int vf) +static int sriov_restore_guids(struct mlx5_core_dev *dev, int vf, u16 func_id) { struct mlx5_core_sriov *sriov = &dev->priv.sriov; struct mlx5_hca_vport_context *in; @@ -59,7 +59,7 @@ static int sriov_restore_guids(struct mlx5_core_dev *dev, int vf) !!(in->node_guid) * MLX5_HCA_VPORT_SEL_NODE_GUID | !!(in->policy) * MLX5_HCA_VPORT_SEL_STATE_POLICY; - err = mlx5_core_modify_hca_vport_context(dev, 1, 1, vf + 1, in); + err = mlx5_core_modify_hca_vport_context(dev, 1, 1, func_id, in); if (err) mlx5_core_warn(dev, "modify vport context failed, unable to restore VF %d settings\n", vf); @@ -73,9 +73,7 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) { struct mlx5_core_sriov *sriov = &dev->priv.sriov; int err, vf, num_msix_count; - - if (!MLX5_ESWITCH_MANAGER(dev)) - goto enable_vfs_hca; + int vport_num; err = mlx5_eswitch_enable(dev->priv.eswitch, num_vfs); if (err) { @@ -84,7 +82,6 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) return err; } -enable_vfs_hca: num_msix_count = mlx5_get_default_msix_vec_count(dev, num_vfs); for (vf = 0; vf < num_vfs; vf++) { /* Notify the VF before its enablement to let it set @@ -108,7 +105,10 @@ enable_vfs_hca: sriov->vfs_ctx[vf].enabled = 1; if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) { - err = sriov_restore_guids(dev, vf); + vport_num = mlx5_core_ec_sriov_enabled(dev) ? + mlx5_core_ec_vf_vport_base(dev) + vf + : vf + 1; + err = sriov_restore_guids(dev, vf, vport_num); if (err) { mlx5_core_warn(dev, "failed to restore VF %d settings, err %d\n", @@ -123,9 +123,11 @@ enable_vfs_hca: } static void -mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf) +mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf, bool num_vf_change) { struct mlx5_core_sriov *sriov = &dev->priv.sriov; + bool wait_for_ec_vf_pages = true; + bool wait_for_vf_pages = true; int err; int vf; @@ -147,11 +149,30 @@ mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf) mlx5_eswitch_disable_sriov(dev->priv.eswitch, clear_vf); + /* There are a number of scenarios when SRIOV is being disabled: + * 1. VFs or ECVFs had been created, and now set back to 0 (num_vf_change == true). + * - If EC SRIOV is enabled then this flow is happening on the + * embedded platform, wait for only EC VF pages. + * - If EC SRIOV is not enabled this flow is happening on non-embedded + * platform, wait for the VF pages. + * + * 2. The driver is being unloaded. In this case wait for all pages. + */ + if (num_vf_change) { + if (mlx5_core_ec_sriov_enabled(dev)) + wait_for_vf_pages = false; + else + wait_for_ec_vf_pages = false; + } + + if (wait_for_ec_vf_pages && mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_EC_VF])) + mlx5_core_warn(dev, "timeout reclaiming EC VFs pages\n"); + /* For ECPFs, skip waiting for host VF pages until ECPF is destroyed */ if (mlx5_core_is_ecpf(dev)) return; - if (mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_VF])) + if (wait_for_vf_pages && mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_VF])) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); } @@ -172,12 +193,12 @@ static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs) err = pci_enable_sriov(pdev, num_vfs); if (err) { mlx5_core_warn(dev, "pci_enable_sriov failed : %d\n", err); - mlx5_device_disable_sriov(dev, num_vfs, true); + mlx5_device_disable_sriov(dev, num_vfs, true, true); } return err; } -void mlx5_sriov_disable(struct pci_dev *pdev) +void mlx5_sriov_disable(struct pci_dev *pdev, bool num_vf_change) { struct mlx5_core_dev *dev = pci_get_drvdata(pdev); struct devlink *devlink = priv_to_devlink(dev); @@ -185,7 +206,7 @@ void mlx5_sriov_disable(struct pci_dev *pdev) pci_disable_sriov(pdev); devl_lock(devlink); - mlx5_device_disable_sriov(dev, num_vfs, true); + mlx5_device_disable_sriov(dev, num_vfs, true, num_vf_change); devl_unlock(devlink); } @@ -200,7 +221,7 @@ int mlx5_core_sriov_configure(struct pci_dev *pdev, int num_vfs) if (num_vfs) err = mlx5_sriov_enable(pdev, num_vfs); else - mlx5_sriov_disable(pdev); + mlx5_sriov_disable(pdev, true); if (!err) sriov->num_vfs = num_vfs; @@ -245,7 +266,7 @@ void mlx5_sriov_detach(struct mlx5_core_dev *dev) if (!mlx5_core_is_pf(dev)) return; - mlx5_device_disable_sriov(dev, pci_num_vf(dev->pdev), false); + mlx5_device_disable_sriov(dev, pci_num_vf(dev->pdev), false, false); } static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev) @@ -264,8 +285,7 @@ static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev) host_total_vfs = MLX5_GET(query_esw_functions_out, out, host_params_context.host_total_vfs); kvfree(out); - if (host_total_vfs) - return host_total_vfs; + return host_total_vfs; } done: @@ -284,6 +304,7 @@ int mlx5_sriov_init(struct mlx5_core_dev *dev) total_vfs = pci_sriov_get_totalvfs(pdev); sriov->max_vfs = mlx5_get_max_vfs(dev); sriov->num_vfs = pci_num_vf(pdev); + sriov->max_ec_vfs = mlx5_core_ec_sriov_enabled(dev) ? pci_sriov_get_totalvfs(dev->pdev) : 0; sriov->vfs_ctx = kcalloc(total_vfs, sizeof(*sriov->vfs_ctx), GFP_KERNEL); if (!sriov->vfs_ctx) return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 0f783e7906cb..54bb0866ed72 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -2077,8 +2077,9 @@ mlx5dr_action_create_dest_vport(struct mlx5dr_domain *dmn, struct mlx5dr_action *action; u8 peer_vport; - peer_vport = vhca_id_valid && (vhca_id != dmn->info.caps.gvmi); - vport_dmn = peer_vport ? dmn->peer_dmn : dmn; + peer_vport = vhca_id_valid && mlx5_core_is_pf(dmn->mdev) && + (vhca_id != dmn->info.caps.gvmi); + vport_dmn = peer_vport ? xa_load(&dmn->peer_dmn_xa, vhca_id) : dmn; if (!vport_dmn) { mlx5dr_dbg(dmn, "No peer vport domain for given vhca_id\n"); return NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 1aa525e509f1..8c2a34a0d6be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -34,6 +34,7 @@ int mlx5dr_cmd_query_esw_vport_context(struct mlx5_core_dev *mdev, int mlx5dr_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_vport, u16 vport_number, u16 *gvmi) { + bool ec_vf_func = other_vport ? mlx5_core_is_ec_vf_vport(mdev, vport_number) : false; u32 in[MLX5_ST_SZ_DW(query_hca_cap_in)] = {}; int out_size; void *out; @@ -46,7 +47,8 @@ int mlx5dr_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_vport, MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP); MLX5_SET(query_hca_cap_in, in, other_function, other_vport); - MLX5_SET(query_hca_cap_in, in, function_id, vport_number); + MLX5_SET(query_hca_cap_in, in, function_id, mlx5_vport_to_func_id(mdev, vport_number, ec_vf_func)); + MLX5_SET(query_hca_cap_in, in, ec_vf_function, ec_vf_func); MLX5_SET(query_hca_cap_in, in, op_mod, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1 | HCA_CAP_OPMOD_GET_CUR); @@ -562,11 +564,12 @@ int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev, err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); if (err) - return err; + goto err_free_in; *reformat_id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id); - kvfree(in); +err_free_in: + kvfree(in); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 9a2dfe6ebe31..3d74109f8230 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -475,6 +475,7 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) mutex_init(&dmn->info.rx.mutex); mutex_init(&dmn->info.tx.mutex); xa_init(&dmn->definers_xa); + xa_init(&dmn->peer_dmn_xa); if (dr_domain_caps_init(mdev, dmn)) { mlx5dr_err(dmn, "Failed init domain, no caps\n"); @@ -507,6 +508,7 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) uninit_caps: dr_domain_caps_uninit(dmn); def_xa_destroy: + xa_destroy(&dmn->peer_dmn_xa); xa_destroy(&dmn->definers_xa); kfree(dmn); return NULL; @@ -547,6 +549,7 @@ int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn) dr_domain_uninit_csum_recalc_fts(dmn); dr_domain_uninit_resources(dmn); dr_domain_caps_uninit(dmn); + xa_destroy(&dmn->peer_dmn_xa); xa_destroy(&dmn->definers_xa); mutex_destroy(&dmn->info.tx.mutex); mutex_destroy(&dmn->info.rx.mutex); @@ -555,17 +558,22 @@ int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn) } void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn, - struct mlx5dr_domain *peer_dmn) + struct mlx5dr_domain *peer_dmn, + u16 peer_vhca_id) { + struct mlx5dr_domain *peer; + mlx5dr_domain_lock(dmn); - if (dmn->peer_dmn) - refcount_dec(&dmn->peer_dmn->refcount); + peer = xa_load(&dmn->peer_dmn_xa, peer_vhca_id); + if (peer) + refcount_dec(&peer->refcount); - dmn->peer_dmn = peer_dmn; + WARN_ON(xa_err(xa_store(&dmn->peer_dmn_xa, peer_vhca_id, peer_dmn, GFP_KERNEL))); - if (dmn->peer_dmn) - refcount_inc(&dmn->peer_dmn->refcount); + peer = xa_load(&dmn->peer_dmn_xa, peer_vhca_id); + if (peer) + refcount_inc(&peer->refcount); mlx5dr_domain_unlock(dmn); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c index d6947fe13d56..8ca534ef5d03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c @@ -82,7 +82,7 @@ dr_ptrn_alloc_pattern(struct mlx5dr_ptrn_mgr *mgr, u32 chunk_size; u32 index; - chunk_size = ilog2(num_of_actions); + chunk_size = ilog2(roundup_pow_of_two(num_of_actions)); /* HW modify action index granularity is at least 64B */ chunk_size = max_t(u32, chunk_size, DR_CHUNK_SIZE_8); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c index 2010d4ac6519..f708b029425a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c @@ -1647,21 +1647,23 @@ dr_ste_v0_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, u8 *tag) { struct mlx5dr_match_misc *misc = &value->misc; + int id = misc->source_eswitch_owner_vhca_id; struct mlx5dr_cmd_vport_cap *vport_cap; struct mlx5dr_domain *dmn = sb->dmn; struct mlx5dr_domain *vport_dmn; u8 *bit_mask = sb->bit_mask; + struct mlx5dr_domain *peer; bool source_gvmi_set; DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn); if (sb->vhca_id_valid) { + peer = xa_load(&dmn->peer_dmn_xa, id); /* Find port GVMI based on the eswitch_owner_vhca_id */ - if (misc->source_eswitch_owner_vhca_id == dmn->info.caps.gvmi) + if (id == dmn->info.caps.gvmi) vport_dmn = dmn; - else if (dmn->peer_dmn && (misc->source_eswitch_owner_vhca_id == - dmn->peer_dmn->info.caps.gvmi)) - vport_dmn = dmn->peer_dmn; + else if (peer && (id == peer->info.caps.gvmi)) + vport_dmn = peer; else return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index 4c0704ad166b..dd856cde188d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -1979,20 +1979,22 @@ static int dr_ste_v1_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, u8 *tag) { struct mlx5dr_match_misc *misc = &value->misc; + int id = misc->source_eswitch_owner_vhca_id; struct mlx5dr_cmd_vport_cap *vport_cap; struct mlx5dr_domain *dmn = sb->dmn; struct mlx5dr_domain *vport_dmn; u8 *bit_mask = sb->bit_mask; + struct mlx5dr_domain *peer; DR_STE_SET_TAG(src_gvmi_qp_v1, tag, source_qp, misc, source_sqn); if (sb->vhca_id_valid) { + peer = xa_load(&dmn->peer_dmn_xa, id); /* Find port GVMI based on the eswitch_owner_vhca_id */ - if (misc->source_eswitch_owner_vhca_id == dmn->info.caps.gvmi) + if (id == dmn->info.caps.gvmi) vport_dmn = dmn; - else if (dmn->peer_dmn && (misc->source_eswitch_owner_vhca_id == - dmn->peer_dmn->info.caps.gvmi)) - vport_dmn = dmn->peer_dmn; + else if (peer && (id == peer->info.caps.gvmi)) + vport_dmn = peer; else return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 678a993ab053..6c59de3e28f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -935,7 +935,6 @@ struct mlx5dr_domain_info { }; struct mlx5dr_domain { - struct mlx5dr_domain *peer_dmn; struct mlx5_core_dev *mdev; u32 pdn; struct mlx5_uars_page *uar; @@ -956,6 +955,7 @@ struct mlx5dr_domain { struct list_head dbg_tbl_list; struct mlx5dr_dbg_dump_info dump_info; struct xarray definers_xa; + struct xarray peer_dmn_xa; /* memory management statistics */ u32 num_buddies[DR_ICM_TYPE_MAX]; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index cc215beb7436..feb307fb3440 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -780,14 +780,15 @@ restore_fte: } static int mlx5_cmd_dr_set_peer(struct mlx5_flow_root_namespace *ns, - struct mlx5_flow_root_namespace *peer_ns) + struct mlx5_flow_root_namespace *peer_ns, + u16 peer_vhca_id) { struct mlx5dr_domain *peer_domain = NULL; if (peer_ns) peer_domain = peer_ns->fs_dr_domain.dr_domain; mlx5dr_domain_set_peer(ns->fs_dr_domain.dr_domain, - peer_domain); + peer_domain, peer_vhca_id); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index d1c04f43d86d..89fced86936f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -48,7 +48,8 @@ int mlx5dr_domain_destroy(struct mlx5dr_domain *domain); int mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags); void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn, - struct mlx5dr_domain *peer_dmn); + struct mlx5dr_domain *peer_dmn, + u16 peer_vhca_id); struct mlx5dr_table * mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level, u32 flags, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/thermal.c b/drivers/net/ethernet/mellanox/mlx5/core/thermal.c index e47fa6fb836f..52199d39657e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/thermal.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/thermal.c @@ -45,7 +45,7 @@ static int mlx5_thermal_get_mtmp_temp(struct mlx5_core_dev *mdev, u32 id, int *p static int mlx5_thermal_get_temp(struct thermal_zone_device *tzdev, int *p_temp) { - struct mlx5_thermal *thermal = tzdev->devdata; + struct mlx5_thermal *thermal = thermal_zone_device_priv(tzdev); struct mlx5_core_dev *mdev = thermal->mdev; int err; @@ -68,30 +68,36 @@ static struct thermal_zone_device_ops mlx5_thermal_ops = { int mlx5_thermal_init(struct mlx5_core_dev *mdev) { + char data[THERMAL_NAME_LENGTH]; struct mlx5_thermal *thermal; - struct thermal_zone_device *tzd; - const char *data = "mlx5"; + int err; - tzd = thermal_zone_get_zone_by_name(data); - if (!IS_ERR(tzd)) + if (!mlx5_core_is_pf(mdev) && !mlx5_core_is_ecpf(mdev)) return 0; + err = snprintf(data, sizeof(data), "mlx5_%s", dev_name(mdev->device)); + if (err < 0 || err >= sizeof(data)) { + mlx5_core_err(mdev, "Failed to setup thermal zone name, %d\n", err); + return -EINVAL; + } + thermal = kzalloc(sizeof(*thermal), GFP_KERNEL); if (!thermal) return -ENOMEM; thermal->mdev = mdev; - thermal->tzdev = thermal_zone_device_register(data, - MLX5_THERMAL_NUM_TRIPS, - MLX5_THERMAL_TRIP_MASK, - thermal, - &mlx5_thermal_ops, - NULL, 0, MLX5_THERMAL_POLL_INT_MSEC); + thermal->tzdev = thermal_zone_device_register_with_trips(data, + NULL, + MLX5_THERMAL_NUM_TRIPS, + MLX5_THERMAL_TRIP_MASK, + thermal, + &mlx5_thermal_ops, + NULL, 0, MLX5_THERMAL_POLL_INT_MSEC); if (IS_ERR(thermal->tzdev)) { - dev_err(mdev->device, "Failed to register thermal zone device (%s) %ld\n", - data, PTR_ERR(thermal->tzdev)); + err = PTR_ERR(thermal->tzdev); + mlx5_core_err(mdev, "Failed to register thermal zone device (%s) %d\n", data, err); kfree(thermal); - return -EINVAL; + return err; } mdev->thermal = thermal; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index ba7e3df22413..5a31fb47ffa5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -288,7 +288,8 @@ int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT); MLX5_SET(query_nic_vport_context_in, in, allowed_list_type, list_type); MLX5_SET(query_nic_vport_context_in, in, vport_number, vport); - MLX5_SET(query_nic_vport_context_in, in, other_vport, 1); + if (vport || mlx5_core_is_ecpf(dev)) + MLX5_SET(query_nic_vport_context_in, in, other_vport, 1); err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz); if (err) @@ -1160,23 +1161,26 @@ u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev) } EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid); -int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, void *out, +int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 vport, void *out, u16 opmod) { + bool ec_vf_func = mlx5_core_is_ec_vf_vport(dev, vport); u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)] = {}; opmod = (opmod << 1) | (HCA_CAP_OPMOD_GET_MAX & 0x01); MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP); MLX5_SET(query_hca_cap_in, in, op_mod, opmod); - MLX5_SET(query_hca_cap_in, in, function_id, function_id); + MLX5_SET(query_hca_cap_in, in, function_id, mlx5_vport_to_func_id(dev, vport, ec_vf_func)); MLX5_SET(query_hca_cap_in, in, other_function, true); + MLX5_SET(query_hca_cap_in, in, ec_vf_function, ec_vf_func); return mlx5_cmd_exec_inout(dev, query_hca_cap, in, out); } EXPORT_SYMBOL_GPL(mlx5_vport_get_other_func_cap); int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap, - u16 function_id, u16 opmod) + u16 vport, u16 opmod) { + bool ec_vf_func = mlx5_core_is_ec_vf_vport(dev, vport); int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in); void *set_hca_cap; void *set_ctx; @@ -1190,8 +1194,10 @@ int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap MLX5_SET(set_hca_cap_in, set_ctx, op_mod, opmod << 1); set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); memcpy(set_hca_cap, hca_cap, MLX5_ST_SZ_BYTES(cmd_hca_cap)); - MLX5_SET(set_hca_cap_in, set_ctx, function_id, function_id); + MLX5_SET(set_hca_cap_in, set_ctx, function_id, + mlx5_vport_to_func_id(dev, vport, ec_vf_func)); MLX5_SET(set_hca_cap_in, set_ctx, other_function, true); + MLX5_SET(set_hca_cap_in, set_ctx, ec_vf_function, ec_vf_func); ret = mlx5_cmd_exec_in(dev, set_hca_cap, set_ctx); kfree(set_ctx); diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h index b001e5258091..47f6cc0401c3 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h @@ -44,7 +44,7 @@ MLXFW_MFA2_TLV(multi, struct mlxfw_mfa2_tlv_multi, MLXFW_MFA2_TLV_MULTI_PART); struct mlxfw_mfa2_tlv_psid { - u8 psid[0]; + DECLARE_FLEX_ARRAY(u8, psid); } __packed; MLXFW_MFA2_TLV_VARSIZE(psid, struct mlxfw_mfa2_tlv_psid, diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 22db0bb15c45..1ccf3b73ed72 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1723,8 +1723,6 @@ static const struct devlink_ops mlxsw_devlink_ops = { BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), .reload_down = mlxsw_devlink_core_bus_device_reload_down, .reload_up = mlxsw_devlink_core_bus_device_reload_up, - .port_split = mlxsw_devlink_port_split, - .port_unsplit = mlxsw_devlink_port_unsplit, .sb_pool_get = mlxsw_devlink_sb_pool_get, .sb_pool_set = mlxsw_devlink_sb_pool_set, .sb_port_pool_get = mlxsw_devlink_sb_port_pool_get, @@ -3116,6 +3114,11 @@ u64 mlxsw_core_res_get(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_res_get); +static const struct devlink_port_ops mlxsw_devlink_port_ops = { + .port_split = mlxsw_devlink_port_split, + .port_unsplit = mlxsw_devlink_port_unsplit, +}; + static int __mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u16 local_port, enum devlink_port_flavour flavour, u8 slot_index, u32 port_number, bool split, @@ -3150,7 +3153,8 @@ static int __mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u16 local_port, devlink_port_linecard_set(devlink_port, linecard->devlink_linecard); } - err = devl_port_register(devlink, devlink_port, local_port); + err = devl_port_register_with_ops(devlink, devlink_port, local_port, + &mlxsw_devlink_port_ops); if (err) memset(mlxsw_core_port, 0, sizeof(*mlxsw_core_port)); return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c index bd1a51a0a540..973de2adc943 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c @@ -32,8 +32,8 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = { MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x18, 0, 8), MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x18, 9, 2), MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x18, 11, 6), - MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_MSB, 0x18, 17, 3), - MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_LSB, 0x18, 20, 8), + MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_MSB, 0x18, 17, 4), + MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_LSB, 0x18, 21, 8), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_96_127, 0x20, 4), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_64_95, 0x24, 4), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_32_63, 0x28, 4), @@ -42,6 +42,7 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = { MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_64_95, 0x34, 4), MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_32_63, 0x38, 4), MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_0_31, 0x3C, 4), + MLXSW_AFK_ELEMENT_INFO_U32(FDB_MISS, 0x40, 0, 1), }; struct mlxsw_afk { diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h index 3a037fe47211..65a4abadc7db 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h @@ -35,6 +35,7 @@ enum mlxsw_afk_element { MLXSW_AFK_ELEMENT_IP_DSCP, MLXSW_AFK_ELEMENT_VIRT_ROUTER_MSB, MLXSW_AFK_ELEMENT_VIRT_ROUTER_LSB, + MLXSW_AFK_ELEMENT_FDB_MISS, MLXSW_AFK_ELEMENT_MAX, }; @@ -69,7 +70,7 @@ struct mlxsw_afk_element_info { MLXSW_AFK_ELEMENT_INFO(MLXSW_AFK_ELEMENT_TYPE_BUF, \ _element, _offset, 0, _size) -#define MLXSW_AFK_ELEMENT_STORAGE_SIZE 0x40 +#define MLXSW_AFK_ELEMENT_STORAGE_SIZE 0x44 struct mlxsw_afk_element_inst { /* element instance in actual block */ enum mlxsw_afk_element element; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c index 70735068cf29..0fd290d776ff 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c @@ -405,7 +405,8 @@ mlxsw_hwmon_module_temp_label_show(struct device *dev, container_of(attr, struct mlxsw_hwmon_attr, dev_attr); return sprintf(buf, "front panel %03u\n", - mlxsw_hwmon_attr->type_index); + mlxsw_hwmon_attr->type_index + 1 - + mlxsw_hwmon_attr->mlxsw_hwmon_dev->sensor_count); } static ssize_t diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index 2c586c2308ae..d23f293e285c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -48,6 +48,7 @@ #define MLXSW_I2C_MBOX_SIZE_BITS 12 #define MLXSW_I2C_ADDR_BUF_SIZE 4 #define MLXSW_I2C_BLK_DEF 32 +#define MLXSW_I2C_BLK_MAX 100 #define MLXSW_I2C_RETRY 5 #define MLXSW_I2C_TIMEOUT_MSECS 5000 #define MLXSW_I2C_MAX_DATA_SIZE 256 @@ -444,7 +445,7 @@ mlxsw_i2c_cmd(struct device *dev, u16 opcode, u32 in_mod, size_t in_mbox_size, } else { /* No input mailbox is case of initialization query command. */ reg_size = MLXSW_I2C_MAX_DATA_SIZE; - num = reg_size / mlxsw_i2c->block_size; + num = DIV_ROUND_UP(reg_size, mlxsw_i2c->block_size); if (mutex_lock_interruptible(&mlxsw_i2c->cmd.lock) < 0) { dev_err(&client->dev, "Could not acquire lock"); @@ -653,7 +654,7 @@ static int mlxsw_i2c_probe(struct i2c_client *client) return -EOPNOTSUPP; } - mlxsw_i2c->block_size = max_t(u16, MLXSW_I2C_BLK_DEF, + mlxsw_i2c->block_size = min_t(u16, MLXSW_I2C_BLK_MAX, min_t(u16, quirks->max_read_len, quirks->max_write_len)); } else { @@ -751,7 +752,7 @@ static void mlxsw_i2c_remove(struct i2c_client *client) int mlxsw_i2c_driver_register(struct i2c_driver *i2c_driver) { - i2c_driver->probe_new = mlxsw_i2c_probe; + i2c_driver->probe = mlxsw_i2c_probe; i2c_driver->remove = mlxsw_i2c_remove; return i2c_add_driver(i2c_driver); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index 6b56eadd736e..6b98c3287b49 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -417,6 +417,7 @@ static int mlxsw_m_linecards_init(struct mlxsw_m *mlxsw_m) err_kmalloc_array: for (i--; i >= 0; i--) kfree(mlxsw_m->line_cards[i]); + kfree(mlxsw_m->line_cards); err_kcalloc: kfree(mlxsw_m->ports); return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index c968309657dd..51eea1f0529c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -517,11 +517,15 @@ static void mlxsw_pci_skb_cb_ts_set(struct mlxsw_pci *mlxsw_pci, struct sk_buff *skb, enum mlxsw_pci_cqe_v cqe_v, char *cqe) { + u8 ts_type; + if (cqe_v != MLXSW_PCI_CQE_V2) return; - if (mlxsw_pci_cqe2_time_stamp_type_get(cqe) != - MLXSW_PCI_CQE_TIME_STAMP_TYPE_UTC) + ts_type = mlxsw_pci_cqe2_time_stamp_type_get(cqe); + + if (ts_type != MLXSW_PCI_CQE_TIME_STAMP_TYPE_UTC && + ts_type != MLXSW_PCI_CQE_TIME_STAMP_TYPE_MIRROR_UTC) return; mlxsw_skb_cb(skb)->cqe_ts.sec = mlxsw_pci_cqe2_time_stamp_sec_get(cqe); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 8165bf31a99a..17160e867bef 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -97,14 +97,6 @@ MLXSW_ITEM32(reg, sspr, m, 0x00, 31, 1); */ MLXSW_ITEM32_LP(reg, sspr, 0x00, 16, 0x00, 12); -/* reg_sspr_sub_port - * Virtual port within the physical port. - * Should be set to 0 when virtual ports are not enabled on the port. - * - * Access: RW - */ -MLXSW_ITEM32(reg, sspr, sub_port, 0x00, 8, 8); - /* reg_sspr_system_port * Unique identifier within the stacking domain that represents all the ports * that are available in the system (external ports). @@ -120,7 +112,6 @@ static inline void mlxsw_reg_sspr_pack(char *payload, u16 local_port) MLXSW_REG_ZERO(sspr, payload); mlxsw_reg_sspr_m_set(payload, 1); mlxsw_reg_sspr_local_port_set(payload, local_port); - mlxsw_reg_sspr_sub_port_set(payload, 0); mlxsw_reg_sspr_system_port_set(payload, local_port); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 02a327744a61..25a01dafde1b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4337,8 +4337,8 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port->default_vlan); /* Join a router interface configured on the LAG, if exists */ - err = mlxsw_sp_port_vlan_router_join(mlxsw_sp_port->default_vlan, - lag_dev, extack); + err = mlxsw_sp_router_port_join_lag(mlxsw_sp_port, lag_dev, + extack); if (err) goto err_router_join; @@ -5139,14 +5139,6 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *nb, return notifier_from_errno(err); } -static struct notifier_block mlxsw_sp_inetaddr_valid_nb __read_mostly = { - .notifier_call = mlxsw_sp_inetaddr_valid_event, -}; - -static struct notifier_block mlxsw_sp_inet6addr_valid_nb __read_mostly = { - .notifier_call = mlxsw_sp_inet6addr_valid_event, -}; - static const struct pci_device_id mlxsw_sp1_pci_id_table[] = { {PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM), 0}, {0, }, @@ -5191,12 +5183,9 @@ static int __init mlxsw_sp_module_init(void) { int err; - register_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb); - register_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb); - err = mlxsw_core_driver_register(&mlxsw_sp1_driver); if (err) - goto err_sp1_core_driver_register; + return err; err = mlxsw_core_driver_register(&mlxsw_sp2_driver); if (err) @@ -5242,9 +5231,6 @@ err_sp3_core_driver_register: mlxsw_core_driver_unregister(&mlxsw_sp2_driver); err_sp2_core_driver_register: mlxsw_core_driver_unregister(&mlxsw_sp1_driver); -err_sp1_core_driver_register: - unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb); - unregister_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb); return err; } @@ -5258,8 +5244,6 @@ static void __exit mlxsw_sp_module_exit(void) mlxsw_core_driver_unregister(&mlxsw_sp3_driver); mlxsw_core_driver_unregister(&mlxsw_sp2_driver); mlxsw_core_driver_unregister(&mlxsw_sp1_driver); - unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb); - unregister_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb); } module_init(mlxsw_sp_module_init); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 4c22f8004514..231e364cbb7c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -755,14 +755,6 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp, const struct net_device *macvlan_dev); -int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused, - unsigned long event, void *ptr); -int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused, - unsigned long event, void *ptr); -int -mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan, - struct net_device *l3_dev, - struct netlink_ext_ack *extack); void mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan); void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c index e4f4cded2b6f..b1178b7a7f51 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c @@ -193,7 +193,7 @@ mlxsw_sp2_mr_tcam_rule_parse(struct mlxsw_sp_acl_rule *rule, key->vrid, GENMASK(7, 0)); mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_VIRT_ROUTER_MSB, - key->vrid >> 8, GENMASK(2, 0)); + key->vrid >> 8, GENMASK(3, 0)); switch (key->proto) { case MLXSW_SP_L3_PROTO_IPV4: return mlxsw_sp2_mr_tcam_rule_parse4(rulei, key); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c index 00c32320f891..ae2d6f12b799 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c @@ -123,10 +123,12 @@ const struct mlxsw_afk_ops mlxsw_sp1_afk_ops = { }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_0[] = { + MLXSW_AFK_ELEMENT_INST_U32(FDB_MISS, 0x00, 3, 1), MLXSW_AFK_ELEMENT_INST_BUF(DMAC_0_31, 0x04, 4), }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_1[] = { + MLXSW_AFK_ELEMENT_INST_U32(FDB_MISS, 0x00, 3, 1), MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x04, 4), }; @@ -169,7 +171,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_2[] = { static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_4[] = { MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_LSB, 0x04, 24, 8), - MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_MSB, 0x00, 0, 3), + MLXSW_AFK_ELEMENT_INST_EXT_U32(VIRT_ROUTER_MSB, 0x00, 0, 3, 0, true), }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_0[] = { @@ -319,7 +321,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_5b[] = { static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_4b[] = { MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_LSB, 0x04, 13, 8), - MLXSW_AFK_ELEMENT_INST_EXT_U32(VIRT_ROUTER_MSB, 0x04, 21, 4, 0, true), + MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_MSB, 0x04, 21, 4), }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_2b[] = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index 5416093c0e35..c8a356accdf8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -221,7 +221,7 @@ start_again: for (; i < rif_count; i++) { struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i); - if (!rif || !mlxsw_sp_rif_dev(rif)) + if (!rif || !mlxsw_sp_rif_has_dev(rif)) continue; err = mlxsw_sp_erif_entry_get(mlxsw_sp, &entry, rif, counters_enabled); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 594cdcb90b3d..72917f09e806 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -281,39 +281,38 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, return 0; } -static int mlxsw_sp_flower_parse_meta(struct mlxsw_sp_acl_rule_info *rulei, - struct flow_cls_offload *f, - struct mlxsw_sp_flow_block *block) +static int +mlxsw_sp_flower_parse_meta_iif(struct mlxsw_sp_acl_rule_info *rulei, + const struct mlxsw_sp_flow_block *block, + const struct flow_match_meta *match, + struct netlink_ext_ack *extack) { - struct flow_rule *rule = flow_cls_offload_flow_rule(f); struct mlxsw_sp_port *mlxsw_sp_port; struct net_device *ingress_dev; - struct flow_match_meta match; - if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META)) + if (!match->mask->ingress_ifindex) return 0; - flow_rule_match_meta(rule, &match); - if (match.mask->ingress_ifindex != 0xFFFFFFFF) { - NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported ingress ifindex mask"); + if (match->mask->ingress_ifindex != 0xFFFFFFFF) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported ingress ifindex mask"); return -EINVAL; } ingress_dev = __dev_get_by_index(block->net, - match.key->ingress_ifindex); + match->key->ingress_ifindex); if (!ingress_dev) { - NL_SET_ERR_MSG_MOD(f->common.extack, "Can't find specified ingress port to match on"); + NL_SET_ERR_MSG_MOD(extack, "Can't find specified ingress port to match on"); return -EINVAL; } if (!mlxsw_sp_port_dev_check(ingress_dev)) { - NL_SET_ERR_MSG_MOD(f->common.extack, "Can't match on non-mlxsw ingress port"); + NL_SET_ERR_MSG_MOD(extack, "Can't match on non-mlxsw ingress port"); return -EINVAL; } mlxsw_sp_port = netdev_priv(ingress_dev); if (mlxsw_sp_port->mlxsw_sp != block->mlxsw_sp) { - NL_SET_ERR_MSG_MOD(f->common.extack, "Can't match on a port from different device"); + NL_SET_ERR_MSG_MOD(extack, "Can't match on a port from different device"); return -EINVAL; } @@ -321,9 +320,29 @@ static int mlxsw_sp_flower_parse_meta(struct mlxsw_sp_acl_rule_info *rulei, MLXSW_AFK_ELEMENT_SRC_SYS_PORT, mlxsw_sp_port->local_port, 0xFFFFFFFF); + return 0; } +static int mlxsw_sp_flower_parse_meta(struct mlxsw_sp_acl_rule_info *rulei, + struct flow_cls_offload *f, + struct mlxsw_sp_flow_block *block) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(f); + struct flow_match_meta match; + + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META)) + return 0; + + flow_rule_match_meta(rule, &match); + + mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_FDB_MISS, + match.key->l2_miss, match.mask->l2_miss); + + return mlxsw_sp_flower_parse_meta_iif(rulei, block, &match, + f->common.extack); +} + static void mlxsw_sp_flower_parse_ipv4(struct mlxsw_sp_acl_rule_info *rulei, struct flow_cls_offload *f) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c index 1f6bc0c7e91d..69cd689dbc83 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -704,12 +704,12 @@ void mlxsw_sp_mr_vif_del(struct mlxsw_sp_mr_table *mr_table, vifi_t vif_index) static struct mlxsw_sp_mr_vif * mlxsw_sp_mr_dev_vif_lookup(struct mlxsw_sp_mr_table *mr_table, - const struct net_device *dev) + const struct mlxsw_sp_rif *rif) { vifi_t vif_index; for (vif_index = 0; vif_index < MAXVIFS; vif_index++) - if (mr_table->vifs[vif_index].dev == dev) + if (mlxsw_sp_rif_dev_is(rif, mr_table->vifs[vif_index].dev)) return &mr_table->vifs[vif_index]; return NULL; } @@ -717,13 +717,12 @@ mlxsw_sp_mr_dev_vif_lookup(struct mlxsw_sp_mr_table *mr_table, int mlxsw_sp_mr_rif_add(struct mlxsw_sp_mr_table *mr_table, const struct mlxsw_sp_rif *rif) { - const struct net_device *rif_dev = mlxsw_sp_rif_dev(rif); struct mlxsw_sp_mr_vif *mr_vif; - if (!rif_dev) + if (!mlxsw_sp_rif_has_dev(rif)) return 0; - mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif_dev); + mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif); if (!mr_vif) return 0; return mlxsw_sp_mr_vif_resolve(mr_table, mr_vif->dev, mr_vif, @@ -733,13 +732,12 @@ int mlxsw_sp_mr_rif_add(struct mlxsw_sp_mr_table *mr_table, void mlxsw_sp_mr_rif_del(struct mlxsw_sp_mr_table *mr_table, const struct mlxsw_sp_rif *rif) { - const struct net_device *rif_dev = mlxsw_sp_rif_dev(rif); struct mlxsw_sp_mr_vif *mr_vif; - if (!rif_dev) + if (!mlxsw_sp_rif_has_dev(rif)) return; - mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif_dev); + mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif); if (!mr_vif) return; mlxsw_sp_mr_vif_unresolve(mr_table, mr_vif->dev, mr_vif); @@ -748,17 +746,16 @@ void mlxsw_sp_mr_rif_del(struct mlxsw_sp_mr_table *mr_table, void mlxsw_sp_mr_rif_mtu_update(struct mlxsw_sp_mr_table *mr_table, const struct mlxsw_sp_rif *rif, int mtu) { - const struct net_device *rif_dev = mlxsw_sp_rif_dev(rif); struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp; struct mlxsw_sp_mr_route_vif_entry *rve; struct mlxsw_sp_mr *mr = mlxsw_sp->mr; struct mlxsw_sp_mr_vif *mr_vif; - if (!rif_dev) + if (!mlxsw_sp_rif_has_dev(rif)) return; /* Search for a VIF that use that RIF */ - mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif_dev); + mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif); if (!mr_vif) return; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c index d309b77a0194..bb8eeb86edf7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c @@ -11,10 +11,12 @@ #include "spectrum_nve.h" #define MLXSW_SP_NVE_VXLAN_IPV4_SUPPORTED_FLAGS (VXLAN_F_UDP_ZERO_CSUM_TX | \ - VXLAN_F_LEARN) + VXLAN_F_LEARN | \ + VXLAN_F_LOCALBYPASS) #define MLXSW_SP_NVE_VXLAN_IPV6_SUPPORTED_FLAGS (VXLAN_F_IPV6 | \ VXLAN_F_UDP_ZERO_CSUM6_TX | \ - VXLAN_F_UDP_ZERO_CSUM6_RX) + VXLAN_F_UDP_ZERO_CSUM6_RX | \ + VXLAN_F_LOCALBYPASS) static bool mlxsw_sp_nve_vxlan_ipv4_flags_check(const struct vxlan_config *cfg, struct netlink_ext_ack *extack) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 4a73e2fe95ef..b32adf277a22 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -51,10 +51,27 @@ struct mlxsw_sp_vr; struct mlxsw_sp_lpm_tree; struct mlxsw_sp_rif_ops; -struct mlxsw_sp_rif { +struct mlxsw_sp_crif_key { + struct net_device *dev; +}; + +struct mlxsw_sp_crif { + struct mlxsw_sp_crif_key key; + struct rhash_head ht_node; + bool can_destroy; struct list_head nexthop_list; + struct mlxsw_sp_rif *rif; +}; + +static const struct rhashtable_params mlxsw_sp_crif_ht_params = { + .key_offset = offsetof(struct mlxsw_sp_crif, key), + .key_len = sizeof_field(struct mlxsw_sp_crif, key), + .head_offset = offsetof(struct mlxsw_sp_crif, ht_node), +}; + +struct mlxsw_sp_rif { + struct mlxsw_sp_crif *crif; /* NULL for underlay RIF */ struct list_head neigh_list; - struct net_device *dev; /* NULL for underlay RIF */ struct mlxsw_sp_fid *fid; unsigned char addr[ETH_ALEN]; int mtu; @@ -71,6 +88,13 @@ struct mlxsw_sp_rif { bool counter_egress_valid; }; +static struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif) +{ + if (!rif->crif) + return NULL; + return rif->crif->key.dev; +} + struct mlxsw_sp_rif_params { struct net_device *dev; union { @@ -96,8 +120,8 @@ struct mlxsw_sp_rif_subport { struct mlxsw_sp_rif_ipip_lb { struct mlxsw_sp_rif common; struct mlxsw_sp_rif_ipip_lb_config lb_config; - u16 ul_vr_id; /* Reserved for Spectrum-2. */ - u16 ul_rif_id; /* Reserved for Spectrum. */ + u16 ul_vr_id; /* Spectrum-1. */ + u16 ul_rif_id; /* Spectrum-2+. */ }; struct mlxsw_sp_rif_params_ipip_lb { @@ -748,10 +772,11 @@ static bool mlxsw_sp_vr_is_used(const struct mlxsw_sp_vr *vr) static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) { + int max_vrs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); struct mlxsw_sp_vr *vr; int i; - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + for (i = 0; i < max_vrs; i++) { vr = &mlxsw_sp->router->vrs[i]; if (!mlxsw_sp_vr_is_used(vr)) return vr; @@ -792,12 +817,13 @@ static u32 mlxsw_sp_fix_tb_id(u32 tb_id) static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp, u32 tb_id) { + int max_vrs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); struct mlxsw_sp_vr *vr; int i; tb_id = mlxsw_sp_fix_tb_id(tb_id); - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + for (i = 0; i < max_vrs; i++) { vr = &mlxsw_sp->router->vrs[i]; if (mlxsw_sp_vr_is_used(vr) && vr->tb_id == tb_id) return vr; @@ -959,6 +985,7 @@ static int mlxsw_sp_vrs_lpm_tree_replace(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib *fib, struct mlxsw_sp_lpm_tree *new_tree) { + int max_vrs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); enum mlxsw_sp_l3proto proto = fib->proto; struct mlxsw_sp_lpm_tree *old_tree; u8 old_id, new_id = new_tree->id; @@ -968,7 +995,7 @@ static int mlxsw_sp_vrs_lpm_tree_replace(struct mlxsw_sp *mlxsw_sp, old_tree = mlxsw_sp->router->lpm.proto_trees[proto]; old_id = old_tree->id; - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + for (i = 0; i < max_vrs; i++) { vr = &mlxsw_sp->router->vrs[i]; if (!mlxsw_sp_vr_lpm_tree_should_replace(vr, proto, old_id)) continue; @@ -1052,6 +1079,61 @@ u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev) return tb_id; } +static void +mlxsw_sp_crif_init(struct mlxsw_sp_crif *crif, struct net_device *dev) +{ + crif->key.dev = dev; + INIT_LIST_HEAD(&crif->nexthop_list); +} + +static struct mlxsw_sp_crif * +mlxsw_sp_crif_alloc(struct net_device *dev) +{ + struct mlxsw_sp_crif *crif; + + crif = kzalloc(sizeof(*crif), GFP_KERNEL); + if (!crif) + return NULL; + + mlxsw_sp_crif_init(crif, dev); + return crif; +} + +static void mlxsw_sp_crif_free(struct mlxsw_sp_crif *crif) +{ + if (WARN_ON(crif->rif)) + return; + + WARN_ON(!list_empty(&crif->nexthop_list)); + kfree(crif); +} + +static int mlxsw_sp_crif_insert(struct mlxsw_sp_router *router, + struct mlxsw_sp_crif *crif) +{ + return rhashtable_insert_fast(&router->crif_ht, &crif->ht_node, + mlxsw_sp_crif_ht_params); +} + +static void mlxsw_sp_crif_remove(struct mlxsw_sp_router *router, + struct mlxsw_sp_crif *crif) +{ + rhashtable_remove_fast(&router->crif_ht, &crif->ht_node, + mlxsw_sp_crif_ht_params); +} + +static struct mlxsw_sp_crif * +mlxsw_sp_crif_lookup(struct mlxsw_sp_router *router, + const struct net_device *dev) +{ + struct mlxsw_sp_crif_key key = { + .dev = (struct net_device *)dev, + }; + + return rhashtable_lookup_fast(&router->crif_ht, &key, + mlxsw_sp_crif_ht_params); +} + static struct mlxsw_sp_rif * mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_rif_params *params, @@ -1557,6 +1639,7 @@ mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif, u16 ul_vr_id, u16 ul_rif_id, bool enable) { struct mlxsw_sp_rif_ipip_lb_config lb_cf = lb_rif->lb_config; + struct net_device *dev = mlxsw_sp_rif_dev(&lb_rif->common); enum mlxsw_reg_ritr_loopback_ipip_options ipip_options; struct mlxsw_sp_rif *rif = &lb_rif->common; struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; @@ -1569,7 +1652,7 @@ mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif, u16 ul_vr_id, case MLXSW_SP_L3_PROTO_IPV4: saddr4 = be32_to_cpu(lb_cf.saddr.addr4); mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_LOOPBACK_IF, - rif->rif_index, rif->vr_id, rif->dev->mtu); + rif->rif_index, rif->vr_id, dev->mtu); mlxsw_reg_ritr_loopback_ipip4_pack(ritr_pl, lb_cf.lb_ipipt, ipip_options, ul_vr_id, ul_rif_id, saddr4, @@ -1579,7 +1662,7 @@ mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif, u16 ul_vr_id, case MLXSW_SP_L3_PROTO_IPV6: saddr6 = &lb_cf.saddr.addr6; mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_LOOPBACK_IF, - rif->rif_index, rif->vr_id, rif->dev->mtu); + rif->rif_index, rif->vr_id, dev->mtu); mlxsw_reg_ritr_loopback_ipip6_pack(ritr_pl, lb_cf.lb_ipipt, ipip_options, ul_vr_id, ul_rif_id, saddr6, @@ -1639,9 +1722,29 @@ static void mlxsw_sp_netdevice_ipip_ol_down_event(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_ipip_entry_ol_down_event(mlxsw_sp, ipip_entry); } -static void mlxsw_sp_nexthop_rif_migrate(struct mlxsw_sp *mlxsw_sp, +static void mlxsw_sp_nexthop_rif_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *rif); + +static void mlxsw_sp_rif_migrate_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *old_rif, - struct mlxsw_sp_rif *new_rif); + struct mlxsw_sp_rif *new_rif, + bool migrate_nhs) +{ + struct mlxsw_sp_crif *crif = old_rif->crif; + struct mlxsw_sp_crif mock_crif = {}; + + if (migrate_nhs) + mlxsw_sp_nexthop_rif_update(mlxsw_sp, new_rif); + + /* Plant a mock CRIF so that destroying the old RIF doesn't unoffload + * our nexthops and IPIP tunnels, and doesn't sever the crif->rif link. + */ + mlxsw_sp_crif_init(&mock_crif, crif->key.dev); + old_rif->crif = &mock_crif; + mock_crif.rif = old_rif; + mlxsw_sp_rif_destroy(old_rif); +} + static int mlxsw_sp_ipip_entry_ol_lb_update(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry, @@ -1659,18 +1762,11 @@ mlxsw_sp_ipip_entry_ol_lb_update(struct mlxsw_sp *mlxsw_sp, return PTR_ERR(new_lb_rif); ipip_entry->ol_lb = new_lb_rif; - if (keep_encap) - mlxsw_sp_nexthop_rif_migrate(mlxsw_sp, &old_lb_rif->common, - &new_lb_rif->common); - - mlxsw_sp_rif_destroy(&old_lb_rif->common); - + mlxsw_sp_rif_migrate_destroy(mlxsw_sp, &old_lb_rif->common, + &new_lb_rif->common, keep_encap); return 0; } -static void mlxsw_sp_nexthop_rif_update(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *rif); - /** * __mlxsw_sp_ipip_entry_update_tunnel - Update offload related to IPIP entry. * @mlxsw_sp: mlxsw_sp. @@ -2329,7 +2425,7 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp, } dipn = htonl(dip); - dev = mlxsw_sp->router->rifs[rif]->dev; + dev = mlxsw_sp_rif_dev(mlxsw_sp->router->rifs[rif]); n = neigh_lookup(&arp_tbl, &dipn, dev); if (!n) return; @@ -2357,7 +2453,7 @@ static void mlxsw_sp_router_neigh_ent_ipv6_process(struct mlxsw_sp *mlxsw_sp, return; } - dev = mlxsw_sp->router->rifs[rif]->dev; + dev = mlxsw_sp_rif_dev(mlxsw_sp->router->rifs[rif]); n = neigh_lookup(&nd_tbl, &dip, dev); if (!n) return; @@ -2745,13 +2841,12 @@ static void mlxsw_sp_router_update_priority_work(struct work_struct *work) } static int mlxsw_sp_router_schedule_work(struct net *net, - struct notifier_block *nb, + struct mlxsw_sp_router *router, + struct neighbour *n, void (*cb)(struct work_struct *)) { struct mlxsw_sp_netevent_work *net_work; - struct mlxsw_sp_router *router; - router = container_of(nb, struct mlxsw_sp_router, netevent_nb); if (!net_eq(net, mlxsw_sp_net(router->mlxsw_sp))) return NOTIFY_DONE; @@ -2761,19 +2856,31 @@ static int mlxsw_sp_router_schedule_work(struct net *net, INIT_WORK(&net_work->work, cb); net_work->mlxsw_sp = router->mlxsw_sp; + net_work->n = n; mlxsw_core_schedule_work(&net_work->work); return NOTIFY_DONE; } +static bool mlxsw_sp_dev_lower_is_port(struct net_device *dev) +{ + struct mlxsw_sp_port *mlxsw_sp_port; + + rcu_read_lock(); + mlxsw_sp_port = mlxsw_sp_port_dev_lower_find_rcu(dev); + rcu_read_unlock(); + return !!mlxsw_sp_port; +} + static int mlxsw_sp_router_netevent_event(struct notifier_block *nb, unsigned long event, void *ptr) { - struct mlxsw_sp_netevent_work *net_work; - struct mlxsw_sp_port *mlxsw_sp_port; - struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_router *router; unsigned long interval; struct neigh_parms *p; struct neighbour *n; + struct net *net; + + router = container_of(nb, struct mlxsw_sp_router, netevent_nb); switch (event) { case NETEVENT_DELAY_PROBE_TIME_UPDATE: @@ -2787,51 +2894,37 @@ static int mlxsw_sp_router_netevent_event(struct notifier_block *nb, /* We are in atomic context and can't take RTNL mutex, * so use RCU variant to walk the device chain. */ - mlxsw_sp_port = mlxsw_sp_port_lower_dev_hold(p->dev); - if (!mlxsw_sp_port) + if (!mlxsw_sp_dev_lower_is_port(p->dev)) return NOTIFY_DONE; - mlxsw_sp = mlxsw_sp_port->mlxsw_sp; interval = jiffies_to_msecs(NEIGH_VAR(p, DELAY_PROBE_TIME)); - mlxsw_sp->router->neighs_update.interval = interval; - - mlxsw_sp_port_dev_put(mlxsw_sp_port); + router->neighs_update.interval = interval; break; case NETEVENT_NEIGH_UPDATE: n = ptr; + net = neigh_parms_net(n->parms); if (n->tbl->family != AF_INET && n->tbl->family != AF_INET6) return NOTIFY_DONE; - mlxsw_sp_port = mlxsw_sp_port_lower_dev_hold(n->dev); - if (!mlxsw_sp_port) + if (!mlxsw_sp_dev_lower_is_port(n->dev)) return NOTIFY_DONE; - net_work = kzalloc(sizeof(*net_work), GFP_ATOMIC); - if (!net_work) { - mlxsw_sp_port_dev_put(mlxsw_sp_port); - return NOTIFY_BAD; - } - - INIT_WORK(&net_work->work, mlxsw_sp_router_neigh_event_work); - net_work->mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - net_work->n = n; - /* Take a reference to ensure the neighbour won't be * destructed until we drop the reference in delayed * work. */ neigh_clone(n); - mlxsw_core_schedule_work(&net_work->work); - mlxsw_sp_port_dev_put(mlxsw_sp_port); - break; + return mlxsw_sp_router_schedule_work(net, router, n, + mlxsw_sp_router_neigh_event_work); + case NETEVENT_IPV4_MPATH_HASH_UPDATE: case NETEVENT_IPV6_MPATH_HASH_UPDATE: - return mlxsw_sp_router_schedule_work(ptr, nb, + return mlxsw_sp_router_schedule_work(ptr, router, NULL, mlxsw_sp_router_mp_hash_event_work); case NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE: - return mlxsw_sp_router_schedule_work(ptr, nb, + return mlxsw_sp_router_schedule_work(ptr, router, NULL, mlxsw_sp_router_update_priority_work); } @@ -2902,7 +2995,7 @@ struct mlxsw_sp_nexthop_key { struct mlxsw_sp_nexthop { struct list_head neigh_list_node; /* member of neigh entry list */ - struct list_head rif_list_node; + struct list_head crif_list_node; struct list_head router_list_node; struct mlxsw_sp_nexthop_group_info *nhgi; /* pointer back to the group * this nexthop belongs to @@ -2915,7 +3008,7 @@ struct mlxsw_sp_nexthop { int nh_weight; int norm_nh_weight; int num_adj_entries; - struct mlxsw_sp_rif *rif; + struct mlxsw_sp_crif *crif; u8 should_offload:1, /* set indicates this nexthop should be written * to the adjacency table. */ @@ -2935,6 +3028,14 @@ struct mlxsw_sp_nexthop { bool counter_valid; }; +static struct net_device * +mlxsw_sp_nexthop_dev(const struct mlxsw_sp_nexthop *nh) +{ + if (!nh->crif) + return NULL; + return nh->crif->key.dev; +} + enum mlxsw_sp_nexthop_group_type { MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4, MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6, @@ -2952,9 +3053,18 @@ struct mlxsw_sp_nexthop_group_info { is_resilient:1; struct list_head list; /* member in nh_res_grp_list */ struct mlxsw_sp_nexthop nexthops[]; -#define nh_rif nexthops[0].rif }; +static struct mlxsw_sp_rif * +mlxsw_sp_nhgi_rif(const struct mlxsw_sp_nexthop_group_info *nhgi) +{ + struct mlxsw_sp_crif *crif = nhgi->nexthops[0].crif; + + if (!crif) + return NULL; + return crif->rif; +} + struct mlxsw_sp_nexthop_group_vr_key { u16 vr_id; enum mlxsw_sp_l3proto proto; @@ -3076,7 +3186,9 @@ int mlxsw_sp_nexthop_indexes(struct mlxsw_sp_nexthop *nh, u32 *p_adj_index, struct mlxsw_sp_rif *mlxsw_sp_nexthop_rif(struct mlxsw_sp_nexthop *nh) { - return nh->rif; + if (WARN_ON(!nh->crif)) + return NULL; + return nh->crif->rif; } bool mlxsw_sp_nexthop_group_has_ipip(struct mlxsw_sp_nexthop *nh) @@ -3461,11 +3573,12 @@ static int __mlxsw_sp_nexthop_eth_update(struct mlxsw_sp *mlxsw_sp, bool force, char *ratr_pl) { struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry; + struct mlxsw_sp_rif *rif = mlxsw_sp_nexthop_rif(nh); enum mlxsw_reg_ratr_op op; u16 rif_index; - rif_index = nh->rif ? nh->rif->rif_index : - mlxsw_sp->router->lb_rif_index; + rif_index = rif ? rif->rif_index : + mlxsw_sp->router->lb_crif->rif->rif_index; op = force ? MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY : MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY_ON_ACTIVITY; mlxsw_reg_ratr_pack(ratr_pl, op, true, MLXSW_REG_RATR_TYPE_ETHERNET, @@ -4008,16 +4121,18 @@ mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp, { struct neighbour *n, *old_n = neigh_entry->key.n; struct mlxsw_sp_nexthop *nh; + struct net_device *dev; bool entry_connected; u8 nud_state, dead; int err; nh = list_first_entry(&neigh_entry->nexthop_list, struct mlxsw_sp_nexthop, neigh_list_node); + dev = mlxsw_sp_nexthop_dev(nh); - n = neigh_lookup(nh->neigh_tbl, &nh->gw_addr, nh->rif->dev); + n = neigh_lookup(nh->neigh_tbl, &nh->gw_addr, dev); if (!n) { - n = neigh_create(nh->neigh_tbl, &nh->gw_addr, nh->rif->dev); + n = neigh_create(nh->neigh_tbl, &nh->gw_addr, dev); if (IS_ERR(n)) return PTR_ERR(n); neigh_event_send(n, NULL); @@ -4081,44 +4196,49 @@ mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp, } } -static void mlxsw_sp_nexthop_rif_init(struct mlxsw_sp_nexthop *nh, - struct mlxsw_sp_rif *rif) +static void mlxsw_sp_nexthop_crif_init(struct mlxsw_sp_nexthop *nh, + struct mlxsw_sp_crif *crif) { - if (nh->rif) + if (nh->crif) return; - nh->rif = rif; - list_add(&nh->rif_list_node, &rif->nexthop_list); + nh->crif = crif; + list_add(&nh->crif_list_node, &crif->nexthop_list); } -static void mlxsw_sp_nexthop_rif_fini(struct mlxsw_sp_nexthop *nh) +static void mlxsw_sp_nexthop_crif_fini(struct mlxsw_sp_nexthop *nh) { - if (!nh->rif) + if (!nh->crif) return; - list_del(&nh->rif_list_node); - nh->rif = NULL; + list_del(&nh->crif_list_node); + nh->crif = NULL; } static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh) { struct mlxsw_sp_neigh_entry *neigh_entry; + struct net_device *dev; struct neighbour *n; u8 nud_state, dead; int err; + if (WARN_ON(!nh->crif->rif)) + return 0; + if (!nh->nhgi->gateway || nh->neigh_entry) return 0; + dev = mlxsw_sp_nexthop_dev(nh); /* Take a reference of neigh here ensuring that neigh would * not be destructed before the nexthop entry is finished. * The reference is taken either in neigh_lookup() or * in neigh_create() in case n is not found. */ - n = neigh_lookup(nh->neigh_tbl, &nh->gw_addr, nh->rif->dev); + n = neigh_lookup(nh->neigh_tbl, &nh->gw_addr, dev); if (!n) { - n = neigh_create(nh->neigh_tbl, &nh->gw_addr, nh->rif->dev); + n = neigh_create(nh->neigh_tbl, &nh->gw_addr, dev); if (IS_ERR(n)) return PTR_ERR(n); neigh_event_send(n, NULL); @@ -4197,15 +4317,20 @@ static void mlxsw_sp_nexthop_ipip_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh, struct mlxsw_sp_ipip_entry *ipip_entry) { + struct mlxsw_sp_crif *crif; bool removing; if (!nh->nhgi->gateway || nh->ipip_entry) return; + crif = mlxsw_sp_crif_lookup(mlxsw_sp->router, ipip_entry->ol_dev); + if (WARN_ON(!crif)) + return; + nh->ipip_entry = ipip_entry; removing = !mlxsw_sp_ipip_netdev_ul_up(ipip_entry->ol_dev); __mlxsw_sp_nexthop_neigh_update(nh, removing); - mlxsw_sp_nexthop_rif_init(nh, &ipip_entry->ol_lb->common); + mlxsw_sp_nexthop_crif_init(nh, crif); } static void mlxsw_sp_nexthop_ipip_fini(struct mlxsw_sp *mlxsw_sp, @@ -4237,7 +4362,7 @@ static int mlxsw_sp_nexthop_type_init(struct mlxsw_sp *mlxsw_sp, { const struct mlxsw_sp_ipip_ops *ipip_ops; struct mlxsw_sp_ipip_entry *ipip_entry; - struct mlxsw_sp_rif *rif; + struct mlxsw_sp_crif *crif; int err; ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, dev); @@ -4251,11 +4376,15 @@ static int mlxsw_sp_nexthop_type_init(struct mlxsw_sp *mlxsw_sp, } nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH; - rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); - if (!rif) + crif = mlxsw_sp_crif_lookup(mlxsw_sp->router, dev); + if (!crif) + return 0; + + mlxsw_sp_nexthop_crif_init(nh, crif); + + if (!crif->rif) return 0; - mlxsw_sp_nexthop_rif_init(nh, rif); err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh); if (err) goto err_neigh_init; @@ -4263,25 +4392,30 @@ static int mlxsw_sp_nexthop_type_init(struct mlxsw_sp *mlxsw_sp, return 0; err_neigh_init: - mlxsw_sp_nexthop_rif_fini(nh); + mlxsw_sp_nexthop_crif_fini(nh); return err; } -static void mlxsw_sp_nexthop_type_fini(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop *nh) +static void mlxsw_sp_nexthop_type_rif_gone(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) { switch (nh->type) { case MLXSW_SP_NEXTHOP_TYPE_ETH: mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh); - mlxsw_sp_nexthop_rif_fini(nh); break; case MLXSW_SP_NEXTHOP_TYPE_IPIP: - mlxsw_sp_nexthop_rif_fini(nh); mlxsw_sp_nexthop_ipip_fini(mlxsw_sp, nh); break; } } +static void mlxsw_sp_nexthop_type_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + mlxsw_sp_nexthop_type_rif_gone(mlxsw_sp, nh); + mlxsw_sp_nexthop_crif_fini(nh); +} + static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp, struct mlxsw_sp_nexthop *nh, @@ -4368,16 +4502,17 @@ static void mlxsw_sp_nexthop4_event(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_nexthop_rif_update(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif) { + struct net_device *dev = mlxsw_sp_rif_dev(rif); struct mlxsw_sp_nexthop *nh; bool removing; - list_for_each_entry(nh, &rif->nexthop_list, rif_list_node) { + list_for_each_entry(nh, &rif->crif->nexthop_list, crif_list_node) { switch (nh->type) { case MLXSW_SP_NEXTHOP_TYPE_ETH: removing = false; break; case MLXSW_SP_NEXTHOP_TYPE_IPIP: - removing = !mlxsw_sp_ipip_netdev_ul_up(rif->dev); + removing = !mlxsw_sp_ipip_netdev_ul_up(dev); break; default: WARN_ON(1); @@ -4389,25 +4524,14 @@ static void mlxsw_sp_nexthop_rif_update(struct mlxsw_sp *mlxsw_sp, } } -static void mlxsw_sp_nexthop_rif_migrate(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *old_rif, - struct mlxsw_sp_rif *new_rif) -{ - struct mlxsw_sp_nexthop *nh; - - list_splice_init(&old_rif->nexthop_list, &new_rif->nexthop_list); - list_for_each_entry(nh, &new_rif->nexthop_list, rif_list_node) - nh->rif = new_rif; - mlxsw_sp_nexthop_rif_update(mlxsw_sp, new_rif); -} - static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif) { struct mlxsw_sp_nexthop *nh, *tmp; - list_for_each_entry_safe(nh, tmp, &rif->nexthop_list, rif_list_node) { - mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh); + list_for_each_entry_safe(nh, tmp, &rif->crif->nexthop_list, + crif_list_node) { + mlxsw_sp_nexthop_type_rif_gone(mlxsw_sp, nh); mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp); } } @@ -4427,7 +4551,7 @@ static int mlxsw_sp_adj_trap_entry_init(struct mlxsw_sp *mlxsw_sp) mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, true, MLXSW_REG_RATR_TYPE_ETHERNET, mlxsw_sp->router->adj_trap_index, - mlxsw_sp->router->lb_rif_index); + mlxsw_sp->router->lb_crif->rif->rif_index); mlxsw_reg_ratr_trap_action_set(ratr_pl, trap_action); mlxsw_reg_ratr_trap_id_set(ratr_pl, MLXSW_TRAP_ID_RTR_EGRESS0); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); @@ -4743,21 +4867,19 @@ static bool mlxsw_sp_nexthop_obj_is_gateway(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_nexthop_obj_blackhole_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh) { - u16 lb_rif_index = mlxsw_sp->router->lb_rif_index; - nh->action = MLXSW_SP_NEXTHOP_ACTION_DISCARD; nh->should_offload = 1; /* While nexthops that discard packets do not forward packets * via an egress RIF, they still need to be programmed using a * valid RIF, so use the loopback RIF created during init. */ - nh->rif = mlxsw_sp->router->rifs[lb_rif_index]; + nh->crif = mlxsw_sp->router->lb_crif; } static void mlxsw_sp_nexthop_obj_blackhole_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh) { - nh->rif = NULL; + nh->crif = NULL; nh->should_offload = 0; } @@ -5491,7 +5613,7 @@ mlxsw_sp_fib_entry_should_offload(const struct mlxsw_sp_fib_entry *fib_entry) case MLXSW_SP_FIB_ENTRY_TYPE_REMOTE: return !!nh_group->nhgi->adj_index_valid; case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL: - return !!nh_group->nhgi->nh_rif; + return !!mlxsw_sp_nhgi_rif(nh_group->nhgi); case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE: case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP: case MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP: @@ -5509,9 +5631,10 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp, for (i = 0; i < nh_grp->nhgi->count; i++) { struct mlxsw_sp_nexthop *nh = &nh_grp->nhgi->nexthops[i]; + struct net_device *dev = mlxsw_sp_nexthop_dev(nh); struct fib6_info *rt = mlxsw_sp_rt6->rt; - if (nh->rif && nh->rif->dev == rt->fib6_nh->fib_nh_dev && + if (dev && dev == rt->fib6_nh->fib_nh_dev && ipv6_addr_equal((const struct in6_addr *) &nh->gw_addr, &rt->fib6_nh->fib_nh_gw6)) return nh; @@ -5752,7 +5875,8 @@ static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP; adjacency_index = nhgi->adj_index; ecmp_size = nhgi->ecmp_size; - } else if (!nhgi->adj_index_valid && nhgi->count && nhgi->nh_rif) { + } else if (!nhgi->adj_index_valid && nhgi->count && + mlxsw_sp_nhgi_rif(nhgi)) { trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP; adjacency_index = mlxsw_sp->router->adj_trap_index; ecmp_size = 1; @@ -5771,7 +5895,7 @@ static int mlxsw_sp_fib_entry_op_local(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, enum mlxsw_reg_ralue_op op) { - struct mlxsw_sp_rif *rif = fib_entry->nh_group->nhgi->nh_rif; + struct mlxsw_sp_rif *rif = mlxsw_sp_nhgi_rif(fib_entry->nh_group->nhgi); enum mlxsw_reg_ralue_trap_action trap_action; char ralue_pl[MLXSW_REG_RALUE_LEN]; u16 trap_id = 0; @@ -7298,9 +7422,10 @@ static void mlxsw_sp_vr_fib_flush(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) { + int max_vrs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); int i, j; - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + for (i = 0; i < max_vrs; i++) { struct mlxsw_sp_vr *vr = &mlxsw_sp->router->vrs[i]; if (!mlxsw_sp_vr_is_used(vr)) @@ -7699,11 +7824,12 @@ static struct mlxsw_sp_rif * mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, const struct net_device *dev) { + int max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); int i; - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) + for (i = 0; i < max_rifs; i++) if (mlxsw_sp->router->rifs[i] && - mlxsw_sp->router->rifs[i]->dev == dev) + mlxsw_sp_rif_dev_is(mlxsw_sp->router->rifs[i], dev)) return mlxsw_sp->router->rifs[i]; return NULL; @@ -7761,33 +7887,52 @@ static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif) static void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif) { + /* Signal to nexthop cleanup that the RIF is going away. */ + rif->crif->rif = NULL; + mlxsw_sp_router_rif_disable(mlxsw_sp, rif->rif_index); mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, rif); mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, rif); } +static bool __mlxsw_sp_dev_addr_list_empty(const struct net_device *dev) +{ + struct inet6_dev *inet6_dev; + struct in_device *idev; + + idev = __in_dev_get_rcu(dev); + if (idev && idev->ifa_list) + return false; + + inet6_dev = __in6_dev_get(dev); + if (inet6_dev && !list_empty(&inet6_dev->addr_list)) + return false; + + return true; +} + +static bool mlxsw_sp_dev_addr_list_empty(const struct net_device *dev) +{ + bool addr_list_empty; + + rcu_read_lock(); + addr_list_empty = __mlxsw_sp_dev_addr_list_empty(dev); + rcu_read_unlock(); + + return addr_list_empty; +} + static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *rif, struct net_device *dev, unsigned long event) { - struct inet6_dev *inet6_dev; - bool addr_list_empty = true; - struct in_device *idev; + bool addr_list_empty; switch (event) { case NETDEV_UP: return rif == NULL; case NETDEV_DOWN: - rcu_read_lock(); - idev = __in_dev_get_rcu(dev); - if (idev && idev->ifa_list) - addr_list_empty = false; - - inet6_dev = __in6_dev_get(dev); - if (addr_list_empty && inet6_dev && - !list_empty(&inet6_dev->addr_list)) - addr_list_empty = false; - rcu_read_unlock(); + addr_list_empty = mlxsw_sp_dev_addr_list_empty(dev); /* macvlans do not have a RIF, but rather piggy back on the * RIF of their lower device. @@ -7796,7 +7941,7 @@ mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *rif, struct net_device *dev, return true; if (rif && addr_list_empty && - !netif_is_l3_slave(rif->dev)) + !netif_is_l3_slave(mlxsw_sp_rif_dev(rif))) return true; /* It is possible we already removed the RIF ourselves * if it was assigned to a netdev that is now a bridge @@ -7854,27 +7999,39 @@ static void mlxsw_sp_rif_index_free(struct mlxsw_sp *mlxsw_sp, u16 rif_index, static struct mlxsw_sp_rif *mlxsw_sp_rif_alloc(size_t rif_size, u16 rif_index, u16 vr_id, - struct net_device *l3_dev) + struct mlxsw_sp_crif *crif) { + struct net_device *l3_dev = crif ? crif->key.dev : NULL; struct mlxsw_sp_rif *rif; rif = kzalloc(rif_size, GFP_KERNEL); if (!rif) return NULL; - INIT_LIST_HEAD(&rif->nexthop_list); INIT_LIST_HEAD(&rif->neigh_list); if (l3_dev) { ether_addr_copy(rif->addr, l3_dev->dev_addr); rif->mtu = l3_dev->mtu; - rif->dev = l3_dev; } rif->vr_id = vr_id; rif->rif_index = rif_index; + if (crif) { + rif->crif = crif; + crif->rif = rif; + } return rif; } +static void mlxsw_sp_rif_free(struct mlxsw_sp_rif *rif) +{ + WARN_ON(!list_empty(&rif->neigh_list)); + + if (rif->crif) + rif->crif->rif = NULL; + kfree(rif); +} + struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp, u16 rif_index) { @@ -7893,7 +8050,8 @@ u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *lb_rif) u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif) { - u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(lb_rif->common.dev); + struct net_device *dev = mlxsw_sp_rif_dev(&lb_rif->common); + u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(dev); struct mlxsw_sp_vr *ul_vr; ul_vr = mlxsw_sp_vr_get(lb_rif->common.mlxsw_sp, ul_tb_id, NULL); @@ -8070,12 +8228,18 @@ mlxsw_sp_router_hwstats_notify_schedule(struct net_device *dev) int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif) { - return rif->dev->ifindex; + return mlxsw_sp_rif_dev(rif)->ifindex; } -const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif) +bool mlxsw_sp_rif_has_dev(const struct mlxsw_sp_rif *rif) +{ + return !!mlxsw_sp_rif_dev(rif); +} + +bool mlxsw_sp_rif_dev_is(const struct mlxsw_sp_rif *rif, + const struct net_device *dev) { - return rif->dev; + return mlxsw_sp_rif_dev(rif) == dev; } static void mlxsw_sp_rif_push_l3_stats(struct mlxsw_sp_rif *rif) @@ -8083,7 +8247,7 @@ static void mlxsw_sp_rif_push_l3_stats(struct mlxsw_sp_rif *rif) struct rtnl_hw_stats64 stats = {}; if (!mlxsw_sp_router_port_l3_stats_fetch(rif, &stats)) - netdev_offload_xstats_push_delta(rif->dev, + netdev_offload_xstats_push_delta(mlxsw_sp_rif_dev(rif), NETDEV_OFFLOAD_XSTATS_TYPE_L3, &stats); } @@ -8098,6 +8262,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_rif_ops *ops; struct mlxsw_sp_fid *fid = NULL; enum mlxsw_sp_rif_type type; + struct mlxsw_sp_crif *crif; struct mlxsw_sp_rif *rif; struct mlxsw_sp_vr *vr; u16 rif_index; @@ -8117,12 +8282,18 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, goto err_rif_index_alloc; } - rif = mlxsw_sp_rif_alloc(ops->rif_size, rif_index, vr->id, params->dev); + crif = mlxsw_sp_crif_lookup(mlxsw_sp->router, params->dev); + if (WARN_ON(!crif)) { + err = -ENOENT; + goto err_crif_lookup; + } + + rif = mlxsw_sp_rif_alloc(ops->rif_size, rif_index, vr->id, crif); if (!rif) { err = -ENOMEM; goto err_rif_alloc; } - dev_hold(rif->dev); + dev_hold(params->dev); mlxsw_sp->router->rifs[rif_index] = rif; rif->mlxsw_sp = mlxsw_sp; rif->ops = ops; @@ -8150,12 +8321,12 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, goto err_mr_rif_add; } - if (netdev_offload_xstats_enabled(rif->dev, + if (netdev_offload_xstats_enabled(params->dev, NETDEV_OFFLOAD_XSTATS_TYPE_L3)) { err = mlxsw_sp_router_port_l3_stats_enable(rif); if (err) goto err_stats_enable; - mlxsw_sp_router_hwstats_notify_schedule(rif->dev); + mlxsw_sp_router_hwstats_notify_schedule(params->dev); } else { mlxsw_sp_rif_counters_alloc(rif); } @@ -8173,9 +8344,10 @@ err_configure: mlxsw_sp_fid_put(fid); err_fid_get: mlxsw_sp->router->rifs[rif_index] = NULL; - dev_put(rif->dev); - kfree(rif); + dev_put(params->dev); + mlxsw_sp_rif_free(rif); err_rif_alloc: +err_crif_lookup: mlxsw_sp_rif_index_free(mlxsw_sp, rif_index, rif_entries); err_rif_index_alloc: vr->rif_count--; @@ -8185,8 +8357,10 @@ err_rif_index_alloc: static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif) { + struct net_device *dev = mlxsw_sp_rif_dev(rif); const struct mlxsw_sp_rif_ops *ops = rif->ops; struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; + struct mlxsw_sp_crif *crif = rif->crif; struct mlxsw_sp_fid *fid = rif->fid; u8 rif_entries = rif->rif_entries; u16 rif_index = rif->rif_index; @@ -8197,11 +8371,10 @@ static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif) mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif); vr = &mlxsw_sp->router->vrs[rif->vr_id]; - if (netdev_offload_xstats_enabled(rif->dev, - NETDEV_OFFLOAD_XSTATS_TYPE_L3)) { + if (netdev_offload_xstats_enabled(dev, NETDEV_OFFLOAD_XSTATS_TYPE_L3)) { mlxsw_sp_rif_push_l3_stats(rif); mlxsw_sp_router_port_l3_stats_disable(rif); - mlxsw_sp_router_hwstats_notify_schedule(rif->dev); + mlxsw_sp_router_hwstats_notify_schedule(dev); } else { mlxsw_sp_rif_counters_free(rif); } @@ -8213,11 +8386,14 @@ static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif) /* Loopback RIFs are not associated with a FID. */ mlxsw_sp_fid_put(fid); mlxsw_sp->router->rifs[rif->rif_index] = NULL; - dev_put(rif->dev); - kfree(rif); + dev_put(dev); + mlxsw_sp_rif_free(rif); mlxsw_sp_rif_index_free(mlxsw_sp, rif_index, rif_entries); vr->rif_count--; mlxsw_sp_vr_put(mlxsw_sp, vr); + + if (crif->can_destroy) + mlxsw_sp_crif_free(crif); } void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp, @@ -8549,25 +8725,20 @@ __mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan) mlxsw_sp_rif_subport_put(rif); } -int -mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan, - struct net_device *l3_dev, - struct netlink_ext_ack *extack) +static int +mlxsw_sp_port_vlan_router_join_existing(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan, + struct net_device *l3_dev, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port_vlan->mlxsw_sp_port->mlxsw_sp; - struct mlxsw_sp_rif *rif; - int err = 0; - mutex_lock(&mlxsw_sp->router->lock); - rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev); - if (!rif) - goto out; + lockdep_assert_held(&mlxsw_sp->router->lock); - err = __mlxsw_sp_port_vlan_router_join(mlxsw_sp_port_vlan, l3_dev, - extack); -out: - mutex_unlock(&mlxsw_sp->router->lock); - return err; + if (!mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev)) + return 0; + + return __mlxsw_sp_port_vlan_router_join(mlxsw_sp_port_vlan, l3_dev, + extack); } void @@ -8874,8 +9045,8 @@ out: return notifier_from_errno(err); } -int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused, - unsigned long event, void *ptr) +static int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused, + unsigned long event, void *ptr) { struct in_validator_info *ivi = (struct in_validator_info *) ptr; struct net_device *dev = ivi->ivi_dev->dev; @@ -8957,8 +9128,8 @@ static int mlxsw_sp_inet6addr_event(struct notifier_block *nb, return NOTIFY_DONE; } -int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused, - unsigned long event, void *ptr) +static int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused, + unsigned long event, void *ptr) { struct in6_validator_info *i6vi = (struct in6_validator_info *) ptr; struct net_device *dev = i6vi->i6vi_dev->dev; @@ -9004,7 +9175,7 @@ mlxsw_sp_router_port_change_event(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif, struct netlink_ext_ack *extack) { - struct net_device *dev = rif->dev; + struct net_device *dev = mlxsw_sp_rif_dev(rif); u8 old_mac_profile; u16 fid_index; int err; @@ -9088,6 +9259,104 @@ static int mlxsw_sp_router_port_pre_changeaddr_event(struct mlxsw_sp_rif *rif, return -ENOBUFS; } +static bool mlxsw_sp_router_netdevice_interesting(struct mlxsw_sp *mlxsw_sp, + struct net_device *dev) +{ + struct vlan_dev_priv *vlan; + + if (netif_is_lag_master(dev) || + netif_is_bridge_master(dev) || + mlxsw_sp_port_dev_check(dev) || + mlxsw_sp_netdev_is_ipip_ol(mlxsw_sp, dev) || + netif_is_l3_master(dev)) + return true; + + if (!is_vlan_dev(dev)) + return false; + + vlan = vlan_dev_priv(dev); + return netif_is_lag_master(vlan->real_dev) || + netif_is_bridge_master(vlan->real_dev) || + mlxsw_sp_port_dev_check(vlan->real_dev); +} + +static struct mlxsw_sp_crif * +mlxsw_sp_crif_register(struct mlxsw_sp_router *router, struct net_device *dev) +{ + struct mlxsw_sp_crif *crif; + int err; + + if (WARN_ON(mlxsw_sp_crif_lookup(router, dev))) + return NULL; + + crif = mlxsw_sp_crif_alloc(dev); + if (!crif) + return ERR_PTR(-ENOMEM); + + err = mlxsw_sp_crif_insert(router, crif); + if (err) + goto err_netdev_insert; + + return crif; + +err_netdev_insert: + mlxsw_sp_crif_free(crif); + return ERR_PTR(err); +} + +static void mlxsw_sp_crif_unregister(struct mlxsw_sp_router *router, + struct mlxsw_sp_crif *crif) +{ + struct mlxsw_sp_nexthop *nh, *tmp; + + mlxsw_sp_crif_remove(router, crif); + + list_for_each_entry_safe(nh, tmp, &crif->nexthop_list, crif_list_node) + mlxsw_sp_nexthop_type_fini(router->mlxsw_sp, nh); + + if (crif->rif) + crif->can_destroy = true; + else + mlxsw_sp_crif_free(crif); +} + +static int mlxsw_sp_netdevice_register(struct mlxsw_sp_router *router, + struct net_device *dev) +{ + struct mlxsw_sp_crif *crif; + + if (!mlxsw_sp_router_netdevice_interesting(router->mlxsw_sp, dev)) + return 0; + + crif = mlxsw_sp_crif_register(router, dev); + return PTR_ERR_OR_ZERO(crif); +} + +static void mlxsw_sp_netdevice_unregister(struct mlxsw_sp_router *router, + struct net_device *dev) +{ + struct mlxsw_sp_crif *crif; + + if (!mlxsw_sp_router_netdevice_interesting(router->mlxsw_sp, dev)) + return; + + /* netdev_run_todo(), by way of netdev_wait_allrefs_any(), rebroadcasts + * the NETDEV_UNREGISTER message, so we can get here twice. If that's + * what happened, the netdevice state is NETREG_UNREGISTERED. In that + * case, we expect to have collected the CRIF already, and warn if it + * still exists. Otherwise we expect the CRIF to exist. + */ + crif = mlxsw_sp_crif_lookup(router, dev); + if (dev->reg_state == NETREG_UNREGISTERED) { + if (!WARN_ON(crif)) + return; + } + if (WARN_ON(!crif)) + return; + + mlxsw_sp_crif_unregister(router, crif); +} + static bool mlxsw_sp_is_offload_xstats_event(unsigned long event) { switch (event) { @@ -9254,6 +9523,46 @@ mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, return err; } +static int +mlxsw_sp_port_vid_router_join_existing(struct mlxsw_sp_port *mlxsw_sp_port, + u16 vid, struct net_device *dev, + struct netlink_ext_ack *extack) +{ + struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; + + mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, + vid); + if (WARN_ON(!mlxsw_sp_port_vlan)) + return -EINVAL; + + return mlxsw_sp_port_vlan_router_join_existing(mlxsw_sp_port_vlan, + dev, extack); +} + +static int __mlxsw_sp_router_port_join_lag(struct mlxsw_sp_port *mlxsw_sp_port, + struct net_device *lag_dev, + struct netlink_ext_ack *extack) +{ + u16 default_vid = MLXSW_SP_DEFAULT_VID; + + return mlxsw_sp_port_vid_router_join_existing(mlxsw_sp_port, + default_vid, lag_dev, + extack); +} + +int mlxsw_sp_router_port_join_lag(struct mlxsw_sp_port *mlxsw_sp_port, + struct net_device *lag_dev, + struct netlink_ext_ack *extack) +{ + int err; + + mutex_lock(&mlxsw_sp_port->mlxsw_sp->router->lock); + err = __mlxsw_sp_router_port_join_lag(mlxsw_sp_port, lag_dev, extack); + mutex_unlock(&mlxsw_sp_port->mlxsw_sp->router->lock); + + return err; +} + static int mlxsw_sp_router_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { @@ -9267,6 +9576,15 @@ static int mlxsw_sp_router_netdevice_event(struct notifier_block *nb, mutex_lock(&mlxsw_sp->router->lock); + if (event == NETDEV_REGISTER) { + err = mlxsw_sp_netdevice_register(router, dev); + if (err) + /* No need to roll this back, UNREGISTER will collect it + * anyhow. + */ + goto out; + } + if (mlxsw_sp_is_offload_xstats_event(event)) err = mlxsw_sp_netdevice_offload_xstats_cmd(mlxsw_sp, dev, event, ptr); @@ -9281,6 +9599,10 @@ static int mlxsw_sp_router_netdevice_event(struct notifier_block *nb, else if (mlxsw_sp_is_vrf_event(event, ptr)) err = mlxsw_sp_netdevice_vrf_event(dev, event, ptr); + if (event == NETDEV_UNREGISTER) + mlxsw_sp_netdevice_unregister(router, dev); + +out: mutex_unlock(&mlxsw_sp->router->lock); return notifier_from_errno(err); @@ -9300,15 +9622,16 @@ static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, static int mlxsw_sp_rif_macvlan_flush(struct mlxsw_sp_rif *rif) { + struct net_device *dev = mlxsw_sp_rif_dev(rif); struct netdev_nested_priv priv = { .data = (void *)rif, }; - if (!netif_is_macvlan_port(rif->dev)) + if (!netif_is_macvlan_port(dev)) return 0; - netdev_warn(rif->dev, "Router interface is deleted. Upper macvlans will not work\n"); - return netdev_walk_all_upper_dev_rcu(rif->dev, + netdev_warn(dev, "Router interface is deleted. Upper macvlans will not work\n"); + return netdev_walk_all_upper_dev_rcu(dev, __mlxsw_sp_rif_macvlan_flush, &priv); } @@ -9329,6 +9652,7 @@ static void mlxsw_sp_rif_subport_setup(struct mlxsw_sp_rif *rif, static int mlxsw_sp_rif_subport_op(struct mlxsw_sp_rif *rif, bool enable) { + struct net_device *dev = mlxsw_sp_rif_dev(rif); struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; struct mlxsw_sp_rif_subport *rif_subport; char ritr_pl[MLXSW_REG_RITR_LEN]; @@ -9336,8 +9660,8 @@ static int mlxsw_sp_rif_subport_op(struct mlxsw_sp_rif *rif, bool enable) rif_subport = mlxsw_sp_rif_subport_rif(rif); mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_SP_IF, - rif->rif_index, rif->vr_id, rif->dev->mtu); - mlxsw_reg_ritr_mac_pack(ritr_pl, rif->dev->dev_addr); + rif->rif_index, rif->vr_id, dev->mtu); + mlxsw_reg_ritr_mac_pack(ritr_pl, dev->dev_addr); mlxsw_reg_ritr_if_mac_profile_id_set(ritr_pl, rif->mac_profile_id); efid = mlxsw_sp_fid_index(rif->fid); mlxsw_reg_ritr_sp_if_pack(ritr_pl, rif_subport->lag, @@ -9350,6 +9674,7 @@ static int mlxsw_sp_rif_subport_op(struct mlxsw_sp_rif *rif, bool enable) static int mlxsw_sp_rif_subport_configure(struct mlxsw_sp_rif *rif, struct netlink_ext_ack *extack) { + struct net_device *dev = mlxsw_sp_rif_dev(rif); u8 mac_profile; int err; @@ -9363,7 +9688,7 @@ static int mlxsw_sp_rif_subport_configure(struct mlxsw_sp_rif *rif, if (err) goto err_rif_subport_op; - err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr, mlxsw_sp_fid_index(rif->fid), true); if (err) goto err_rif_fdb_op; @@ -9375,7 +9700,7 @@ static int mlxsw_sp_rif_subport_configure(struct mlxsw_sp_rif *rif, return 0; err_fid_rif_set: - mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr, mlxsw_sp_fid_index(rif->fid), false); err_rif_fdb_op: mlxsw_sp_rif_subport_op(rif, false); @@ -9386,10 +9711,11 @@ err_rif_subport_op: static void mlxsw_sp_rif_subport_deconfigure(struct mlxsw_sp_rif *rif) { + struct net_device *dev = mlxsw_sp_rif_dev(rif); struct mlxsw_sp_fid *fid = rif->fid; mlxsw_sp_fid_rif_unset(fid); - mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr, mlxsw_sp_fid_index(fid), false); mlxsw_sp_rif_macvlan_flush(rif); mlxsw_sp_rif_subport_op(rif, false); @@ -9415,12 +9741,13 @@ static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_subport_ops = { static int mlxsw_sp_rif_fid_op(struct mlxsw_sp_rif *rif, u16 fid, bool enable) { enum mlxsw_reg_ritr_if_type type = MLXSW_REG_RITR_FID_IF; + struct net_device *dev = mlxsw_sp_rif_dev(rif); struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; char ritr_pl[MLXSW_REG_RITR_LEN]; mlxsw_reg_ritr_pack(ritr_pl, enable, type, rif->rif_index, rif->vr_id, - rif->dev->mtu); - mlxsw_reg_ritr_mac_pack(ritr_pl, rif->dev->dev_addr); + dev->mtu); + mlxsw_reg_ritr_mac_pack(ritr_pl, dev->dev_addr); mlxsw_reg_ritr_if_mac_profile_id_set(ritr_pl, rif->mac_profile_id); mlxsw_reg_ritr_fid_if_fid_set(ritr_pl, fid); @@ -9435,6 +9762,7 @@ u16 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp) static int mlxsw_sp_rif_fid_configure(struct mlxsw_sp_rif *rif, struct netlink_ext_ack *extack) { + struct net_device *dev = mlxsw_sp_rif_dev(rif); struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; u16 fid_index = mlxsw_sp_fid_index(rif->fid); u8 mac_profile; @@ -9460,7 +9788,7 @@ static int mlxsw_sp_rif_fid_configure(struct mlxsw_sp_rif *rif, if (err) goto err_fid_bc_flood_set; - err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr, mlxsw_sp_fid_index(rif->fid), true); if (err) goto err_rif_fdb_op; @@ -9472,7 +9800,7 @@ static int mlxsw_sp_rif_fid_configure(struct mlxsw_sp_rif *rif, return 0; err_fid_rif_set: - mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr, mlxsw_sp_fid_index(rif->fid), false); err_rif_fdb_op: mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC, @@ -9489,12 +9817,13 @@ err_rif_fid_op: static void mlxsw_sp_rif_fid_deconfigure(struct mlxsw_sp_rif *rif) { + struct net_device *dev = mlxsw_sp_rif_dev(rif); u16 fid_index = mlxsw_sp_fid_index(rif->fid); struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; struct mlxsw_sp_fid *fid = rif->fid; mlxsw_sp_fid_rif_unset(fid); - mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr, mlxsw_sp_fid_index(fid), false); mlxsw_sp_rif_macvlan_flush(rif); mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC, @@ -9509,7 +9838,9 @@ static struct mlxsw_sp_fid * mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif, struct netlink_ext_ack *extack) { - return mlxsw_sp_fid_8021d_get(rif->mlxsw_sp, rif->dev->ifindex); + int rif_ifindex = mlxsw_sp_rif_dev_ifindex(rif); + + return mlxsw_sp_fid_8021d_get(rif->mlxsw_sp, rif_ifindex); } static void mlxsw_sp_rif_fid_fdb_del(struct mlxsw_sp_rif *rif, const char *mac) @@ -9517,7 +9848,7 @@ static void mlxsw_sp_rif_fid_fdb_del(struct mlxsw_sp_rif *rif, const char *mac) struct switchdev_notifier_fdb_info info = {}; struct net_device *dev; - dev = br_fdb_find_port(rif->dev, mac, 0); + dev = br_fdb_find_port(mlxsw_sp_rif_dev(rif), mac, 0); if (!dev) return; @@ -9540,17 +9871,18 @@ static struct mlxsw_sp_fid * mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif, struct netlink_ext_ack *extack) { + struct net_device *dev = mlxsw_sp_rif_dev(rif); struct net_device *br_dev; u16 vid; int err; - if (is_vlan_dev(rif->dev)) { - vid = vlan_dev_vlan_id(rif->dev); - br_dev = vlan_dev_real_dev(rif->dev); + if (is_vlan_dev(dev)) { + vid = vlan_dev_vlan_id(dev); + br_dev = vlan_dev_real_dev(dev); if (WARN_ON(!netif_is_bridge_master(br_dev))) return ERR_PTR(-EINVAL); } else { - err = br_vlan_get_pvid(rif->dev, &vid); + err = br_vlan_get_pvid(dev, &vid); if (err < 0 || !vid) { NL_SET_ERR_MSG_MOD(extack, "Couldn't determine bridge PVID"); return ERR_PTR(-EINVAL); @@ -9562,12 +9894,13 @@ mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif, static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac) { + struct net_device *rif_dev = mlxsw_sp_rif_dev(rif); struct switchdev_notifier_fdb_info info = {}; u16 vid = mlxsw_sp_fid_8021q_vid(rif->fid); struct net_device *br_dev; struct net_device *dev; - br_dev = is_vlan_dev(rif->dev) ? vlan_dev_real_dev(rif->dev) : rif->dev; + br_dev = is_vlan_dev(rif_dev) ? vlan_dev_real_dev(rif_dev) : rif_dev; dev = br_fdb_find_port(br_dev, mac, vid); if (!dev) return; @@ -9581,11 +9914,12 @@ static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac) static int mlxsw_sp_rif_vlan_op(struct mlxsw_sp_rif *rif, u16 vid, u16 efid, bool enable) { + struct net_device *dev = mlxsw_sp_rif_dev(rif); struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; char ritr_pl[MLXSW_REG_RITR_LEN]; mlxsw_reg_ritr_vlan_if_pack(ritr_pl, enable, rif->rif_index, rif->vr_id, - rif->dev->mtu, rif->dev->dev_addr, + dev->mtu, dev->dev_addr, rif->mac_profile_id, vid, efid); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); @@ -9594,6 +9928,7 @@ static int mlxsw_sp_rif_vlan_op(struct mlxsw_sp_rif *rif, u16 vid, u16 efid, static int mlxsw_sp_rif_vlan_configure(struct mlxsw_sp_rif *rif, u16 efid, struct netlink_ext_ack *extack) { + struct net_device *dev = mlxsw_sp_rif_dev(rif); u16 vid = mlxsw_sp_fid_8021q_vid(rif->fid); struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; u8 mac_profile; @@ -9619,7 +9954,7 @@ static int mlxsw_sp_rif_vlan_configure(struct mlxsw_sp_rif *rif, u16 efid, if (err) goto err_fid_bc_flood_set; - err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr, mlxsw_sp_fid_index(rif->fid), true); if (err) goto err_rif_fdb_op; @@ -9631,7 +9966,7 @@ static int mlxsw_sp_rif_vlan_configure(struct mlxsw_sp_rif *rif, u16 efid, return 0; err_fid_rif_set: - mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr, mlxsw_sp_fid_index(rif->fid), false); err_rif_fdb_op: mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC, @@ -9648,11 +9983,12 @@ err_rif_vlan_fid_op: static void mlxsw_sp_rif_vlan_deconfigure(struct mlxsw_sp_rif *rif) { + struct net_device *dev = mlxsw_sp_rif_dev(rif); u16 vid = mlxsw_sp_fid_8021q_vid(rif->fid); struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; mlxsw_sp_fid_rif_unset(rif->fid); - mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr, mlxsw_sp_fid_index(rif->fid), false); mlxsw_sp_rif_macvlan_flush(rif); mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC, @@ -9719,12 +10055,13 @@ mlxsw_sp1_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif, struct netlink_ext_ack *extack) { struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif); - u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(rif->dev); + struct net_device *dev = mlxsw_sp_rif_dev(rif); + u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(dev); struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; struct mlxsw_sp_vr *ul_vr; int err; - ul_vr = mlxsw_sp_vr_get(mlxsw_sp, ul_tb_id, NULL); + ul_vr = mlxsw_sp_vr_get(mlxsw_sp, ul_tb_id, extack); if (IS_ERR(ul_vr)) return PTR_ERR(ul_vr); @@ -9786,6 +10123,7 @@ mlxsw_sp_rif_ipip_lb_ul_rif_op(struct mlxsw_sp_rif *ul_rif, bool enable) static struct mlxsw_sp_rif * mlxsw_sp_ul_rif_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, + struct mlxsw_sp_crif *ul_crif, struct netlink_ext_ack *extack) { struct mlxsw_sp_rif *ul_rif; @@ -9799,7 +10137,8 @@ mlxsw_sp_ul_rif_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, return ERR_PTR(err); } - ul_rif = mlxsw_sp_rif_alloc(sizeof(*ul_rif), rif_index, vr->id, NULL); + ul_rif = mlxsw_sp_rif_alloc(sizeof(*ul_rif), rif_index, vr->id, + ul_crif); if (!ul_rif) { err = -ENOMEM; goto err_rif_alloc; @@ -9817,7 +10156,7 @@ mlxsw_sp_ul_rif_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, ul_rif_op_err: mlxsw_sp->router->rifs[rif_index] = NULL; - kfree(ul_rif); + mlxsw_sp_rif_free(ul_rif); err_rif_alloc: mlxsw_sp_rif_index_free(mlxsw_sp, rif_index, rif_entries); return ERR_PTR(err); @@ -9832,12 +10171,13 @@ static void mlxsw_sp_ul_rif_destroy(struct mlxsw_sp_rif *ul_rif) atomic_sub(rif_entries, &mlxsw_sp->router->rifs_count); mlxsw_sp_rif_ipip_lb_ul_rif_op(ul_rif, false); mlxsw_sp->router->rifs[ul_rif->rif_index] = NULL; - kfree(ul_rif); + mlxsw_sp_rif_free(ul_rif); mlxsw_sp_rif_index_free(mlxsw_sp, rif_index, rif_entries); } static struct mlxsw_sp_rif * mlxsw_sp_ul_rif_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id, + struct mlxsw_sp_crif *ul_crif, struct netlink_ext_ack *extack) { struct mlxsw_sp_vr *vr; @@ -9850,7 +10190,7 @@ mlxsw_sp_ul_rif_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id, if (refcount_inc_not_zero(&vr->ul_rif_refcnt)) return vr->ul_rif; - vr->ul_rif = mlxsw_sp_ul_rif_create(mlxsw_sp, vr, extack); + vr->ul_rif = mlxsw_sp_ul_rif_create(mlxsw_sp, vr, ul_crif, extack); if (IS_ERR(vr->ul_rif)) { err = PTR_ERR(vr->ul_rif); goto err_ul_rif_create; @@ -9888,7 +10228,7 @@ int mlxsw_sp_router_ul_rif_get(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, int err = 0; mutex_lock(&mlxsw_sp->router->lock); - ul_rif = mlxsw_sp_ul_rif_get(mlxsw_sp, ul_tb_id, NULL); + ul_rif = mlxsw_sp_ul_rif_get(mlxsw_sp, ul_tb_id, NULL, NULL); if (IS_ERR(ul_rif)) { err = PTR_ERR(ul_rif); goto out; @@ -9918,12 +10258,13 @@ mlxsw_sp2_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif, struct netlink_ext_ack *extack) { struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif); - u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(rif->dev); + struct net_device *dev = mlxsw_sp_rif_dev(rif); + u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(dev); struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; struct mlxsw_sp_rif *ul_rif; int err; - ul_rif = mlxsw_sp_ul_rif_get(mlxsw_sp, ul_tb_id, NULL); + ul_rif = mlxsw_sp_ul_rif_get(mlxsw_sp, ul_tb_id, NULL, extack); if (IS_ERR(ul_rif)) return PTR_ERR(ul_rif); @@ -10041,11 +10382,12 @@ err_rifs_table_init: static void mlxsw_sp_rifs_fini(struct mlxsw_sp *mlxsw_sp) { + int max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); int i; WARN_ON_ONCE(atomic_read(&mlxsw_sp->router->rifs_count)); - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) + for (i = 0; i < max_rifs; i++) WARN_ON_ONCE(mlxsw_sp->router->rifs[i]); devl_resource_occ_get_unregister(devlink, MLXSW_SP_RESOURCE_RIFS); @@ -10444,28 +10786,41 @@ static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); } -static int mlxsw_sp_lb_rif_init(struct mlxsw_sp *mlxsw_sp) +static int mlxsw_sp_lb_rif_init(struct mlxsw_sp *mlxsw_sp, + struct netlink_ext_ack *extack) { - u16 lb_rif_index; + struct mlxsw_sp_router *router = mlxsw_sp->router; + struct mlxsw_sp_rif *lb_rif; int err; + router->lb_crif = mlxsw_sp_crif_alloc(NULL); + if (!router->lb_crif) + return -ENOMEM; + /* Create a generic loopback RIF associated with the main table * (default VRF). Any table can be used, but the main table exists - * anyway, so we do not waste resources. + * anyway, so we do not waste resources. Loopback RIFs are usually + * created with a NULL CRIF, but this RIF is used as a fallback RIF + * for blackhole nexthops, and nexthops expect to have a valid CRIF. */ - err = mlxsw_sp_router_ul_rif_get(mlxsw_sp, RT_TABLE_MAIN, - &lb_rif_index); - if (err) - return err; - - mlxsw_sp->router->lb_rif_index = lb_rif_index; + lb_rif = mlxsw_sp_ul_rif_get(mlxsw_sp, RT_TABLE_MAIN, router->lb_crif, + extack); + if (IS_ERR(lb_rif)) { + err = PTR_ERR(lb_rif); + goto err_ul_rif_get; + } return 0; + +err_ul_rif_get: + mlxsw_sp_crif_free(router->lb_crif); + return err; } static void mlxsw_sp_lb_rif_fini(struct mlxsw_sp *mlxsw_sp) { - mlxsw_sp_router_ul_rif_put(mlxsw_sp, mlxsw_sp->router->lb_rif_index); + mlxsw_sp_ul_rif_put(mlxsw_sp->router->lb_crif->rif); + mlxsw_sp_crif_free(mlxsw_sp->router->lb_crif); } static int mlxsw_sp1_router_init(struct mlxsw_sp *mlxsw_sp) @@ -10504,6 +10859,7 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, struct netlink_ext_ack *extack) { struct mlxsw_sp_router *router; + struct notifier_block *nb; int err; router = kzalloc(sizeof(*mlxsw_sp->router), GFP_KERNEL); @@ -10525,14 +10881,19 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_router_init; - err = mlxsw_sp_rifs_init(mlxsw_sp); - if (err) - goto err_rifs_init; - err = mlxsw_sp->router_ops->ipips_init(mlxsw_sp); if (err) goto err_ipips_init; + err = rhashtable_init(&mlxsw_sp->router->crif_ht, + &mlxsw_sp_crif_ht_params); + if (err) + goto err_crif_ht_init; + + err = mlxsw_sp_rifs_init(mlxsw_sp); + if (err) + goto err_rifs_init; + err = rhashtable_init(&mlxsw_sp->router->nexthop_ht, &mlxsw_sp_nexthop_ht_params); if (err) @@ -10556,7 +10917,7 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_vrs_init; - err = mlxsw_sp_lb_rif_init(mlxsw_sp); + err = mlxsw_sp_lb_rif_init(mlxsw_sp, extack); if (err) goto err_lb_rif_init; @@ -10582,6 +10943,17 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_register_inet6addr_notifier; + router->inetaddr_valid_nb.notifier_call = mlxsw_sp_inetaddr_valid_event; + err = register_inetaddr_validator_notifier(&router->inetaddr_valid_nb); + if (err) + goto err_register_inetaddr_valid_notifier; + + nb = &router->inet6addr_valid_nb; + nb->notifier_call = mlxsw_sp_inet6addr_valid_event; + err = register_inet6addr_validator_notifier(nb); + if (err) + goto err_register_inet6addr_valid_notifier; + mlxsw_sp->router->netevent_nb.notifier_call = mlxsw_sp_router_netevent_event; err = register_netevent_notifier(&mlxsw_sp->router->netevent_nb); @@ -10621,6 +10993,10 @@ err_register_fib_notifier: err_register_nexthop_notifier: unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); err_register_netevent_notifier: + unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb); +err_register_inet6addr_valid_notifier: + unregister_inetaddr_validator_notifier(&router->inetaddr_valid_nb); +err_register_inetaddr_valid_notifier: unregister_inet6addr_notifier(&router->inet6addr_nb); err_register_inet6addr_notifier: unregister_inetaddr_notifier(&router->inetaddr_nb); @@ -10643,10 +11019,12 @@ err_lpm_init: err_nexthop_group_ht_init: rhashtable_destroy(&mlxsw_sp->router->nexthop_ht); err_nexthop_ht_init: - mlxsw_sp_ipips_fini(mlxsw_sp); -err_ipips_init: mlxsw_sp_rifs_fini(mlxsw_sp); err_rifs_init: + rhashtable_destroy(&mlxsw_sp->router->crif_ht); +err_crif_ht_init: + mlxsw_sp_ipips_fini(mlxsw_sp); +err_ipips_init: __mlxsw_sp_router_fini(mlxsw_sp); err_router_init: cancel_delayed_work_sync(&mlxsw_sp->router->nh_grp_activity_dw); @@ -10658,15 +11036,18 @@ err_router_ops_init: void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) { + struct mlxsw_sp_router *router = mlxsw_sp->router; + unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), - &mlxsw_sp->router->netdevice_nb); - unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), - &mlxsw_sp->router->fib_nb); + &router->netdevice_nb); + unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), &router->fib_nb); unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp), - &mlxsw_sp->router->nexthop_nb); - unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); - unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb); - unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb); + &router->nexthop_nb); + unregister_netevent_notifier(&router->netevent_nb); + unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb); + unregister_inetaddr_validator_notifier(&router->inetaddr_valid_nb); + unregister_inet6addr_notifier(&router->inet6addr_nb); + unregister_inetaddr_notifier(&router->inetaddr_nb); mlxsw_core_flush_owq(); mlxsw_sp_mp_hash_fini(mlxsw_sp); mlxsw_sp_neigh_fini(mlxsw_sp); @@ -10674,12 +11055,13 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_sp_vrs_fini(mlxsw_sp); mlxsw_sp_mr_fini(mlxsw_sp); mlxsw_sp_lpm_fini(mlxsw_sp); - rhashtable_destroy(&mlxsw_sp->router->nexthop_group_ht); - rhashtable_destroy(&mlxsw_sp->router->nexthop_ht); - mlxsw_sp_ipips_fini(mlxsw_sp); + rhashtable_destroy(&router->nexthop_group_ht); + rhashtable_destroy(&router->nexthop_ht); mlxsw_sp_rifs_fini(mlxsw_sp); + rhashtable_destroy(&mlxsw_sp->router->crif_ht); + mlxsw_sp_ipips_fini(mlxsw_sp); __mlxsw_sp_router_fini(mlxsw_sp); - cancel_delayed_work_sync(&mlxsw_sp->router->nh_grp_activity_dw); - mutex_destroy(&mlxsw_sp->router->lock); - kfree(mlxsw_sp->router); + cancel_delayed_work_sync(&router->nh_grp_activity_dw); + mutex_destroy(&router->lock); + kfree(router); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index 37d6e4c80e6a..9a2669a08480 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -20,6 +20,7 @@ struct mlxsw_sp_router_nve_decap { struct mlxsw_sp_router { struct mlxsw_sp *mlxsw_sp; + struct rhashtable crif_ht; struct gen_pool *rifs_table; struct mlxsw_sp_rif **rifs; struct idr rif_mac_profiles_idr; @@ -52,12 +53,14 @@ struct mlxsw_sp_router { struct notifier_block inetaddr_nb; struct notifier_block inet6addr_nb; struct notifier_block netdevice_nb; + struct notifier_block inetaddr_valid_nb; + struct notifier_block inet6addr_valid_nb; const struct mlxsw_sp_rif_ops **rif_ops_arr; const struct mlxsw_sp_ipip_ops **ipip_ops_arr; struct mlxsw_sp_router_nve_decap nve_decap_config; struct mutex lock; /* Protects shared router resources */ struct mlxsw_sp_fib_entry_op_ctx *ll_op_ctx; - u16 lb_rif_index; + struct mlxsw_sp_crif *lb_crif; const struct mlxsw_sp_adj_grp_size_range *adj_grp_size_ranges; size_t adj_grp_size_ranges_count; struct delayed_work nh_grp_activity_dw; @@ -91,7 +94,9 @@ u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *rif); u16 mlxsw_sp_ipip_lb_ul_rif_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif); u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev); int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif); -const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif); +bool mlxsw_sp_rif_has_dev(const struct mlxsw_sp_rif *rif); +bool mlxsw_sp_rif_dev_is(const struct mlxsw_sp_rif *rif, + const struct net_device *dev); int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif, enum mlxsw_sp_rif_counter_dir dir, @@ -166,5 +171,8 @@ int mlxsw_sp_ipip_ecn_encap_init(struct mlxsw_sp *mlxsw_sp); int mlxsw_sp_ipip_ecn_decap_init(struct mlxsw_sp *mlxsw_sp); struct net_device * mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev); +int mlxsw_sp_router_port_join_lag(struct mlxsw_sp_port *mlxsw_sp_port, + struct net_device *lag_dev, + struct netlink_ext_ack *extack); #endif /* _MLXSW_ROUTER_H_*/ |