diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlxsw')
28 files changed, 4057 insertions, 765 deletions
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index 872e9910bb7c..a619d90559f7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -6,6 +6,7 @@ config MLXSW_CORE tristate "Mellanox Technologies Switch ASICs support" select NET_DEVLINK + select MLXFW help This driver supports Mellanox Technologies Switch ASICs family. @@ -82,7 +83,6 @@ config MLXSW_SPECTRUM select GENERIC_ALLOCATOR select PARMAN select OBJAGG - select MLXFW imply PTP_1588_CLOCK select NET_PTP_CLASSIFY if PTP_1588_CLOCK default m diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index 892724380ea2..f545fd2c5896 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -15,6 +15,7 @@ mlxsw_switchx2-objs := switchx2.o obj-$(CONFIG_MLXSW_SPECTRUM) += mlxsw_spectrum.o mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \ spectrum_switchdev.o spectrum_router.o \ + spectrum_router_xm.o \ spectrum1_kvdl.o spectrum2_kvdl.o \ spectrum_kvdl.o \ spectrum_acl_tcam.o spectrum_acl_ctcam.o \ diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h index 5ffdfb532cb7..392ce3cb27f7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h +++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h @@ -343,6 +343,23 @@ static inline int mlxsw_cmd_boardinfo(struct mlxsw_core *mlxsw_core, 0, 0, false, out_mbox, MLXSW_CMD_MBOX_SIZE); } +/* cmd_mbox_xm_num_local_ports + * Number of local_ports connected to the xm. + * Each local port is a 4x + * Spectrum-2/3: 25G + * Spectrum-4: 50G + */ +MLXSW_ITEM32(cmd_mbox, boardinfo, xm_num_local_ports, 0x00, 4, 3); + +/* cmd_mbox_xm_exists + * An XM (eXtanded Mezanine, e.g. used for the XLT) is connected on the board. + */ +MLXSW_ITEM32(cmd_mbox, boardinfo, xm_exists, 0x00, 0, 1); + +/* cmd_mbox_xm_local_port_entry + */ +MLXSW_ITEM_BIT_ARRAY(cmd_mbox, boardinfo, xm_local_port_entry, 0x04, 4, 8); + /* cmd_mbox_boardinfo_intapin * When PCIe interrupt messages are being used, this value is used for clearing * an interrupt. When using MSI-X, this register is not used. @@ -657,6 +674,12 @@ MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_double_size, 0x0C, 26, 1); */ MLXSW_ITEM32(cmd_mbox, config_profile, set_cqe_version, 0x08, 0, 1); +/* cmd_mbox_config_set_kvh_xlt_cache_mode + * Capability bit. Setting a bit to 1 configures the profile + * according to the mailbox contents. + */ +MLXSW_ITEM32(cmd_mbox, config_profile, set_kvh_xlt_cache_mode, 0x08, 3, 1); + /* cmd_mbox_config_profile_max_vepa_channels * Maximum number of VEPA channels per port (0 through 16) * 0 - multi-channel VEPA is disabled @@ -783,6 +806,13 @@ MLXSW_ITEM32(cmd_mbox, config_profile, adaptive_routing_group_cap, 0x4C, 0, 16); */ MLXSW_ITEM32(cmd_mbox, config_profile, arn, 0x50, 31, 1); +/* cmd_mbox_config_profile_kvh_xlt_cache_mode + * KVH XLT cache mode: + * 0 - XLT can use all KVH as best-effort + * 1 - XLT cache uses 1/2 KVH + */ +MLXSW_ITEM32(cmd_mbox, config_profile, kvh_xlt_cache_mode, 0x50, 8, 4); + /* cmd_mbox_config_kvd_linear_size * KVD Linear Size * Valid for Spectrum only diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 937b8e46f8c7..685037e052af 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -160,6 +160,7 @@ struct mlxsw_rx_listener_item { struct mlxsw_event_listener_item { struct list_head list; + struct mlxsw_core *mlxsw_core; struct mlxsw_event_listener el; void *priv; }; @@ -571,7 +572,8 @@ static void mlxsw_emad_trans_timeout_schedule(struct mlxsw_reg_trans *trans) if (trans->core->fw_flash_in_progress) timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS); - queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, timeout); + queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, + timeout << trans->retries); } static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core, @@ -1116,16 +1118,7 @@ static int mlxsw_core_fw_flash_update(struct mlxsw_core *mlxsw_core, struct devlink_flash_update_params *params, struct netlink_ext_ack *extack) { - const struct firmware *firmware; - int err; - - err = request_firmware_direct(&firmware, params->file_name, mlxsw_core->bus_info->dev); - if (err) - return err; - err = mlxsw_core_fw_flash(mlxsw_core, firmware, extack); - release_firmware(firmware); - - return err; + return mlxsw_core_fw_flash(mlxsw_core, params->fw, extack); } static int mlxsw_core_devlink_param_fw_load_policy_validate(struct devlink *devlink, u32 id, @@ -2179,11 +2172,16 @@ static void mlxsw_core_event_listener_func(struct sk_buff *skb, u8 local_port, void *priv) { struct mlxsw_event_listener_item *event_listener_item = priv; + struct mlxsw_core *mlxsw_core; struct mlxsw_reg_info reg; char *payload; char *reg_tlv; char *op_tlv; + mlxsw_core = event_listener_item->mlxsw_core; + trace_devlink_hwmsg(priv_to_devlink(mlxsw_core), true, 0, + skb->data, skb->len); + mlxsw_emad_tlv_parse(skb); op_tlv = mlxsw_emad_op_tlv(skb); reg_tlv = mlxsw_emad_reg_tlv(skb); @@ -2233,6 +2231,7 @@ int mlxsw_core_event_listener_register(struct mlxsw_core *mlxsw_core, el_item = kmalloc(sizeof(*el_item), GFP_KERNEL); if (!el_item) return -ENOMEM; + el_item->mlxsw_core = mlxsw_core; el_item->el = *el; el_item->priv = priv; @@ -2857,6 +2856,18 @@ mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_port_devlink_port_get); +bool mlxsw_core_port_is_xm(const struct mlxsw_core *mlxsw_core, u8 local_port) +{ + const struct mlxsw_bus_info *bus_info = mlxsw_core->bus_info; + int i; + + for (i = 0; i < bus_info->xm_local_ports_count; i++) + if (bus_info->xm_local_ports[i] == local_port) + return true; + return false; +} +EXPORT_SYMBOL(mlxsw_core_port_is_xm); + struct mlxsw_env *mlxsw_core_env(const struct mlxsw_core *mlxsw_core) { return mlxsw_core->env; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 92f7398287be..6b3ccbf6b238 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -223,6 +223,7 @@ enum devlink_port_type mlxsw_core_port_type_get(struct mlxsw_core *mlxsw_core, struct devlink_port * mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core, u8 local_port); +bool mlxsw_core_port_is_xm(const struct mlxsw_core *mlxsw_core, u8 local_port); struct mlxsw_env *mlxsw_core_env(const struct mlxsw_core *mlxsw_core); bool mlxsw_core_is_initialized(const struct mlxsw_core *mlxsw_core); int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module); @@ -255,7 +256,8 @@ struct mlxsw_config_profile { used_max_pkey:1, used_ar_sec:1, used_adaptive_routing_group_cap:1, - used_kvd_sizes:1; + used_kvd_sizes:1, + used_kvh_xlt_cache_mode:1; u8 max_vepa_channels; u16 max_mid; u16 max_pgt; @@ -277,6 +279,7 @@ struct mlxsw_config_profile { u32 kvd_linear_size; u8 kvd_hash_single_parts; u8 kvd_hash_double_parts; + u8 kvh_xlt_cache_mode; struct mlxsw_swid_config swid_config[MLXSW_CONFIG_PROFILE_SWID_COUNT]; }; @@ -435,6 +438,8 @@ struct mlxsw_fw_rev { u16 can_reset_minor; }; +#define MLXSW_BUS_INFO_XM_LOCAL_PORTS_MAX 4 + struct mlxsw_bus_info { const char *device_kind; const char *device_name; @@ -443,7 +448,10 @@ struct mlxsw_bus_info { u8 vsd[MLXSW_CMD_BOARDINFO_VSD_LEN]; u8 psid[MLXSW_CMD_BOARDINFO_PSID_LEN]; u8 low_frequency:1, - read_frc_capable:1; + read_frc_capable:1, + xm_exists:1; + u8 xm_local_ports_count; + u8 xm_local_ports[MLXSW_BUS_INFO_XM_LOCAL_PORTS_MAX]; }; struct mlxsw_hwmon; 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 9f6905fa6b47..f1b09c2f9eda 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c @@ -133,10 +133,8 @@ mlxsw_afk_key_info_find(struct mlxsw_afk *mlxsw_afk, } struct mlxsw_afk_picker { - struct { - DECLARE_BITMAP(element, MLXSW_AFK_ELEMENT_MAX); - unsigned int total; - } hits[0]; + DECLARE_BITMAP(element, MLXSW_AFK_ELEMENT_MAX); + unsigned int total; }; static void mlxsw_afk_picker_count_hits(struct mlxsw_afk *mlxsw_afk, @@ -154,8 +152,8 @@ static void mlxsw_afk_picker_count_hits(struct mlxsw_afk *mlxsw_afk, elinst = &block->instances[j]; if (elinst->element == element) { - __set_bit(element, picker->hits[i].element); - picker->hits[i].total++; + __set_bit(element, picker[i].element); + picker[i].total++; } } } @@ -169,13 +167,13 @@ static void mlxsw_afk_picker_subtract_hits(struct mlxsw_afk *mlxsw_afk, int i; int j; - memcpy(&hits_element, &picker->hits[block_index].element, + memcpy(&hits_element, &picker[block_index].element, sizeof(hits_element)); for (i = 0; i < mlxsw_afk->blocks_count; i++) { for_each_set_bit(j, hits_element, MLXSW_AFK_ELEMENT_MAX) { - if (__test_and_clear_bit(j, picker->hits[i].element)) - picker->hits[i].total--; + if (__test_and_clear_bit(j, picker[i].element)) + picker[i].total--; } } } @@ -188,8 +186,8 @@ static int mlxsw_afk_picker_most_hits_get(struct mlxsw_afk *mlxsw_afk, int i; for (i = 0; i < mlxsw_afk->blocks_count; i++) { - if (picker->hits[i].total > most_hits) { - most_hits = picker->hits[i].total; + if (picker[i].total > most_hits) { + most_hits = picker[i].total; most_index = i; } } @@ -206,7 +204,7 @@ static int mlxsw_afk_picker_key_info_add(struct mlxsw_afk *mlxsw_afk, if (key_info->blocks_count == mlxsw_afk->max_blocks) return -EINVAL; - for_each_set_bit(element, picker->hits[block_index].element, + for_each_set_bit(element, picker[block_index].element, MLXSW_AFK_ELEMENT_MAX) { key_info->element_to_block[element] = key_info->blocks_count; mlxsw_afk_element_usage_add(&key_info->elusage, element); @@ -224,11 +222,9 @@ static int mlxsw_afk_picker(struct mlxsw_afk *mlxsw_afk, { struct mlxsw_afk_picker *picker; enum mlxsw_afk_element element; - size_t alloc_size; int err; - alloc_size = sizeof(picker->hits[0]) * mlxsw_afk->blocks_count; - picker = kzalloc(alloc_size, GFP_KERNEL); + picker = kcalloc(mlxsw_afk->blocks_count, sizeof(*picker), GFP_KERNEL); if (!picker) return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.h b/drivers/net/ethernet/mellanox/mlxsw/core_env.h index 8e36a2634ef5..2b23f8a87862 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.h @@ -4,6 +4,9 @@ #ifndef _MLXSW_CORE_ENV_H #define _MLXSW_CORE_ENV_H +struct ethtool_modinfo; +struct ethtool_eeprom; + int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, int off, int *temp); diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index c010db2c9dba..b34c44723f8b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -291,7 +291,8 @@ static int mlxsw_m_ports_create(struct mlxsw_m *mlxsw_m) /* Create port objects for each valid entry */ for (i = 0; i < mlxsw_m->max_ports; i++) { - if (mlxsw_m->module_to_port[i] > 0) { + if (mlxsw_m->module_to_port[i] > 0 && + !mlxsw_core_port_is_xm(mlxsw_m->core, i)) { err = mlxsw_m_port_create(mlxsw_m, mlxsw_m->module_to_port[i], i); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 641cdd81882b..4eeae8d78006 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1196,6 +1196,12 @@ static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox, mlxsw_cmd_mbox_config_profile_kvd_hash_double_size_set(mbox, MLXSW_RES_GET(res, KVD_DOUBLE_SIZE)); } + if (profile->used_kvh_xlt_cache_mode) { + mlxsw_cmd_mbox_config_profile_set_kvh_xlt_cache_mode_set( + mbox, 1); + mlxsw_cmd_mbox_config_profile_kvh_xlt_cache_mode_set( + mbox, profile->kvh_xlt_cache_mode); + } for (i = 0; i < MLXSW_CONFIG_PROFILE_SWID_COUNT; i++) mlxsw_pci_config_profile_swid_config(mlxsw_pci, mbox, i, @@ -1209,6 +1215,30 @@ static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox, return mlxsw_cmd_config_profile_set(mlxsw_pci->core, mbox); } +static int mlxsw_pci_boardinfo_xm_process(struct mlxsw_pci *mlxsw_pci, + struct mlxsw_bus_info *bus_info, + char *mbox) +{ + int count = mlxsw_cmd_mbox_boardinfo_xm_num_local_ports_get(mbox); + int i; + + if (!mlxsw_cmd_mbox_boardinfo_xm_exists_get(mbox)) + return 0; + + bus_info->xm_exists = true; + + if (count > MLXSW_BUS_INFO_XM_LOCAL_PORTS_MAX) { + dev_err(&mlxsw_pci->pdev->dev, "Invalid number of XM local ports\n"); + return -EINVAL; + } + bus_info->xm_local_ports_count = count; + for (i = 0; i < count; i++) + bus_info->xm_local_ports[i] = + mlxsw_cmd_mbox_boardinfo_xm_local_port_entry_get(mbox, + i); + return 0; +} + static int mlxsw_pci_boardinfo(struct mlxsw_pci *mlxsw_pci, char *mbox) { struct mlxsw_bus_info *bus_info = &mlxsw_pci->bus_info; @@ -1220,7 +1250,8 @@ static int mlxsw_pci_boardinfo(struct mlxsw_pci *mlxsw_pci, char *mbox) return err; mlxsw_cmd_mbox_boardinfo_vsd_memcpy_from(mbox, bus_info->vsd); mlxsw_cmd_mbox_boardinfo_psid_memcpy_from(mbox, bus_info->psid); - return 0; + + return mlxsw_pci_boardinfo_xm_process(mlxsw_pci, bus_info, mbox); } static int mlxsw_pci_fw_area_init(struct mlxsw_pci *mlxsw_pci, char *mbox, diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 39eff6a57ba2..16e2df6ef2f4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -581,6 +581,13 @@ mlxsw_reg_sfd_uc_tunnel_pack(char *payload, int rec_index, mlxsw_reg_sfd_uc_tunnel_protocol_set(payload, rec_index, proto); } +enum mlxsw_reg_tunnel_port { + MLXSW_REG_TUNNEL_PORT_NVE, + MLXSW_REG_TUNNEL_PORT_VPLS, + MLXSW_REG_TUNNEL_PORT_FLEX_TUNNEL0, + MLXSW_REG_TUNNEL_PORT_FLEX_TUNNEL1, +}; + /* SFN - Switch FDB Notification Register * ------------------------------------------- * The switch provides notifications on newly learned FDB entries and @@ -738,13 +745,6 @@ MLXSW_ITEM32_INDEXED(reg, sfn, uc_tunnel_protocol, MLXSW_REG_SFN_BASE_LEN, 27, MLXSW_ITEM32_INDEXED(reg, sfn, uc_tunnel_uip_lsb, MLXSW_REG_SFN_BASE_LEN, 0, 24, MLXSW_REG_SFN_REC_LEN, 0x0C, false); -enum mlxsw_reg_sfn_tunnel_port { - MLXSW_REG_SFN_TUNNEL_PORT_NVE, - MLXSW_REG_SFN_TUNNEL_PORT_VPLS, - MLXSW_REG_SFN_TUNNEL_FLEX_TUNNEL0, - MLXSW_REG_SFN_TUNNEL_FLEX_TUNNEL1, -}; - /* reg_sfn_uc_tunnel_port * Tunnel port. * Reserved on Spectrum. @@ -821,8 +821,16 @@ static inline void mlxsw_reg_spms_vid_pack(char *payload, u16 vid, MLXSW_REG_DEFINE(spvid, MLXSW_REG_SPVID_ID, MLXSW_REG_SPVID_LEN); +/* reg_spvid_tport + * Port is tunnel port. + * Reserved when SwitchX/-2 or Spectrum-1. + * Access: Index + */ +MLXSW_ITEM32(reg, spvid, tport, 0x00, 24, 1); + /* reg_spvid_local_port - * Local port number. + * When tport = 0: Local port number. Not supported for CPU port. + * When tport = 1: Tunnel port. * Access: Index */ MLXSW_ITEM32(reg, spvid, local_port, 0x00, 16, 8); @@ -834,17 +842,30 @@ MLXSW_ITEM32(reg, spvid, local_port, 0x00, 16, 8); */ MLXSW_ITEM32(reg, spvid, sub_port, 0x00, 8, 8); +/* reg_spvid_et_vlan + * EtherType used for when VLAN is pushed at ingress (for untagged + * packets or for QinQ push mode). + * 0: ether_type0 - (default) + * 1: ether_type1 + * 2: ether_type2 - Reserved when Spectrum-1, supported by Spectrum-2 + * Ethertype IDs are configured by SVER. + * Access: RW + */ +MLXSW_ITEM32(reg, spvid, et_vlan, 0x04, 16, 2); + /* reg_spvid_pvid * Port default VID * Access: RW */ MLXSW_ITEM32(reg, spvid, pvid, 0x04, 0, 12); -static inline void mlxsw_reg_spvid_pack(char *payload, u8 local_port, u16 pvid) +static inline void mlxsw_reg_spvid_pack(char *payload, u8 local_port, u16 pvid, + u8 et_vlan) { MLXSW_REG_ZERO(spvid, payload); mlxsw_reg_spvid_local_port_set(payload, local_port); mlxsw_reg_spvid_pvid_set(payload, pvid); + mlxsw_reg_spvid_et_vlan_set(payload, et_vlan); } /* SPVM - Switch Port VLAN Membership @@ -1680,6 +1701,109 @@ static inline void mlxsw_reg_svfa_pack(char *payload, u8 local_port, mlxsw_reg_svfa_vid_set(payload, vid); } +/* SPVTR - Switch Port VLAN Stacking Register + * ------------------------------------------ + * The Switch Port VLAN Stacking register configures the VLAN mode of the port + * to enable VLAN stacking. + */ +#define MLXSW_REG_SPVTR_ID 0x201D +#define MLXSW_REG_SPVTR_LEN 0x10 + +MLXSW_REG_DEFINE(spvtr, MLXSW_REG_SPVTR_ID, MLXSW_REG_SPVTR_LEN); + +/* reg_spvtr_tport + * Port is tunnel port. + * Access: Index + * + * Note: Reserved when SwitchX/-2 or Spectrum-1. + */ +MLXSW_ITEM32(reg, spvtr, tport, 0x00, 24, 1); + +/* reg_spvtr_local_port + * When tport = 0: local port number (Not supported from/to CPU). + * When tport = 1: tunnel port. + * Access: Index + */ +MLXSW_ITEM32(reg, spvtr, local_port, 0x00, 16, 8); + +/* reg_spvtr_ippe + * Ingress Port Prio Mode Update Enable. + * When set, the Port Prio Mode is updated with the provided ipprio_mode field. + * Reserved on Get operations. + * Access: OP + */ +MLXSW_ITEM32(reg, spvtr, ippe, 0x04, 31, 1); + +/* reg_spvtr_ipve + * Ingress Port VID Mode Update Enable. + * When set, the Ingress Port VID Mode is updated with the provided ipvid_mode + * field. + * Reserved on Get operations. + * Access: OP + */ +MLXSW_ITEM32(reg, spvtr, ipve, 0x04, 30, 1); + +/* reg_spvtr_epve + * Egress Port VID Mode Update Enable. + * When set, the Egress Port VID Mode is updated with the provided epvid_mode + * field. + * Access: OP + */ +MLXSW_ITEM32(reg, spvtr, epve, 0x04, 29, 1); + +/* reg_spvtr_ipprio_mode + * Ingress Port Priority Mode. + * This controls the PCP and DEI of the new outer VLAN + * Note: for SwitchX/-2 the DEI is not affected. + * 0: use port default PCP and DEI (configured by QPDPC). + * 1: use C-VLAN PCP and DEI. + * Has no effect when ipvid_mode = 0. + * Reserved when tport = 1. + * Access: RW + */ +MLXSW_ITEM32(reg, spvtr, ipprio_mode, 0x04, 20, 4); + +enum mlxsw_reg_spvtr_ipvid_mode { + /* IEEE Compliant PVID (default) */ + MLXSW_REG_SPVTR_IPVID_MODE_IEEE_COMPLIANT_PVID, + /* Push VLAN (for VLAN stacking, except prio tagged packets) */ + MLXSW_REG_SPVTR_IPVID_MODE_PUSH_VLAN_FOR_UNTAGGED_PACKET, + /* Always push VLAN (also for prio tagged packets) */ + MLXSW_REG_SPVTR_IPVID_MODE_ALWAYS_PUSH_VLAN, +}; + +/* reg_spvtr_ipvid_mode + * Ingress Port VLAN-ID Mode. + * For Spectrum family, this affects the values of SPVM.i + * Access: RW + */ +MLXSW_ITEM32(reg, spvtr, ipvid_mode, 0x04, 16, 4); + +enum mlxsw_reg_spvtr_epvid_mode { + /* IEEE Compliant VLAN membership */ + MLXSW_REG_SPVTR_EPVID_MODE_IEEE_COMPLIANT_VLAN_MEMBERSHIP, + /* Pop VLAN (for VLAN stacking) */ + MLXSW_REG_SPVTR_EPVID_MODE_POP_VLAN, +}; + +/* reg_spvtr_epvid_mode + * Egress Port VLAN-ID Mode. + * For Spectrum family, this affects the values of SPVM.e,u,pt. + * Access: WO + */ +MLXSW_ITEM32(reg, spvtr, epvid_mode, 0x04, 0, 4); + +static inline void mlxsw_reg_spvtr_pack(char *payload, bool tport, + u8 local_port, + enum mlxsw_reg_spvtr_ipvid_mode ipvid_mode) +{ + MLXSW_REG_ZERO(spvtr, payload); + mlxsw_reg_spvtr_tport_set(payload, tport); + mlxsw_reg_spvtr_local_port_set(payload, local_port); + mlxsw_reg_spvtr_ipvid_mode_set(payload, ipvid_mode); + mlxsw_reg_spvtr_ipve_set(payload, true); +} + /* SVPE - Switch Virtual-Port Enabling Register * -------------------------------------------- * Enables port virtualization. @@ -1857,6 +1981,104 @@ static inline void mlxsw_reg_spvmlr_pack(char *payload, u8 local_port, } } +/* SPVC - Switch Port VLAN Classification Register + * ----------------------------------------------- + * Configures the port to identify packets as untagged / single tagged / + * double packets based on the packet EtherTypes. + * Ethertype IDs are configured by SVER. + */ +#define MLXSW_REG_SPVC_ID 0x2026 +#define MLXSW_REG_SPVC_LEN 0x0C + +MLXSW_REG_DEFINE(spvc, MLXSW_REG_SPVC_ID, MLXSW_REG_SPVC_LEN); + +/* reg_spvc_local_port + * Local port. + * Access: Index + * + * Note: applies both to Rx port and Tx port, so if a packet traverses + * through Rx port i and a Tx port j then port i and port j must have the + * same configuration. + */ +MLXSW_ITEM32(reg, spvc, local_port, 0x00, 16, 8); + +/* reg_spvc_inner_et2 + * Vlan Tag1 EtherType2 enable. + * Packet is initially classified as double VLAN Tag if in addition to + * being classified with a tag0 VLAN Tag its tag1 EtherType value is + * equal to ether_type2. + * 0: disable (default) + * 1: enable + * Access: RW + */ +MLXSW_ITEM32(reg, spvc, inner_et2, 0x08, 17, 1); + +/* reg_spvc_et2 + * Vlan Tag0 EtherType2 enable. + * Packet is initially classified as VLAN Tag if its tag0 EtherType is + * equal to ether_type2. + * 0: disable (default) + * 1: enable + * Access: RW + */ +MLXSW_ITEM32(reg, spvc, et2, 0x08, 16, 1); + +/* reg_spvc_inner_et1 + * Vlan Tag1 EtherType1 enable. + * Packet is initially classified as double VLAN Tag if in addition to + * being classified with a tag0 VLAN Tag its tag1 EtherType value is + * equal to ether_type1. + * 0: disable + * 1: enable (default) + * Access: RW + */ +MLXSW_ITEM32(reg, spvc, inner_et1, 0x08, 9, 1); + +/* reg_spvc_et1 + * Vlan Tag0 EtherType1 enable. + * Packet is initially classified as VLAN Tag if its tag0 EtherType is + * equal to ether_type1. + * 0: disable + * 1: enable (default) + * Access: RW + */ +MLXSW_ITEM32(reg, spvc, et1, 0x08, 8, 1); + +/* reg_inner_et0 + * Vlan Tag1 EtherType0 enable. + * Packet is initially classified as double VLAN Tag if in addition to + * being classified with a tag0 VLAN Tag its tag1 EtherType value is + * equal to ether_type0. + * 0: disable + * 1: enable (default) + * Access: RW + */ +MLXSW_ITEM32(reg, spvc, inner_et0, 0x08, 1, 1); + +/* reg_et0 + * Vlan Tag0 EtherType0 enable. + * Packet is initially classified as VLAN Tag if its tag0 EtherType is + * equal to ether_type0. + * 0: disable + * 1: enable (default) + * Access: RW + */ +MLXSW_ITEM32(reg, spvc, et0, 0x08, 0, 1); + +static inline void mlxsw_reg_spvc_pack(char *payload, u8 local_port, bool et1, + bool et0) +{ + MLXSW_REG_ZERO(spvc, payload); + mlxsw_reg_spvc_local_port_set(payload, local_port); + /* Enable inner_et1 and inner_et0 to enable identification of double + * tagged packets. + */ + mlxsw_reg_spvc_inner_et1_set(payload, 1); + mlxsw_reg_spvc_inner_et0_set(payload, 1); + mlxsw_reg_spvc_et1_set(payload, et1); + mlxsw_reg_spvc_et0_set(payload, et0); +} + /* CWTP - Congetion WRED ECN TClass Profile * ---------------------------------------- * Configures the profiles for queues of egress port and traffic class @@ -7279,10 +7501,11 @@ static inline void mlxsw_reg_ralue_pack4(char *payload, enum mlxsw_reg_ralxx_protocol protocol, enum mlxsw_reg_ralue_op op, u16 virtual_router, u8 prefix_len, - u32 dip) + u32 *dip) { mlxsw_reg_ralue_pack(payload, protocol, op, virtual_router, prefix_len); - mlxsw_reg_ralue_dip4_set(payload, dip); + if (dip) + mlxsw_reg_ralue_dip4_set(payload, *dip); } static inline void mlxsw_reg_ralue_pack6(char *payload, @@ -7292,7 +7515,8 @@ static inline void mlxsw_reg_ralue_pack6(char *payload, const void *dip) { mlxsw_reg_ralue_pack(payload, protocol, op, virtual_router, prefix_len); - mlxsw_reg_ralue_dip6_memcpy_to(payload, dip); + if (dip) + mlxsw_reg_ralue_dip6_memcpy_to(payload, dip); } static inline void @@ -8245,6 +8469,658 @@ mlxsw_reg_rmft2_ipv6_pack(char *payload, bool v, u16 offset, u16 virtual_router, mlxsw_reg_rmft2_sip6_mask_memcpy_to(payload, (void *)&sip6_mask); } +/* RXLTE - Router XLT Enable Register + * ---------------------------------- + * The RXLTE enables XLT (eXtended Lookup Table) LPM lookups if a capable + * XM is present on the system. + */ + +#define MLXSW_REG_RXLTE_ID 0x8050 +#define MLXSW_REG_RXLTE_LEN 0x0C + +MLXSW_REG_DEFINE(rxlte, MLXSW_REG_RXLTE_ID, MLXSW_REG_RXLTE_LEN); + +/* reg_rxlte_virtual_router + * Virtual router ID associated with the router interface. + * Range is 0..cap_max_virtual_routers-1 + * Access: Index + */ +MLXSW_ITEM32(reg, rxlte, virtual_router, 0x00, 0, 16); + +enum mlxsw_reg_rxlte_protocol { + MLXSW_REG_RXLTE_PROTOCOL_IPV4, + MLXSW_REG_RXLTE_PROTOCOL_IPV6, +}; + +/* reg_rxlte_protocol + * Access: Index + */ +MLXSW_ITEM32(reg, rxlte, protocol, 0x04, 0, 4); + +/* reg_rxlte_lpm_xlt_en + * Access: RW + */ +MLXSW_ITEM32(reg, rxlte, lpm_xlt_en, 0x08, 0, 1); + +static inline void mlxsw_reg_rxlte_pack(char *payload, u16 virtual_router, + enum mlxsw_reg_rxlte_protocol protocol, + bool lpm_xlt_en) +{ + MLXSW_REG_ZERO(rxlte, payload); + mlxsw_reg_rxlte_virtual_router_set(payload, virtual_router); + mlxsw_reg_rxlte_protocol_set(payload, protocol); + mlxsw_reg_rxlte_lpm_xlt_en_set(payload, lpm_xlt_en); +} + +/* RXLTM - Router XLT M select Register + * ------------------------------------ + * The RXLTM configures and selects the M for the XM lookups. + */ + +#define MLXSW_REG_RXLTM_ID 0x8051 +#define MLXSW_REG_RXLTM_LEN 0x14 + +MLXSW_REG_DEFINE(rxltm, MLXSW_REG_RXLTM_ID, MLXSW_REG_RXLTM_LEN); + +/* reg_rxltm_m0_val_v6 + * Global M0 value For IPv6. + * Range 0..128 + * Access: RW + */ +MLXSW_ITEM32(reg, rxltm, m0_val_v6, 0x10, 16, 8); + +/* reg_rxltm_m0_val_v4 + * Global M0 value For IPv4. + * Range 0..32 + * Access: RW + */ +MLXSW_ITEM32(reg, rxltm, m0_val_v4, 0x10, 0, 6); + +static inline void mlxsw_reg_rxltm_pack(char *payload, u8 m0_val_v4, u8 m0_val_v6) +{ + MLXSW_REG_ZERO(rxltm, payload); + mlxsw_reg_rxltm_m0_val_v6_set(payload, m0_val_v6); + mlxsw_reg_rxltm_m0_val_v4_set(payload, m0_val_v4); +} + +/* RLCMLD - Router LPM Cache ML Delete Register + * -------------------------------------------- + * The RLCMLD register is used to bulk delete the XLT-LPM cache ML entries. + * This can be used by SW when L is increased or decreased, thus need to + * remove entries with old ML values. + */ + +#define MLXSW_REG_RLCMLD_ID 0x8055 +#define MLXSW_REG_RLCMLD_LEN 0x30 + +MLXSW_REG_DEFINE(rlcmld, MLXSW_REG_RLCMLD_ID, MLXSW_REG_RLCMLD_LEN); + +enum mlxsw_reg_rlcmld_select { + MLXSW_REG_RLCMLD_SELECT_ML_ENTRIES, + MLXSW_REG_RLCMLD_SELECT_M_ENTRIES, + MLXSW_REG_RLCMLD_SELECT_M_AND_ML_ENTRIES, +}; + +/* reg_rlcmld_select + * Which entries to delete. + * Access: Index + */ +MLXSW_ITEM32(reg, rlcmld, select, 0x00, 16, 2); + +enum mlxsw_reg_rlcmld_filter_fields { + MLXSW_REG_RLCMLD_FILTER_FIELDS_BY_PROTOCOL = 0x04, + MLXSW_REG_RLCMLD_FILTER_FIELDS_BY_VIRTUAL_ROUTER = 0x08, + MLXSW_REG_RLCMLD_FILTER_FIELDS_BY_DIP = 0x10, +}; + +/* reg_rlcmld_filter_fields + * If a bit is '0' then the relevant field is ignored. + * Access: Index + */ +MLXSW_ITEM32(reg, rlcmld, filter_fields, 0x00, 0, 8); + +enum mlxsw_reg_rlcmld_protocol { + MLXSW_REG_RLCMLD_PROTOCOL_UC_IPV4, + MLXSW_REG_RLCMLD_PROTOCOL_UC_IPV6, +}; + +/* reg_rlcmld_protocol + * Access: Index + */ +MLXSW_ITEM32(reg, rlcmld, protocol, 0x08, 0, 4); + +/* reg_rlcmld_virtual_router + * Virtual router ID. + * Range is 0..cap_max_virtual_routers-1 + * Access: Index + */ +MLXSW_ITEM32(reg, rlcmld, virtual_router, 0x0C, 0, 16); + +/* reg_rlcmld_dip + * The prefix of the route or of the marker that the object of the LPM + * is compared with. The most significant bits of the dip are the prefix. + * Access: Index + */ +MLXSW_ITEM32(reg, rlcmld, dip4, 0x1C, 0, 32); +MLXSW_ITEM_BUF(reg, rlcmld, dip6, 0x10, 16); + +/* reg_rlcmld_dip_mask + * per bit: + * 0: no match + * 1: match + * Access: Index + */ +MLXSW_ITEM32(reg, rlcmld, dip_mask4, 0x2C, 0, 32); +MLXSW_ITEM_BUF(reg, rlcmld, dip_mask6, 0x20, 16); + +static inline void __mlxsw_reg_rlcmld_pack(char *payload, + enum mlxsw_reg_rlcmld_select select, + enum mlxsw_reg_rlcmld_protocol protocol, + u16 virtual_router) +{ + u8 filter_fields = MLXSW_REG_RLCMLD_FILTER_FIELDS_BY_PROTOCOL | + MLXSW_REG_RLCMLD_FILTER_FIELDS_BY_VIRTUAL_ROUTER | + MLXSW_REG_RLCMLD_FILTER_FIELDS_BY_DIP; + + MLXSW_REG_ZERO(rlcmld, payload); + mlxsw_reg_rlcmld_select_set(payload, select); + mlxsw_reg_rlcmld_filter_fields_set(payload, filter_fields); + mlxsw_reg_rlcmld_protocol_set(payload, protocol); + mlxsw_reg_rlcmld_virtual_router_set(payload, virtual_router); +} + +static inline void mlxsw_reg_rlcmld_pack4(char *payload, + enum mlxsw_reg_rlcmld_select select, + u16 virtual_router, + u32 dip, u32 dip_mask) +{ + __mlxsw_reg_rlcmld_pack(payload, select, + MLXSW_REG_RLCMLD_PROTOCOL_UC_IPV4, + virtual_router); + mlxsw_reg_rlcmld_dip4_set(payload, dip); + mlxsw_reg_rlcmld_dip_mask4_set(payload, dip_mask); +} + +static inline void mlxsw_reg_rlcmld_pack6(char *payload, + enum mlxsw_reg_rlcmld_select select, + u16 virtual_router, + const void *dip, const void *dip_mask) +{ + __mlxsw_reg_rlcmld_pack(payload, select, + MLXSW_REG_RLCMLD_PROTOCOL_UC_IPV6, + virtual_router); + mlxsw_reg_rlcmld_dip6_memcpy_to(payload, dip); + mlxsw_reg_rlcmld_dip_mask6_memcpy_to(payload, dip_mask); +} + +/* RLPMCE - Router LPM Cache Enable Register + * ----------------------------------------- + * Allows disabling the LPM cache. Can be changed on the fly. + */ + +#define MLXSW_REG_RLPMCE_ID 0x8056 +#define MLXSW_REG_RLPMCE_LEN 0x4 + +MLXSW_REG_DEFINE(rlpmce, MLXSW_REG_RLPMCE_ID, MLXSW_REG_RLPMCE_LEN); + +/* reg_rlpmce_flush + * Flush: + * 0: do not flush the cache (default) + * 1: flush (clear) the cache + * Access: WO + */ +MLXSW_ITEM32(reg, rlpmce, flush, 0x00, 4, 1); + +/* reg_rlpmce_disable + * LPM cache: + * 0: enabled (default) + * 1: disabled + * Access: RW + */ +MLXSW_ITEM32(reg, rlpmce, disable, 0x00, 0, 1); + +static inline void mlxsw_reg_rlpmce_pack(char *payload, bool flush, + bool disable) +{ + MLXSW_REG_ZERO(rlpmce, payload); + mlxsw_reg_rlpmce_flush_set(payload, flush); + mlxsw_reg_rlpmce_disable_set(payload, disable); +} + +/* Note that XLTQ, XMDR, XRMT and XRALXX register positions violate the rule + * of ordering register definitions by the ID. However, XRALXX pack helpers are + * using RALXX pack helpers, RALXX registers have higher IDs. + * Also XMDR is using RALUE enums. XLRQ and XRMT are just put alongside with the + * related registers. + */ + +/* XLTQ - XM Lookup Table Query Register + * ------------------------------------- + */ +#define MLXSW_REG_XLTQ_ID 0x7802 +#define MLXSW_REG_XLTQ_LEN 0x2C + +MLXSW_REG_DEFINE(xltq, MLXSW_REG_XLTQ_ID, MLXSW_REG_XLTQ_LEN); + +enum mlxsw_reg_xltq_xm_device_id { + MLXSW_REG_XLTQ_XM_DEVICE_ID_UNKNOWN, + MLXSW_REG_XLTQ_XM_DEVICE_ID_XLT = 0xCF71, +}; + +/* reg_xltq_xm_device_id + * XM device ID. + * Access: RO + */ +MLXSW_ITEM32(reg, xltq, xm_device_id, 0x04, 0, 16); + +/* reg_xltq_xlt_cap_ipv4_lpm + * Access: RO + */ +MLXSW_ITEM32(reg, xltq, xlt_cap_ipv4_lpm, 0x10, 0, 1); + +/* reg_xltq_xlt_cap_ipv6_lpm + * Access: RO + */ +MLXSW_ITEM32(reg, xltq, xlt_cap_ipv6_lpm, 0x10, 1, 1); + +/* reg_xltq_cap_xlt_entries + * Number of XLT entries + * Note: SW must not fill more than 80% in order to avoid overflow + * Access: RO + */ +MLXSW_ITEM32(reg, xltq, cap_xlt_entries, 0x20, 0, 32); + +/* reg_xltq_cap_xlt_mtable + * XLT M-Table max size + * Access: RO + */ +MLXSW_ITEM32(reg, xltq, cap_xlt_mtable, 0x24, 0, 32); + +static inline void mlxsw_reg_xltq_pack(char *payload) +{ + MLXSW_REG_ZERO(xltq, payload); +} + +static inline void mlxsw_reg_xltq_unpack(char *payload, u16 *xm_device_id, bool *xlt_cap_ipv4_lpm, + bool *xlt_cap_ipv6_lpm, u32 *cap_xlt_entries, + u32 *cap_xlt_mtable) +{ + *xm_device_id = mlxsw_reg_xltq_xm_device_id_get(payload); + *xlt_cap_ipv4_lpm = mlxsw_reg_xltq_xlt_cap_ipv4_lpm_get(payload); + *xlt_cap_ipv6_lpm = mlxsw_reg_xltq_xlt_cap_ipv6_lpm_get(payload); + *cap_xlt_entries = mlxsw_reg_xltq_cap_xlt_entries_get(payload); + *cap_xlt_mtable = mlxsw_reg_xltq_cap_xlt_mtable_get(payload); +} + +/* XMDR - XM Direct Register + * ------------------------- + * The XMDR allows direct access to the XM device via the switch. + * Working in synchronous mode. FW waits for response from the XLT + * for each command. FW acks the XMDR accordingly. + */ +#define MLXSW_REG_XMDR_ID 0x7803 +#define MLXSW_REG_XMDR_BASE_LEN 0x20 +#define MLXSW_REG_XMDR_TRANS_LEN 0x80 +#define MLXSW_REG_XMDR_LEN (MLXSW_REG_XMDR_BASE_LEN + \ + MLXSW_REG_XMDR_TRANS_LEN) + +MLXSW_REG_DEFINE(xmdr, MLXSW_REG_XMDR_ID, MLXSW_REG_XMDR_LEN); + +/* reg_xmdr_bulk_entry + * Bulk_entry + * 0: Last entry - immediate flush of XRT-cache + * 1: Bulk entry - do not flush the XRT-cache + * Access: OP + */ +MLXSW_ITEM32(reg, xmdr, bulk_entry, 0x04, 8, 1); + +/* reg_xmdr_num_rec + * Number of records for Direct access to XM + * Supported: 0..4 commands (except NOP which is a filler) + * 0 commands is reserved when bulk_entry = 1. + * 0 commands is allowed when bulk_entry = 0 for immediate XRT-cache flush. + * Access: OP + */ +MLXSW_ITEM32(reg, xmdr, num_rec, 0x04, 0, 4); + +/* reg_xmdr_reply_vect + * Reply Vector + * Bit i for command index i+1 + * values per bit: + * 0: failed + * 1: succeeded + * e.g. if commands 1, 2, 4 succeeded and command 3 failed then binary + * value will be 0b1011 + * Access: RO + */ +MLXSW_ITEM_BIT_ARRAY(reg, xmdr, reply_vect, 0x08, 4, 1); + +static inline void mlxsw_reg_xmdr_pack(char *payload, bool bulk_entry) +{ + MLXSW_REG_ZERO(xmdr, payload); + mlxsw_reg_xmdr_bulk_entry_set(payload, bulk_entry); +} + +enum mlxsw_reg_xmdr_c_cmd_id { + MLXSW_REG_XMDR_C_CMD_ID_LT_ROUTE_V4 = 0x30, + MLXSW_REG_XMDR_C_CMD_ID_LT_ROUTE_V6 = 0x31, +}; + +#define MLXSW_REG_XMDR_C_LT_ROUTE_V4_LEN 32 +#define MLXSW_REG_XMDR_C_LT_ROUTE_V6_LEN 48 + +/* reg_xmdr_c_cmd_id + */ +MLXSW_ITEM32(reg, xmdr_c, cmd_id, 0x00, 24, 8); + +/* reg_xmdr_c_seq_number + */ +MLXSW_ITEM32(reg, xmdr_c, seq_number, 0x00, 12, 12); + +enum mlxsw_reg_xmdr_c_ltr_op { + /* Activity is set */ + MLXSW_REG_XMDR_C_LTR_OP_WRITE = 0, + /* There is no update mask. All fields are updated. */ + MLXSW_REG_XMDR_C_LTR_OP_UPDATE = 1, + MLXSW_REG_XMDR_C_LTR_OP_DELETE = 2, +}; + +/* reg_xmdr_c_ltr_op + * Operation. + */ +MLXSW_ITEM32(reg, xmdr_c, ltr_op, 0x04, 24, 8); + +/* reg_xmdr_c_ltr_trap_action + * Trap action. + * Values are defined in enum mlxsw_reg_ralue_trap_action. + */ +MLXSW_ITEM32(reg, xmdr_c, ltr_trap_action, 0x04, 20, 4); + +enum mlxsw_reg_xmdr_c_ltr_trap_id_num { + MLXSW_REG_XMDR_C_LTR_TRAP_ID_NUM_RTR_INGRESS0, + MLXSW_REG_XMDR_C_LTR_TRAP_ID_NUM_RTR_INGRESS1, + MLXSW_REG_XMDR_C_LTR_TRAP_ID_NUM_RTR_INGRESS2, + MLXSW_REG_XMDR_C_LTR_TRAP_ID_NUM_RTR_INGRESS3, +}; + +/* reg_xmdr_c_ltr_trap_id_num + * Trap-ID number. + */ +MLXSW_ITEM32(reg, xmdr_c, ltr_trap_id_num, 0x04, 16, 4); + +/* reg_xmdr_c_ltr_virtual_router + * Virtual Router ID. + * Range is 0..cap_max_virtual_routers-1 + */ +MLXSW_ITEM32(reg, xmdr_c, ltr_virtual_router, 0x04, 0, 16); + +/* reg_xmdr_c_ltr_prefix_len + * Number of bits in the prefix of the LPM route. + */ +MLXSW_ITEM32(reg, xmdr_c, ltr_prefix_len, 0x08, 24, 8); + +/* reg_xmdr_c_ltr_bmp_len + * The best match prefix length in the case that there is no match for + * longer prefixes. + * If (entry_type != MARKER_ENTRY), bmp_len must be equal to prefix_len + */ +MLXSW_ITEM32(reg, xmdr_c, ltr_bmp_len, 0x08, 16, 8); + +/* reg_xmdr_c_ltr_entry_type + * Entry type. + * Values are defined in enum mlxsw_reg_ralue_entry_type. + */ +MLXSW_ITEM32(reg, xmdr_c, ltr_entry_type, 0x08, 4, 4); + +enum mlxsw_reg_xmdr_c_ltr_action_type { + MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_LOCAL, + MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_REMOTE, + MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_IP2ME, +}; + +/* reg_xmdr_c_ltr_action_type + * Action Type. + */ +MLXSW_ITEM32(reg, xmdr_c, ltr_action_type, 0x08, 0, 4); + +/* reg_xmdr_c_ltr_erif + * Egress Router Interface. + * Only relevant in case of LOCAL action. + */ +MLXSW_ITEM32(reg, xmdr_c, ltr_erif, 0x10, 0, 16); + +/* reg_xmdr_c_ltr_adjacency_index + * Points to the first entry of the group-based ECMP. + * Only relevant in case of REMOTE action. + */ +MLXSW_ITEM32(reg, xmdr_c, ltr_adjacency_index, 0x10, 0, 24); + +#define MLXSW_REG_XMDR_C_LTR_POINTER_TO_TUNNEL_DISABLED_MAGIC 0xFFFFFF + +/* reg_xmdr_c_ltr_pointer_to_tunnel + * Only relevant in case of IP2ME action. + */ +MLXSW_ITEM32(reg, xmdr_c, ltr_pointer_to_tunnel, 0x10, 0, 24); + +/* reg_xmdr_c_ltr_ecmp_size + * Amount of sequential entries starting + * from the adjacency_index (the number of ECMPs). + * The valid range is 1-64, 512, 1024, 2048 and 4096. + * Only relevant in case of REMOTE action. + */ +MLXSW_ITEM32(reg, xmdr_c, ltr_ecmp_size, 0x14, 0, 32); + +/* reg_xmdr_c_ltr_dip* + * The prefix of the route or of the marker that the object of the LPM + * is compared with. The most significant bits of the dip are the prefix. + * The least significant bits must be '0' if the prefix_len is smaller + * than 128 for IPv6 or smaller than 32 for IPv4. + */ +MLXSW_ITEM32(reg, xmdr_c, ltr_dip4, 0x1C, 0, 32); +MLXSW_ITEM_BUF(reg, xmdr_c, ltr_dip6, 0x1C, 16); + +static inline void +mlxsw_reg_xmdr_c_ltr_pack(char *xmdr_payload, unsigned int trans_offset, + enum mlxsw_reg_xmdr_c_cmd_id cmd_id, u16 seq_number, + enum mlxsw_reg_xmdr_c_ltr_op op, u16 virtual_router, + u8 prefix_len) +{ + char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; + u8 num_rec = mlxsw_reg_xmdr_num_rec_get(xmdr_payload); + + mlxsw_reg_xmdr_num_rec_set(xmdr_payload, num_rec + 1); + + mlxsw_reg_xmdr_c_cmd_id_set(payload, cmd_id); + mlxsw_reg_xmdr_c_seq_number_set(payload, seq_number); + mlxsw_reg_xmdr_c_ltr_op_set(payload, op); + mlxsw_reg_xmdr_c_ltr_virtual_router_set(payload, virtual_router); + mlxsw_reg_xmdr_c_ltr_prefix_len_set(payload, prefix_len); + mlxsw_reg_xmdr_c_ltr_entry_type_set(payload, + MLXSW_REG_RALUE_ENTRY_TYPE_ROUTE_ENTRY); + mlxsw_reg_xmdr_c_ltr_bmp_len_set(payload, prefix_len); +} + +static inline unsigned int +mlxsw_reg_xmdr_c_ltr_pack4(char *xmdr_payload, unsigned int trans_offset, + u16 seq_number, enum mlxsw_reg_xmdr_c_ltr_op op, + u16 virtual_router, u8 prefix_len, u32 *dip) +{ + char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; + + mlxsw_reg_xmdr_c_ltr_pack(xmdr_payload, trans_offset, + MLXSW_REG_XMDR_C_CMD_ID_LT_ROUTE_V4, + seq_number, op, virtual_router, prefix_len); + if (dip) + mlxsw_reg_xmdr_c_ltr_dip4_set(payload, *dip); + return MLXSW_REG_XMDR_C_LT_ROUTE_V4_LEN; +} + +static inline unsigned int +mlxsw_reg_xmdr_c_ltr_pack6(char *xmdr_payload, unsigned int trans_offset, + u16 seq_number, enum mlxsw_reg_xmdr_c_ltr_op op, + u16 virtual_router, u8 prefix_len, const void *dip) +{ + char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; + + mlxsw_reg_xmdr_c_ltr_pack(xmdr_payload, trans_offset, + MLXSW_REG_XMDR_C_CMD_ID_LT_ROUTE_V6, + seq_number, op, virtual_router, prefix_len); + if (dip) + mlxsw_reg_xmdr_c_ltr_dip6_memcpy_to(payload, dip); + return MLXSW_REG_XMDR_C_LT_ROUTE_V6_LEN; +} + +static inline void +mlxsw_reg_xmdr_c_ltr_act_remote_pack(char *xmdr_payload, unsigned int trans_offset, + enum mlxsw_reg_ralue_trap_action trap_action, + enum mlxsw_reg_xmdr_c_ltr_trap_id_num trap_id_num, + u32 adjacency_index, u16 ecmp_size) +{ + char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; + + mlxsw_reg_xmdr_c_ltr_action_type_set(payload, MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_REMOTE); + mlxsw_reg_xmdr_c_ltr_trap_action_set(payload, trap_action); + mlxsw_reg_xmdr_c_ltr_trap_id_num_set(payload, trap_id_num); + mlxsw_reg_xmdr_c_ltr_adjacency_index_set(payload, adjacency_index); + mlxsw_reg_xmdr_c_ltr_ecmp_size_set(payload, ecmp_size); +} + +static inline void +mlxsw_reg_xmdr_c_ltr_act_local_pack(char *xmdr_payload, unsigned int trans_offset, + enum mlxsw_reg_ralue_trap_action trap_action, + enum mlxsw_reg_xmdr_c_ltr_trap_id_num trap_id_num, u16 erif) +{ + char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; + + mlxsw_reg_xmdr_c_ltr_action_type_set(payload, MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_LOCAL); + mlxsw_reg_xmdr_c_ltr_trap_action_set(payload, trap_action); + mlxsw_reg_xmdr_c_ltr_trap_id_num_set(payload, trap_id_num); + mlxsw_reg_xmdr_c_ltr_erif_set(payload, erif); +} + +static inline void mlxsw_reg_xmdr_c_ltr_act_ip2me_pack(char *xmdr_payload, + unsigned int trans_offset) +{ + char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; + + mlxsw_reg_xmdr_c_ltr_action_type_set(payload, MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_IP2ME); + mlxsw_reg_xmdr_c_ltr_pointer_to_tunnel_set(payload, + MLXSW_REG_XMDR_C_LTR_POINTER_TO_TUNNEL_DISABLED_MAGIC); +} + +static inline void mlxsw_reg_xmdr_c_ltr_act_ip2me_tun_pack(char *xmdr_payload, + unsigned int trans_offset, + u32 pointer_to_tunnel) +{ + char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; + + mlxsw_reg_xmdr_c_ltr_action_type_set(payload, MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_IP2ME); + mlxsw_reg_xmdr_c_ltr_pointer_to_tunnel_set(payload, pointer_to_tunnel); +} + +/* XRMT - XM Router M Table Register + * --------------------------------- + * The XRMT configures the M-Table for the XLT-LPM. + */ +#define MLXSW_REG_XRMT_ID 0x7810 +#define MLXSW_REG_XRMT_LEN 0x14 + +MLXSW_REG_DEFINE(xrmt, MLXSW_REG_XRMT_ID, MLXSW_REG_XRMT_LEN); + +/* reg_xrmt_index + * Index in M-Table. + * Range 0..cap_xlt_mtable-1 + * Access: Index + */ +MLXSW_ITEM32(reg, xrmt, index, 0x04, 0, 20); + +/* reg_xrmt_l0_val + * Access: RW + */ +MLXSW_ITEM32(reg, xrmt, l0_val, 0x10, 24, 8); + +static inline void mlxsw_reg_xrmt_pack(char *payload, u32 index, u8 l0_val) +{ + MLXSW_REG_ZERO(xrmt, payload); + mlxsw_reg_xrmt_index_set(payload, index); + mlxsw_reg_xrmt_l0_val_set(payload, l0_val); +} + +/* XRALTA - XM Router Algorithmic LPM Tree Allocation Register + * ----------------------------------------------------------- + * The XRALTA is used to allocate the XLT LPM trees. + * + * This register embeds original RALTA register. + */ +#define MLXSW_REG_XRALTA_ID 0x7811 +#define MLXSW_REG_XRALTA_LEN 0x08 +#define MLXSW_REG_XRALTA_RALTA_OFFSET 0x04 + +MLXSW_REG_DEFINE(xralta, MLXSW_REG_XRALTA_ID, MLXSW_REG_XRALTA_LEN); + +static inline void mlxsw_reg_xralta_pack(char *payload, bool alloc, + enum mlxsw_reg_ralxx_protocol protocol, + u8 tree_id) +{ + char *ralta_payload = payload + MLXSW_REG_XRALTA_RALTA_OFFSET; + + MLXSW_REG_ZERO(xralta, payload); + mlxsw_reg_ralta_pack(ralta_payload, alloc, protocol, tree_id); +} + +/* XRALST - XM Router Algorithmic LPM Structure Tree Register + * ---------------------------------------------------------- + * The XRALST is used to set and query the structure of an XLT LPM tree. + * + * This register embeds original RALST register. + */ +#define MLXSW_REG_XRALST_ID 0x7812 +#define MLXSW_REG_XRALST_LEN 0x108 +#define MLXSW_REG_XRALST_RALST_OFFSET 0x04 + +MLXSW_REG_DEFINE(xralst, MLXSW_REG_XRALST_ID, MLXSW_REG_XRALST_LEN); + +static inline void mlxsw_reg_xralst_pack(char *payload, u8 root_bin, u8 tree_id) +{ + char *ralst_payload = payload + MLXSW_REG_XRALST_RALST_OFFSET; + + MLXSW_REG_ZERO(xralst, payload); + mlxsw_reg_ralst_pack(ralst_payload, root_bin, tree_id); +} + +static inline void mlxsw_reg_xralst_bin_pack(char *payload, u8 bin_number, + u8 left_child_bin, + u8 right_child_bin) +{ + char *ralst_payload = payload + MLXSW_REG_XRALST_RALST_OFFSET; + + mlxsw_reg_ralst_bin_pack(ralst_payload, bin_number, left_child_bin, + right_child_bin); +} + +/* XRALTB - XM Router Algorithmic LPM Tree Binding Register + * -------------------------------------------------------- + * The XRALTB register is used to bind virtual router and protocol + * to an allocated LPM tree. + * + * This register embeds original RALTB register. + */ +#define MLXSW_REG_XRALTB_ID 0x7813 +#define MLXSW_REG_XRALTB_LEN 0x08 +#define MLXSW_REG_XRALTB_RALTB_OFFSET 0x04 + +MLXSW_REG_DEFINE(xraltb, MLXSW_REG_XRALTB_ID, MLXSW_REG_XRALTB_LEN); + +static inline void mlxsw_reg_xraltb_pack(char *payload, u16 virtual_router, + enum mlxsw_reg_ralxx_protocol protocol, + u8 tree_id) +{ + char *raltb_payload = payload + MLXSW_REG_XRALTB_RALTB_OFFSET; + + MLXSW_REG_ZERO(xraltb, payload); + mlxsw_reg_raltb_pack(raltb_payload, virtual_router, protocol, tree_id); +} + /* MFCR - Management Fan Control Register * -------------------------------------- * This register controls the settings of the Fan Speed PWM mechanism. @@ -10314,13 +11190,6 @@ enum mlxsw_reg_tnumt_record_type { */ MLXSW_ITEM32(reg, tnumt, record_type, 0x00, 28, 4); -enum mlxsw_reg_tnumt_tunnel_port { - MLXSW_REG_TNUMT_TUNNEL_PORT_NVE, - MLXSW_REG_TNUMT_TUNNEL_PORT_VPLS, - MLXSW_REG_TNUMT_TUNNEL_FLEX_TUNNEL0, - MLXSW_REG_TNUMT_TUNNEL_FLEX_TUNNEL1, -}; - /* reg_tnumt_tunnel_port * Tunnel port. * Access: RW @@ -10368,7 +11237,7 @@ MLXSW_ITEM32_INDEXED(reg, tnumt, udip_ptr, 0x0C, 0, 24, 0x04, 0x00, false); static inline void mlxsw_reg_tnumt_pack(char *payload, enum mlxsw_reg_tnumt_record_type type, - enum mlxsw_reg_tnumt_tunnel_port tport, + enum mlxsw_reg_tunnel_port tport, u32 underlay_mc_ptr, bool vnext, u32 next_underlay_mc_ptr, u8 record_size) @@ -10532,13 +11401,6 @@ static inline void mlxsw_reg_tndem_pack(char *payload, u8 underlay_ecn, MLXSW_REG_DEFINE(tnpc, MLXSW_REG_TNPC_ID, MLXSW_REG_TNPC_LEN); -enum mlxsw_reg_tnpc_tunnel_port { - MLXSW_REG_TNPC_TUNNEL_PORT_NVE, - MLXSW_REG_TNPC_TUNNEL_PORT_VPLS, - MLXSW_REG_TNPC_TUNNEL_FLEX_TUNNEL0, - MLXSW_REG_TNPC_TUNNEL_FLEX_TUNNEL1, -}; - /* reg_tnpc_tunnel_port * Tunnel port. * Access: Index @@ -10558,7 +11420,7 @@ MLXSW_ITEM32(reg, tnpc, learn_enable_v6, 0x04, 1, 1); MLXSW_ITEM32(reg, tnpc, learn_enable_v4, 0x04, 0, 1); static inline void mlxsw_reg_tnpc_pack(char *payload, - enum mlxsw_reg_tnpc_tunnel_port tport, + enum mlxsw_reg_tunnel_port tport, bool learn_enable) { MLXSW_REG_ZERO(tnpc, payload); @@ -11127,9 +11989,11 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(slcor), MLXSW_REG(spmlr), MLXSW_REG(svfa), + MLXSW_REG(spvtr), MLXSW_REG(svpe), MLXSW_REG(sfmr), MLXSW_REG(spvmlr), + MLXSW_REG(spvc), MLXSW_REG(cwtp), MLXSW_REG(cwtpm), MLXSW_REG(pgcr), @@ -11195,6 +12059,16 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(rigr2), MLXSW_REG(recr2), MLXSW_REG(rmft2), + MLXSW_REG(rxlte), + MLXSW_REG(rxltm), + MLXSW_REG(rlcmld), + MLXSW_REG(rlpmce), + MLXSW_REG(xltq), + MLXSW_REG(xmdr), + MLXSW_REG(xrmt), + MLXSW_REG(xralta), + MLXSW_REG(xralst), + MLXSW_REG(xraltb), MLXSW_REG(mfcr), MLXSW_REG(mfsc), MLXSW_REG(mfsm), diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index b08853f71b2b..1650d9852b5b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -45,7 +45,7 @@ #define MLXSW_SP1_FWREV_MAJOR 13 #define MLXSW_SP1_FWREV_MINOR 2008 -#define MLXSW_SP1_FWREV_SUBMINOR 1310 +#define MLXSW_SP1_FWREV_SUBMINOR 2018 #define MLXSW_SP1_FWREV_CAN_RESET_MINOR 1702 static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = { @@ -62,7 +62,7 @@ static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = { #define MLXSW_SP2_FWREV_MAJOR 29 #define MLXSW_SP2_FWREV_MINOR 2008 -#define MLXSW_SP2_FWREV_SUBMINOR 1310 +#define MLXSW_SP2_FWREV_SUBMINOR 2018 static const struct mlxsw_fw_rev mlxsw_sp2_fw_rev = { .major = MLXSW_SP2_FWREV_MAJOR, @@ -77,7 +77,7 @@ static const struct mlxsw_fw_rev mlxsw_sp2_fw_rev = { #define MLXSW_SP3_FWREV_MAJOR 30 #define MLXSW_SP3_FWREV_MINOR 2008 -#define MLXSW_SP3_FWREV_SUBMINOR 1310 +#define MLXSW_SP3_FWREV_SUBMINOR 2018 static const struct mlxsw_fw_rev mlxsw_sp3_fw_rev = { .major = MLXSW_SP3_FWREV_MAJOR, @@ -384,13 +384,37 @@ int mlxsw_sp_port_vid_learning_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, return err; } +int mlxsw_sp_ethtype_to_sver_type(u16 ethtype, u8 *p_sver_type) +{ + switch (ethtype) { + case ETH_P_8021Q: + *p_sver_type = 0; + break; + case ETH_P_8021AD: + *p_sver_type = 1; + break; + default: + return -EINVAL; + } + + return 0; +} + static int __mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, - u16 vid) + u16 vid, u16 ethtype) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char spvid_pl[MLXSW_REG_SPVID_LEN]; + u8 sver_type; + int err; + + err = mlxsw_sp_ethtype_to_sver_type(ethtype, &sver_type); + if (err) + return err; + + mlxsw_reg_spvid_pack(spvid_pl, mlxsw_sp_port->local_port, vid, + sver_type); - mlxsw_reg_spvid_pack(spvid_pl, mlxsw_sp_port->local_port, vid); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvid), spvid_pl); } @@ -404,7 +428,8 @@ static int mlxsw_sp_port_allow_untagged_set(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spaft), spaft_pl); } -int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) +int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, + u16 ethtype) { int err; @@ -413,7 +438,7 @@ int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) if (err) return err; } else { - err = __mlxsw_sp_port_pvid_set(mlxsw_sp_port, vid); + err = __mlxsw_sp_port_pvid_set(mlxsw_sp_port, vid, ethtype); if (err) return err; err = mlxsw_sp_port_allow_untagged_set(mlxsw_sp_port, true); @@ -425,7 +450,7 @@ int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) return 0; err_port_allow_untagged_set: - __mlxsw_sp_port_pvid_set(mlxsw_sp_port, mlxsw_sp_port->pvid); + __mlxsw_sp_port_pvid_set(mlxsw_sp_port, mlxsw_sp_port->pvid, ethtype); return err; } @@ -1386,6 +1411,19 @@ static int mlxsw_sp_port_overheat_init_val_set(struct mlxsw_sp_port *mlxsw_sp_po return 0; } +int +mlxsw_sp_port_vlan_classification_set(struct mlxsw_sp_port *mlxsw_sp_port, + bool is_8021ad_tagged, + bool is_8021q_tagged) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char spvc_pl[MLXSW_REG_SPVC_LEN]; + + mlxsw_reg_spvc_pack(spvc_pl, mlxsw_sp_port->local_port, + is_8021ad_tagged, is_8021q_tagged); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvc), spvc_pl); +} + static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, u8 split_base_local_port, struct mlxsw_sp_port_mapping *port_mapping) @@ -1575,7 +1613,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, goto err_port_nve_init; } - err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID); + err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID, + ETH_P_8021Q); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set PVID\n", mlxsw_sp_port->local_port); @@ -1592,6 +1631,16 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, } mlxsw_sp_port->default_vlan = mlxsw_sp_port_vlan; + /* Set SPVC.et0=true and SPVC.et1=false to make the local port to treat + * only packets with 802.1q header as tagged packets. + */ + err = mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, false, true); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set default VLAN classification\n", + local_port); + goto err_port_vlan_classification_set; + } + INIT_DELAYED_WORK(&mlxsw_sp_port->ptp.shaper_dw, mlxsw_sp->ptp_ops->shaper_work); @@ -1618,6 +1667,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, err_register_netdev: err_port_overheat_init_val_set: + mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, true, true); +err_port_vlan_classification_set: mlxsw_sp->ports[local_port] = NULL; mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan); err_port_vlan_create: @@ -1664,6 +1715,7 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) mlxsw_sp_port_ptp_clear(mlxsw_sp_port); mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp); unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */ + mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, true, true); mlxsw_sp->ports[local_port] = NULL; mlxsw_sp_port_vlan_flush(mlxsw_sp_port, true); mlxsw_sp_port_nve_fini(mlxsw_sp_port); @@ -1788,6 +1840,9 @@ static int mlxsw_sp_port_module_info_init(struct mlxsw_sp *mlxsw_sp) return -ENOMEM; for (i = 1; i < max_ports; i++) { + if (mlxsw_core_port_is_xm(mlxsw_sp->core, i)) + continue; + err = mlxsw_sp_port_module_info_get(mlxsw_sp, i, &port_mapping); if (err) goto err_port_module_info_get; @@ -2881,6 +2936,8 @@ static const struct mlxsw_config_profile mlxsw_sp2_config_profile = { .max_ib_mc = 0, .used_max_pkey = 1, .max_pkey = 0, + .used_kvh_xlt_cache_mode = 1, + .kvh_xlt_cache_mode = 1, .swid_config = { { .used_type = 1, @@ -3543,7 +3600,8 @@ static int mlxsw_sp_port_lag_index_get(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, - struct net_device *lag_dev) + struct net_device *lag_dev, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_upper *lag; @@ -3579,8 +3637,20 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, if (mlxsw_sp_port->default_vlan->fid) 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); + if (err) + goto err_router_join; + return 0; +err_router_join: + lag->ref_count--; + mlxsw_sp_port->lagged = 0; + mlxsw_core_lag_mapping_clear(mlxsw_sp->core, lag_id, + mlxsw_sp_port->local_port); + mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id); err_col_port_add: if (!lag->ref_count) mlxsw_sp_lag_destroy(mlxsw_sp, lag_id); @@ -3618,7 +3688,8 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, lag->ref_count--; /* Make sure untagged frames are allowed to ingress */ - mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID); + mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID, + ETH_P_8021Q); } static int mlxsw_sp_lag_dist_port_add(struct mlxsw_sp_port *mlxsw_sp_port, @@ -3840,6 +3911,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, struct net_device *upper_dev; struct mlxsw_sp *mlxsw_sp; int err = 0; + u16 proto; mlxsw_sp_port = netdev_priv(dev); mlxsw_sp = mlxsw_sp_port->mlxsw_sp; @@ -3897,6 +3969,36 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on an OVS port"); return -EINVAL; } + if (netif_is_bridge_master(upper_dev)) { + br_vlan_get_proto(upper_dev, &proto); + if (br_vlan_enabled(upper_dev) && + proto != ETH_P_8021Q && proto != ETH_P_8021AD) { + NL_SET_ERR_MSG_MOD(extack, "Enslaving a port to a bridge with unknown VLAN protocol is not supported"); + return -EOPNOTSUPP; + } + if (vlan_uses_dev(lower_dev) && + br_vlan_enabled(upper_dev) && + proto == ETH_P_8021AD) { + NL_SET_ERR_MSG_MOD(extack, "Enslaving a port that already has a VLAN upper to an 802.1ad bridge is not supported"); + return -EOPNOTSUPP; + } + } + if (netif_is_bridge_port(lower_dev) && is_vlan_dev(upper_dev)) { + struct net_device *br_dev = netdev_master_upper_dev_get(lower_dev); + + if (br_vlan_enabled(br_dev)) { + br_vlan_get_proto(br_dev, &proto); + if (proto == ETH_P_8021AD) { + NL_SET_ERR_MSG_MOD(extack, "VLAN uppers are not supported on a port enslaved to an 802.1ad bridge"); + return -EOPNOTSUPP; + } + } + } + if (is_vlan_dev(upper_dev) && + ntohs(vlan_dev_vlan_proto(upper_dev)) != ETH_P_8021Q) { + NL_SET_ERR_MSG_MOD(extack, "VLAN uppers are only supported with 802.1q VLAN protocol"); + return -EOPNOTSUPP; + } break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; @@ -3913,7 +4015,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, } else if (netif_is_lag_master(upper_dev)) { if (info->linking) { err = mlxsw_sp_port_lag_join(mlxsw_sp_port, - upper_dev); + upper_dev, extack); } else { mlxsw_sp_port_lag_col_dist_disable(mlxsw_sp_port); mlxsw_sp_port_lag_leave(mlxsw_sp_port, @@ -4162,6 +4264,7 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev, struct netdev_notifier_changeupper_info *info = ptr; struct netlink_ext_ack *extack; struct net_device *upper_dev; + u16 proto; if (!mlxsw_sp) return 0; @@ -4177,6 +4280,18 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev, } if (!info->linking) break; + if (br_vlan_enabled(br_dev)) { + br_vlan_get_proto(br_dev, &proto); + if (proto == ETH_P_8021AD) { + NL_SET_ERR_MSG_MOD(extack, "Uppers are not supported on top of an 802.1ad bridge"); + return -EOPNOTSUPP; + } + } + if (is_vlan_dev(upper_dev) && + ntohs(vlan_dev_vlan_proto(upper_dev)) != ETH_P_8021Q) { + NL_SET_ERR_MSG_MOD(extack, "VLAN uppers are only supported with 802.1q VLAN protocol"); + return -EOPNOTSUPP; + } if (netif_is_macvlan(upper_dev) && !mlxsw_sp_rif_exists(mlxsw_sp, br_dev)) { NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces"); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 74b3959b36d4..a6956cfc9cb1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -4,6 +4,7 @@ #ifndef _MLXSW_SPECTRUM_H #define _MLXSW_SPECTRUM_H +#include <linux/ethtool.h> #include <linux/types.h> #include <linux/netdevice.h> #include <linux/rhashtable.h> @@ -427,6 +428,10 @@ int mlxsw_sp_port_get_stats_raw(struct net_device *dev, int grp, int prio, char *ppcnt_pl); int mlxsw_sp_port_admin_status_set(struct mlxsw_sp_port *mlxsw_sp_port, bool is_up); +int +mlxsw_sp_port_vlan_classification_set(struct mlxsw_sp_port *mlxsw_sp_port, + bool is_8021ad_tagged, + bool is_8021q_tagged); /* spectrum_buffers.c */ struct mlxsw_sp_hdroom_prio { @@ -579,7 +584,9 @@ int mlxsw_sp_port_vid_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, int mlxsw_sp_port_vp_mode_set(struct mlxsw_sp_port *mlxsw_sp_port, bool enable); int mlxsw_sp_port_vid_learning_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, bool learn_enable); -int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid); +int mlxsw_sp_ethtype_to_sver_type(u16 ethtype, u8 *p_sver_type); +int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, + u16 ethtype); struct mlxsw_sp_port_vlan * mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid); void mlxsw_sp_port_vlan_destroy(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan); @@ -650,6 +657,10 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, struct net_device *l3_dev, unsigned long event, struct netdev_notifier_info *info); +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, @@ -1192,6 +1203,7 @@ struct mlxsw_sp_nve_params { enum mlxsw_sp_nve_type type; __be32 vni; const struct net_device *dev; + u16 ethertype; }; extern const struct mlxsw_sp_nve_ops *mlxsw_sp1_nve_ops_arr[]; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index daf029931b5f..ed81d4fa48ac 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -913,7 +913,8 @@ static u64 mlxsw_sp_dpipe_table_adj_size(struct mlxsw_sp *mlxsw_sp) mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) if (mlxsw_sp_nexthop_offload(nh) && - !mlxsw_sp_nexthop_group_has_ipip(nh)) + !mlxsw_sp_nexthop_group_has_ipip(nh) && + !mlxsw_sp_nexthop_is_discard(nh)) size++; return size; } @@ -1105,7 +1106,8 @@ start_again: nh_count = 0; mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) { if (!mlxsw_sp_nexthop_offload(nh) || - mlxsw_sp_nexthop_group_has_ipip(nh)) + mlxsw_sp_nexthop_group_has_ipip(nh) || + mlxsw_sp_nexthop_is_discard(nh)) continue; if (nh_count < nh_skip) @@ -1186,7 +1188,8 @@ static int mlxsw_sp_dpipe_table_adj_counters_update(void *priv, bool enable) mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) { if (!mlxsw_sp_nexthop_offload(nh) || - mlxsw_sp_nexthop_group_has_ipip(nh)) + mlxsw_sp_nexthop_group_has_ipip(nh) || + mlxsw_sp_nexthop_is_discard(nh)) continue; mlxsw_sp_nexthop_indexes(nh, &adj_index, &adj_size, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index a8525992528f..6ccca39bae84 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -142,9 +142,9 @@ mlxsw_sp_ipip_nexthop_update_gre4(struct mlxsw_sp *mlxsw_sp, u32 adj_index, } static int -mlxsw_sp_ipip_fib_entry_op_gre4_rtdp(struct mlxsw_sp *mlxsw_sp, - u32 tunnel_index, - struct mlxsw_sp_ipip_entry *ipip_entry) +mlxsw_sp_ipip_decap_config_gre4(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + u32 tunnel_index) { u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb); u16 ul_rif_id = mlxsw_sp_ipip_lb_ul_rif_id(ipip_entry->ol_lb); @@ -180,41 +180,6 @@ mlxsw_sp_ipip_fib_entry_op_gre4_rtdp(struct mlxsw_sp *mlxsw_sp, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtdp), rtdp_pl); } -static int -mlxsw_sp_ipip_fib_entry_op_gre4_ralue(struct mlxsw_sp *mlxsw_sp, - u32 dip, u8 prefix_len, u16 ul_vr_id, - enum mlxsw_reg_ralue_op op, - u32 tunnel_index) -{ - char ralue_pl[MLXSW_REG_RALUE_LEN]; - - mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_REG_RALXX_PROTOCOL_IPV4, op, - ul_vr_id, prefix_len, dip); - mlxsw_reg_ralue_act_ip2me_tun_pack(ralue_pl, tunnel_index); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); -} - -static int mlxsw_sp_ipip_fib_entry_op_gre4(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_ipip_entry *ipip_entry, - enum mlxsw_reg_ralue_op op, - u32 tunnel_index) -{ - u16 ul_vr_id = mlxsw_sp_ipip_lb_ul_vr_id(ipip_entry->ol_lb); - __be32 dip; - int err; - - err = mlxsw_sp_ipip_fib_entry_op_gre4_rtdp(mlxsw_sp, tunnel_index, - ipip_entry); - if (err) - return err; - - dip = mlxsw_sp_ipip_netdev_saddr(MLXSW_SP_L3_PROTO_IPV4, - ipip_entry->ol_dev).addr4; - return mlxsw_sp_ipip_fib_entry_op_gre4_ralue(mlxsw_sp, be32_to_cpu(dip), - 32, ul_vr_id, op, - tunnel_index); -} - static bool mlxsw_sp_ipip_tunnel_complete(enum mlxsw_sp_l3proto proto, const struct net_device *ol_dev) { @@ -231,8 +196,7 @@ static bool mlxsw_sp_ipip_tunnel_complete(enum mlxsw_sp_l3proto proto, } static bool mlxsw_sp_ipip_can_offload_gre4(const struct mlxsw_sp *mlxsw_sp, - const struct net_device *ol_dev, - enum mlxsw_sp_l3proto ol_proto) + const struct net_device *ol_dev) { struct ip_tunnel *tunnel = netdev_priv(ol_dev); __be16 okflags = TUNNEL_KEY; /* We can't offload any other features. */ @@ -331,7 +295,7 @@ static const struct mlxsw_sp_ipip_ops mlxsw_sp_ipip_gre4_ops = { .dev_type = ARPHRD_IPGRE, .ul_proto = MLXSW_SP_L3_PROTO_IPV4, .nexthop_update = mlxsw_sp_ipip_nexthop_update_gre4, - .fib_entry_op = mlxsw_sp_ipip_fib_entry_op_gre4, + .decap_config = mlxsw_sp_ipip_decap_config_gre4, .can_offload = mlxsw_sp_ipip_can_offload_gre4, .ol_loopback_config = mlxsw_sp_ipip_ol_loopback_config_gre4, .ol_netdev_change = mlxsw_sp_ipip_ol_netdev_change_gre4, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h index bb5c4d4a5872..87bef9880e5e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h @@ -43,17 +43,15 @@ struct mlxsw_sp_ipip_ops { struct mlxsw_sp_ipip_entry *ipip_entry); bool (*can_offload)(const struct mlxsw_sp *mlxsw_sp, - const struct net_device *ol_dev, - enum mlxsw_sp_l3proto ol_proto); + const struct net_device *ol_dev); /* Return a configuration for creating an overlay loopback RIF. */ struct mlxsw_sp_rif_ipip_lb_config (*ol_loopback_config)(struct mlxsw_sp *mlxsw_sp, const struct net_device *ol_dev); - int (*fib_entry_op)(struct mlxsw_sp *mlxsw_sp, + int (*decap_config)(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry, - enum mlxsw_reg_ralue_op op, u32 tunnel_index); int (*ol_netdev_change)(struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c index 47eb751a2570..7846a21555ef 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -15,7 +15,7 @@ struct mlxsw_sp_mr { struct list_head table_list; struct mutex table_list_lock; /* Protects table_list */ #define MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL 5000 /* ms */ - unsigned long priv[0]; + unsigned long priv[]; /* priv has to be always the last item */ }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c index 54d3e7dcd303..e5ec595593f4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c @@ -368,7 +368,7 @@ mlxsw_sp_nve_mc_record_refresh(struct mlxsw_sp_nve_mc_record *mc_record) next_valid = true; } - mlxsw_reg_tnumt_pack(tnumt_pl, type, MLXSW_REG_TNUMT_TUNNEL_PORT_NVE, + mlxsw_reg_tnumt_pack(tnumt_pl, type, MLXSW_REG_TUNNEL_PORT_NVE, mc_record->kvdl_index, next_valid, next_kvdl_index, mc_record->num_entries); @@ -798,11 +798,11 @@ int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid, ops = nve->nve_ops_arr[params->type]; - if (!ops->can_offload(nve, params->dev, extack)) + if (!ops->can_offload(nve, params, extack)) return -EINVAL; memset(&config, 0, sizeof(config)); - ops->nve_config(nve, params->dev, &config); + ops->nve_config(nve, params, &config); if (nve->num_nve_tunnels && memcmp(&config, &nve->config, sizeof(config))) { NL_SET_ERR_MSG_MOD(extack, "Conflicting NVE tunnels configuration"); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h index 12f664f42f21..2796d3659979 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h @@ -18,6 +18,7 @@ struct mlxsw_sp_nve_config { u32 ul_tb_id; enum mlxsw_sp_l3proto ul_proto; union mlxsw_sp_l3addr ul_sip; + u16 ethertype; }; struct mlxsw_sp_nve { @@ -35,10 +36,10 @@ struct mlxsw_sp_nve { struct mlxsw_sp_nve_ops { enum mlxsw_sp_nve_type type; bool (*can_offload)(const struct mlxsw_sp_nve *nve, - const struct net_device *dev, + const struct mlxsw_sp_nve_params *params, struct netlink_ext_ack *extack); void (*nve_config)(const struct mlxsw_sp_nve *nve, - const struct net_device *dev, + const struct mlxsw_sp_nve_params *params, struct mlxsw_sp_nve_config *config); int (*init)(struct mlxsw_sp_nve *nve, const struct mlxsw_sp_nve_config *config); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c index 05517c7feaa5..3e2bb22e9ca6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c @@ -22,10 +22,10 @@ VXLAN_F_LEARN) static bool mlxsw_sp_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve, - const struct net_device *dev, + const struct mlxsw_sp_nve_params *params, struct netlink_ext_ack *extack) { - struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_dev *vxlan = netdev_priv(params->dev); struct vxlan_config *cfg = &vxlan->cfg; if (cfg->saddr.sa.sa_family != AF_INET) { @@ -86,11 +86,23 @@ static bool mlxsw_sp_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve, return true; } +static bool mlxsw_sp1_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve, + const struct mlxsw_sp_nve_params *params, + struct netlink_ext_ack *extack) +{ + if (params->ethertype == ETH_P_8021AD) { + NL_SET_ERR_MSG_MOD(extack, "VxLAN: 802.1ad bridge is not supported with VxLAN"); + return false; + } + + return mlxsw_sp_nve_vxlan_can_offload(nve, params, extack); +} + static void mlxsw_sp_nve_vxlan_config(const struct mlxsw_sp_nve *nve, - const struct net_device *dev, + const struct mlxsw_sp_nve_params *params, struct mlxsw_sp_nve_config *config) { - struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_dev *vxlan = netdev_priv(params->dev); struct vxlan_config *cfg = &vxlan->cfg; config->type = MLXSW_SP_NVE_TYPE_VXLAN; @@ -101,6 +113,7 @@ static void mlxsw_sp_nve_vxlan_config(const struct mlxsw_sp_nve *nve, config->ul_proto = MLXSW_SP_L3_PROTO_IPV4; config->ul_sip.addr4 = cfg->saddr.sin.sin_addr.s_addr; config->udp_dport = cfg->dst_port; + config->ethertype = params->ethertype; } static int __mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp, @@ -286,7 +299,7 @@ mlxsw_sp_nve_vxlan_clear_offload(const struct net_device *nve_dev, __be32 vni) const struct mlxsw_sp_nve_ops mlxsw_sp1_nve_vxlan_ops = { .type = MLXSW_SP_NVE_TYPE_VXLAN, - .can_offload = mlxsw_sp_nve_vxlan_can_offload, + .can_offload = mlxsw_sp1_nve_vxlan_can_offload, .nve_config = mlxsw_sp_nve_vxlan_config, .init = mlxsw_sp1_nve_vxlan_init, .fini = mlxsw_sp1_nve_vxlan_fini, @@ -299,16 +312,35 @@ static bool mlxsw_sp2_nve_vxlan_learning_set(struct mlxsw_sp *mlxsw_sp, { char tnpc_pl[MLXSW_REG_TNPC_LEN]; - mlxsw_reg_tnpc_pack(tnpc_pl, MLXSW_REG_TNPC_TUNNEL_PORT_NVE, + mlxsw_reg_tnpc_pack(tnpc_pl, MLXSW_REG_TUNNEL_PORT_NVE, learning_en); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tnpc), tnpc_pl); } static int +mlxsw_sp2_nve_decap_ethertype_set(struct mlxsw_sp *mlxsw_sp, u16 ethertype) +{ + char spvid_pl[MLXSW_REG_SPVID_LEN] = {}; + u8 sver_type; + int err; + + mlxsw_reg_spvid_tport_set(spvid_pl, true); + mlxsw_reg_spvid_local_port_set(spvid_pl, + MLXSW_REG_TUNNEL_PORT_NVE); + err = mlxsw_sp_ethtype_to_sver_type(ethertype, &sver_type); + if (err) + return err; + + mlxsw_reg_spvid_et_vlan_set(spvid_pl, sver_type); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvid), spvid_pl); +} + +static int mlxsw_sp2_nve_vxlan_config_set(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_nve_config *config) { char tngcr_pl[MLXSW_REG_TNGCR_LEN]; + char spvtr_pl[MLXSW_REG_SPVTR_LEN]; u16 ul_rif_index; int err; @@ -329,8 +361,25 @@ mlxsw_sp2_nve_vxlan_config_set(struct mlxsw_sp *mlxsw_sp, if (err) goto err_tngcr_write; + mlxsw_reg_spvtr_pack(spvtr_pl, true, MLXSW_REG_TUNNEL_PORT_NVE, + MLXSW_REG_SPVTR_IPVID_MODE_ALWAYS_PUSH_VLAN); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvtr), spvtr_pl); + if (err) + goto err_spvtr_write; + + err = mlxsw_sp2_nve_decap_ethertype_set(mlxsw_sp, config->ethertype); + if (err) + goto err_decap_ethertype_set; + return 0; +err_decap_ethertype_set: + mlxsw_reg_spvtr_pack(spvtr_pl, true, MLXSW_REG_TUNNEL_PORT_NVE, + MLXSW_REG_SPVTR_IPVID_MODE_IEEE_COMPLIANT_PVID); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvtr), spvtr_pl); +err_spvtr_write: + mlxsw_reg_tngcr_pack(tngcr_pl, MLXSW_REG_TNGCR_TYPE_VXLAN, false, 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tngcr), tngcr_pl); err_tngcr_write: mlxsw_sp2_nve_vxlan_learning_set(mlxsw_sp, false); err_vxlan_learning_set: @@ -340,8 +389,14 @@ err_vxlan_learning_set: static void mlxsw_sp2_nve_vxlan_config_clear(struct mlxsw_sp *mlxsw_sp) { + char spvtr_pl[MLXSW_REG_SPVTR_LEN]; char tngcr_pl[MLXSW_REG_TNGCR_LEN]; + /* Set default EtherType */ + mlxsw_sp2_nve_decap_ethertype_set(mlxsw_sp, ETH_P_8021Q); + mlxsw_reg_spvtr_pack(spvtr_pl, true, MLXSW_REG_TUNNEL_PORT_NVE, + MLXSW_REG_SPVTR_IPVID_MODE_IEEE_COMPLIANT_PVID); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvtr), spvtr_pl); mlxsw_reg_tngcr_pack(tngcr_pl, MLXSW_REG_TNGCR_TYPE_VXLAN, false, 0); mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tngcr), tngcr_pl); mlxsw_sp2_nve_vxlan_learning_set(mlxsw_sp, false); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index ca8090a28dec..d6e9ecb14681 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -828,10 +828,10 @@ struct mlxsw_sp_ptp_state *mlxsw_sp1_ptp_init(struct mlxsw_sp *mlxsw_sp) goto err_hashtable_init; /* Delive these message types as PTP0. */ - message_type = BIT(MLXSW_SP_PTP_MESSAGE_TYPE_SYNC) | - BIT(MLXSW_SP_PTP_MESSAGE_TYPE_DELAY_REQ) | - BIT(MLXSW_SP_PTP_MESSAGE_TYPE_PDELAY_REQ) | - BIT(MLXSW_SP_PTP_MESSAGE_TYPE_PDELAY_RESP); + message_type = BIT(PTP_MSGTYPE_SYNC) | + BIT(PTP_MSGTYPE_DELAY_REQ) | + BIT(PTP_MSGTYPE_PDELAY_REQ) | + BIT(PTP_MSGTYPE_PDELAY_RESP); err = mlxsw_sp_ptp_mtptpt_set(mlxsw_sp, MLXSW_REG_MTPTPT_TRAP_ID_PTP0, message_type); if (err) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h index 8c386571afce..1d43a3755285 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h @@ -11,13 +11,6 @@ struct mlxsw_sp; struct mlxsw_sp_port; struct mlxsw_sp_ptp_clock; -enum { - MLXSW_SP_PTP_MESSAGE_TYPE_SYNC, - MLXSW_SP_PTP_MESSAGE_TYPE_DELAY_REQ, - MLXSW_SP_PTP_MESSAGE_TYPE_PDELAY_REQ, - MLXSW_SP_PTP_MESSAGE_TYPE_PDELAY_RESP, -}; - static inline int mlxsw_sp_ptp_get_ts_info_noptp(struct ethtool_ts_info *info) { info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 4381f8c6c3fb..41424ee909a0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -352,6 +352,7 @@ enum mlxsw_sp_fib_entry_type { MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP, }; +struct mlxsw_sp_nexthop_group_info; struct mlxsw_sp_nexthop_group; struct mlxsw_sp_fib_entry; @@ -368,18 +369,71 @@ struct mlxsw_sp_fib_entry_decap { u32 tunnel_index; }; +static struct mlxsw_sp_fib_entry_priv * +mlxsw_sp_fib_entry_priv_create(const struct mlxsw_sp_router_ll_ops *ll_ops) +{ + struct mlxsw_sp_fib_entry_priv *priv; + + if (!ll_ops->fib_entry_priv_size) + /* No need to have priv */ + return NULL; + + priv = kzalloc(sizeof(*priv) + ll_ops->fib_entry_priv_size, GFP_KERNEL); + if (!priv) + return ERR_PTR(-ENOMEM); + refcount_set(&priv->refcnt, 1); + return priv; +} + +static void +mlxsw_sp_fib_entry_priv_destroy(struct mlxsw_sp_fib_entry_priv *priv) +{ + kfree(priv); +} + +static void mlxsw_sp_fib_entry_priv_hold(struct mlxsw_sp_fib_entry_priv *priv) +{ + refcount_inc(&priv->refcnt); +} + +static void mlxsw_sp_fib_entry_priv_put(struct mlxsw_sp_fib_entry_priv *priv) +{ + if (!priv || !refcount_dec_and_test(&priv->refcnt)) + return; + mlxsw_sp_fib_entry_priv_destroy(priv); +} + +static void mlxsw_sp_fib_entry_op_ctx_priv_hold(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + struct mlxsw_sp_fib_entry_priv *priv) +{ + if (!priv) + return; + mlxsw_sp_fib_entry_priv_hold(priv); + list_add(&priv->list, &op_ctx->fib_entry_priv_list); +} + +static void mlxsw_sp_fib_entry_op_ctx_priv_put_all(struct mlxsw_sp_fib_entry_op_ctx *op_ctx) +{ + struct mlxsw_sp_fib_entry_priv *priv, *tmp; + + list_for_each_entry_safe(priv, tmp, &op_ctx->fib_entry_priv_list, list) + mlxsw_sp_fib_entry_priv_put(priv); + INIT_LIST_HEAD(&op_ctx->fib_entry_priv_list); +} + struct mlxsw_sp_fib_entry { struct mlxsw_sp_fib_node *fib_node; enum mlxsw_sp_fib_entry_type type; struct list_head nexthop_group_node; struct mlxsw_sp_nexthop_group *nh_group; struct mlxsw_sp_fib_entry_decap decap; /* Valid for decap entries. */ + struct mlxsw_sp_fib_entry_priv *priv; }; struct mlxsw_sp_fib4_entry { struct mlxsw_sp_fib_entry common; + struct fib_info *fi; u32 tb_id; - u32 prio; u8 tos; u8 type; }; @@ -409,6 +463,7 @@ struct mlxsw_sp_fib { struct mlxsw_sp_vr *vr; struct mlxsw_sp_lpm_tree *lpm_tree; enum mlxsw_sp_l3proto proto; + const struct mlxsw_sp_router_ll_ops *ll_ops; }; struct mlxsw_sp_vr { @@ -422,16 +477,45 @@ struct mlxsw_sp_vr { refcount_t ul_rif_refcnt; }; +static int mlxsw_sp_router_ll_basic_init(struct mlxsw_sp *mlxsw_sp, u16 vr_id, + enum mlxsw_sp_l3proto proto) +{ + return 0; +} + +static int mlxsw_sp_router_ll_basic_ralta_write(struct mlxsw_sp *mlxsw_sp, char *xralta_pl) +{ + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), + xralta_pl + MLXSW_REG_XRALTA_RALTA_OFFSET); +} + +static int mlxsw_sp_router_ll_basic_ralst_write(struct mlxsw_sp *mlxsw_sp, char *xralst_pl) +{ + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), + xralst_pl + MLXSW_REG_XRALST_RALST_OFFSET); +} + +static int mlxsw_sp_router_ll_basic_raltb_write(struct mlxsw_sp *mlxsw_sp, char *xraltb_pl) +{ + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), + xraltb_pl + MLXSW_REG_XRALTB_RALTB_OFFSET); +} + static const struct rhashtable_params mlxsw_sp_fib_ht_params; static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, enum mlxsw_sp_l3proto proto) { + const struct mlxsw_sp_router_ll_ops *ll_ops = mlxsw_sp->router->proto_ll_ops[proto]; struct mlxsw_sp_lpm_tree *lpm_tree; struct mlxsw_sp_fib *fib; int err; + err = ll_ops->init(mlxsw_sp, vr->id, proto); + if (err) + return ERR_PTR(err); + lpm_tree = mlxsw_sp->router->lpm.proto_trees[proto]; fib = kzalloc(sizeof(*fib), GFP_KERNEL); if (!fib) @@ -443,6 +527,7 @@ static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp *mlxsw_sp, fib->proto = proto; fib->vr = vr; fib->lpm_tree = lpm_tree; + fib->ll_ops = ll_ops; mlxsw_sp_lpm_tree_hold(lpm_tree); err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib, lpm_tree->id); if (err) @@ -481,33 +566,36 @@ mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp) } static int mlxsw_sp_lpm_tree_alloc(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_lpm_tree *lpm_tree) { - char ralta_pl[MLXSW_REG_RALTA_LEN]; + char xralta_pl[MLXSW_REG_XRALTA_LEN]; - mlxsw_reg_ralta_pack(ralta_pl, true, - (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto, - lpm_tree->id); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); + mlxsw_reg_xralta_pack(xralta_pl, true, + (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto, + lpm_tree->id); + return ll_ops->ralta_write(mlxsw_sp, xralta_pl); } static void mlxsw_sp_lpm_tree_free(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_lpm_tree *lpm_tree) { - char ralta_pl[MLXSW_REG_RALTA_LEN]; + char xralta_pl[MLXSW_REG_XRALTA_LEN]; - mlxsw_reg_ralta_pack(ralta_pl, false, - (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto, - lpm_tree->id); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); + mlxsw_reg_xralta_pack(xralta_pl, false, + (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto, + lpm_tree->id); + ll_ops->ralta_write(mlxsw_sp, xralta_pl); } static int mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_prefix_usage *prefix_usage, struct mlxsw_sp_lpm_tree *lpm_tree) { - char ralst_pl[MLXSW_REG_RALST_LEN]; + char xralst_pl[MLXSW_REG_XRALST_LEN]; u8 root_bin = 0; u8 prefix; u8 last_prefix = MLXSW_REG_RALST_BIN_NO_CHILD; @@ -515,19 +603,20 @@ mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) root_bin = prefix; - mlxsw_reg_ralst_pack(ralst_pl, root_bin, lpm_tree->id); + mlxsw_reg_xralst_pack(xralst_pl, root_bin, lpm_tree->id); mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) { if (prefix == 0) continue; - mlxsw_reg_ralst_bin_pack(ralst_pl, prefix, last_prefix, - MLXSW_REG_RALST_BIN_NO_CHILD); + mlxsw_reg_xralst_bin_pack(xralst_pl, prefix, last_prefix, + MLXSW_REG_RALST_BIN_NO_CHILD); last_prefix = prefix; } - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), ralst_pl); + return ll_ops->ralst_write(mlxsw_sp, xralst_pl); } static struct mlxsw_sp_lpm_tree * mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_prefix_usage *prefix_usage, enum mlxsw_sp_l3proto proto) { @@ -538,12 +627,11 @@ mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, if (!lpm_tree) return ERR_PTR(-EBUSY); lpm_tree->proto = proto; - err = mlxsw_sp_lpm_tree_alloc(mlxsw_sp, lpm_tree); + err = mlxsw_sp_lpm_tree_alloc(mlxsw_sp, ll_ops, lpm_tree); if (err) return ERR_PTR(err); - err = mlxsw_sp_lpm_tree_left_struct_set(mlxsw_sp, prefix_usage, - lpm_tree); + err = mlxsw_sp_lpm_tree_left_struct_set(mlxsw_sp, ll_ops, prefix_usage, lpm_tree); if (err) goto err_left_struct_set; memcpy(&lpm_tree->prefix_usage, prefix_usage, @@ -554,14 +642,15 @@ mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, return lpm_tree; err_left_struct_set: - mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree); + mlxsw_sp_lpm_tree_free(mlxsw_sp, ll_ops, lpm_tree); return ERR_PTR(err); } static void mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_lpm_tree *lpm_tree) { - mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree); + mlxsw_sp_lpm_tree_free(mlxsw_sp, ll_ops, lpm_tree); } static struct mlxsw_sp_lpm_tree * @@ -569,6 +658,7 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_prefix_usage *prefix_usage, enum mlxsw_sp_l3proto proto) { + const struct mlxsw_sp_router_ll_ops *ll_ops = mlxsw_sp->router->proto_ll_ops[proto]; struct mlxsw_sp_lpm_tree *lpm_tree; int i; @@ -582,7 +672,7 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, return lpm_tree; } } - return mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage, proto); + return mlxsw_sp_lpm_tree_create(mlxsw_sp, ll_ops, prefix_usage, proto); } static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree) @@ -593,8 +683,11 @@ static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree) static void mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_lpm_tree *lpm_tree) { + const struct mlxsw_sp_router_ll_ops *ll_ops = + mlxsw_sp->router->proto_ll_ops[lpm_tree->proto]; + if (--lpm_tree->ref_count == 0) - mlxsw_sp_lpm_tree_destroy(mlxsw_sp, lpm_tree); + mlxsw_sp_lpm_tree_destroy(mlxsw_sp, ll_ops, lpm_tree); } #define MLXSW_SP_LPM_TREE_MIN 1 /* tree 0 is reserved */ @@ -684,23 +777,23 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_fib *fib, u8 tree_id) { - char raltb_pl[MLXSW_REG_RALTB_LEN]; + char xraltb_pl[MLXSW_REG_XRALTB_LEN]; - mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id, - (enum mlxsw_reg_ralxx_protocol) fib->proto, - tree_id); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); + mlxsw_reg_xraltb_pack(xraltb_pl, fib->vr->id, + (enum mlxsw_reg_ralxx_protocol) fib->proto, + tree_id); + return fib->ll_ops->raltb_write(mlxsw_sp, xraltb_pl); } static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_fib *fib) { - char raltb_pl[MLXSW_REG_RALTB_LEN]; + char xraltb_pl[MLXSW_REG_XRALTB_LEN]; /* Bind to tree 0 which is default */ - mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id, - (enum mlxsw_reg_ralxx_protocol) fib->proto, 0); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); + mlxsw_reg_xraltb_pack(xraltb_pl, fib->vr->id, + (enum mlxsw_reg_ralxx_protocol) fib->proto, 0); + return fib->ll_ops->raltb_write(mlxsw_sp, xraltb_pl); } static u32 mlxsw_sp_fix_tb_id(u32 tb_id) @@ -1270,21 +1363,33 @@ mlxsw_sp_ipip_entry_matches_decap(struct mlxsw_sp *mlxsw_sp, /* Given decap parameters, find the corresponding IPIP entry. */ static struct mlxsw_sp_ipip_entry * -mlxsw_sp_ipip_entry_find_by_decap(struct mlxsw_sp *mlxsw_sp, - const struct net_device *ul_dev, +mlxsw_sp_ipip_entry_find_by_decap(struct mlxsw_sp *mlxsw_sp, int ul_dev_ifindex, enum mlxsw_sp_l3proto ul_proto, union mlxsw_sp_l3addr ul_dip) { - struct mlxsw_sp_ipip_entry *ipip_entry; + struct mlxsw_sp_ipip_entry *ipip_entry = NULL; + struct net_device *ul_dev; + + rcu_read_lock(); + + ul_dev = dev_get_by_index_rcu(mlxsw_sp_net(mlxsw_sp), ul_dev_ifindex); + if (!ul_dev) + goto out_unlock; list_for_each_entry(ipip_entry, &mlxsw_sp->router->ipip_list, ipip_list_node) if (mlxsw_sp_ipip_entry_matches_decap(mlxsw_sp, ul_dev, ul_proto, ul_dip, ipip_entry)) - return ipip_entry; + goto out_unlock; + + rcu_read_unlock(); return NULL; + +out_unlock: + rcu_read_unlock(); + return ipip_entry; } static bool mlxsw_sp_netdev_ipip_type(const struct mlxsw_sp *mlxsw_sp, @@ -1370,11 +1475,7 @@ static bool mlxsw_sp_netdevice_ipip_can_offload(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_ipip_ops *ops = mlxsw_sp->router->ipip_ops_arr[ipipt]; - /* For deciding whether decap should be offloaded, we don't care about - * overlay protocol, so ask whether either one is supported. - */ - return ops->can_offload(mlxsw_sp, ol_dev, MLXSW_SP_L3_PROTO_IPV4) || - ops->can_offload(mlxsw_sp, ol_dev, MLXSW_SP_L3_PROTO_IPV6); + return ops->can_offload(mlxsw_sp, ol_dev); } static int mlxsw_sp_netdevice_ipip_ol_reg_event(struct mlxsw_sp *mlxsw_sp, @@ -2749,10 +2850,11 @@ struct mlxsw_sp_nexthop { struct list_head neigh_list_node; /* member of neigh entry list */ struct list_head rif_list_node; struct list_head router_list_node; - struct mlxsw_sp_nexthop_group *nh_grp; /* pointer back to the group - * this belongs to - */ + struct mlxsw_sp_nexthop_group_info *nhgi; /* pointer back to the group + * this nexthop belongs to + */ struct rhash_head ht_node; + struct neigh_table *neigh_tbl; struct mlxsw_sp_nexthop_key key; unsigned char gw_addr[sizeof(struct in6_addr)]; int ifindex; @@ -2766,9 +2868,10 @@ struct mlxsw_sp_nexthop { offloaded:1, /* set in case the neigh is actually put into * KVD linear area of this group. */ - update:1; /* set indicates that MAC of this neigh should be + update:1, /* set indicates that MAC of this neigh should be * updated in HW */ + discard:1; /* nexthop is programmed to discard packets */ enum mlxsw_sp_nexthop_type type; union { struct mlxsw_sp_neigh_entry *neigh_entry; @@ -2778,21 +2881,54 @@ struct mlxsw_sp_nexthop { bool counter_valid; }; -struct mlxsw_sp_nexthop_group { - void *priv; - struct rhash_head ht_node; - struct list_head fib_list; /* list of fib entries that use this group */ - struct neigh_table *neigh_tbl; - u8 adj_index_valid:1, - gateway:1; /* routes using the group use a gateway */ +enum mlxsw_sp_nexthop_group_type { + MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4, + MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6, + MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ, +}; + +struct mlxsw_sp_nexthop_group_info { + struct mlxsw_sp_nexthop_group *nh_grp; u32 adj_index; u16 ecmp_size; u16 count; int sum_norm_weight; + u8 adj_index_valid:1, + gateway:1; /* routes using the group use a gateway */ struct mlxsw_sp_nexthop nexthops[0]; #define nh_rif nexthops[0].rif }; +struct mlxsw_sp_nexthop_group_vr_key { + u16 vr_id; + enum mlxsw_sp_l3proto proto; +}; + +struct mlxsw_sp_nexthop_group_vr_entry { + struct list_head list; /* member in vr_list */ + struct rhash_head ht_node; /* member in vr_ht */ + refcount_t ref_count; + struct mlxsw_sp_nexthop_group_vr_key key; +}; + +struct mlxsw_sp_nexthop_group { + struct rhash_head ht_node; + struct list_head fib_list; /* list of fib entries that use this group */ + union { + struct { + struct fib_info *fi; + } ipv4; + struct { + u32 id; + } obj; + }; + struct mlxsw_sp_nexthop_group_info *nhgi; + struct list_head vr_list; + struct rhashtable vr_ht; + enum mlxsw_sp_nexthop_group_type type; + bool can_destroy; +}; + void mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh) { @@ -2858,18 +2994,18 @@ unsigned char *mlxsw_sp_nexthop_ha(struct mlxsw_sp_nexthop *nh) int mlxsw_sp_nexthop_indexes(struct mlxsw_sp_nexthop *nh, u32 *p_adj_index, u32 *p_adj_size, u32 *p_adj_hash_index) { - struct mlxsw_sp_nexthop_group *nh_grp = nh->nh_grp; + struct mlxsw_sp_nexthop_group_info *nhgi = nh->nhgi; u32 adj_hash_index = 0; int i; - if (!nh->offloaded || !nh_grp->adj_index_valid) + if (!nh->offloaded || !nhgi->adj_index_valid) return -EINVAL; - *p_adj_index = nh_grp->adj_index; - *p_adj_size = nh_grp->ecmp_size; + *p_adj_index = nhgi->adj_index; + *p_adj_size = nhgi->ecmp_size; - for (i = 0; i < nh_grp->count; i++) { - struct mlxsw_sp_nexthop *nh_iter = &nh_grp->nexthops[i]; + for (i = 0; i < nhgi->count; i++) { + struct mlxsw_sp_nexthop *nh_iter = &nhgi->nexthops[i]; if (nh_iter == nh) break; @@ -2888,11 +3024,11 @@ struct mlxsw_sp_rif *mlxsw_sp_nexthop_rif(struct mlxsw_sp_nexthop *nh) bool mlxsw_sp_nexthop_group_has_ipip(struct mlxsw_sp_nexthop *nh) { - struct mlxsw_sp_nexthop_group *nh_grp = nh->nh_grp; + struct mlxsw_sp_nexthop_group_info *nhgi = nh->nhgi; int i; - for (i = 0; i < nh_grp->count; i++) { - struct mlxsw_sp_nexthop *nh_iter = &nh_grp->nexthops[i]; + for (i = 0; i < nhgi->count; i++) { + struct mlxsw_sp_nexthop *nh_iter = &nhgi->nexthops[i]; if (nh_iter->type == MLXSW_SP_NEXTHOP_TYPE_IPIP) return true; @@ -2900,17 +3036,107 @@ bool mlxsw_sp_nexthop_group_has_ipip(struct mlxsw_sp_nexthop *nh) return false; } -static struct fib_info * -mlxsw_sp_nexthop4_group_fi(const struct mlxsw_sp_nexthop_group *nh_grp) +bool mlxsw_sp_nexthop_is_discard(const struct mlxsw_sp_nexthop *nh) +{ + return nh->discard; +} + +static const struct rhashtable_params mlxsw_sp_nexthop_group_vr_ht_params = { + .key_offset = offsetof(struct mlxsw_sp_nexthop_group_vr_entry, key), + .head_offset = offsetof(struct mlxsw_sp_nexthop_group_vr_entry, ht_node), + .key_len = sizeof(struct mlxsw_sp_nexthop_group_vr_key), + .automatic_shrinking = true, +}; + +static struct mlxsw_sp_nexthop_group_vr_entry * +mlxsw_sp_nexthop_group_vr_entry_lookup(struct mlxsw_sp_nexthop_group *nh_grp, + const struct mlxsw_sp_fib *fib) +{ + struct mlxsw_sp_nexthop_group_vr_key key; + + memset(&key, 0, sizeof(key)); + key.vr_id = fib->vr->id; + key.proto = fib->proto; + return rhashtable_lookup_fast(&nh_grp->vr_ht, &key, + mlxsw_sp_nexthop_group_vr_ht_params); +} + +static int +mlxsw_sp_nexthop_group_vr_entry_create(struct mlxsw_sp_nexthop_group *nh_grp, + const struct mlxsw_sp_fib *fib) +{ + struct mlxsw_sp_nexthop_group_vr_entry *vr_entry; + int err; + + vr_entry = kzalloc(sizeof(*vr_entry), GFP_KERNEL); + if (!vr_entry) + return -ENOMEM; + + vr_entry->key.vr_id = fib->vr->id; + vr_entry->key.proto = fib->proto; + refcount_set(&vr_entry->ref_count, 1); + + err = rhashtable_insert_fast(&nh_grp->vr_ht, &vr_entry->ht_node, + mlxsw_sp_nexthop_group_vr_ht_params); + if (err) + goto err_hashtable_insert; + + list_add(&vr_entry->list, &nh_grp->vr_list); + + return 0; + +err_hashtable_insert: + kfree(vr_entry); + return err; +} + +static void +mlxsw_sp_nexthop_group_vr_entry_destroy(struct mlxsw_sp_nexthop_group *nh_grp, + struct mlxsw_sp_nexthop_group_vr_entry *vr_entry) +{ + list_del(&vr_entry->list); + rhashtable_remove_fast(&nh_grp->vr_ht, &vr_entry->ht_node, + mlxsw_sp_nexthop_group_vr_ht_params); + kfree(vr_entry); +} + +static int +mlxsw_sp_nexthop_group_vr_link(struct mlxsw_sp_nexthop_group *nh_grp, + const struct mlxsw_sp_fib *fib) { - return nh_grp->priv; + struct mlxsw_sp_nexthop_group_vr_entry *vr_entry; + + vr_entry = mlxsw_sp_nexthop_group_vr_entry_lookup(nh_grp, fib); + if (vr_entry) { + refcount_inc(&vr_entry->ref_count); + return 0; + } + + return mlxsw_sp_nexthop_group_vr_entry_create(nh_grp, fib); +} + +static void +mlxsw_sp_nexthop_group_vr_unlink(struct mlxsw_sp_nexthop_group *nh_grp, + const struct mlxsw_sp_fib *fib) +{ + struct mlxsw_sp_nexthop_group_vr_entry *vr_entry; + + vr_entry = mlxsw_sp_nexthop_group_vr_entry_lookup(nh_grp, fib); + if (WARN_ON_ONCE(!vr_entry)) + return; + + if (!refcount_dec_and_test(&vr_entry->ref_count)) + return; + + mlxsw_sp_nexthop_group_vr_entry_destroy(nh_grp, vr_entry); } struct mlxsw_sp_nexthop_group_cmp_arg { - enum mlxsw_sp_l3proto proto; + enum mlxsw_sp_nexthop_group_type type; union { struct fib_info *fi; struct mlxsw_sp_fib6_entry *fib6_entry; + u32 id; }; }; @@ -2921,10 +3147,10 @@ mlxsw_sp_nexthop6_group_has_nexthop(const struct mlxsw_sp_nexthop_group *nh_grp, { int i; - for (i = 0; i < nh_grp->count; i++) { + for (i = 0; i < nh_grp->nhgi->count; i++) { const struct mlxsw_sp_nexthop *nh; - nh = &nh_grp->nexthops[i]; + nh = &nh_grp->nhgi->nexthops[i]; if (nh->ifindex == ifindex && nh->nh_weight == weight && ipv6_addr_equal(gw, (struct in6_addr *) nh->gw_addr)) return true; @@ -2939,7 +3165,7 @@ mlxsw_sp_nexthop6_group_cmp(const struct mlxsw_sp_nexthop_group *nh_grp, { struct mlxsw_sp_rt6 *mlxsw_sp_rt6; - if (nh_grp->count != fib6_entry->nrt6) + if (nh_grp->nhgi->count != fib6_entry->nrt6) return false; list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { @@ -2964,24 +3190,23 @@ mlxsw_sp_nexthop_group_cmp(struct rhashtable_compare_arg *arg, const void *ptr) const struct mlxsw_sp_nexthop_group_cmp_arg *cmp_arg = arg->key; const struct mlxsw_sp_nexthop_group *nh_grp = ptr; - switch (cmp_arg->proto) { - case MLXSW_SP_L3_PROTO_IPV4: - return cmp_arg->fi != mlxsw_sp_nexthop4_group_fi(nh_grp); - case MLXSW_SP_L3_PROTO_IPV6: + if (nh_grp->type != cmp_arg->type) + return 1; + + switch (cmp_arg->type) { + case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4: + return cmp_arg->fi != nh_grp->ipv4.fi; + case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6: return !mlxsw_sp_nexthop6_group_cmp(nh_grp, cmp_arg->fib6_entry); + case MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ: + return cmp_arg->id != nh_grp->obj.id; default: WARN_ON(1); return 1; } } -static int -mlxsw_sp_nexthop_group_type(const struct mlxsw_sp_nexthop_group *nh_grp) -{ - return nh_grp->neigh_tbl->family; -} - static u32 mlxsw_sp_nexthop_group_hash_obj(const void *data, u32 len, u32 seed) { const struct mlxsw_sp_nexthop_group *nh_grp = data; @@ -2990,18 +3215,20 @@ static u32 mlxsw_sp_nexthop_group_hash_obj(const void *data, u32 len, u32 seed) unsigned int val; int i; - switch (mlxsw_sp_nexthop_group_type(nh_grp)) { - case AF_INET: - fi = mlxsw_sp_nexthop4_group_fi(nh_grp); + switch (nh_grp->type) { + case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4: + fi = nh_grp->ipv4.fi; return jhash(&fi, sizeof(fi), seed); - case AF_INET6: - val = nh_grp->count; - for (i = 0; i < nh_grp->count; i++) { - nh = &nh_grp->nexthops[i]; + case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6: + val = nh_grp->nhgi->count; + for (i = 0; i < nh_grp->nhgi->count; i++) { + nh = &nh_grp->nhgi->nexthops[i]; val ^= jhash(&nh->ifindex, sizeof(nh->ifindex), seed); val ^= jhash(&nh->gw_addr, sizeof(nh->gw_addr), seed); } return jhash(&val, sizeof(val), seed); + case MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ: + return jhash(&nh_grp->obj.id, sizeof(nh_grp->obj.id), seed); default: WARN_ON(1); return 0; @@ -3031,11 +3258,13 @@ mlxsw_sp_nexthop_group_hash(const void *data, u32 len, u32 seed) { const struct mlxsw_sp_nexthop_group_cmp_arg *cmp_arg = data; - switch (cmp_arg->proto) { - case MLXSW_SP_L3_PROTO_IPV4: + switch (cmp_arg->type) { + case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4: return jhash(&cmp_arg->fi, sizeof(cmp_arg->fi), seed); - case MLXSW_SP_L3_PROTO_IPV6: + case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6: return mlxsw_sp_nexthop6_group_hash(cmp_arg->fib6_entry, seed); + case MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ: + return jhash(&cmp_arg->id, sizeof(cmp_arg->id), seed); default: WARN_ON(1); return 0; @@ -3052,8 +3281,8 @@ static const struct rhashtable_params mlxsw_sp_nexthop_group_ht_params = { static int mlxsw_sp_nexthop_group_insert(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp) { - if (mlxsw_sp_nexthop_group_type(nh_grp) == AF_INET6 && - !nh_grp->gateway) + if (nh_grp->type == MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6 && + !nh_grp->nhgi->gateway) return 0; return rhashtable_insert_fast(&mlxsw_sp->router->nexthop_group_ht, @@ -3064,8 +3293,8 @@ static int mlxsw_sp_nexthop_group_insert(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_nexthop_group_remove(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp) { - if (mlxsw_sp_nexthop_group_type(nh_grp) == AF_INET6 && - !nh_grp->gateway) + if (nh_grp->type == MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6 && + !nh_grp->nhgi->gateway) return; rhashtable_remove_fast(&mlxsw_sp->router->nexthop_group_ht, @@ -3079,7 +3308,7 @@ mlxsw_sp_nexthop4_group_lookup(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_nexthop_group_cmp_arg cmp_arg; - cmp_arg.proto = MLXSW_SP_L3_PROTO_IPV4; + cmp_arg.type = MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4; cmp_arg.fi = fi; return rhashtable_lookup_fast(&mlxsw_sp->router->nexthop_group_ht, &cmp_arg, @@ -3092,7 +3321,7 @@ mlxsw_sp_nexthop6_group_lookup(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_nexthop_group_cmp_arg cmp_arg; - cmp_arg.proto = MLXSW_SP_L3_PROTO_IPV6; + cmp_arg.type = MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6; cmp_arg.fib6_entry = fib6_entry; return rhashtable_lookup_fast(&mlxsw_sp->router->nexthop_group_ht, &cmp_arg, @@ -3128,7 +3357,8 @@ mlxsw_sp_nexthop_lookup(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_fib *fib, + enum mlxsw_sp_l3proto proto, + u16 vr_id, u32 adj_index, u16 ecmp_size, u32 new_adj_index, u16 new_ecmp_size) @@ -3136,8 +3366,8 @@ static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp, char raleu_pl[MLXSW_REG_RALEU_LEN]; mlxsw_reg_raleu_pack(raleu_pl, - (enum mlxsw_reg_ralxx_protocol) fib->proto, - fib->vr->id, adj_index, ecmp_size, new_adj_index, + (enum mlxsw_reg_ralxx_protocol) proto, vr_id, + adj_index, ecmp_size, new_adj_index, new_ecmp_size); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raleu), raleu_pl); } @@ -3146,23 +3376,31 @@ static int mlxsw_sp_adj_index_mass_update(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp, u32 old_adj_index, u16 old_ecmp_size) { - struct mlxsw_sp_fib_entry *fib_entry; - struct mlxsw_sp_fib *fib = NULL; + struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi; + struct mlxsw_sp_nexthop_group_vr_entry *vr_entry; int err; - list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) { - if (fib == fib_entry->fib_node->fib) - continue; - fib = fib_entry->fib_node->fib; - err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, fib, + list_for_each_entry(vr_entry, &nh_grp->vr_list, list) { + err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, + vr_entry->key.proto, + vr_entry->key.vr_id, old_adj_index, old_ecmp_size, - nh_grp->adj_index, - nh_grp->ecmp_size); + nhgi->adj_index, + nhgi->ecmp_size); if (err) - return err; + goto err_mass_update_vr; } return 0; + +err_mass_update_vr: + list_for_each_entry_continue_reverse(vr_entry, &nh_grp->vr_list, list) + mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, vr_entry->key.proto, + vr_entry->key.vr_id, + nhgi->adj_index, + nhgi->ecmp_size, + old_adj_index, old_ecmp_size); + return err; } static int __mlxsw_sp_nexthop_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, @@ -3173,8 +3411,12 @@ static int __mlxsw_sp_nexthop_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, true, MLXSW_REG_RATR_TYPE_ETHERNET, - adj_index, neigh_entry->rif); - mlxsw_reg_ratr_eth_entry_pack(ratr_pl, neigh_entry->ha); + adj_index, nh->rif->rif_index); + if (nh->discard) + mlxsw_reg_ratr_trap_action_set(ratr_pl, + MLXSW_REG_RATR_TRAP_ACTION_DISCARD_ERRORS); + else + mlxsw_reg_ratr_eth_entry_pack(ratr_pl, neigh_entry->ha); if (nh->counter_valid) mlxsw_reg_ratr_counter_pack(ratr_pl, nh->counter_index, true); else @@ -3229,15 +3471,15 @@ static int mlxsw_sp_nexthop_ipip_update(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp_nexthop_group_update(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop_group *nh_grp, + struct mlxsw_sp_nexthop_group_info *nhgi, bool reallocate) { - u32 adj_index = nh_grp->adj_index; /* base */ + u32 adj_index = nhgi->adj_index; /* base */ struct mlxsw_sp_nexthop *nh; int i; - for (i = 0; i < nh_grp->count; i++) { - nh = &nh_grp->nexthops[i]; + for (i = 0; i < nhgi->count; i++) { + nh = &nhgi->nexthops[i]; if (!nh->should_offload) { nh->offloaded = 0; @@ -3337,13 +3579,13 @@ static int mlxsw_sp_fix_adj_grp_size(struct mlxsw_sp *mlxsw_sp, } static void -mlxsw_sp_nexthop_group_normalize(struct mlxsw_sp_nexthop_group *nh_grp) +mlxsw_sp_nexthop_group_normalize(struct mlxsw_sp_nexthop_group_info *nhgi) { int i, g = 0, sum_norm_weight = 0; struct mlxsw_sp_nexthop *nh; - for (i = 0; i < nh_grp->count; i++) { - nh = &nh_grp->nexthops[i]; + for (i = 0; i < nhgi->count; i++) { + nh = &nhgi->nexthops[i]; if (!nh->should_offload) continue; @@ -3353,8 +3595,8 @@ mlxsw_sp_nexthop_group_normalize(struct mlxsw_sp_nexthop_group *nh_grp) g = nh->nh_weight; } - for (i = 0; i < nh_grp->count; i++) { - nh = &nh_grp->nexthops[i]; + for (i = 0; i < nhgi->count; i++) { + nh = &nhgi->nexthops[i]; if (!nh->should_offload) continue; @@ -3362,18 +3604,18 @@ mlxsw_sp_nexthop_group_normalize(struct mlxsw_sp_nexthop_group *nh_grp) sum_norm_weight += nh->norm_nh_weight; } - nh_grp->sum_norm_weight = sum_norm_weight; + nhgi->sum_norm_weight = sum_norm_weight; } static void -mlxsw_sp_nexthop_group_rebalance(struct mlxsw_sp_nexthop_group *nh_grp) +mlxsw_sp_nexthop_group_rebalance(struct mlxsw_sp_nexthop_group_info *nhgi) { - int total = nh_grp->sum_norm_weight; - u16 ecmp_size = nh_grp->ecmp_size; int i, weight = 0, lower_bound = 0; + int total = nhgi->sum_norm_weight; + u16 ecmp_size = nhgi->ecmp_size; - for (i = 0; i < nh_grp->count; i++) { - struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i]; + for (i = 0; i < nhgi->count; i++) { + struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i]; int upper_bound; if (!nh->should_offload) @@ -3395,8 +3637,8 @@ mlxsw_sp_nexthop4_group_offload_refresh(struct mlxsw_sp *mlxsw_sp, { int i; - for (i = 0; i < nh_grp->count; i++) { - struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i]; + for (i = 0; i < nh_grp->nhgi->count; i++) { + struct mlxsw_sp_nexthop *nh = &nh_grp->nhgi->nexthops[i]; if (nh->offloaded) nh->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD; @@ -3439,39 +3681,59 @@ mlxsw_sp_nexthop6_group_offload_refresh(struct mlxsw_sp *mlxsw_sp, } static void +mlxsw_sp_nexthop_obj_group_offload_refresh(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp) +{ + /* Do not update the flags if the nexthop group is being destroyed + * since: + * 1. The nexthop objects is being deleted, in which case the flags are + * irrelevant. + * 2. The nexthop group was replaced by a newer group, in which case + * the flags of the nexthop object were already updated based on the + * new group. + */ + if (nh_grp->can_destroy) + return; + + nexthop_set_hw_flags(mlxsw_sp_net(mlxsw_sp), nh_grp->obj.id, + nh_grp->nhgi->adj_index_valid, false); +} + +static void mlxsw_sp_nexthop_group_offload_refresh(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp) { - switch (mlxsw_sp_nexthop_group_type(nh_grp)) { - case AF_INET: + switch (nh_grp->type) { + case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4: mlxsw_sp_nexthop4_group_offload_refresh(mlxsw_sp, nh_grp); break; - case AF_INET6: + case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6: mlxsw_sp_nexthop6_group_offload_refresh(mlxsw_sp, nh_grp); break; + case MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ: + mlxsw_sp_nexthop_obj_group_offload_refresh(mlxsw_sp, nh_grp); + break; } } -static void +static int mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp) { + struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi; u16 ecmp_size, old_ecmp_size; struct mlxsw_sp_nexthop *nh; bool offload_change = false; u32 adj_index; bool old_adj_index_valid; + int i, err2, err = 0; u32 old_adj_index; - int i; - int err; - if (!nh_grp->gateway) { - mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp); - return; - } + if (!nhgi->gateway) + return mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp); - for (i = 0; i < nh_grp->count; i++) { - nh = &nh_grp->nexthops[i]; + for (i = 0; i < nhgi->count; i++) { + nh = &nhgi->nexthops[i]; if (nh->should_offload != nh->offloaded) { offload_change = true; @@ -3483,21 +3745,21 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, /* Nothing was added or removed, so no need to reallocate. Just * update MAC on existing adjacency indexes. */ - err = mlxsw_sp_nexthop_group_update(mlxsw_sp, nh_grp, false); + err = mlxsw_sp_nexthop_group_update(mlxsw_sp, nhgi, false); if (err) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n"); goto set_trap; } - return; + return 0; } - mlxsw_sp_nexthop_group_normalize(nh_grp); - if (!nh_grp->sum_norm_weight) + mlxsw_sp_nexthop_group_normalize(nhgi); + if (!nhgi->sum_norm_weight) /* No neigh of this group is connected so we just set * the trap and let everthing flow through kernel. */ goto set_trap; - ecmp_size = nh_grp->sum_norm_weight; + ecmp_size = nhgi->sum_norm_weight; err = mlxsw_sp_fix_adj_grp_size(mlxsw_sp, &ecmp_size); if (err) /* No valid allocation size available. */ @@ -3512,14 +3774,14 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, dev_warn(mlxsw_sp->bus_info->dev, "Failed to allocate KVD linear area for nexthop group.\n"); goto set_trap; } - old_adj_index_valid = nh_grp->adj_index_valid; - old_adj_index = nh_grp->adj_index; - old_ecmp_size = nh_grp->ecmp_size; - nh_grp->adj_index_valid = 1; - nh_grp->adj_index = adj_index; - nh_grp->ecmp_size = ecmp_size; - mlxsw_sp_nexthop_group_rebalance(nh_grp); - err = mlxsw_sp_nexthop_group_update(mlxsw_sp, nh_grp, true); + old_adj_index_valid = nhgi->adj_index_valid; + old_adj_index = nhgi->adj_index; + old_ecmp_size = nhgi->ecmp_size; + nhgi->adj_index_valid = 1; + nhgi->adj_index = adj_index; + nhgi->ecmp_size = ecmp_size; + mlxsw_sp_nexthop_group_rebalance(nhgi); + err = mlxsw_sp_nexthop_group_update(mlxsw_sp, nhgi, true); if (err) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n"); goto set_trap; @@ -3536,7 +3798,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, dev_warn(mlxsw_sp->bus_info->dev, "Failed to add adjacency index to fib entries.\n"); goto set_trap; } - return; + return 0; } err = mlxsw_sp_adj_index_mass_update(mlxsw_sp, nh_grp, @@ -3548,22 +3810,23 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, goto set_trap; } - return; + return 0; set_trap: - old_adj_index_valid = nh_grp->adj_index_valid; - nh_grp->adj_index_valid = 0; - for (i = 0; i < nh_grp->count; i++) { - nh = &nh_grp->nexthops[i]; + old_adj_index_valid = nhgi->adj_index_valid; + nhgi->adj_index_valid = 0; + for (i = 0; i < nhgi->count; i++) { + nh = &nhgi->nexthops[i]; nh->offloaded = 0; } - err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp); - if (err) + err2 = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp); + if (err2) dev_warn(mlxsw_sp->bus_info->dev, "Failed to set traps for fib entries.\n"); mlxsw_sp_nexthop_group_offload_refresh(mlxsw_sp, nh_grp); if (old_adj_index_valid) mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, - nh_grp->ecmp_size, nh_grp->adj_index); + nhgi->ecmp_size, nhgi->adj_index); + return err; } static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh, @@ -3589,10 +3852,9 @@ mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp, nh = list_first_entry(&neigh_entry->nexthop_list, struct mlxsw_sp_nexthop, neigh_list_node); - n = neigh_lookup(nh->nh_grp->neigh_tbl, &nh->gw_addr, nh->rif->dev); + n = neigh_lookup(nh->neigh_tbl, &nh->gw_addr, nh->rif->dev); if (!n) { - n = neigh_create(nh->nh_grp->neigh_tbl, &nh->gw_addr, - nh->rif->dev); + n = neigh_create(nh->neigh_tbl, &nh->gw_addr, nh->rif->dev); if (IS_ERR(n)) return PTR_ERR(n); neigh_event_send(n, NULL); @@ -3615,7 +3877,7 @@ mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp, neigh_release(old_n); neigh_clone(n); __mlxsw_sp_nexthop_neigh_update(nh, !entry_connected); - mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp); + mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp); } neigh_release(n); @@ -3652,7 +3914,7 @@ mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp, list_for_each_entry(nh, &neigh_entry->nexthop_list, neigh_list_node) { __mlxsw_sp_nexthop_neigh_update(nh, removing); - mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp); + mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp); } } @@ -3683,7 +3945,7 @@ static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp, u8 nud_state, dead; int err; - if (!nh->nh_grp->gateway || nh->neigh_entry) + if (!nh->nhgi->gateway || nh->neigh_entry) return 0; /* Take a reference of neigh here ensuring that neigh would @@ -3691,10 +3953,9 @@ static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp, * The reference is taken either in neigh_lookup() or * in neigh_create() in case n is not found. */ - n = neigh_lookup(nh->nh_grp->neigh_tbl, &nh->gw_addr, nh->rif->dev); + n = neigh_lookup(nh->neigh_tbl, &nh->gw_addr, nh->rif->dev); if (!n) { - n = neigh_create(nh->nh_grp->neigh_tbl, &nh->gw_addr, - nh->rif->dev); + n = neigh_create(nh->neigh_tbl, &nh->gw_addr, nh->rif->dev); if (IS_ERR(n)) return PTR_ERR(n); neigh_event_send(n, NULL); @@ -3775,7 +4036,7 @@ static void mlxsw_sp_nexthop_ipip_init(struct mlxsw_sp *mlxsw_sp, { bool removing; - if (!nh->nh_grp->gateway || nh->ipip_entry) + if (!nh->nhgi->gateway || nh->ipip_entry) return; nh->ipip_entry = ipip_entry; @@ -3807,27 +4068,11 @@ static bool mlxsw_sp_nexthop4_ipip_type(const struct mlxsw_sp *mlxsw_sp, mlxsw_sp_netdev_ipip_type(mlxsw_sp, dev, p_ipipt); } -static void mlxsw_sp_nexthop_type_fini(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 int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop *nh, - struct fib_nh *fib_nh) +static int mlxsw_sp_nexthop_type_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh, + const struct net_device *dev) { const struct mlxsw_sp_ipip_ops *ipip_ops; - struct net_device *dev = fib_nh->fib_nh_dev; struct mlxsw_sp_ipip_entry *ipip_entry; struct mlxsw_sp_rif *rif; int err; @@ -3835,8 +4080,7 @@ static int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp, ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, dev); if (ipip_entry) { ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]; - if (ipip_ops->can_offload(mlxsw_sp, dev, - MLXSW_SP_L3_PROTO_IPV4)) { + if (ipip_ops->can_offload(mlxsw_sp, dev)) { nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP; mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, ipip_entry); return 0; @@ -3860,10 +4104,19 @@ err_neigh_init: return err; } -static void mlxsw_sp_nexthop4_type_fini(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop *nh) +static void mlxsw_sp_nexthop_type_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) { - mlxsw_sp_nexthop_type_fini(mlxsw_sp, 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 int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, @@ -3875,7 +4128,7 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, struct in_device *in_dev; int err; - nh->nh_grp = nh_grp; + nh->nhgi = nh_grp->nhgi; nh->key.fib_nh = fib_nh; #ifdef CONFIG_IP_ROUTE_MULTIPATH nh->nh_weight = fib_nh->fib_nh_weight; @@ -3883,6 +4136,7 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, nh->nh_weight = 1; #endif memcpy(&nh->gw_addr, &fib_nh->fib_nh_gw4, sizeof(fib_nh->fib_nh_gw4)); + nh->neigh_tbl = &arp_tbl; err = mlxsw_sp_nexthop_insert(mlxsw_sp, nh); if (err) return err; @@ -3892,6 +4146,7 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, if (!dev) return 0; + nh->ifindex = dev->ifindex; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); @@ -3902,7 +4157,7 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, } rcu_read_unlock(); - err = mlxsw_sp_nexthop4_type_init(mlxsw_sp, nh, fib_nh); + err = mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, dev); if (err) goto err_nexthop_neigh_init; @@ -3916,7 +4171,7 @@ err_nexthop_neigh_init: static void mlxsw_sp_nexthop4_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh) { - mlxsw_sp_nexthop4_type_fini(mlxsw_sp, nh); + mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh); list_del(&nh->router_list_node); mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); mlxsw_sp_nexthop_remove(mlxsw_sp, nh); @@ -3938,14 +4193,14 @@ static void mlxsw_sp_nexthop4_event(struct mlxsw_sp *mlxsw_sp, switch (event) { case FIB_EVENT_NH_ADD: - mlxsw_sp_nexthop4_type_init(mlxsw_sp, nh, fib_nh); + mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, fib_nh->fib_nh_dev); break; case FIB_EVENT_NH_DEL: - mlxsw_sp_nexthop4_type_fini(mlxsw_sp, nh); + mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh); break; } - mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp); + mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp); } static void mlxsw_sp_nexthop_rif_update(struct mlxsw_sp *mlxsw_sp, @@ -3968,7 +4223,7 @@ static void mlxsw_sp_nexthop_rif_update(struct mlxsw_sp *mlxsw_sp, } __mlxsw_sp_nexthop_neigh_update(nh, removing); - mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp); + mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp); } } @@ -3991,10 +4246,450 @@ static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, list_for_each_entry_safe(nh, tmp, &rif->nexthop_list, rif_list_node) { mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh); - mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp); + mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp); } } +static int +mlxsw_sp_nexthop_obj_single_validate(struct mlxsw_sp *mlxsw_sp, + const struct nh_notifier_single_info *nh, + struct netlink_ext_ack *extack) +{ + int err = -EINVAL; + + if (nh->is_fdb) + NL_SET_ERR_MSG_MOD(extack, "FDB nexthops are not supported"); + else if (nh->has_encap) + NL_SET_ERR_MSG_MOD(extack, "Encapsulating nexthops are not supported"); + else + err = 0; + + return err; +} + +static int +mlxsw_sp_nexthop_obj_group_validate(struct mlxsw_sp *mlxsw_sp, + const struct nh_notifier_grp_info *nh_grp, + struct netlink_ext_ack *extack) +{ + int i; + + if (nh_grp->is_fdb) { + NL_SET_ERR_MSG_MOD(extack, "FDB nexthop groups are not supported"); + return -EINVAL; + } + + for (i = 0; i < nh_grp->num_nh; i++) { + const struct nh_notifier_single_info *nh; + int err; + + nh = &nh_grp->nh_entries[i].nh; + err = mlxsw_sp_nexthop_obj_single_validate(mlxsw_sp, nh, + extack); + if (err) + return err; + + /* Device only nexthops with an IPIP device are programmed as + * encapsulating adjacency entries. + */ + if (!nh->gw_family && !nh->is_reject && + !mlxsw_sp_netdev_ipip_type(mlxsw_sp, nh->dev, NULL)) { + NL_SET_ERR_MSG_MOD(extack, "Nexthop group entry does not have a gateway"); + return -EINVAL; + } + } + + return 0; +} + +static int mlxsw_sp_nexthop_obj_validate(struct mlxsw_sp *mlxsw_sp, + unsigned long event, + struct nh_notifier_info *info) +{ + if (event != NEXTHOP_EVENT_REPLACE) + return 0; + + if (!info->is_grp) + return mlxsw_sp_nexthop_obj_single_validate(mlxsw_sp, info->nh, + info->extack); + return mlxsw_sp_nexthop_obj_group_validate(mlxsw_sp, info->nh_grp, + info->extack); +} + +static bool mlxsw_sp_nexthop_obj_is_gateway(struct mlxsw_sp *mlxsw_sp, + const struct nh_notifier_info *info) +{ + const struct net_device *dev; + + if (info->is_grp) + /* Already validated earlier. */ + return true; + + dev = info->nh->dev; + return info->nh->gw_family || info->nh->is_reject || + mlxsw_sp_netdev_ipip_type(mlxsw_sp, dev, NULL); +} + +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->discard = 1; + 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]; +} + +static void mlxsw_sp_nexthop_obj_blackhole_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + nh->rif = NULL; + nh->should_offload = 0; +} + +static int +mlxsw_sp_nexthop_obj_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp, + struct mlxsw_sp_nexthop *nh, + struct nh_notifier_single_info *nh_obj, int weight) +{ + struct net_device *dev = nh_obj->dev; + int err; + + nh->nhgi = nh_grp->nhgi; + nh->nh_weight = weight; + + switch (nh_obj->gw_family) { + case AF_INET: + memcpy(&nh->gw_addr, &nh_obj->ipv4, sizeof(nh_obj->ipv4)); + nh->neigh_tbl = &arp_tbl; + break; + case AF_INET6: + memcpy(&nh->gw_addr, &nh_obj->ipv6, sizeof(nh_obj->ipv6)); +#if IS_ENABLED(CONFIG_IPV6) + nh->neigh_tbl = &nd_tbl; +#endif + break; + } + + mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh); + list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list); + nh->ifindex = dev->ifindex; + + err = mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, dev); + if (err) + goto err_type_init; + + if (nh_obj->is_reject) + mlxsw_sp_nexthop_obj_blackhole_init(mlxsw_sp, nh); + + return 0; + +err_type_init: + list_del(&nh->router_list_node); + mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); + return err; +} + +static void mlxsw_sp_nexthop_obj_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + if (nh->discard) + mlxsw_sp_nexthop_obj_blackhole_fini(mlxsw_sp, nh); + mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh); + list_del(&nh->router_list_node); + mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); +} + +static int +mlxsw_sp_nexthop_obj_group_info_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp, + struct nh_notifier_info *info) +{ + unsigned int nhs = info->is_grp ? info->nh_grp->num_nh : 1; + struct mlxsw_sp_nexthop_group_info *nhgi; + struct mlxsw_sp_nexthop *nh; + int err, i; + + nhgi = kzalloc(struct_size(nhgi, nexthops, nhs), GFP_KERNEL); + if (!nhgi) + return -ENOMEM; + nh_grp->nhgi = nhgi; + nhgi->nh_grp = nh_grp; + nhgi->gateway = mlxsw_sp_nexthop_obj_is_gateway(mlxsw_sp, info); + nhgi->count = nhs; + for (i = 0; i < nhgi->count; i++) { + struct nh_notifier_single_info *nh_obj; + int weight; + + nh = &nhgi->nexthops[i]; + if (info->is_grp) { + nh_obj = &info->nh_grp->nh_entries[i].nh; + weight = info->nh_grp->nh_entries[i].weight; + } else { + nh_obj = info->nh; + weight = 1; + } + err = mlxsw_sp_nexthop_obj_init(mlxsw_sp, nh_grp, nh, nh_obj, + weight); + if (err) + goto err_nexthop_obj_init; + } + err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); + if (err) { + NL_SET_ERR_MSG_MOD(info->extack, "Failed to write adjacency entries to the device"); + goto err_group_refresh; + } + + return 0; + +err_group_refresh: + i = nhgi->count; +err_nexthop_obj_init: + for (i--; i >= 0; i--) { + nh = &nhgi->nexthops[i]; + mlxsw_sp_nexthop_obj_fini(mlxsw_sp, nh); + } + kfree(nhgi); + return err; +} + +static void +mlxsw_sp_nexthop_obj_group_info_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp) +{ + struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi; + int i; + + for (i = nhgi->count - 1; i >= 0; i--) { + struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i]; + + mlxsw_sp_nexthop_obj_fini(mlxsw_sp, nh); + } + mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); + WARN_ON_ONCE(nhgi->adj_index_valid); + kfree(nhgi); +} + +static struct mlxsw_sp_nexthop_group * +mlxsw_sp_nexthop_obj_group_create(struct mlxsw_sp *mlxsw_sp, + struct nh_notifier_info *info) +{ + struct mlxsw_sp_nexthop_group *nh_grp; + int err; + + nh_grp = kzalloc(sizeof(*nh_grp), GFP_KERNEL); + if (!nh_grp) + return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&nh_grp->vr_list); + err = rhashtable_init(&nh_grp->vr_ht, + &mlxsw_sp_nexthop_group_vr_ht_params); + if (err) + goto err_nexthop_group_vr_ht_init; + INIT_LIST_HEAD(&nh_grp->fib_list); + nh_grp->type = MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ; + nh_grp->obj.id = info->id; + + err = mlxsw_sp_nexthop_obj_group_info_init(mlxsw_sp, nh_grp, info); + if (err) + goto err_nexthop_group_info_init; + + nh_grp->can_destroy = false; + + return nh_grp; + +err_nexthop_group_info_init: + rhashtable_destroy(&nh_grp->vr_ht); +err_nexthop_group_vr_ht_init: + kfree(nh_grp); + return ERR_PTR(err); +} + +static void +mlxsw_sp_nexthop_obj_group_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp) +{ + if (!nh_grp->can_destroy) + return; + mlxsw_sp_nexthop_obj_group_info_fini(mlxsw_sp, nh_grp); + WARN_ON_ONCE(!list_empty(&nh_grp->fib_list)); + WARN_ON_ONCE(!list_empty(&nh_grp->vr_list)); + rhashtable_destroy(&nh_grp->vr_ht); + kfree(nh_grp); +} + +static struct mlxsw_sp_nexthop_group * +mlxsw_sp_nexthop_obj_group_lookup(struct mlxsw_sp *mlxsw_sp, u32 id) +{ + struct mlxsw_sp_nexthop_group_cmp_arg cmp_arg; + + cmp_arg.type = MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ; + cmp_arg.id = id; + return rhashtable_lookup_fast(&mlxsw_sp->router->nexthop_group_ht, + &cmp_arg, + mlxsw_sp_nexthop_group_ht_params); +} + +static int mlxsw_sp_nexthop_obj_group_add(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp) +{ + return mlxsw_sp_nexthop_group_insert(mlxsw_sp, nh_grp); +} + +static int +mlxsw_sp_nexthop_obj_group_replace(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp, + struct mlxsw_sp_nexthop_group *old_nh_grp, + struct netlink_ext_ack *extack) +{ + struct mlxsw_sp_nexthop_group_info *old_nhgi = old_nh_grp->nhgi; + struct mlxsw_sp_nexthop_group_info *new_nhgi = nh_grp->nhgi; + int err; + + old_nh_grp->nhgi = new_nhgi; + new_nhgi->nh_grp = old_nh_grp; + nh_grp->nhgi = old_nhgi; + old_nhgi->nh_grp = nh_grp; + + if (old_nhgi->adj_index_valid && new_nhgi->adj_index_valid) { + /* Both the old adjacency index and the new one are valid. + * Routes are currently using the old one. Tell the device to + * replace the old adjacency index with the new one. + */ + err = mlxsw_sp_adj_index_mass_update(mlxsw_sp, old_nh_grp, + old_nhgi->adj_index, + old_nhgi->ecmp_size); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to replace old adjacency index with new one"); + goto err_out; + } + } else if (old_nhgi->adj_index_valid && !new_nhgi->adj_index_valid) { + /* The old adjacency index is valid, while the new one is not. + * Iterate over all the routes using the group and change them + * to trap packets to the CPU. + */ + err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, old_nh_grp); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to update routes to trap packets"); + goto err_out; + } + } else if (!old_nhgi->adj_index_valid && new_nhgi->adj_index_valid) { + /* The old adjacency index is invalid, while the new one is. + * Iterate over all the routes using the group and change them + * to forward packets using the new valid index. + */ + err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, old_nh_grp); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to update routes to forward packets"); + goto err_out; + } + } + + /* Make sure the flags are set / cleared based on the new nexthop group + * information. + */ + mlxsw_sp_nexthop_obj_group_offload_refresh(mlxsw_sp, old_nh_grp); + + /* At this point 'nh_grp' is just a shell that is not used by anyone + * and its nexthop group info is the old info that was just replaced + * with the new one. Remove it. + */ + nh_grp->can_destroy = true; + mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp); + + return 0; + +err_out: + old_nhgi->nh_grp = old_nh_grp; + nh_grp->nhgi = new_nhgi; + new_nhgi->nh_grp = nh_grp; + old_nh_grp->nhgi = old_nhgi; + return err; +} + +static int mlxsw_sp_nexthop_obj_new(struct mlxsw_sp *mlxsw_sp, + struct nh_notifier_info *info) +{ + struct mlxsw_sp_nexthop_group *nh_grp, *old_nh_grp; + struct netlink_ext_ack *extack = info->extack; + int err; + + nh_grp = mlxsw_sp_nexthop_obj_group_create(mlxsw_sp, info); + if (IS_ERR(nh_grp)) + return PTR_ERR(nh_grp); + + old_nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, info->id); + if (!old_nh_grp) + err = mlxsw_sp_nexthop_obj_group_add(mlxsw_sp, nh_grp); + else + err = mlxsw_sp_nexthop_obj_group_replace(mlxsw_sp, nh_grp, + old_nh_grp, extack); + + if (err) { + nh_grp->can_destroy = true; + mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp); + } + + return err; +} + +static void mlxsw_sp_nexthop_obj_del(struct mlxsw_sp *mlxsw_sp, + struct nh_notifier_info *info) +{ + struct mlxsw_sp_nexthop_group *nh_grp; + + nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, info->id); + if (!nh_grp) + return; + + nh_grp->can_destroy = true; + mlxsw_sp_nexthop_group_remove(mlxsw_sp, nh_grp); + + /* If the group still has routes using it, then defer the delete + * operation until the last route using it is deleted. + */ + if (!list_empty(&nh_grp->fib_list)) + return; + mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp); +} + +static int mlxsw_sp_nexthop_obj_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct nh_notifier_info *info = ptr; + struct mlxsw_sp_router *router; + int err = 0; + + router = container_of(nb, struct mlxsw_sp_router, nexthop_nb); + err = mlxsw_sp_nexthop_obj_validate(router->mlxsw_sp, event, info); + if (err) + goto out; + + mutex_lock(&router->lock); + + ASSERT_RTNL(); + + switch (event) { + case NEXTHOP_EVENT_REPLACE: + err = mlxsw_sp_nexthop_obj_new(router->mlxsw_sp, info); + break; + case NEXTHOP_EVENT_DEL: + mlxsw_sp_nexthop_obj_del(router->mlxsw_sp, info); + break; + default: + break; + } + + mutex_unlock(&router->lock); + +out: + return notifier_from_errno(err); +} + static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp, struct fib_info *fi) { @@ -4004,46 +4699,102 @@ static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, nh, NULL); } +static int +mlxsw_sp_nexthop4_group_info_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp) +{ + unsigned int nhs = fib_info_num_path(nh_grp->ipv4.fi); + struct mlxsw_sp_nexthop_group_info *nhgi; + struct mlxsw_sp_nexthop *nh; + int err, i; + + nhgi = kzalloc(struct_size(nhgi, nexthops, nhs), GFP_KERNEL); + if (!nhgi) + return -ENOMEM; + nh_grp->nhgi = nhgi; + nhgi->nh_grp = nh_grp; + nhgi->gateway = mlxsw_sp_fi_is_gateway(mlxsw_sp, nh_grp->ipv4.fi); + nhgi->count = nhs; + for (i = 0; i < nhgi->count; i++) { + struct fib_nh *fib_nh; + + nh = &nhgi->nexthops[i]; + fib_nh = fib_info_nh(nh_grp->ipv4.fi, i); + err = mlxsw_sp_nexthop4_init(mlxsw_sp, nh_grp, nh, fib_nh); + if (err) + goto err_nexthop4_init; + } + err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); + if (err) + goto err_group_refresh; + + return 0; + +err_group_refresh: + i = nhgi->count; +err_nexthop4_init: + for (i--; i >= 0; i--) { + nh = &nhgi->nexthops[i]; + mlxsw_sp_nexthop4_fini(mlxsw_sp, nh); + } + kfree(nhgi); + return err; +} + +static void +mlxsw_sp_nexthop4_group_info_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp) +{ + struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi; + int i; + + for (i = nhgi->count - 1; i >= 0; i--) { + struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i]; + + mlxsw_sp_nexthop4_fini(mlxsw_sp, nh); + } + mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); + WARN_ON_ONCE(nhgi->adj_index_valid); + kfree(nhgi); +} + static struct mlxsw_sp_nexthop_group * mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi) { - unsigned int nhs = fib_info_num_path(fi); struct mlxsw_sp_nexthop_group *nh_grp; - struct mlxsw_sp_nexthop *nh; - struct fib_nh *fib_nh; - int i; int err; - nh_grp = kzalloc(struct_size(nh_grp, nexthops, nhs), GFP_KERNEL); + nh_grp = kzalloc(sizeof(*nh_grp), GFP_KERNEL); if (!nh_grp) return ERR_PTR(-ENOMEM); - nh_grp->priv = fi; + INIT_LIST_HEAD(&nh_grp->vr_list); + err = rhashtable_init(&nh_grp->vr_ht, + &mlxsw_sp_nexthop_group_vr_ht_params); + if (err) + goto err_nexthop_group_vr_ht_init; INIT_LIST_HEAD(&nh_grp->fib_list); - nh_grp->neigh_tbl = &arp_tbl; - - nh_grp->gateway = mlxsw_sp_fi_is_gateway(mlxsw_sp, fi); - nh_grp->count = nhs; + nh_grp->type = MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4; + nh_grp->ipv4.fi = fi; fib_info_hold(fi); - for (i = 0; i < nh_grp->count; i++) { - nh = &nh_grp->nexthops[i]; - fib_nh = fib_info_nh(fi, i); - err = mlxsw_sp_nexthop4_init(mlxsw_sp, nh_grp, nh, fib_nh); - if (err) - goto err_nexthop4_init; - } + + err = mlxsw_sp_nexthop4_group_info_init(mlxsw_sp, nh_grp); + if (err) + goto err_nexthop_group_info_init; + err = mlxsw_sp_nexthop_group_insert(mlxsw_sp, nh_grp); if (err) goto err_nexthop_group_insert; - mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); + + nh_grp->can_destroy = true; + return nh_grp; err_nexthop_group_insert: -err_nexthop4_init: - for (i--; i >= 0; i--) { - nh = &nh_grp->nexthops[i]; - mlxsw_sp_nexthop4_fini(mlxsw_sp, nh); - } + mlxsw_sp_nexthop4_group_info_fini(mlxsw_sp, nh_grp); +err_nexthop_group_info_init: fib_info_put(fi); + rhashtable_destroy(&nh_grp->vr_ht); +err_nexthop_group_vr_ht_init: kfree(nh_grp); return ERR_PTR(err); } @@ -4052,17 +4803,13 @@ static void mlxsw_sp_nexthop4_group_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp) { - struct mlxsw_sp_nexthop *nh; - int i; - + if (!nh_grp->can_destroy) + return; mlxsw_sp_nexthop_group_remove(mlxsw_sp, nh_grp); - for (i = 0; i < nh_grp->count; i++) { - nh = &nh_grp->nexthops[i]; - mlxsw_sp_nexthop4_fini(mlxsw_sp, nh); - } - mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); - WARN_ON_ONCE(nh_grp->adj_index_valid); - fib_info_put(mlxsw_sp_nexthop4_group_fi(nh_grp)); + mlxsw_sp_nexthop4_group_info_fini(mlxsw_sp, nh_grp); + fib_info_put(nh_grp->ipv4.fi); + WARN_ON_ONCE(!list_empty(&nh_grp->vr_list)); + rhashtable_destroy(&nh_grp->vr_ht); kfree(nh_grp); } @@ -4072,12 +4819,21 @@ static int mlxsw_sp_nexthop4_group_get(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_nexthop_group *nh_grp; + if (fi->nh) { + nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, + fi->nh->id); + if (WARN_ON_ONCE(!nh_grp)) + return -EINVAL; + goto out; + } + nh_grp = mlxsw_sp_nexthop4_group_lookup(mlxsw_sp, fi); if (!nh_grp) { nh_grp = mlxsw_sp_nexthop4_group_create(mlxsw_sp, fi); if (IS_ERR(nh_grp)) return PTR_ERR(nh_grp); } +out: list_add_tail(&fib_entry->nexthop_group_node, &nh_grp->fib_list); fib_entry->nh_group = nh_grp; return 0; @@ -4091,6 +4847,12 @@ static void mlxsw_sp_nexthop4_group_put(struct mlxsw_sp *mlxsw_sp, list_del(&fib_entry->nexthop_group_node); if (!list_empty(&nh_grp->fib_list)) return; + + if (nh_grp->type == MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ) { + mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp); + return; + } + mlxsw_sp_nexthop4_group_destroy(mlxsw_sp, nh_grp); } @@ -4120,9 +4882,9 @@ mlxsw_sp_fib_entry_should_offload(const struct mlxsw_sp_fib_entry *fib_entry) switch (fib_entry->type) { case MLXSW_SP_FIB_ENTRY_TYPE_REMOTE: - return !!nh_group->adj_index_valid; + return !!nh_group->nhgi->adj_index_valid; case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL: - return !!nh_group->nh_rif; + return !!nh_group->nhgi->nh_rif; case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE: case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP: case MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP: @@ -4138,8 +4900,8 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp, { int i; - for (i = 0; i < nh_grp->count; i++) { - struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i]; + for (i = 0; i < nh_grp->nhgi->count; i++) { + struct mlxsw_sp_nexthop *nh = &nh_grp->nhgi->nexthops[i]; struct fib6_info *rt = mlxsw_sp_rt6->rt; if (nh->rif && nh->rif->dev == rt->fib6_nh->fib_nh_dev && @@ -4156,7 +4918,6 @@ static void mlxsw_sp_fib4_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry) { - struct fib_info *fi = mlxsw_sp_nexthop4_group_fi(fib_entry->nh_group); u32 *p_dst = (u32 *) fib_entry->fib_node->key.addr; int dst_len = fib_entry->fib_node->key.prefix_len; struct mlxsw_sp_fib4_entry *fib4_entry; @@ -4166,7 +4927,7 @@ mlxsw_sp_fib4_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp, should_offload = mlxsw_sp_fib_entry_should_offload(fib_entry); fib4_entry = container_of(fib_entry, struct mlxsw_sp_fib4_entry, common); - fri.fi = fi; + fri.fi = fib4_entry->fi; fri.tb_id = fib4_entry->tb_id; fri.dst = cpu_to_be32(*p_dst); fri.dst_len = dst_len; @@ -4181,7 +4942,6 @@ static void mlxsw_sp_fib4_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry) { - struct fib_info *fi = mlxsw_sp_nexthop4_group_fi(fib_entry->nh_group); u32 *p_dst = (u32 *) fib_entry->fib_node->key.addr; int dst_len = fib_entry->fib_node->key.prefix_len; struct mlxsw_sp_fib4_entry *fib4_entry; @@ -4189,7 +4949,7 @@ mlxsw_sp_fib4_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp, fib4_entry = container_of(fib_entry, struct mlxsw_sp_fib4_entry, common); - fri.fi = fi; + fri.fi = fib4_entry->fi; fri.tb_id = fib4_entry->tb_id; fri.dst = cpu_to_be32(*p_dst); fri.dst_len = dst_len; @@ -4264,13 +5024,14 @@ mlxsw_sp_fib_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_fib_entry_hw_flags_refresh(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) + enum mlxsw_sp_fib_entry_op op) { switch (op) { - case MLXSW_REG_RALUE_OP_WRITE_WRITE: + case MLXSW_SP_FIB_ENTRY_OP_WRITE: + case MLXSW_SP_FIB_ENTRY_OP_UPDATE: mlxsw_sp_fib_entry_hw_flags_set(mlxsw_sp, fib_entry); break; - case MLXSW_REG_RALUE_OP_WRITE_DELETE: + case MLXSW_SP_FIB_ENTRY_OP_DELETE: mlxsw_sp_fib_entry_hw_flags_clear(mlxsw_sp, fib_entry); break; default: @@ -4278,33 +5039,133 @@ mlxsw_sp_fib_entry_hw_flags_refresh(struct mlxsw_sp *mlxsw_sp, } } +struct mlxsw_sp_fib_entry_op_ctx_basic { + char ralue_pl[MLXSW_REG_RALUE_LEN]; +}; + static void -mlxsw_sp_fib_entry_ralue_pack(char *ralue_pl, - const struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) +mlxsw_sp_router_ll_basic_fib_entry_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + enum mlxsw_sp_l3proto proto, + enum mlxsw_sp_fib_entry_op op, + u16 virtual_router, u8 prefix_len, + unsigned char *addr, + struct mlxsw_sp_fib_entry_priv *priv) { - struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; - enum mlxsw_reg_ralxx_protocol proto; - u32 *p_dip; + struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv; + enum mlxsw_reg_ralxx_protocol ralxx_proto; + char *ralue_pl = op_ctx_basic->ralue_pl; + enum mlxsw_reg_ralue_op ralue_op; - proto = (enum mlxsw_reg_ralxx_protocol) fib->proto; + ralxx_proto = (enum mlxsw_reg_ralxx_protocol) proto; - switch (fib->proto) { + switch (op) { + case MLXSW_SP_FIB_ENTRY_OP_WRITE: + case MLXSW_SP_FIB_ENTRY_OP_UPDATE: + ralue_op = MLXSW_REG_RALUE_OP_WRITE_WRITE; + break; + case MLXSW_SP_FIB_ENTRY_OP_DELETE: + ralue_op = MLXSW_REG_RALUE_OP_WRITE_DELETE; + break; + default: + WARN_ON_ONCE(1); + return; + } + + switch (proto) { case MLXSW_SP_L3_PROTO_IPV4: - p_dip = (u32 *) fib_entry->fib_node->key.addr; - mlxsw_reg_ralue_pack4(ralue_pl, proto, op, fib->vr->id, - fib_entry->fib_node->key.prefix_len, - *p_dip); + mlxsw_reg_ralue_pack4(ralue_pl, ralxx_proto, ralue_op, + virtual_router, prefix_len, (u32 *) addr); break; case MLXSW_SP_L3_PROTO_IPV6: - mlxsw_reg_ralue_pack6(ralue_pl, proto, op, fib->vr->id, - fib_entry->fib_node->key.prefix_len, - fib_entry->fib_node->key.addr); + mlxsw_reg_ralue_pack6(ralue_pl, ralxx_proto, ralue_op, + virtual_router, prefix_len, addr); break; } } -static int mlxsw_sp_adj_discard_write(struct mlxsw_sp *mlxsw_sp, u16 rif_index) +static void +mlxsw_sp_router_ll_basic_fib_entry_act_remote_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + enum mlxsw_reg_ralue_trap_action trap_action, + u16 trap_id, u32 adjacency_index, u16 ecmp_size) +{ + struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv; + + mlxsw_reg_ralue_act_remote_pack(op_ctx_basic->ralue_pl, trap_action, + trap_id, adjacency_index, ecmp_size); +} + +static void +mlxsw_sp_router_ll_basic_fib_entry_act_local_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + enum mlxsw_reg_ralue_trap_action trap_action, + u16 trap_id, u16 local_erif) +{ + struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv; + + mlxsw_reg_ralue_act_local_pack(op_ctx_basic->ralue_pl, trap_action, + trap_id, local_erif); +} + +static void +mlxsw_sp_router_ll_basic_fib_entry_act_ip2me_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx) +{ + struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv; + + mlxsw_reg_ralue_act_ip2me_pack(op_ctx_basic->ralue_pl); +} + +static void +mlxsw_sp_router_ll_basic_fib_entry_act_ip2me_tun_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + u32 tunnel_ptr) +{ + struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv; + + mlxsw_reg_ralue_act_ip2me_tun_pack(op_ctx_basic->ralue_pl, tunnel_ptr); +} + +static int +mlxsw_sp_router_ll_basic_fib_entry_commit(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + bool *postponed_for_bulk) +{ + struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv; + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), + op_ctx_basic->ralue_pl); +} + +static bool +mlxsw_sp_router_ll_basic_fib_entry_is_committed(struct mlxsw_sp_fib_entry_priv *priv) +{ + return true; +} + +static void mlxsw_sp_fib_entry_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_sp_fib_entry_op op) +{ + struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; + + mlxsw_sp_fib_entry_op_ctx_priv_hold(op_ctx, fib_entry->priv); + fib->ll_ops->fib_entry_pack(op_ctx, fib->proto, op, fib->vr->id, + fib_entry->fib_node->key.prefix_len, + fib_entry->fib_node->key.addr, + fib_entry->priv); +} + +static int mlxsw_sp_fib_entry_commit(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + const struct mlxsw_sp_router_ll_ops *ll_ops) +{ + bool postponed_for_bulk = false; + int err; + + err = ll_ops->fib_entry_commit(mlxsw_sp, op_ctx, &postponed_for_bulk); + if (!postponed_for_bulk) + mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); + return err; +} + +static int mlxsw_sp_adj_discard_write(struct mlxsw_sp *mlxsw_sp) { enum mlxsw_reg_ratr_trap_action trap_action; char ratr_pl[MLXSW_REG_RATR_LEN]; @@ -4318,11 +5179,13 @@ static int mlxsw_sp_adj_discard_write(struct mlxsw_sp *mlxsw_sp, u16 rif_index) if (err) return err; - trap_action = MLXSW_REG_RATR_TRAP_ACTION_DISCARD_ERRORS; + trap_action = MLXSW_REG_RATR_TRAP_ACTION_TRAP; mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, true, MLXSW_REG_RATR_TYPE_ETHERNET, - mlxsw_sp->router->adj_discard_index, rif_index); + mlxsw_sp->router->adj_discard_index, + mlxsw_sp->router->lb_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); if (err) goto err_ratr_write; @@ -4338,11 +5201,13 @@ err_ratr_write: } static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) + enum mlxsw_sp_fib_entry_op op) { + const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; struct mlxsw_sp_nexthop_group *nh_group = fib_entry->nh_group; - char ralue_pl[MLXSW_REG_RALUE_LEN]; + struct mlxsw_sp_nexthop_group_info *nhgi = nh_group->nhgi; enum mlxsw_reg_ralue_trap_action trap_action; u16 trap_id = 0; u32 adjacency_index = 0; @@ -4355,12 +5220,10 @@ static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, */ if (mlxsw_sp_fib_entry_should_offload(fib_entry)) { trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP; - adjacency_index = fib_entry->nh_group->adj_index; - ecmp_size = fib_entry->nh_group->ecmp_size; - } else if (!nh_group->adj_index_valid && nh_group->count && - nh_group->nh_rif) { - err = mlxsw_sp_adj_discard_write(mlxsw_sp, - nh_group->nh_rif->rif_index); + adjacency_index = nhgi->adj_index; + ecmp_size = nhgi->ecmp_size; + } else if (!nhgi->adj_index_valid && nhgi->count && nhgi->nh_rif) { + err = mlxsw_sp_adj_discard_write(mlxsw_sp); if (err) return err; trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP; @@ -4371,19 +5234,20 @@ static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, trap_id = MLXSW_TRAP_ID_RTR_INGRESS0; } - mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); - mlxsw_reg_ralue_act_remote_pack(ralue_pl, trap_action, trap_id, - adjacency_index, ecmp_size); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); + mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); + ll_ops->fib_entry_act_remote_pack(op_ctx, trap_action, trap_id, + adjacency_index, ecmp_size); + return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); } static int mlxsw_sp_fib_entry_op_local(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) + enum mlxsw_sp_fib_entry_op op) { - struct mlxsw_sp_rif *rif = fib_entry->nh_group->nh_rif; + const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; + struct mlxsw_sp_rif *rif = fib_entry->nh_group->nhgi->nh_rif; enum mlxsw_reg_ralue_trap_action trap_action; - char ralue_pl[MLXSW_REG_RALUE_LEN]; u16 trap_id = 0; u16 rif_index = 0; @@ -4395,111 +5259,124 @@ static int mlxsw_sp_fib_entry_op_local(struct mlxsw_sp *mlxsw_sp, trap_id = MLXSW_TRAP_ID_RTR_INGRESS0; } - mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); - mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, - rif_index); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); + mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); + ll_ops->fib_entry_act_local_pack(op_ctx, trap_action, trap_id, rif_index); + return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); } static int mlxsw_sp_fib_entry_op_trap(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) + enum mlxsw_sp_fib_entry_op op) { - char ralue_pl[MLXSW_REG_RALUE_LEN]; + const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; - mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); - mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); + mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); + ll_ops->fib_entry_act_ip2me_pack(op_ctx); + return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); } static int mlxsw_sp_fib_entry_op_blackhole(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) + enum mlxsw_sp_fib_entry_op op) { + const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; enum mlxsw_reg_ralue_trap_action trap_action; - char ralue_pl[MLXSW_REG_RALUE_LEN]; trap_action = MLXSW_REG_RALUE_TRAP_ACTION_DISCARD_ERROR; - mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); - mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, 0, 0); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); + mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); + ll_ops->fib_entry_act_local_pack(op_ctx, trap_action, 0, 0); + return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); } static int mlxsw_sp_fib_entry_op_unreachable(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) + enum mlxsw_sp_fib_entry_op op) { + const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; enum mlxsw_reg_ralue_trap_action trap_action; - char ralue_pl[MLXSW_REG_RALUE_LEN]; u16 trap_id; trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP; trap_id = MLXSW_TRAP_ID_RTR_INGRESS1; - mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); - mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, 0); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); + mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); + ll_ops->fib_entry_act_local_pack(op_ctx, trap_action, trap_id, 0); + return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); } static int mlxsw_sp_fib_entry_op_ipip_decap(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) + enum mlxsw_sp_fib_entry_op op) { + const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; struct mlxsw_sp_ipip_entry *ipip_entry = fib_entry->decap.ipip_entry; const struct mlxsw_sp_ipip_ops *ipip_ops; + int err; if (WARN_ON(!ipip_entry)) return -EINVAL; ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]; - return ipip_ops->fib_entry_op(mlxsw_sp, ipip_entry, op, - fib_entry->decap.tunnel_index); + err = ipip_ops->decap_config(mlxsw_sp, ipip_entry, + fib_entry->decap.tunnel_index); + if (err) + return err; + + mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); + ll_ops->fib_entry_act_ip2me_tun_pack(op_ctx, + fib_entry->decap.tunnel_index); + return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); } static int mlxsw_sp_fib_entry_op_nve_decap(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) + enum mlxsw_sp_fib_entry_op op) { - char ralue_pl[MLXSW_REG_RALUE_LEN]; + const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; - mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); - mlxsw_reg_ralue_act_ip2me_tun_pack(ralue_pl, - fib_entry->decap.tunnel_index); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); + mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); + ll_ops->fib_entry_act_ip2me_tun_pack(op_ctx, + fib_entry->decap.tunnel_index); + return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); } static int __mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) + enum mlxsw_sp_fib_entry_op op) { switch (fib_entry->type) { case MLXSW_SP_FIB_ENTRY_TYPE_REMOTE: - return mlxsw_sp_fib_entry_op_remote(mlxsw_sp, fib_entry, op); + return mlxsw_sp_fib_entry_op_remote(mlxsw_sp, op_ctx, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL: - return mlxsw_sp_fib_entry_op_local(mlxsw_sp, fib_entry, op); + return mlxsw_sp_fib_entry_op_local(mlxsw_sp, op_ctx, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_TRAP: - return mlxsw_sp_fib_entry_op_trap(mlxsw_sp, fib_entry, op); + return mlxsw_sp_fib_entry_op_trap(mlxsw_sp, op_ctx, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE: - return mlxsw_sp_fib_entry_op_blackhole(mlxsw_sp, fib_entry, op); + return mlxsw_sp_fib_entry_op_blackhole(mlxsw_sp, op_ctx, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE: - return mlxsw_sp_fib_entry_op_unreachable(mlxsw_sp, fib_entry, - op); + return mlxsw_sp_fib_entry_op_unreachable(mlxsw_sp, op_ctx, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP: - return mlxsw_sp_fib_entry_op_ipip_decap(mlxsw_sp, - fib_entry, op); + return mlxsw_sp_fib_entry_op_ipip_decap(mlxsw_sp, op_ctx, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP: - return mlxsw_sp_fib_entry_op_nve_decap(mlxsw_sp, fib_entry, op); + return mlxsw_sp_fib_entry_op_nve_decap(mlxsw_sp, op_ctx, fib_entry, op); } return -EINVAL; } static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) + enum mlxsw_sp_fib_entry_op op) { - int err = __mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, op); + int err = __mlxsw_sp_fib_entry_op(mlxsw_sp, op_ctx, fib_entry, op); if (err) return err; @@ -4509,18 +5386,35 @@ static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, return err; } +static int __mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + struct mlxsw_sp_fib_entry *fib_entry, + bool is_new) +{ + return mlxsw_sp_fib_entry_op(mlxsw_sp, op_ctx, fib_entry, + is_new ? MLXSW_SP_FIB_ENTRY_OP_WRITE : + MLXSW_SP_FIB_ENTRY_OP_UPDATE); +} + static int mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry) { - return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, - MLXSW_REG_RALUE_OP_WRITE_WRITE); + struct mlxsw_sp_fib_entry_op_ctx *op_ctx = mlxsw_sp->router->ll_op_ctx; + + mlxsw_sp_fib_entry_op_ctx_clear(op_ctx); + return __mlxsw_sp_fib_entry_update(mlxsw_sp, op_ctx, fib_entry, false); } static int mlxsw_sp_fib_entry_del(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry) { - return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, - MLXSW_REG_RALUE_OP_WRITE_DELETE); + const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; + + if (!ll_ops->fib_entry_is_committed(fib_entry->priv)) + return 0; + return mlxsw_sp_fib_entry_op(mlxsw_sp, op_ctx, fib_entry, + MLXSW_SP_FIB_ENTRY_OP_DELETE); } static int @@ -4528,17 +5422,17 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, const struct fib_entry_notifier_info *fen_info, struct mlxsw_sp_fib_entry *fib_entry) { - struct net_device *dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev; + struct mlxsw_sp_nexthop_group_info *nhgi = fib_entry->nh_group->nhgi; union mlxsw_sp_l3addr dip = { .addr4 = htonl(fen_info->dst) }; struct mlxsw_sp_router *router = mlxsw_sp->router; u32 tb_id = mlxsw_sp_fix_tb_id(fen_info->tb_id); + int ifindex = nhgi->nexthops[0].ifindex; struct mlxsw_sp_ipip_entry *ipip_entry; - struct fib_info *fi = fen_info->fi; switch (fen_info->type) { case RTN_LOCAL: - ipip_entry = mlxsw_sp_ipip_entry_find_by_decap(mlxsw_sp, dev, - MLXSW_SP_L3_PROTO_IPV4, dip); + ipip_entry = mlxsw_sp_ipip_entry_find_by_decap(mlxsw_sp, ifindex, + MLXSW_SP_L3_PROTO_IPV4, dip); if (ipip_entry && ipip_entry->ol_dev->flags & IFF_UP) { fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP; return mlxsw_sp_fib_entry_decap_init(mlxsw_sp, @@ -4571,7 +5465,7 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE; return 0; case RTN_UNICAST: - if (mlxsw_sp_fi_is_gateway(mlxsw_sp, fi)) + if (nhgi->gateway) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; else fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; @@ -4608,15 +5502,27 @@ mlxsw_sp_fib4_entry_create(struct mlxsw_sp *mlxsw_sp, return ERR_PTR(-ENOMEM); fib_entry = &fib4_entry->common; - err = mlxsw_sp_fib4_entry_type_set(mlxsw_sp, fen_info, fib_entry); - if (err) - goto err_fib4_entry_type_set; + fib_entry->priv = mlxsw_sp_fib_entry_priv_create(fib_node->fib->ll_ops); + if (IS_ERR(fib_entry->priv)) { + err = PTR_ERR(fib_entry->priv); + goto err_fib_entry_priv_create; + } err = mlxsw_sp_nexthop4_group_get(mlxsw_sp, fib_entry, fen_info->fi); if (err) goto err_nexthop4_group_get; - fib4_entry->prio = fen_info->fi->fib_priority; + err = mlxsw_sp_nexthop_group_vr_link(fib_entry->nh_group, + fib_node->fib); + if (err) + goto err_nexthop_group_vr_link; + + err = mlxsw_sp_fib4_entry_type_set(mlxsw_sp, fen_info, fib_entry); + if (err) + goto err_fib4_entry_type_set; + + fib4_entry->fi = fen_info->fi; + fib_info_hold(fib4_entry->fi); fib4_entry->tb_id = fen_info->tb_id; fib4_entry->type = fen_info->type; fib4_entry->tos = fen_info->tos; @@ -4625,9 +5531,13 @@ mlxsw_sp_fib4_entry_create(struct mlxsw_sp *mlxsw_sp, return fib4_entry; -err_nexthop4_group_get: - mlxsw_sp_fib4_entry_type_unset(mlxsw_sp, fib_entry); err_fib4_entry_type_set: + mlxsw_sp_nexthop_group_vr_unlink(fib_entry->nh_group, fib_node->fib); +err_nexthop_group_vr_link: + mlxsw_sp_nexthop4_group_put(mlxsw_sp, &fib4_entry->common); +err_nexthop4_group_get: + mlxsw_sp_fib_entry_priv_put(fib_entry->priv); +err_fib_entry_priv_create: kfree(fib4_entry); return ERR_PTR(err); } @@ -4635,8 +5545,14 @@ err_fib4_entry_type_set: static void mlxsw_sp_fib4_entry_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib4_entry *fib4_entry) { - mlxsw_sp_nexthop4_group_put(mlxsw_sp, &fib4_entry->common); + struct mlxsw_sp_fib_node *fib_node = fib4_entry->common.fib_node; + + fib_info_put(fib4_entry->fi); mlxsw_sp_fib4_entry_type_unset(mlxsw_sp, &fib4_entry->common); + mlxsw_sp_nexthop_group_vr_unlink(fib4_entry->common.nh_group, + fib_node->fib); + mlxsw_sp_nexthop4_group_put(mlxsw_sp, &fib4_entry->common); + mlxsw_sp_fib_entry_priv_put(fib4_entry->common.priv); kfree(fib4_entry); } @@ -4665,8 +5581,7 @@ mlxsw_sp_fib4_entry_lookup(struct mlxsw_sp *mlxsw_sp, if (fib4_entry->tb_id == fen_info->tb_id && fib4_entry->tos == fen_info->tos && fib4_entry->type == fen_info->type && - mlxsw_sp_nexthop4_group_fi(fib4_entry->common.nh_group) == - fen_info->fi) + fib4_entry->fi == fen_info->fi) return fib4_entry; return NULL; @@ -4875,14 +5790,16 @@ static void mlxsw_sp_fib_node_put(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_fib_node_entry_link(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry) { struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node; + bool is_new = !fib_node->fib_entry; int err; fib_node->fib_entry = fib_entry; - err = mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry); + err = __mlxsw_sp_fib_entry_update(mlxsw_sp, op_ctx, fib_entry, is_new); if (err) goto err_fib_entry_update; @@ -4893,14 +5810,25 @@ err_fib_entry_update: return err; } -static void -mlxsw_sp_fib_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry) +static int __mlxsw_sp_fib_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + struct mlxsw_sp_fib_entry *fib_entry) { struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node; + int err; - mlxsw_sp_fib_entry_del(mlxsw_sp, fib_entry); + err = mlxsw_sp_fib_entry_del(mlxsw_sp, op_ctx, fib_entry); fib_node->fib_entry = NULL; + return err; +} + +static void mlxsw_sp_fib_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) +{ + struct mlxsw_sp_fib_entry_op_ctx *op_ctx = mlxsw_sp->router->ll_op_ctx; + + mlxsw_sp_fib_entry_op_ctx_clear(op_ctx); + __mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, op_ctx, fib_entry); } static bool mlxsw_sp_fib4_allow_replace(struct mlxsw_sp_fib4_entry *fib4_entry) @@ -4922,6 +5850,7 @@ static bool mlxsw_sp_fib4_allow_replace(struct mlxsw_sp_fib4_entry *fib4_entry) static int mlxsw_sp_router_fib4_replace(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, const struct fib_entry_notifier_info *fen_info) { struct mlxsw_sp_fib4_entry *fib4_entry, *fib4_replaced; @@ -4955,7 +5884,7 @@ mlxsw_sp_router_fib4_replace(struct mlxsw_sp *mlxsw_sp, } replaced = fib_node->fib_entry; - err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, &fib4_entry->common); + err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, op_ctx, &fib4_entry->common); if (err) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to link FIB entry to node\n"); goto err_fib_node_entry_link; @@ -4980,23 +5909,26 @@ err_fib4_entry_create: return err; } -static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, - struct fib_entry_notifier_info *fen_info) +static int mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + struct fib_entry_notifier_info *fen_info) { struct mlxsw_sp_fib4_entry *fib4_entry; struct mlxsw_sp_fib_node *fib_node; + int err; if (mlxsw_sp->router->aborted) - return; + return 0; fib4_entry = mlxsw_sp_fib4_entry_lookup(mlxsw_sp, fen_info); if (!fib4_entry) - return; + return 0; fib_node = fib4_entry->common.fib_node; - mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, &fib4_entry->common); + err = __mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, op_ctx, &fib4_entry->common); mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib4_entry); mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); + return err; } static bool mlxsw_sp_fib6_rt_should_ignore(const struct fib6_info *rt) @@ -5047,7 +5979,8 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6) { struct fib6_nh *fib6_nh = mlxsw_sp_rt6->rt->fib6_nh; - fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD; + if (!mlxsw_sp_rt6->rt->nh) + fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD; mlxsw_sp_rt6_release(mlxsw_sp_rt6->rt); kfree(mlxsw_sp_rt6); } @@ -5081,51 +6014,6 @@ static bool mlxsw_sp_nexthop6_ipip_type(const struct mlxsw_sp *mlxsw_sp, mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->fib6_nh->fib_nh_dev, ret); } -static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop_group *nh_grp, - struct mlxsw_sp_nexthop *nh, - const struct fib6_info *rt) -{ - const struct mlxsw_sp_ipip_ops *ipip_ops; - struct mlxsw_sp_ipip_entry *ipip_entry; - struct net_device *dev = rt->fib6_nh->fib_nh_dev; - struct mlxsw_sp_rif *rif; - int err; - - ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, dev); - if (ipip_entry) { - ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]; - if (ipip_ops->can_offload(mlxsw_sp, dev, - MLXSW_SP_L3_PROTO_IPV6)) { - nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP; - mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, ipip_entry); - return 0; - } - } - - nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH; - rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); - if (!rif) - return 0; - mlxsw_sp_nexthop_rif_init(nh, rif); - - err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh); - if (err) - goto err_nexthop_neigh_init; - - return 0; - -err_nexthop_neigh_init: - mlxsw_sp_nexthop_rif_fini(nh); - return err; -} - -static void mlxsw_sp_nexthop6_type_fini(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop *nh) -{ - mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh); -} - static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp, struct mlxsw_sp_nexthop *nh, @@ -5133,9 +6021,12 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp, { struct net_device *dev = rt->fib6_nh->fib_nh_dev; - nh->nh_grp = nh_grp; + nh->nhgi = nh_grp->nhgi; nh->nh_weight = rt->fib6_nh->fib_nh_weight; memcpy(&nh->gw_addr, &rt->fib6_nh->fib_nh_gw6, sizeof(nh->gw_addr)); +#if IS_ENABLED(CONFIG_IPV6) + nh->neigh_tbl = &nd_tbl; +#endif mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh); list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list); @@ -5144,13 +6035,13 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp, return 0; nh->ifindex = dev->ifindex; - return mlxsw_sp_nexthop6_type_init(mlxsw_sp, nh_grp, nh, rt); + return mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, dev); } static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh) { - mlxsw_sp_nexthop6_type_fini(mlxsw_sp, nh); + mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh); list_del(&nh->router_list_node); mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); } @@ -5162,51 +6053,105 @@ static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, NULL); } -static struct mlxsw_sp_nexthop_group * -mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib6_entry *fib6_entry) +static int +mlxsw_sp_nexthop6_group_info_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp, + struct mlxsw_sp_fib6_entry *fib6_entry) { - struct mlxsw_sp_nexthop_group *nh_grp; + struct mlxsw_sp_nexthop_group_info *nhgi; struct mlxsw_sp_rt6 *mlxsw_sp_rt6; struct mlxsw_sp_nexthop *nh; - int i = 0; - int err; + int err, i; - nh_grp = kzalloc(struct_size(nh_grp, nexthops, fib6_entry->nrt6), - GFP_KERNEL); - if (!nh_grp) - return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(&nh_grp->fib_list); -#if IS_ENABLED(CONFIG_IPV6) - nh_grp->neigh_tbl = &nd_tbl; -#endif + nhgi = kzalloc(struct_size(nhgi, nexthops, fib6_entry->nrt6), + GFP_KERNEL); + if (!nhgi) + return -ENOMEM; + nh_grp->nhgi = nhgi; + nhgi->nh_grp = nh_grp; mlxsw_sp_rt6 = list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6, list); - nh_grp->gateway = mlxsw_sp_rt6_is_gateway(mlxsw_sp, mlxsw_sp_rt6->rt); - nh_grp->count = fib6_entry->nrt6; - for (i = 0; i < nh_grp->count; i++) { + nhgi->gateway = mlxsw_sp_rt6_is_gateway(mlxsw_sp, mlxsw_sp_rt6->rt); + nhgi->count = fib6_entry->nrt6; + for (i = 0; i < nhgi->count; i++) { struct fib6_info *rt = mlxsw_sp_rt6->rt; - nh = &nh_grp->nexthops[i]; + nh = &nhgi->nexthops[i]; err = mlxsw_sp_nexthop6_init(mlxsw_sp, nh_grp, nh, rt); if (err) goto err_nexthop6_init; mlxsw_sp_rt6 = list_next_entry(mlxsw_sp_rt6, list); } + nh_grp->nhgi = nhgi; + err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); + if (err) + goto err_group_refresh; + + return 0; + +err_group_refresh: + i = nhgi->count; +err_nexthop6_init: + for (i--; i >= 0; i--) { + nh = &nhgi->nexthops[i]; + mlxsw_sp_nexthop6_fini(mlxsw_sp, nh); + } + kfree(nhgi); + return err; +} + +static void +mlxsw_sp_nexthop6_group_info_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp) +{ + struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi; + int i; + + for (i = nhgi->count - 1; i >= 0; i--) { + struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i]; + + mlxsw_sp_nexthop6_fini(mlxsw_sp, nh); + } + mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); + WARN_ON_ONCE(nhgi->adj_index_valid); + kfree(nhgi); +} + +static struct mlxsw_sp_nexthop_group * +mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry) +{ + struct mlxsw_sp_nexthop_group *nh_grp; + int err; + + nh_grp = kzalloc(sizeof(*nh_grp), GFP_KERNEL); + if (!nh_grp) + return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&nh_grp->vr_list); + err = rhashtable_init(&nh_grp->vr_ht, + &mlxsw_sp_nexthop_group_vr_ht_params); + if (err) + goto err_nexthop_group_vr_ht_init; + INIT_LIST_HEAD(&nh_grp->fib_list); + nh_grp->type = MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6; + + err = mlxsw_sp_nexthop6_group_info_init(mlxsw_sp, nh_grp, fib6_entry); + if (err) + goto err_nexthop_group_info_init; err = mlxsw_sp_nexthop_group_insert(mlxsw_sp, nh_grp); if (err) goto err_nexthop_group_insert; - mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); + nh_grp->can_destroy = true; + return nh_grp; err_nexthop_group_insert: -err_nexthop6_init: - for (i--; i >= 0; i--) { - nh = &nh_grp->nexthops[i]; - mlxsw_sp_nexthop6_fini(mlxsw_sp, nh); - } + mlxsw_sp_nexthop6_group_info_fini(mlxsw_sp, nh_grp); +err_nexthop_group_info_init: + rhashtable_destroy(&nh_grp->vr_ht); +err_nexthop_group_vr_ht_init: kfree(nh_grp); return ERR_PTR(err); } @@ -5215,24 +6160,29 @@ static void mlxsw_sp_nexthop6_group_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp) { - struct mlxsw_sp_nexthop *nh; - int i = nh_grp->count; - + if (!nh_grp->can_destroy) + return; mlxsw_sp_nexthop_group_remove(mlxsw_sp, nh_grp); - for (i--; i >= 0; i--) { - nh = &nh_grp->nexthops[i]; - mlxsw_sp_nexthop6_fini(mlxsw_sp, nh); - } - mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); - WARN_ON(nh_grp->adj_index_valid); + mlxsw_sp_nexthop6_group_info_fini(mlxsw_sp, nh_grp); + WARN_ON_ONCE(!list_empty(&nh_grp->vr_list)); + rhashtable_destroy(&nh_grp->vr_ht); kfree(nh_grp); } static int mlxsw_sp_nexthop6_group_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib6_entry *fib6_entry) { + struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry); struct mlxsw_sp_nexthop_group *nh_grp; + if (rt->nh) { + nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, + rt->nh->id); + if (WARN_ON_ONCE(!nh_grp)) + return -EINVAL; + goto out; + } + nh_grp = mlxsw_sp_nexthop6_group_lookup(mlxsw_sp, fib6_entry); if (!nh_grp) { nh_grp = mlxsw_sp_nexthop6_group_create(mlxsw_sp, fib6_entry); @@ -5240,15 +6190,16 @@ static int mlxsw_sp_nexthop6_group_get(struct mlxsw_sp *mlxsw_sp, return PTR_ERR(nh_grp); } - list_add_tail(&fib6_entry->common.nexthop_group_node, - &nh_grp->fib_list); - fib6_entry->common.nh_group = nh_grp; - /* The route and the nexthop are described by the same struct, so we * need to the update the nexthop offload indication for the new route. */ __mlxsw_sp_nexthop6_group_offload_refresh(nh_grp, fib6_entry); +out: + list_add_tail(&fib6_entry->common.nexthop_group_node, + &nh_grp->fib_list); + fib6_entry->common.nh_group = nh_grp; + return 0; } @@ -5260,16 +6211,24 @@ static void mlxsw_sp_nexthop6_group_put(struct mlxsw_sp *mlxsw_sp, list_del(&fib_entry->nexthop_group_node); if (!list_empty(&nh_grp->fib_list)) return; + + if (nh_grp->type == MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ) { + mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp); + return; + } + mlxsw_sp_nexthop6_group_destroy(mlxsw_sp, nh_grp); } -static int -mlxsw_sp_nexthop6_group_update(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib6_entry *fib6_entry) +static int mlxsw_sp_nexthop6_group_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + struct mlxsw_sp_fib6_entry *fib6_entry) { struct mlxsw_sp_nexthop_group *old_nh_grp = fib6_entry->common.nh_group; + struct mlxsw_sp_fib_node *fib_node = fib6_entry->common.fib_node; int err; + mlxsw_sp_nexthop_group_vr_unlink(old_nh_grp, fib_node->fib); fib6_entry->common.nh_group = NULL; list_del(&fib6_entry->common.nexthop_group_node); @@ -5277,11 +6236,17 @@ mlxsw_sp_nexthop6_group_update(struct mlxsw_sp *mlxsw_sp, if (err) goto err_nexthop6_group_get; + err = mlxsw_sp_nexthop_group_vr_link(fib6_entry->common.nh_group, + fib_node->fib); + if (err) + goto err_nexthop_group_vr_link; + /* In case this entry is offloaded, then the adjacency index * currently associated with it in the device's table is that * of the old group. Start using the new one instead. */ - err = mlxsw_sp_fib_entry_update(mlxsw_sp, &fib6_entry->common); + err = __mlxsw_sp_fib_entry_update(mlxsw_sp, op_ctx, + &fib6_entry->common, false); if (err) goto err_fib_entry_update; @@ -5291,16 +6256,21 @@ mlxsw_sp_nexthop6_group_update(struct mlxsw_sp *mlxsw_sp, return 0; err_fib_entry_update: + mlxsw_sp_nexthop_group_vr_unlink(fib6_entry->common.nh_group, + fib_node->fib); +err_nexthop_group_vr_link: mlxsw_sp_nexthop6_group_put(mlxsw_sp, &fib6_entry->common); err_nexthop6_group_get: list_add_tail(&fib6_entry->common.nexthop_group_node, &old_nh_grp->fib_list); fib6_entry->common.nh_group = old_nh_grp; + mlxsw_sp_nexthop_group_vr_link(old_nh_grp, fib_node->fib); return err; } static int mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib6_entry *fib6_entry, struct fib6_info **rt_arr, unsigned int nrt6) { @@ -5318,7 +6288,7 @@ mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp, fib6_entry->nrt6++; } - err = mlxsw_sp_nexthop6_group_update(mlxsw_sp, fib6_entry); + err = mlxsw_sp_nexthop6_group_update(mlxsw_sp, op_ctx, fib6_entry); if (err) goto err_nexthop6_group_update; @@ -5339,6 +6309,7 @@ err_rt6_create: static void mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib6_entry *fib6_entry, struct fib6_info **rt_arr, unsigned int nrt6) { @@ -5356,26 +6327,20 @@ mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); } - mlxsw_sp_nexthop6_group_update(mlxsw_sp, fib6_entry); + mlxsw_sp_nexthop6_group_update(mlxsw_sp, op_ctx, fib6_entry); } static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, const struct fib6_info *rt) { - /* Packets hitting RTF_REJECT routes need to be discarded by the - * stack. We can rely on their destination device not having a - * RIF (it's the loopback device) and can thus use action type - * local, which will cause them to be trapped with a lower - * priority than packets that need to be locally received. - */ if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; else if (rt->fib6_type == RTN_BLACKHOLE) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE; else if (rt->fib6_flags & RTF_REJECT) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE; - else if (mlxsw_sp_rt6_is_gateway(mlxsw_sp, rt)) + else if (fib_entry->nh_group->nhgi->gateway) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; else fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; @@ -5409,6 +6374,12 @@ mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp, return ERR_PTR(-ENOMEM); fib_entry = &fib6_entry->common; + fib_entry->priv = mlxsw_sp_fib_entry_priv_create(fib_node->fib->ll_ops); + if (IS_ERR(fib_entry->priv)) { + err = PTR_ERR(fib_entry->priv); + goto err_fib_entry_priv_create; + } + INIT_LIST_HEAD(&fib6_entry->rt6_list); for (i = 0; i < nrt6; i++) { @@ -5421,16 +6392,23 @@ mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp, fib6_entry->nrt6++; } - mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, rt_arr[0]); - err = mlxsw_sp_nexthop6_group_get(mlxsw_sp, fib6_entry); if (err) goto err_nexthop6_group_get; + err = mlxsw_sp_nexthop_group_vr_link(fib_entry->nh_group, + fib_node->fib); + if (err) + goto err_nexthop_group_vr_link; + + mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, rt_arr[0]); + fib_entry->fib_node = fib_node; return fib6_entry; +err_nexthop_group_vr_link: + mlxsw_sp_nexthop6_group_put(mlxsw_sp, fib_entry); err_nexthop6_group_get: i = nrt6; err_rt6_create: @@ -5441,6 +6419,8 @@ err_rt6_create: list_del(&mlxsw_sp_rt6->list); mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); } + mlxsw_sp_fib_entry_priv_put(fib_entry->priv); +err_fib_entry_priv_create: kfree(fib6_entry); return ERR_PTR(err); } @@ -5448,9 +6428,14 @@ err_rt6_create: static void mlxsw_sp_fib6_entry_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib6_entry *fib6_entry) { + struct mlxsw_sp_fib_node *fib_node = fib6_entry->common.fib_node; + + mlxsw_sp_nexthop_group_vr_unlink(fib6_entry->common.nh_group, + fib_node->fib); mlxsw_sp_nexthop6_group_put(mlxsw_sp, &fib6_entry->common); mlxsw_sp_fib6_entry_rt_destroy_all(fib6_entry); WARN_ON(fib6_entry->nrt6); + mlxsw_sp_fib_entry_priv_put(fib6_entry->common.priv); kfree(fib6_entry); } @@ -5508,8 +6493,8 @@ static bool mlxsw_sp_fib6_allow_replace(struct mlxsw_sp_fib6_entry *fib6_entry) } static int mlxsw_sp_router_fib6_replace(struct mlxsw_sp *mlxsw_sp, - struct fib6_info **rt_arr, - unsigned int nrt6) + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + struct fib6_info **rt_arr, unsigned int nrt6) { struct mlxsw_sp_fib6_entry *fib6_entry, *fib6_replaced; struct mlxsw_sp_fib_entry *replaced; @@ -5548,7 +6533,7 @@ static int mlxsw_sp_router_fib6_replace(struct mlxsw_sp *mlxsw_sp, } replaced = fib_node->fib_entry; - err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, &fib6_entry->common); + err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, op_ctx, &fib6_entry->common); if (err) goto err_fib_node_entry_link; @@ -5572,8 +6557,8 @@ err_fib6_entry_create: } static int mlxsw_sp_router_fib6_append(struct mlxsw_sp *mlxsw_sp, - struct fib6_info **rt_arr, - unsigned int nrt6) + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + struct fib6_info **rt_arr, unsigned int nrt6) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; @@ -5604,8 +6589,7 @@ static int mlxsw_sp_router_fib6_append(struct mlxsw_sp *mlxsw_sp, fib6_entry = container_of(fib_node->fib_entry, struct mlxsw_sp_fib6_entry, common); - err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, fib6_entry, rt_arr, - nrt6); + err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, op_ctx, fib6_entry, rt_arr, nrt6); if (err) goto err_fib6_entry_nexthop_add; @@ -5616,19 +6600,20 @@ err_fib6_entry_nexthop_add: return err; } -static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, - struct fib6_info **rt_arr, - unsigned int nrt6) +static int mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + struct fib6_info **rt_arr, unsigned int nrt6) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; struct fib6_info *rt = rt_arr[0]; + int err; if (mlxsw_sp->router->aborted) - return; + return 0; if (mlxsw_sp_fib6_rt_should_ignore(rt)) - return; + return 0; /* Multipath routes are first added to the FIB trie and only then * notified. If we vetoed the addition, we will get a delete @@ -5637,58 +6622,66 @@ static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, */ fib6_entry = mlxsw_sp_fib6_entry_lookup(mlxsw_sp, rt); if (!fib6_entry) - return; + return 0; /* If not all the nexthops are deleted, then only reduce the nexthop * group. */ if (nrt6 != fib6_entry->nrt6) { - mlxsw_sp_fib6_entry_nexthop_del(mlxsw_sp, fib6_entry, rt_arr, - nrt6); - return; + mlxsw_sp_fib6_entry_nexthop_del(mlxsw_sp, op_ctx, fib6_entry, rt_arr, nrt6); + return 0; } fib_node = fib6_entry->common.fib_node; - mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, &fib6_entry->common); + err = __mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, op_ctx, &fib6_entry->common); mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_entry); mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); + return err; } static int __mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp, - enum mlxsw_reg_ralxx_protocol proto, + enum mlxsw_sp_l3proto proto, u8 tree_id) { - char ralta_pl[MLXSW_REG_RALTA_LEN]; - char ralst_pl[MLXSW_REG_RALST_LEN]; + const struct mlxsw_sp_router_ll_ops *ll_ops = mlxsw_sp->router->proto_ll_ops[proto]; + enum mlxsw_reg_ralxx_protocol ralxx_proto = + (enum mlxsw_reg_ralxx_protocol) proto; + struct mlxsw_sp_fib_entry_priv *priv; + char xralta_pl[MLXSW_REG_XRALTA_LEN]; + char xralst_pl[MLXSW_REG_XRALST_LEN]; int i, err; - mlxsw_reg_ralta_pack(ralta_pl, true, proto, tree_id); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); + mlxsw_reg_xralta_pack(xralta_pl, true, ralxx_proto, tree_id); + err = ll_ops->ralta_write(mlxsw_sp, xralta_pl); if (err) return err; - mlxsw_reg_ralst_pack(ralst_pl, 0xff, tree_id); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), ralst_pl); + mlxsw_reg_xralst_pack(xralst_pl, 0xff, tree_id); + err = ll_ops->ralst_write(mlxsw_sp, xralst_pl); if (err) return err; for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + struct mlxsw_sp_fib_entry_op_ctx *op_ctx = mlxsw_sp->router->ll_op_ctx; struct mlxsw_sp_vr *vr = &mlxsw_sp->router->vrs[i]; - char raltb_pl[MLXSW_REG_RALTB_LEN]; - char ralue_pl[MLXSW_REG_RALUE_LEN]; + char xraltb_pl[MLXSW_REG_XRALTB_LEN]; - mlxsw_reg_raltb_pack(raltb_pl, vr->id, proto, tree_id); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), - raltb_pl); + mlxsw_sp_fib_entry_op_ctx_clear(op_ctx); + mlxsw_reg_xraltb_pack(xraltb_pl, vr->id, ralxx_proto, tree_id); + err = ll_ops->raltb_write(mlxsw_sp, xraltb_pl); if (err) return err; - mlxsw_reg_ralue_pack(ralue_pl, proto, - MLXSW_REG_RALUE_OP_WRITE_WRITE, vr->id, 0); - mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), - ralue_pl); + priv = mlxsw_sp_fib_entry_priv_create(ll_ops); + if (IS_ERR(priv)) + return PTR_ERR(priv); + + ll_ops->fib_entry_pack(op_ctx, proto, MLXSW_SP_FIB_ENTRY_OP_WRITE, + vr->id, 0, NULL, priv); + ll_ops->fib_entry_act_ip2me_pack(op_ctx); + err = ll_ops->fib_entry_commit(mlxsw_sp, op_ctx, NULL); + mlxsw_sp_fib_entry_priv_put(priv); if (err) return err; } @@ -5784,7 +6777,7 @@ mlxsw_sp_router_fibmr_vif_del(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) { - enum mlxsw_reg_ralxx_protocol proto = MLXSW_REG_RALXX_PROTOCOL_IPV4; + enum mlxsw_sp_l3proto proto = MLXSW_SP_L3_PROTO_IPV4; int err; err = __mlxsw_sp_router_set_abort_trap(mlxsw_sp, proto, @@ -5796,7 +6789,7 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) * packets that don't match any routes are trapped to the CPU. */ - proto = MLXSW_REG_RALXX_PROTOCOL_IPV6; + proto = MLXSW_SP_L3_PROTO_IPV6; return __mlxsw_sp_router_set_abort_trap(mlxsw_sp, proto, MLXSW_SP_LPM_TREE_MIN + 1); } @@ -5901,15 +6894,15 @@ static void mlxsw_sp_router_fib_abort(struct mlxsw_sp *mlxsw_sp) dev_warn(mlxsw_sp->bus_info->dev, "Failed to set abort trap.\n"); } -struct mlxsw_sp_fib6_event_work { +struct mlxsw_sp_fib6_event { struct fib6_info **rt_arr; unsigned int nrt6; }; -struct mlxsw_sp_fib_event_work { - struct work_struct work; +struct mlxsw_sp_fib_event { + struct list_head list; /* node in fib queue */ union { - struct mlxsw_sp_fib6_event_work fib6_work; + struct mlxsw_sp_fib6_event fib6_event; struct fib_entry_notifier_info fen_info; struct fib_rule_notifier_info fr_info; struct fib_nh_notifier_info fnh_info; @@ -5918,11 +6911,12 @@ struct mlxsw_sp_fib_event_work { }; struct mlxsw_sp *mlxsw_sp; unsigned long event; + int family; }; static int -mlxsw_sp_router_fib6_work_init(struct mlxsw_sp_fib6_event_work *fib6_work, - struct fib6_entry_notifier_info *fen6_info) +mlxsw_sp_router_fib6_event_init(struct mlxsw_sp_fib6_event *fib6_event, + struct fib6_entry_notifier_info *fen6_info) { struct fib6_info *rt = fen6_info->rt; struct fib6_info **rt_arr; @@ -5936,8 +6930,8 @@ mlxsw_sp_router_fib6_work_init(struct mlxsw_sp_fib6_event_work *fib6_work, if (!rt_arr) return -ENOMEM; - fib6_work->rt_arr = rt_arr; - fib6_work->nrt6 = nrt6; + fib6_event->rt_arr = rt_arr; + fib6_event->nrt6 = nrt6; rt_arr[0] = rt; fib6_info_hold(rt); @@ -5959,170 +6953,233 @@ mlxsw_sp_router_fib6_work_init(struct mlxsw_sp_fib6_event_work *fib6_work, } static void -mlxsw_sp_router_fib6_work_fini(struct mlxsw_sp_fib6_event_work *fib6_work) +mlxsw_sp_router_fib6_event_fini(struct mlxsw_sp_fib6_event *fib6_event) { int i; - for (i = 0; i < fib6_work->nrt6; i++) - mlxsw_sp_rt6_release(fib6_work->rt_arr[i]); - kfree(fib6_work->rt_arr); + for (i = 0; i < fib6_event->nrt6; i++) + mlxsw_sp_rt6_release(fib6_event->rt_arr[i]); + kfree(fib6_event->rt_arr); } -static void mlxsw_sp_router_fib4_event_work(struct work_struct *work) +static void mlxsw_sp_router_fib4_event_process(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + struct mlxsw_sp_fib_event *fib_event) { - struct mlxsw_sp_fib_event_work *fib_work = - container_of(work, struct mlxsw_sp_fib_event_work, work); - struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; int err; - mutex_lock(&mlxsw_sp->router->lock); mlxsw_sp_span_respin(mlxsw_sp); - switch (fib_work->event) { + switch (fib_event->event) { case FIB_EVENT_ENTRY_REPLACE: - err = mlxsw_sp_router_fib4_replace(mlxsw_sp, - &fib_work->fen_info); - if (err) + err = mlxsw_sp_router_fib4_replace(mlxsw_sp, op_ctx, &fib_event->fen_info); + if (err) { + mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); mlxsw_sp_router_fib_abort(mlxsw_sp); - fib_info_put(fib_work->fen_info.fi); + } + fib_info_put(fib_event->fen_info.fi); break; case FIB_EVENT_ENTRY_DEL: - mlxsw_sp_router_fib4_del(mlxsw_sp, &fib_work->fen_info); - fib_info_put(fib_work->fen_info.fi); + err = mlxsw_sp_router_fib4_del(mlxsw_sp, op_ctx, &fib_event->fen_info); + if (err) + mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); + fib_info_put(fib_event->fen_info.fi); break; case FIB_EVENT_NH_ADD: case FIB_EVENT_NH_DEL: - mlxsw_sp_nexthop4_event(mlxsw_sp, fib_work->event, - fib_work->fnh_info.fib_nh); - fib_info_put(fib_work->fnh_info.fib_nh->nh_parent); + mlxsw_sp_nexthop4_event(mlxsw_sp, fib_event->event, fib_event->fnh_info.fib_nh); + fib_info_put(fib_event->fnh_info.fib_nh->nh_parent); break; } - mutex_unlock(&mlxsw_sp->router->lock); - kfree(fib_work); } -static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) +static void mlxsw_sp_router_fib6_event_process(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + struct mlxsw_sp_fib_event *fib_event) { - struct mlxsw_sp_fib_event_work *fib_work = - container_of(work, struct mlxsw_sp_fib_event_work, work); - struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; int err; - mutex_lock(&mlxsw_sp->router->lock); mlxsw_sp_span_respin(mlxsw_sp); - switch (fib_work->event) { + switch (fib_event->event) { case FIB_EVENT_ENTRY_REPLACE: - err = mlxsw_sp_router_fib6_replace(mlxsw_sp, - fib_work->fib6_work.rt_arr, - fib_work->fib6_work.nrt6); - if (err) + err = mlxsw_sp_router_fib6_replace(mlxsw_sp, op_ctx, fib_event->fib6_event.rt_arr, + fib_event->fib6_event.nrt6); + if (err) { + mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); mlxsw_sp_router_fib_abort(mlxsw_sp); - mlxsw_sp_router_fib6_work_fini(&fib_work->fib6_work); + } + mlxsw_sp_router_fib6_event_fini(&fib_event->fib6_event); break; case FIB_EVENT_ENTRY_APPEND: - err = mlxsw_sp_router_fib6_append(mlxsw_sp, - fib_work->fib6_work.rt_arr, - fib_work->fib6_work.nrt6); - if (err) + err = mlxsw_sp_router_fib6_append(mlxsw_sp, op_ctx, fib_event->fib6_event.rt_arr, + fib_event->fib6_event.nrt6); + if (err) { + mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); mlxsw_sp_router_fib_abort(mlxsw_sp); - mlxsw_sp_router_fib6_work_fini(&fib_work->fib6_work); + } + mlxsw_sp_router_fib6_event_fini(&fib_event->fib6_event); break; case FIB_EVENT_ENTRY_DEL: - mlxsw_sp_router_fib6_del(mlxsw_sp, - fib_work->fib6_work.rt_arr, - fib_work->fib6_work.nrt6); - mlxsw_sp_router_fib6_work_fini(&fib_work->fib6_work); + err = mlxsw_sp_router_fib6_del(mlxsw_sp, op_ctx, fib_event->fib6_event.rt_arr, + fib_event->fib6_event.nrt6); + if (err) + mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); + mlxsw_sp_router_fib6_event_fini(&fib_event->fib6_event); break; } - mutex_unlock(&mlxsw_sp->router->lock); - kfree(fib_work); } -static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work) +static void mlxsw_sp_router_fibmr_event_process(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_event *fib_event) { - struct mlxsw_sp_fib_event_work *fib_work = - container_of(work, struct mlxsw_sp_fib_event_work, work); - struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; bool replace; int err; rtnl_lock(); mutex_lock(&mlxsw_sp->router->lock); - switch (fib_work->event) { + switch (fib_event->event) { case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_ADD: - replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE; + replace = fib_event->event == FIB_EVENT_ENTRY_REPLACE; - err = mlxsw_sp_router_fibmr_add(mlxsw_sp, &fib_work->men_info, - replace); + err = mlxsw_sp_router_fibmr_add(mlxsw_sp, &fib_event->men_info, replace); if (err) mlxsw_sp_router_fib_abort(mlxsw_sp); - mr_cache_put(fib_work->men_info.mfc); + mr_cache_put(fib_event->men_info.mfc); break; case FIB_EVENT_ENTRY_DEL: - mlxsw_sp_router_fibmr_del(mlxsw_sp, &fib_work->men_info); - mr_cache_put(fib_work->men_info.mfc); + mlxsw_sp_router_fibmr_del(mlxsw_sp, &fib_event->men_info); + mr_cache_put(fib_event->men_info.mfc); break; case FIB_EVENT_VIF_ADD: err = mlxsw_sp_router_fibmr_vif_add(mlxsw_sp, - &fib_work->ven_info); + &fib_event->ven_info); if (err) mlxsw_sp_router_fib_abort(mlxsw_sp); - dev_put(fib_work->ven_info.dev); + dev_put(fib_event->ven_info.dev); break; case FIB_EVENT_VIF_DEL: - mlxsw_sp_router_fibmr_vif_del(mlxsw_sp, - &fib_work->ven_info); - dev_put(fib_work->ven_info.dev); + mlxsw_sp_router_fibmr_vif_del(mlxsw_sp, &fib_event->ven_info); + dev_put(fib_event->ven_info.dev); break; } mutex_unlock(&mlxsw_sp->router->lock); rtnl_unlock(); - kfree(fib_work); } -static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work, +static void mlxsw_sp_router_fib_event_work(struct work_struct *work) +{ + struct mlxsw_sp_router *router = container_of(work, struct mlxsw_sp_router, fib_event_work); + struct mlxsw_sp_fib_entry_op_ctx *op_ctx = router->ll_op_ctx; + struct mlxsw_sp *mlxsw_sp = router->mlxsw_sp; + struct mlxsw_sp_fib_event *next_fib_event; + struct mlxsw_sp_fib_event *fib_event; + int last_family = AF_UNSPEC; + LIST_HEAD(fib_event_queue); + + spin_lock_bh(&router->fib_event_queue_lock); + list_splice_init(&router->fib_event_queue, &fib_event_queue); + spin_unlock_bh(&router->fib_event_queue_lock); + + /* Router lock is held here to make sure per-instance + * operation context is not used in between FIB4/6 events + * processing. + */ + mutex_lock(&router->lock); + mlxsw_sp_fib_entry_op_ctx_clear(op_ctx); + list_for_each_entry_safe(fib_event, next_fib_event, + &fib_event_queue, list) { + /* Check if the next entry in the queue exists and it is + * of the same type (family and event) as the currect one. + * In that case it is permitted to do the bulking + * of multiple FIB entries to a single register write. + */ + op_ctx->bulk_ok = !list_is_last(&fib_event->list, &fib_event_queue) && + fib_event->family == next_fib_event->family && + fib_event->event == next_fib_event->event; + op_ctx->event = fib_event->event; + + /* In case family of this and the previous entry are different, context + * reinitialization is going to be needed now, indicate that. + * Note that since last_family is initialized to AF_UNSPEC, this is always + * going to happen for the first entry processed in the work. + */ + if (fib_event->family != last_family) + op_ctx->initialized = false; + + switch (fib_event->family) { + case AF_INET: + mlxsw_sp_router_fib4_event_process(mlxsw_sp, op_ctx, + fib_event); + break; + case AF_INET6: + mlxsw_sp_router_fib6_event_process(mlxsw_sp, op_ctx, + fib_event); + break; + case RTNL_FAMILY_IP6MR: + case RTNL_FAMILY_IPMR: + /* Unlock here as inside FIBMR the lock is taken again + * under RTNL. The per-instance operation context + * is not used by FIBMR. + */ + mutex_unlock(&router->lock); + mlxsw_sp_router_fibmr_event_process(mlxsw_sp, + fib_event); + mutex_lock(&router->lock); + break; + default: + WARN_ON_ONCE(1); + } + last_family = fib_event->family; + kfree(fib_event); + cond_resched(); + } + WARN_ON_ONCE(!list_empty(&router->ll_op_ctx->fib_entry_priv_list)); + mutex_unlock(&router->lock); +} + +static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event *fib_event, struct fib_notifier_info *info) { struct fib_entry_notifier_info *fen_info; struct fib_nh_notifier_info *fnh_info; - switch (fib_work->event) { + switch (fib_event->event) { case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_DEL: fen_info = container_of(info, struct fib_entry_notifier_info, info); - fib_work->fen_info = *fen_info; + fib_event->fen_info = *fen_info; /* Take reference on fib_info to prevent it from being - * freed while work is queued. Release it afterwards. + * freed while event is queued. Release it afterwards. */ - fib_info_hold(fib_work->fen_info.fi); + fib_info_hold(fib_event->fen_info.fi); break; case FIB_EVENT_NH_ADD: case FIB_EVENT_NH_DEL: fnh_info = container_of(info, struct fib_nh_notifier_info, info); - fib_work->fnh_info = *fnh_info; - fib_info_hold(fib_work->fnh_info.fib_nh->nh_parent); + fib_event->fnh_info = *fnh_info; + fib_info_hold(fib_event->fnh_info.fib_nh->nh_parent); break; } } -static int mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work, +static int mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event *fib_event, struct fib_notifier_info *info) { struct fib6_entry_notifier_info *fen6_info; int err; - switch (fib_work->event) { + switch (fib_event->event) { case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_APPEND: case FIB_EVENT_ENTRY_DEL: fen6_info = container_of(info, struct fib6_entry_notifier_info, info); - err = mlxsw_sp_router_fib6_work_init(&fib_work->fib6_work, - fen6_info); + err = mlxsw_sp_router_fib6_event_init(&fib_event->fib6_event, + fen6_info); if (err) return err; break; @@ -6132,20 +7189,20 @@ static int mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work, } static void -mlxsw_sp_router_fibmr_event(struct mlxsw_sp_fib_event_work *fib_work, +mlxsw_sp_router_fibmr_event(struct mlxsw_sp_fib_event *fib_event, struct fib_notifier_info *info) { - switch (fib_work->event) { + switch (fib_event->event) { case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_ADD: case FIB_EVENT_ENTRY_DEL: - memcpy(&fib_work->men_info, info, sizeof(fib_work->men_info)); - mr_cache_hold(fib_work->men_info.mfc); + memcpy(&fib_event->men_info, info, sizeof(fib_event->men_info)); + mr_cache_hold(fib_event->men_info.mfc); break; case FIB_EVENT_VIF_ADD: case FIB_EVENT_VIF_DEL: - memcpy(&fib_work->ven_info, info, sizeof(fib_work->ven_info)); - dev_hold(fib_work->ven_info.dev); + memcpy(&fib_event->ven_info, info, sizeof(fib_event->ven_info)); + dev_hold(fib_event->ven_info.dev); break; } } @@ -6202,7 +7259,7 @@ static int mlxsw_sp_router_fib_rule_event(unsigned long event, static int mlxsw_sp_router_fib_event(struct notifier_block *nb, unsigned long event, void *ptr) { - struct mlxsw_sp_fib_event_work *fib_work; + struct mlxsw_sp_fib_event *fib_event; struct fib_notifier_info *info = ptr; struct mlxsw_sp_router *router; int err; @@ -6234,55 +7291,43 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported"); return notifier_from_errno(-EINVAL); } - if (fen_info->fi->nh) { - NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported"); - return notifier_from_errno(-EINVAL); - } - } else if (info->family == AF_INET6) { - struct fib6_entry_notifier_info *fen6_info; - - fen6_info = container_of(info, - struct fib6_entry_notifier_info, - info); - if (fen6_info->rt->nh) { - NL_SET_ERR_MSG_MOD(info->extack, "IPv6 route with nexthop objects is not supported"); - return notifier_from_errno(-EINVAL); - } } break; } - fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC); - if (!fib_work) + fib_event = kzalloc(sizeof(*fib_event), GFP_ATOMIC); + if (!fib_event) return NOTIFY_BAD; - fib_work->mlxsw_sp = router->mlxsw_sp; - fib_work->event = event; + fib_event->mlxsw_sp = router->mlxsw_sp; + fib_event->event = event; + fib_event->family = info->family; switch (info->family) { case AF_INET: - INIT_WORK(&fib_work->work, mlxsw_sp_router_fib4_event_work); - mlxsw_sp_router_fib4_event(fib_work, info); + mlxsw_sp_router_fib4_event(fib_event, info); break; case AF_INET6: - INIT_WORK(&fib_work->work, mlxsw_sp_router_fib6_event_work); - err = mlxsw_sp_router_fib6_event(fib_work, info); + err = mlxsw_sp_router_fib6_event(fib_event, info); if (err) goto err_fib_event; break; case RTNL_FAMILY_IP6MR: case RTNL_FAMILY_IPMR: - INIT_WORK(&fib_work->work, mlxsw_sp_router_fibmr_event_work); - mlxsw_sp_router_fibmr_event(fib_work, info); + mlxsw_sp_router_fibmr_event(fib_event, info); break; } - mlxsw_core_schedule_work(&fib_work->work); + /* Enqueue the event and trigger the work */ + spin_lock_bh(&router->fib_event_queue_lock); + list_add_tail(&fib_event->list, &router->fib_event_queue); + spin_unlock_bh(&router->fib_event_queue_lock); + mlxsw_core_schedule_work(&router->fib_event_work); return NOTIFY_DONE; err_fib_event: - kfree(fib_work); + kfree(fib_event); return NOTIFY_BAD; } @@ -6671,9 +7716,9 @@ static void mlxsw_sp_rif_subport_put(struct mlxsw_sp_rif *rif) } static 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) +__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) { struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port; struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; @@ -6738,6 +7783,27 @@ __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) +{ + 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; + + err = __mlxsw_sp_port_vlan_router_join(mlxsw_sp_port_vlan, l3_dev, + extack); +out: + mutex_unlock(&mlxsw_sp->router->lock); + return err; +} + void mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan) { @@ -6762,8 +7828,8 @@ static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev, switch (event) { case NETDEV_UP: - return mlxsw_sp_port_vlan_router_join(mlxsw_sp_port_vlan, - l3_dev, extack); + return __mlxsw_sp_port_vlan_router_join(mlxsw_sp_port_vlan, + l3_dev, extack); case NETDEV_DOWN: __mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan); break; @@ -6831,6 +7897,15 @@ static int mlxsw_sp_inetaddr_bridge_event(struct mlxsw_sp *mlxsw_sp, switch (event) { case NETDEV_UP: + if (netif_is_bridge_master(l3_dev) && br_vlan_enabled(l3_dev)) { + u16 proto; + + br_vlan_get_proto(l3_dev, &proto); + if (proto == ETH_P_8021AD) { + NL_SET_ERR_MSG_MOD(extack, "Adding an IP address to 802.1ad bridge is not supported"); + return -EOPNOTSUPP; + } + } rif = mlxsw_sp_rif_create(mlxsw_sp, ¶ms, extack); if (IS_ERR(rif)) return PTR_ERR(rif); @@ -8057,6 +9132,70 @@ static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); } +static const struct mlxsw_sp_router_ll_ops mlxsw_sp_router_ll_basic_ops = { + .init = mlxsw_sp_router_ll_basic_init, + .ralta_write = mlxsw_sp_router_ll_basic_ralta_write, + .ralst_write = mlxsw_sp_router_ll_basic_ralst_write, + .raltb_write = mlxsw_sp_router_ll_basic_raltb_write, + .fib_entry_op_ctx_size = sizeof(struct mlxsw_sp_fib_entry_op_ctx_basic), + .fib_entry_pack = mlxsw_sp_router_ll_basic_fib_entry_pack, + .fib_entry_act_remote_pack = mlxsw_sp_router_ll_basic_fib_entry_act_remote_pack, + .fib_entry_act_local_pack = mlxsw_sp_router_ll_basic_fib_entry_act_local_pack, + .fib_entry_act_ip2me_pack = mlxsw_sp_router_ll_basic_fib_entry_act_ip2me_pack, + .fib_entry_act_ip2me_tun_pack = mlxsw_sp_router_ll_basic_fib_entry_act_ip2me_tun_pack, + .fib_entry_commit = mlxsw_sp_router_ll_basic_fib_entry_commit, + .fib_entry_is_committed = mlxsw_sp_router_ll_basic_fib_entry_is_committed, +}; + +static int mlxsw_sp_router_ll_op_ctx_init(struct mlxsw_sp_router *router) +{ + size_t max_size = 0; + int i; + + for (i = 0; i < MLXSW_SP_L3_PROTO_MAX; i++) { + size_t size = router->proto_ll_ops[i]->fib_entry_op_ctx_size; + + if (size > max_size) + max_size = size; + } + router->ll_op_ctx = kzalloc(sizeof(*router->ll_op_ctx) + max_size, + GFP_KERNEL); + if (!router->ll_op_ctx) + return -ENOMEM; + INIT_LIST_HEAD(&router->ll_op_ctx->fib_entry_priv_list); + return 0; +} + +static void mlxsw_sp_router_ll_op_ctx_fini(struct mlxsw_sp_router *router) +{ + WARN_ON(!list_empty(&router->ll_op_ctx->fib_entry_priv_list)); + kfree(router->ll_op_ctx); +} + +static int mlxsw_sp_lb_rif_init(struct mlxsw_sp *mlxsw_sp) +{ + u16 lb_rif_index; + int err; + + /* 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. + */ + 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; + + return 0; +} + +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); +} + int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, struct netlink_ext_ack *extack) { @@ -8070,6 +9209,19 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, mlxsw_sp->router = router; router->mlxsw_sp = mlxsw_sp; + err = mlxsw_sp_router_xm_init(mlxsw_sp); + if (err) + goto err_xm_init; + + router->proto_ll_ops[MLXSW_SP_L3_PROTO_IPV4] = mlxsw_sp_router_xm_ipv4_is_supported(mlxsw_sp) ? + &mlxsw_sp_router_ll_xm_ops : + &mlxsw_sp_router_ll_basic_ops; + router->proto_ll_ops[MLXSW_SP_L3_PROTO_IPV6] = &mlxsw_sp_router_ll_basic_ops; + + err = mlxsw_sp_router_ll_op_ctx_init(router); + if (err) + goto err_ll_op_ctx_init; + INIT_LIST_HEAD(&mlxsw_sp->router->nexthop_neighs_list); err = __mlxsw_sp_router_init(mlxsw_sp); if (err) @@ -8106,6 +9258,10 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_vrs_init; + err = mlxsw_sp_lb_rif_init(mlxsw_sp); + if (err) + goto err_lb_rif_init; + err = mlxsw_sp_neigh_init(mlxsw_sp); if (err) goto err_neigh_init; @@ -8118,6 +9274,10 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_dscp_init; + INIT_WORK(&router->fib_event_work, mlxsw_sp_router_fib_event_work); + INIT_LIST_HEAD(&router->fib_event_queue); + spin_lock_init(&router->fib_event_queue_lock); + router->inetaddr_nb.notifier_call = mlxsw_sp_inetaddr_event; err = register_inetaddr_notifier(&router->inetaddr_nb); if (err) @@ -8134,6 +9294,14 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_register_netevent_notifier; + mlxsw_sp->router->nexthop_nb.notifier_call = + mlxsw_sp_nexthop_obj_event; + err = register_nexthop_notifier(mlxsw_sp_net(mlxsw_sp), + &mlxsw_sp->router->nexthop_nb, + extack); + if (err) + goto err_register_nexthop_notifier; + mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event; err = register_fib_notifier(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->router->fib_nb, @@ -8144,6 +9312,9 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, return 0; err_register_fib_notifier: + unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp), + &mlxsw_sp->router->nexthop_nb); +err_register_nexthop_notifier: unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); err_register_netevent_notifier: unregister_inet6addr_notifier(&router->inet6addr_nb); @@ -8151,10 +9322,13 @@ err_register_inet6addr_notifier: unregister_inetaddr_notifier(&router->inetaddr_nb); err_register_inetaddr_notifier: mlxsw_core_flush_owq(); + WARN_ON(!list_empty(&router->fib_event_queue)); err_dscp_init: err_mp_hash_init: mlxsw_sp_neigh_fini(mlxsw_sp); err_neigh_init: + mlxsw_sp_lb_rif_fini(mlxsw_sp); +err_lb_rif_init: mlxsw_sp_vrs_fini(mlxsw_sp); err_vrs_init: mlxsw_sp_mr_fini(mlxsw_sp); @@ -8171,6 +9345,10 @@ err_ipips_init: err_rifs_init: __mlxsw_sp_router_fini(mlxsw_sp); err_router_init: + mlxsw_sp_router_ll_op_ctx_fini(router); +err_ll_op_ctx_init: + mlxsw_sp_router_xm_fini(mlxsw_sp); +err_xm_init: mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); return err; @@ -8180,11 +9358,15 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) { unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), &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); mlxsw_core_flush_owq(); + WARN_ON(!list_empty(&mlxsw_sp->router->fib_event_queue)); mlxsw_sp_neigh_fini(mlxsw_sp); + mlxsw_sp_lb_rif_fini(mlxsw_sp); mlxsw_sp_vrs_fini(mlxsw_sp); mlxsw_sp_mr_fini(mlxsw_sp); mlxsw_sp_lpm_fini(mlxsw_sp); @@ -8193,6 +9375,8 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_sp_ipips_fini(mlxsw_sp); mlxsw_sp_rifs_fini(mlxsw_sp); __mlxsw_sp_router_fini(mlxsw_sp); + mlxsw_sp_router_ll_op_ctx_fini(mlxsw_sp->router); + mlxsw_sp_router_xm_fini(mlxsw_sp); mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index 8418dc3ae967..2875ee8ec537 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -15,6 +15,27 @@ struct mlxsw_sp_router_nve_decap { u8 valid:1; }; +struct mlxsw_sp_fib_entry_op_ctx { + u8 bulk_ok:1, /* Indicate to the low-level op it is ok to bulk + * the actual entry with the one that is the next + * in queue. + */ + initialized:1; /* Bit that the low-level op sets in case + * the context priv is initialized. + */ + struct list_head fib_entry_priv_list; + unsigned long event; + unsigned long ll_priv[]; +}; + +static inline void +mlxsw_sp_fib_entry_op_ctx_clear(struct mlxsw_sp_fib_entry_op_ctx *op_ctx) +{ + WARN_ON_ONCE(!list_empty(&op_ctx->fib_entry_priv_list)); + memset(op_ctx, 0, sizeof(*op_ctx)); + INIT_LIST_HEAD(&op_ctx->fib_entry_priv_list); +} + struct mlxsw_sp_router { struct mlxsw_sp *mlxsw_sp; struct mlxsw_sp_rif **rifs; @@ -38,6 +59,7 @@ struct mlxsw_sp_router { struct list_head nexthop_neighs_list; struct list_head ipip_list; bool aborted; + struct notifier_block nexthop_nb; struct notifier_block fib_nb; struct notifier_block netevent_nb; struct notifier_block inetaddr_nb; @@ -48,6 +70,56 @@ struct mlxsw_sp_router { bool adj_discard_index_valid; struct mlxsw_sp_router_nve_decap nve_decap_config; struct mutex lock; /* Protects shared router resources */ + struct work_struct fib_event_work; + struct list_head fib_event_queue; + spinlock_t fib_event_queue_lock; /* Protects fib event queue list */ + /* One set of ops for each protocol: IPv4 and IPv6 */ + const struct mlxsw_sp_router_ll_ops *proto_ll_ops[MLXSW_SP_L3_PROTO_MAX]; + struct mlxsw_sp_fib_entry_op_ctx *ll_op_ctx; + u16 lb_rif_index; + struct mlxsw_sp_router_xm *xm; +}; + +struct mlxsw_sp_fib_entry_priv { + refcount_t refcnt; + struct list_head list; /* Member in op_ctx->fib_entry_priv_list */ + unsigned long priv[]; +}; + +enum mlxsw_sp_fib_entry_op { + MLXSW_SP_FIB_ENTRY_OP_WRITE, + MLXSW_SP_FIB_ENTRY_OP_UPDATE, + MLXSW_SP_FIB_ENTRY_OP_DELETE, +}; + +/* Low-level router ops. Basically this is to handle the different + * register sets to work with ordinary and XM trees and FIB entries. + */ +struct mlxsw_sp_router_ll_ops { + int (*init)(struct mlxsw_sp *mlxsw_sp, u16 vr_id, + enum mlxsw_sp_l3proto proto); + int (*ralta_write)(struct mlxsw_sp *mlxsw_sp, char *xralta_pl); + int (*ralst_write)(struct mlxsw_sp *mlxsw_sp, char *xralst_pl); + int (*raltb_write)(struct mlxsw_sp *mlxsw_sp, char *xraltb_pl); + size_t fib_entry_op_ctx_size; + size_t fib_entry_priv_size; + void (*fib_entry_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + enum mlxsw_sp_l3proto proto, enum mlxsw_sp_fib_entry_op op, + u16 virtual_router, u8 prefix_len, unsigned char *addr, + struct mlxsw_sp_fib_entry_priv *priv); + void (*fib_entry_act_remote_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + enum mlxsw_reg_ralue_trap_action trap_action, + u16 trap_id, u32 adjacency_index, u16 ecmp_size); + void (*fib_entry_act_local_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + enum mlxsw_reg_ralue_trap_action trap_action, + u16 trap_id, u16 local_erif); + void (*fib_entry_act_ip2me_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx); + void (*fib_entry_act_ip2me_tun_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + u32 tunnel_ptr); + int (*fib_entry_commit)(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + bool *postponed_for_bulk); + bool (*fib_entry_is_committed)(struct mlxsw_sp_fib_entry_priv *priv); }; struct mlxsw_sp_rif_ipip_lb; @@ -129,6 +201,7 @@ int mlxsw_sp_nexthop_indexes(struct mlxsw_sp_nexthop *nh, u32 *p_adj_index, u32 *p_adj_size, u32 *p_adj_hash_index); struct mlxsw_sp_rif *mlxsw_sp_nexthop_rif(struct mlxsw_sp_nexthop *nh); bool mlxsw_sp_nexthop_group_has_ipip(struct mlxsw_sp_nexthop *nh); +bool mlxsw_sp_nexthop_is_discard(const struct mlxsw_sp_nexthop *nh); #define mlxsw_sp_nexthop_for_each(nh, router) \ for (nh = mlxsw_sp_nexthop_next(router, NULL); nh; \ nh = mlxsw_sp_nexthop_next(router, nh)) @@ -150,4 +223,10 @@ static inline bool mlxsw_sp_l3addr_eq(const union mlxsw_sp_l3addr *addr1, int mlxsw_sp_ipip_ecn_encap_init(struct mlxsw_sp *mlxsw_sp); int mlxsw_sp_ipip_ecn_decap_init(struct mlxsw_sp *mlxsw_sp); +extern const struct mlxsw_sp_router_ll_ops mlxsw_sp_router_ll_xm_ops; + +int mlxsw_sp_router_xm_init(struct mlxsw_sp *mlxsw_sp); +void mlxsw_sp_router_xm_fini(struct mlxsw_sp *mlxsw_sp); +bool mlxsw_sp_router_xm_ipv4_is_supported(const struct mlxsw_sp *mlxsw_sp); + #endif /* _MLXSW_ROUTER_H_*/ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router_xm.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router_xm.c new file mode 100644 index 000000000000..d213af723a2a --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router_xm.c @@ -0,0 +1,812 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 +/* Copyright (c) 2020 Mellanox Technologies. All rights reserved */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/rhashtable.h> + +#include "spectrum.h" +#include "core.h" +#include "reg.h" +#include "spectrum_router.h" + +#define MLXSW_SP_ROUTER_XM_M_VAL 16 + +static const u8 mlxsw_sp_router_xm_m_val[] = { + [MLXSW_SP_L3_PROTO_IPV4] = MLXSW_SP_ROUTER_XM_M_VAL, + [MLXSW_SP_L3_PROTO_IPV6] = 0, /* Currently unused. */ +}; + +#define MLXSW_SP_ROUTER_XM_L_VAL_MAX 16 + +struct mlxsw_sp_router_xm { + bool ipv4_supported; + bool ipv6_supported; + unsigned int entries_size; + struct rhashtable ltable_ht; + struct rhashtable flush_ht; /* Stores items about to be flushed from cache */ + unsigned int flush_count; + bool flush_all_mode; +}; + +struct mlxsw_sp_router_xm_ltable_node { + struct rhash_head ht_node; /* Member of router_xm->ltable_ht */ + u16 mindex; + u8 current_lvalue; + refcount_t refcnt; + unsigned int lvalue_ref[MLXSW_SP_ROUTER_XM_L_VAL_MAX + 1]; +}; + +static const struct rhashtable_params mlxsw_sp_router_xm_ltable_ht_params = { + .key_offset = offsetof(struct mlxsw_sp_router_xm_ltable_node, mindex), + .head_offset = offsetof(struct mlxsw_sp_router_xm_ltable_node, ht_node), + .key_len = sizeof(u16), + .automatic_shrinking = true, +}; + +struct mlxsw_sp_router_xm_flush_info { + bool all; + enum mlxsw_sp_l3proto proto; + u16 virtual_router; + u8 prefix_len; + unsigned char addr[sizeof(struct in6_addr)]; +}; + +struct mlxsw_sp_router_xm_fib_entry { + bool committed; + struct mlxsw_sp_router_xm_ltable_node *ltable_node; /* Parent node */ + u16 mindex; /* Store for processing from commit op */ + u8 lvalue; + struct mlxsw_sp_router_xm_flush_info flush_info; +}; + +#define MLXSW_SP_ROUTE_LL_XM_ENTRIES_MAX \ + (MLXSW_REG_XMDR_TRANS_LEN / MLXSW_REG_XMDR_C_LT_ROUTE_V4_LEN) + +struct mlxsw_sp_fib_entry_op_ctx_xm { + bool initialized; + char xmdr_pl[MLXSW_REG_XMDR_LEN]; + unsigned int trans_offset; /* Offset of the current command within one + * transaction of XMDR register. + */ + unsigned int trans_item_len; /* The current command length. This is used + * to advance 'trans_offset' when the next + * command is appended. + */ + unsigned int entries_count; + struct mlxsw_sp_router_xm_fib_entry *entries[MLXSW_SP_ROUTE_LL_XM_ENTRIES_MAX]; +}; + +static int mlxsw_sp_router_ll_xm_init(struct mlxsw_sp *mlxsw_sp, u16 vr_id, + enum mlxsw_sp_l3proto proto) +{ + char rxlte_pl[MLXSW_REG_RXLTE_LEN]; + + mlxsw_reg_rxlte_pack(rxlte_pl, vr_id, + (enum mlxsw_reg_rxlte_protocol) proto, true); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rxlte), rxlte_pl); +} + +static int mlxsw_sp_router_ll_xm_ralta_write(struct mlxsw_sp *mlxsw_sp, char *xralta_pl) +{ + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(xralta), xralta_pl); +} + +static int mlxsw_sp_router_ll_xm_ralst_write(struct mlxsw_sp *mlxsw_sp, char *xralst_pl) +{ + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(xralst), xralst_pl); +} + +static int mlxsw_sp_router_ll_xm_raltb_write(struct mlxsw_sp *mlxsw_sp, char *xraltb_pl) +{ + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(xraltb), xraltb_pl); +} + +static u16 mlxsw_sp_router_ll_xm_mindex_get4(const u32 addr) +{ + /* Currently the M-index is set to linear mode. That means it is defined + * as 16 MSB of IP address. + */ + return addr >> MLXSW_SP_ROUTER_XM_L_VAL_MAX; +} + +static u16 mlxsw_sp_router_ll_xm_mindex_get6(const unsigned char *addr) +{ + WARN_ON_ONCE(1); + return 0; /* currently unused */ +} + +static void mlxsw_sp_router_ll_xm_op_ctx_check_init(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm) +{ + if (op_ctx->initialized) + return; + op_ctx->initialized = true; + + mlxsw_reg_xmdr_pack(op_ctx_xm->xmdr_pl, true); + op_ctx_xm->trans_offset = 0; + op_ctx_xm->entries_count = 0; +} + +static void mlxsw_sp_router_ll_xm_fib_entry_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + enum mlxsw_sp_l3proto proto, + enum mlxsw_sp_fib_entry_op op, + u16 virtual_router, u8 prefix_len, + unsigned char *addr, + struct mlxsw_sp_fib_entry_priv *priv) +{ + struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm = (void *) op_ctx->ll_priv; + struct mlxsw_sp_router_xm_fib_entry *fib_entry = (void *) priv->priv; + struct mlxsw_sp_router_xm_flush_info *flush_info; + enum mlxsw_reg_xmdr_c_ltr_op xmdr_c_ltr_op; + unsigned int len; + + mlxsw_sp_router_ll_xm_op_ctx_check_init(op_ctx, op_ctx_xm); + + switch (op) { + case MLXSW_SP_FIB_ENTRY_OP_WRITE: + xmdr_c_ltr_op = MLXSW_REG_XMDR_C_LTR_OP_WRITE; + break; + case MLXSW_SP_FIB_ENTRY_OP_UPDATE: + xmdr_c_ltr_op = MLXSW_REG_XMDR_C_LTR_OP_UPDATE; + break; + case MLXSW_SP_FIB_ENTRY_OP_DELETE: + xmdr_c_ltr_op = MLXSW_REG_XMDR_C_LTR_OP_DELETE; + break; + default: + WARN_ON_ONCE(1); + return; + } + + switch (proto) { + case MLXSW_SP_L3_PROTO_IPV4: + len = mlxsw_reg_xmdr_c_ltr_pack4(op_ctx_xm->xmdr_pl, op_ctx_xm->trans_offset, + op_ctx_xm->entries_count, xmdr_c_ltr_op, + virtual_router, prefix_len, (u32 *) addr); + fib_entry->mindex = mlxsw_sp_router_ll_xm_mindex_get4(*((u32 *) addr)); + break; + case MLXSW_SP_L3_PROTO_IPV6: + len = mlxsw_reg_xmdr_c_ltr_pack6(op_ctx_xm->xmdr_pl, op_ctx_xm->trans_offset, + op_ctx_xm->entries_count, xmdr_c_ltr_op, + virtual_router, prefix_len, addr); + fib_entry->mindex = mlxsw_sp_router_ll_xm_mindex_get6(addr); + break; + default: + WARN_ON_ONCE(1); + return; + } + if (!op_ctx_xm->trans_offset) + op_ctx_xm->trans_item_len = len; + else + WARN_ON_ONCE(op_ctx_xm->trans_item_len != len); + + op_ctx_xm->entries[op_ctx_xm->entries_count] = fib_entry; + + fib_entry->lvalue = prefix_len > mlxsw_sp_router_xm_m_val[proto] ? + prefix_len - mlxsw_sp_router_xm_m_val[proto] : 0; + + flush_info = &fib_entry->flush_info; + flush_info->proto = proto; + flush_info->virtual_router = virtual_router; + flush_info->prefix_len = prefix_len; + if (addr) + memcpy(flush_info->addr, addr, sizeof(flush_info->addr)); + else + memset(flush_info->addr, 0, sizeof(flush_info->addr)); +} + +static void +mlxsw_sp_router_ll_xm_fib_entry_act_remote_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + enum mlxsw_reg_ralue_trap_action trap_action, + u16 trap_id, u32 adjacency_index, u16 ecmp_size) +{ + struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm = (void *) op_ctx->ll_priv; + + mlxsw_reg_xmdr_c_ltr_act_remote_pack(op_ctx_xm->xmdr_pl, op_ctx_xm->trans_offset, + trap_action, trap_id, adjacency_index, ecmp_size); +} + +static void +mlxsw_sp_router_ll_xm_fib_entry_act_local_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + enum mlxsw_reg_ralue_trap_action trap_action, + u16 trap_id, u16 local_erif) +{ + struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm = (void *) op_ctx->ll_priv; + + mlxsw_reg_xmdr_c_ltr_act_local_pack(op_ctx_xm->xmdr_pl, op_ctx_xm->trans_offset, + trap_action, trap_id, local_erif); +} + +static void +mlxsw_sp_router_ll_xm_fib_entry_act_ip2me_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx) +{ + struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm = (void *) op_ctx->ll_priv; + + mlxsw_reg_xmdr_c_ltr_act_ip2me_pack(op_ctx_xm->xmdr_pl, op_ctx_xm->trans_offset); +} + +static void +mlxsw_sp_router_ll_xm_fib_entry_act_ip2me_tun_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + u32 tunnel_ptr) +{ + struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm = (void *) op_ctx->ll_priv; + + mlxsw_reg_xmdr_c_ltr_act_ip2me_tun_pack(op_ctx_xm->xmdr_pl, op_ctx_xm->trans_offset, + tunnel_ptr); +} + +static struct mlxsw_sp_router_xm_ltable_node * +mlxsw_sp_router_xm_ltable_node_get(struct mlxsw_sp_router_xm *router_xm, u16 mindex) +{ + struct mlxsw_sp_router_xm_ltable_node *ltable_node; + int err; + + ltable_node = rhashtable_lookup_fast(&router_xm->ltable_ht, &mindex, + mlxsw_sp_router_xm_ltable_ht_params); + if (ltable_node) { + refcount_inc(<able_node->refcnt); + return ltable_node; + } + ltable_node = kzalloc(sizeof(*ltable_node), GFP_KERNEL); + if (!ltable_node) + return ERR_PTR(-ENOMEM); + ltable_node->mindex = mindex; + refcount_set(<able_node->refcnt, 1); + + err = rhashtable_insert_fast(&router_xm->ltable_ht, <able_node->ht_node, + mlxsw_sp_router_xm_ltable_ht_params); + if (err) + goto err_insert; + + return ltable_node; + +err_insert: + kfree(ltable_node); + return ERR_PTR(err); +} + +static void mlxsw_sp_router_xm_ltable_node_put(struct mlxsw_sp_router_xm *router_xm, + struct mlxsw_sp_router_xm_ltable_node *ltable_node) +{ + if (!refcount_dec_and_test(<able_node->refcnt)) + return; + rhashtable_remove_fast(&router_xm->ltable_ht, <able_node->ht_node, + mlxsw_sp_router_xm_ltable_ht_params); + kfree(ltable_node); +} + +static int mlxsw_sp_router_xm_ltable_lvalue_set(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_router_xm_ltable_node *ltable_node) +{ + char xrmt_pl[MLXSW_REG_XRMT_LEN]; + + mlxsw_reg_xrmt_pack(xrmt_pl, ltable_node->mindex, ltable_node->current_lvalue); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(xrmt), xrmt_pl); +} + +struct mlxsw_sp_router_xm_flush_node { + struct rhash_head ht_node; /* Member of router_xm->flush_ht */ + struct list_head list; + struct mlxsw_sp_router_xm_flush_info flush_info; + struct delayed_work dw; + struct mlxsw_sp *mlxsw_sp; + unsigned long start_jiffies; + unsigned int reuses; /* By how many flush calls this was reused. */ + refcount_t refcnt; +}; + +static const struct rhashtable_params mlxsw_sp_router_xm_flush_ht_params = { + .key_offset = offsetof(struct mlxsw_sp_router_xm_flush_node, flush_info), + .head_offset = offsetof(struct mlxsw_sp_router_xm_flush_node, ht_node), + .key_len = sizeof(struct mlxsw_sp_router_xm_flush_info), + .automatic_shrinking = true, +}; + +static struct mlxsw_sp_router_xm_flush_node * +mlxsw_sp_router_xm_cache_flush_node_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_router_xm_flush_info *flush_info) +{ + struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; + struct mlxsw_sp_router_xm_flush_node *flush_node; + int err; + + flush_node = kzalloc(sizeof(*flush_node), GFP_KERNEL); + if (!flush_node) + return ERR_PTR(-ENOMEM); + + flush_node->flush_info = *flush_info; + err = rhashtable_insert_fast(&router_xm->flush_ht, &flush_node->ht_node, + mlxsw_sp_router_xm_flush_ht_params); + if (err) { + kfree(flush_node); + return ERR_PTR(err); + } + router_xm->flush_count++; + flush_node->mlxsw_sp = mlxsw_sp; + flush_node->start_jiffies = jiffies; + refcount_set(&flush_node->refcnt, 1); + return flush_node; +} + +static void +mlxsw_sp_router_xm_cache_flush_node_hold(struct mlxsw_sp_router_xm_flush_node *flush_node) +{ + if (!flush_node) + return; + refcount_inc(&flush_node->refcnt); +} + +static void +mlxsw_sp_router_xm_cache_flush_node_put(struct mlxsw_sp_router_xm_flush_node *flush_node) +{ + if (!flush_node || !refcount_dec_and_test(&flush_node->refcnt)) + return; + kfree(flush_node); +} + +static void +mlxsw_sp_router_xm_cache_flush_node_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_router_xm_flush_node *flush_node) +{ + struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; + + router_xm->flush_count--; + rhashtable_remove_fast(&router_xm->flush_ht, &flush_node->ht_node, + mlxsw_sp_router_xm_flush_ht_params); + mlxsw_sp_router_xm_cache_flush_node_put(flush_node); +} + +static u32 mlxsw_sp_router_xm_flush_mask4(u8 prefix_len) +{ + return GENMASK(31, 32 - prefix_len); +} + +static unsigned char *mlxsw_sp_router_xm_flush_mask6(u8 prefix_len) +{ + static unsigned char mask[sizeof(struct in6_addr)]; + + memset(mask, 0, sizeof(mask)); + memset(mask, 0xff, prefix_len / 8); + mask[prefix_len / 8] = GENMASK(8, 8 - prefix_len % 8); + return mask; +} + +#define MLXSW_SP_ROUTER_XM_CACHE_PARALLEL_FLUSHES_LIMIT 15 +#define MLXSW_SP_ROUTER_XM_CACHE_FLUSH_ALL_MIN_REUSES 15 +#define MLXSW_SP_ROUTER_XM_CACHE_DELAY 50 /* usecs */ +#define MLXSW_SP_ROUTER_XM_CACHE_MAX_WAIT (MLXSW_SP_ROUTER_XM_CACHE_DELAY * 10) + +static void mlxsw_sp_router_xm_cache_flush_work(struct work_struct *work) +{ + struct mlxsw_sp_router_xm_flush_info *flush_info; + struct mlxsw_sp_router_xm_flush_node *flush_node; + char rlcmld_pl[MLXSW_REG_RLCMLD_LEN]; + enum mlxsw_reg_rlcmld_select select; + struct mlxsw_sp *mlxsw_sp; + u32 addr4; + int err; + + flush_node = container_of(work, struct mlxsw_sp_router_xm_flush_node, + dw.work); + mlxsw_sp = flush_node->mlxsw_sp; + flush_info = &flush_node->flush_info; + + if (flush_info->all) { + char rlpmce_pl[MLXSW_REG_RLPMCE_LEN]; + + mlxsw_reg_rlpmce_pack(rlpmce_pl, true, false); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rlpmce), + rlpmce_pl); + if (err) + dev_err(mlxsw_sp->bus_info->dev, "Failed to flush XM cache\n"); + + if (flush_node->reuses < + MLXSW_SP_ROUTER_XM_CACHE_FLUSH_ALL_MIN_REUSES) + /* Leaving flush-all mode. */ + mlxsw_sp->router->xm->flush_all_mode = false; + goto out; + } + + select = MLXSW_REG_RLCMLD_SELECT_M_AND_ML_ENTRIES; + + switch (flush_info->proto) { + case MLXSW_SP_L3_PROTO_IPV4: + addr4 = *((u32 *) flush_info->addr); + addr4 &= mlxsw_sp_router_xm_flush_mask4(flush_info->prefix_len); + + /* In case the flush prefix length is bigger than M-value, + * it makes no sense to flush M entries. So just flush + * the ML entries. + */ + if (flush_info->prefix_len > MLXSW_SP_ROUTER_XM_M_VAL) + select = MLXSW_REG_RLCMLD_SELECT_ML_ENTRIES; + + mlxsw_reg_rlcmld_pack4(rlcmld_pl, select, + flush_info->virtual_router, addr4, + mlxsw_sp_router_xm_flush_mask4(flush_info->prefix_len)); + break; + case MLXSW_SP_L3_PROTO_IPV6: + mlxsw_reg_rlcmld_pack6(rlcmld_pl, select, + flush_info->virtual_router, flush_info->addr, + mlxsw_sp_router_xm_flush_mask6(flush_info->prefix_len)); + break; + default: + WARN_ON(true); + goto out; + } + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rlcmld), rlcmld_pl); + if (err) + dev_err(mlxsw_sp->bus_info->dev, "Failed to flush XM cache\n"); + +out: + mlxsw_sp_router_xm_cache_flush_node_destroy(mlxsw_sp, flush_node); +} + +static bool +mlxsw_sp_router_xm_cache_flush_may_cancel(struct mlxsw_sp_router_xm_flush_node *flush_node) +{ + unsigned long max_wait = usecs_to_jiffies(MLXSW_SP_ROUTER_XM_CACHE_MAX_WAIT); + unsigned long delay = usecs_to_jiffies(MLXSW_SP_ROUTER_XM_CACHE_DELAY); + + /* In case there is the same flushing work pending, check + * if we can consolidate with it. We can do it up to MAX_WAIT. + * Cancel the delayed work. If the work was still pending. + */ + if (time_is_before_jiffies(flush_node->start_jiffies + max_wait - delay) && + cancel_delayed_work_sync(&flush_node->dw)) + return true; + return false; +} + +static int +mlxsw_sp_router_xm_cache_flush_schedule(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_router_xm_flush_info *flush_info) +{ + unsigned long delay = usecs_to_jiffies(MLXSW_SP_ROUTER_XM_CACHE_DELAY); + struct mlxsw_sp_router_xm_flush_info flush_all_info = {.all = true}; + struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; + struct mlxsw_sp_router_xm_flush_node *flush_node; + + /* Check if the queued number of flushes reached critical amount after + * which it is better to just flush the whole cache. + */ + if (router_xm->flush_count == MLXSW_SP_ROUTER_XM_CACHE_PARALLEL_FLUSHES_LIMIT) + /* Entering flush-all mode. */ + router_xm->flush_all_mode = true; + + if (router_xm->flush_all_mode) + flush_info = &flush_all_info; + + rcu_read_lock(); + flush_node = rhashtable_lookup_fast(&router_xm->flush_ht, flush_info, + mlxsw_sp_router_xm_flush_ht_params); + /* Take a reference so the object is not freed before possible + * delayed work cancel could be done. + */ + mlxsw_sp_router_xm_cache_flush_node_hold(flush_node); + rcu_read_unlock(); + + if (flush_node && mlxsw_sp_router_xm_cache_flush_may_cancel(flush_node)) { + flush_node->reuses++; + mlxsw_sp_router_xm_cache_flush_node_put(flush_node); + /* Original work was within wait period and was canceled. + * That means that the reference is still held and the + * flush_node_put() call above did not free the flush_node. + * Reschedule it with fresh delay. + */ + goto schedule_work; + } else { + mlxsw_sp_router_xm_cache_flush_node_put(flush_node); + } + + flush_node = mlxsw_sp_router_xm_cache_flush_node_create(mlxsw_sp, flush_info); + if (IS_ERR(flush_node)) + return PTR_ERR(flush_node); + INIT_DELAYED_WORK(&flush_node->dw, mlxsw_sp_router_xm_cache_flush_work); + +schedule_work: + mlxsw_core_schedule_dw(&flush_node->dw, delay); + return 0; +} + +static int +mlxsw_sp_router_xm_ml_entry_add(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_router_xm_fib_entry *fib_entry) +{ + struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; + struct mlxsw_sp_router_xm_ltable_node *ltable_node; + u8 lvalue = fib_entry->lvalue; + int err; + + ltable_node = mlxsw_sp_router_xm_ltable_node_get(router_xm, + fib_entry->mindex); + if (IS_ERR(ltable_node)) + return PTR_ERR(ltable_node); + if (lvalue > ltable_node->current_lvalue) { + /* The L-value is bigger then the one currently set, update. */ + ltable_node->current_lvalue = lvalue; + err = mlxsw_sp_router_xm_ltable_lvalue_set(mlxsw_sp, + ltable_node); + if (err) + goto err_lvalue_set; + + /* The L value for prefix/M is increased. + * Therefore, all entries in M and ML caches matching + * {prefix/M, proto, VR} need to be flushed. Set the flush + * prefix length to M to achieve that. + */ + fib_entry->flush_info.prefix_len = MLXSW_SP_ROUTER_XM_M_VAL; + } + + ltable_node->lvalue_ref[lvalue]++; + fib_entry->ltable_node = ltable_node; + + return 0; + +err_lvalue_set: + mlxsw_sp_router_xm_ltable_node_put(router_xm, ltable_node); + return err; +} + +static void +mlxsw_sp_router_xm_ml_entry_del(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_router_xm_fib_entry *fib_entry) +{ + struct mlxsw_sp_router_xm_ltable_node *ltable_node = + fib_entry->ltable_node; + struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; + u8 lvalue = fib_entry->lvalue; + + ltable_node->lvalue_ref[lvalue]--; + if (lvalue == ltable_node->current_lvalue && lvalue && + !ltable_node->lvalue_ref[lvalue]) { + u8 new_lvalue = lvalue - 1; + + /* Find the biggest L-value left out there. */ + while (new_lvalue > 0 && !ltable_node->lvalue_ref[lvalue]) + new_lvalue--; + + ltable_node->current_lvalue = new_lvalue; + mlxsw_sp_router_xm_ltable_lvalue_set(mlxsw_sp, ltable_node); + + /* The L value for prefix/M is decreased. + * Therefore, all entries in M and ML caches matching + * {prefix/M, proto, VR} need to be flushed. Set the flush + * prefix length to M to achieve that. + */ + fib_entry->flush_info.prefix_len = MLXSW_SP_ROUTER_XM_M_VAL; + } + mlxsw_sp_router_xm_ltable_node_put(router_xm, ltable_node); +} + +static int +mlxsw_sp_router_xm_ml_entries_add(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm) +{ + struct mlxsw_sp_router_xm_fib_entry *fib_entry; + int err; + int i; + + for (i = 0; i < op_ctx_xm->entries_count; i++) { + fib_entry = op_ctx_xm->entries[i]; + err = mlxsw_sp_router_xm_ml_entry_add(mlxsw_sp, fib_entry); + if (err) + goto rollback; + } + return 0; + +rollback: + for (i--; i >= 0; i--) { + fib_entry = op_ctx_xm->entries[i]; + mlxsw_sp_router_xm_ml_entry_del(mlxsw_sp, fib_entry); + } + return err; +} + +static void +mlxsw_sp_router_xm_ml_entries_del(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm) +{ + struct mlxsw_sp_router_xm_fib_entry *fib_entry; + int i; + + for (i = 0; i < op_ctx_xm->entries_count; i++) { + fib_entry = op_ctx_xm->entries[i]; + mlxsw_sp_router_xm_ml_entry_del(mlxsw_sp, fib_entry); + } +} + +static void +mlxsw_sp_router_xm_ml_entries_cache_flush(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm) +{ + struct mlxsw_sp_router_xm_fib_entry *fib_entry; + int err; + int i; + + for (i = 0; i < op_ctx_xm->entries_count; i++) { + fib_entry = op_ctx_xm->entries[i]; + err = mlxsw_sp_router_xm_cache_flush_schedule(mlxsw_sp, + &fib_entry->flush_info); + if (err) + dev_err(mlxsw_sp->bus_info->dev, "Failed to flush XM cache\n"); + } +} + +static int mlxsw_sp_router_ll_xm_fib_entry_commit(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry_op_ctx *op_ctx, + bool *postponed_for_bulk) +{ + struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm = (void *) op_ctx->ll_priv; + struct mlxsw_sp_router_xm_fib_entry *fib_entry; + u8 num_rec; + int err; + int i; + + op_ctx_xm->trans_offset += op_ctx_xm->trans_item_len; + op_ctx_xm->entries_count++; + + /* Check if bulking is possible and there is still room for another + * FIB entry record. The size of 'trans_item_len' is either size of IPv4 + * command or size of IPv6 command. Not possible to mix those in a + * single XMDR write. + */ + if (op_ctx->bulk_ok && + op_ctx_xm->trans_offset + op_ctx_xm->trans_item_len <= MLXSW_REG_XMDR_TRANS_LEN) { + if (postponed_for_bulk) + *postponed_for_bulk = true; + return 0; + } + + if (op_ctx->event == FIB_EVENT_ENTRY_REPLACE) { + /* The L-table is updated inside. It has to be done before + * the prefix is inserted. + */ + err = mlxsw_sp_router_xm_ml_entries_add(mlxsw_sp, op_ctx_xm); + if (err) + goto out; + } + + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(xmdr), op_ctx_xm->xmdr_pl); + if (err) + goto out; + num_rec = mlxsw_reg_xmdr_num_rec_get(op_ctx_xm->xmdr_pl); + if (num_rec > op_ctx_xm->entries_count) { + dev_err(mlxsw_sp->bus_info->dev, "Invalid XMDR number of records\n"); + err = -EIO; + goto out; + } + for (i = 0; i < num_rec; i++) { + if (!mlxsw_reg_xmdr_reply_vect_get(op_ctx_xm->xmdr_pl, i)) { + dev_err(mlxsw_sp->bus_info->dev, "Command send over XMDR failed\n"); + err = -EIO; + goto out; + } else { + fib_entry = op_ctx_xm->entries[i]; + fib_entry->committed = true; + } + } + + if (op_ctx->event == FIB_EVENT_ENTRY_DEL) + /* The L-table is updated inside. It has to be done after + * the prefix was removed. + */ + mlxsw_sp_router_xm_ml_entries_del(mlxsw_sp, op_ctx_xm); + + /* At the very end, do the XLT cache flushing to evict stale + * M and ML cache entries after prefixes were inserted/removed. + */ + mlxsw_sp_router_xm_ml_entries_cache_flush(mlxsw_sp, op_ctx_xm); + +out: + /* Next pack call is going to do reinitialization */ + op_ctx->initialized = false; + return err; +} + +static bool mlxsw_sp_router_ll_xm_fib_entry_is_committed(struct mlxsw_sp_fib_entry_priv *priv) +{ + struct mlxsw_sp_router_xm_fib_entry *fib_entry = (void *) priv->priv; + + return fib_entry->committed; +} + +const struct mlxsw_sp_router_ll_ops mlxsw_sp_router_ll_xm_ops = { + .init = mlxsw_sp_router_ll_xm_init, + .ralta_write = mlxsw_sp_router_ll_xm_ralta_write, + .ralst_write = mlxsw_sp_router_ll_xm_ralst_write, + .raltb_write = mlxsw_sp_router_ll_xm_raltb_write, + .fib_entry_op_ctx_size = sizeof(struct mlxsw_sp_fib_entry_op_ctx_xm), + .fib_entry_priv_size = sizeof(struct mlxsw_sp_router_xm_fib_entry), + .fib_entry_pack = mlxsw_sp_router_ll_xm_fib_entry_pack, + .fib_entry_act_remote_pack = mlxsw_sp_router_ll_xm_fib_entry_act_remote_pack, + .fib_entry_act_local_pack = mlxsw_sp_router_ll_xm_fib_entry_act_local_pack, + .fib_entry_act_ip2me_pack = mlxsw_sp_router_ll_xm_fib_entry_act_ip2me_pack, + .fib_entry_act_ip2me_tun_pack = mlxsw_sp_router_ll_xm_fib_entry_act_ip2me_tun_pack, + .fib_entry_commit = mlxsw_sp_router_ll_xm_fib_entry_commit, + .fib_entry_is_committed = mlxsw_sp_router_ll_xm_fib_entry_is_committed, +}; + +#define MLXSW_SP_ROUTER_XM_MINDEX_SIZE (64 * 1024) + +int mlxsw_sp_router_xm_init(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_router_xm *router_xm; + char rxltm_pl[MLXSW_REG_RXLTM_LEN]; + char xltq_pl[MLXSW_REG_XLTQ_LEN]; + u32 mindex_size; + u16 device_id; + int err; + + if (!mlxsw_sp->bus_info->xm_exists) + return 0; + + router_xm = kzalloc(sizeof(*router_xm), GFP_KERNEL); + if (!router_xm) + return -ENOMEM; + + mlxsw_reg_xltq_pack(xltq_pl); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(xltq), xltq_pl); + if (err) + goto err_xltq_query; + mlxsw_reg_xltq_unpack(xltq_pl, &device_id, &router_xm->ipv4_supported, + &router_xm->ipv6_supported, &router_xm->entries_size, &mindex_size); + + if (device_id != MLXSW_REG_XLTQ_XM_DEVICE_ID_XLT) { + dev_err(mlxsw_sp->bus_info->dev, "Invalid XM device id\n"); + err = -EINVAL; + goto err_device_id_check; + } + + if (mindex_size != MLXSW_SP_ROUTER_XM_MINDEX_SIZE) { + dev_err(mlxsw_sp->bus_info->dev, "Unexpected M-index size\n"); + err = -EINVAL; + goto err_mindex_size_check; + } + + mlxsw_reg_rxltm_pack(rxltm_pl, mlxsw_sp_router_xm_m_val[MLXSW_SP_L3_PROTO_IPV4], + mlxsw_sp_router_xm_m_val[MLXSW_SP_L3_PROTO_IPV6]); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rxltm), rxltm_pl); + if (err) + goto err_rxltm_write; + + err = rhashtable_init(&router_xm->ltable_ht, &mlxsw_sp_router_xm_ltable_ht_params); + if (err) + goto err_ltable_ht_init; + + err = rhashtable_init(&router_xm->flush_ht, &mlxsw_sp_router_xm_flush_ht_params); + if (err) + goto err_flush_ht_init; + + mlxsw_sp->router->xm = router_xm; + return 0; + +err_flush_ht_init: + rhashtable_destroy(&router_xm->ltable_ht); +err_ltable_ht_init: +err_rxltm_write: +err_mindex_size_check: +err_device_id_check: +err_xltq_query: + kfree(router_xm); + return err; +} + +void mlxsw_sp_router_xm_fini(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; + + if (!mlxsw_sp->bus_info->xm_exists) + return; + + rhashtable_destroy(&router_xm->flush_ht); + rhashtable_destroy(&router_xm->ltable_ht); + kfree(router_xm); +} + +bool mlxsw_sp_router_xm_ipv4_is_supported(const struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; + + return router_xm && router_xm->ipv4_supported; +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 6501ce94ace5..cea42f6ed89b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -41,6 +41,7 @@ struct mlxsw_sp_bridge { DECLARE_BITMAP(mids_bitmap, MLXSW_SP_MID_MAX); const struct mlxsw_sp_bridge_ops *bridge_8021q_ops; const struct mlxsw_sp_bridge_ops *bridge_8021d_ops; + const struct mlxsw_sp_bridge_ops *bridge_8021ad_ops; }; struct mlxsw_sp_bridge_device { @@ -228,8 +229,14 @@ mlxsw_sp_bridge_device_create(struct mlxsw_sp_bridge *bridge, bridge_device->mrouter = br_multicast_router(br_dev); INIT_LIST_HEAD(&bridge_device->ports_list); if (vlan_enabled) { + u16 proto; + bridge->vlan_enabled_exists = true; - bridge_device->ops = bridge->bridge_8021q_ops; + br_vlan_get_proto(br_dev, &proto); + if (proto == ETH_P_8021AD) + bridge_device->ops = bridge->bridge_8021ad_ops; + else + bridge_device->ops = bridge->bridge_8021q_ops; } else { bridge_device->ops = bridge->bridge_8021d_ops; } @@ -757,6 +764,25 @@ static int mlxsw_sp_port_attr_br_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, return -EINVAL; } +static int mlxsw_sp_port_attr_br_vlan_proto_set(struct mlxsw_sp_port *mlxsw_sp_port, + struct switchdev_trans *trans, + struct net_device *orig_dev, + u16 vlan_proto) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_bridge_device *bridge_device; + + if (!switchdev_trans_ph_prepare(trans)) + return 0; + + bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, orig_dev); + if (WARN_ON(!bridge_device)) + return -EINVAL; + + netdev_err(bridge_device->dev, "VLAN protocol can't be changed on existing bridge\n"); + return -EINVAL; +} + static int mlxsw_sp_port_attr_mrouter_set(struct mlxsw_sp_port *mlxsw_sp_port, struct switchdev_trans *trans, struct net_device *orig_dev, @@ -926,6 +952,11 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev, attr->orig_dev, attr->u.vlan_filtering); break; + case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL: + err = mlxsw_sp_port_attr_br_vlan_proto_set(mlxsw_sp_port, trans, + attr->orig_dev, + attr->u.vlan_protocol); + break; case SWITCHDEV_ATTR_ID_PORT_MROUTER: err = mlxsw_sp_port_attr_mrouter_set(mlxsw_sp_port, trans, attr->orig_dev, @@ -1129,6 +1160,7 @@ mlxsw_sp_bridge_port_vlan_add(struct mlxsw_sp_port *mlxsw_sp_port, u16 pvid = mlxsw_sp_port_pvid_determine(mlxsw_sp_port, vid, is_pvid); struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; u16 old_pvid = mlxsw_sp_port->pvid; + u16 proto; int err; /* The only valid scenario in which a port-vlan already exists, is if @@ -1152,7 +1184,8 @@ mlxsw_sp_bridge_port_vlan_add(struct mlxsw_sp_port *mlxsw_sp_port, if (err) goto err_port_vlan_set; - err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, pvid); + br_vlan_get_proto(bridge_port->bridge_device->dev, &proto); + err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, pvid, proto); if (err) goto err_port_pvid_set; @@ -1164,7 +1197,7 @@ mlxsw_sp_bridge_port_vlan_add(struct mlxsw_sp_port *mlxsw_sp_port, return 0; err_port_vlan_bridge_join: - mlxsw_sp_port_pvid_set(mlxsw_sp_port, old_pvid); + mlxsw_sp_port_pvid_set(mlxsw_sp_port, old_pvid, proto); err_port_pvid_set: mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false); err_port_vlan_set: @@ -1821,13 +1854,15 @@ mlxsw_sp_bridge_port_vlan_del(struct mlxsw_sp_port *mlxsw_sp_port, { u16 pvid = mlxsw_sp_port->pvid == vid ? 0 : mlxsw_sp_port->pvid; struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; + u16 proto; mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid); if (WARN_ON(!mlxsw_sp_port_vlan)) return; mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan); - mlxsw_sp_port_pvid_set(mlxsw_sp_port, pvid); + br_vlan_get_proto(bridge_port->bridge_device->dev, &proto); + mlxsw_sp_port_pvid_set(mlxsw_sp_port, pvid, proto); mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false); mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan); } @@ -1975,10 +2010,9 @@ static struct mlxsw_sp_port *mlxsw_sp_lag_rep_port(struct mlxsw_sp *mlxsw_sp, } static int -mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device, - struct mlxsw_sp_bridge_port *bridge_port, - struct mlxsw_sp_port *mlxsw_sp_port, - struct netlink_ext_ack *extack) +mlxsw_sp_bridge_vlan_aware_port_join(struct mlxsw_sp_bridge_port *bridge_port, + struct mlxsw_sp_port *mlxsw_sp_port, + struct netlink_ext_ack *extack) { if (is_vlan_dev(bridge_port->dev)) { NL_SET_ERR_MSG_MOD(extack, "Can not enslave a VLAN device to a VLAN-aware bridge"); @@ -1992,19 +2026,37 @@ mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device, return 0; } +static int +mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device, + struct mlxsw_sp_bridge_port *bridge_port, + struct mlxsw_sp_port *mlxsw_sp_port, + struct netlink_ext_ack *extack) +{ + return mlxsw_sp_bridge_vlan_aware_port_join(bridge_port, mlxsw_sp_port, + extack); +} + +static void +mlxsw_sp_bridge_vlan_aware_port_leave(struct mlxsw_sp_port *mlxsw_sp_port) +{ + /* Make sure untagged frames are allowed to ingress */ + mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID, + ETH_P_8021Q); +} + static void mlxsw_sp_bridge_8021q_port_leave(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_bridge_port *bridge_port, struct mlxsw_sp_port *mlxsw_sp_port) { - /* Make sure untagged frames are allowed to ingress */ - mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID); + mlxsw_sp_bridge_vlan_aware_port_leave(mlxsw_sp_port); } static int -mlxsw_sp_bridge_8021q_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device, - const struct net_device *vxlan_dev, u16 vid, - struct netlink_ext_ack *extack) +mlxsw_sp_bridge_vlan_aware_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device, + const struct net_device *vxlan_dev, + u16 vid, u16 ethertype, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev); struct vxlan_dev *vxlan = netdev_priv(vxlan_dev); @@ -2012,6 +2064,7 @@ mlxsw_sp_bridge_8021q_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device, .type = MLXSW_SP_NVE_TYPE_VXLAN, .vni = vxlan->cfg.vni, .dev = vxlan_dev, + .ethertype = ethertype, }; struct mlxsw_sp_fid *fid; int err; @@ -2050,6 +2103,15 @@ err_vni_exists: return err; } +static int +mlxsw_sp_bridge_8021q_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device, + const struct net_device *vxlan_dev, u16 vid, + struct netlink_ext_ack *extack) +{ + return mlxsw_sp_bridge_vlan_aware_vxlan_join(bridge_device, vxlan_dev, + vid, ETH_P_8021Q, extack); +} + static struct net_device * mlxsw_sp_bridge_8021q_vxlan_dev_find(struct net_device *br_dev, u16 vid) { @@ -2180,6 +2242,7 @@ mlxsw_sp_bridge_8021d_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device, .type = MLXSW_SP_NVE_TYPE_VXLAN, .vni = vxlan->cfg.vni, .dev = vxlan_dev, + .ethertype = ETH_P_8021Q, }; struct mlxsw_sp_fid *fid; int err; @@ -2246,6 +2309,57 @@ static const struct mlxsw_sp_bridge_ops mlxsw_sp_bridge_8021d_ops = { .fid_vid = mlxsw_sp_bridge_8021d_fid_vid, }; +static int +mlxsw_sp_bridge_8021ad_port_join(struct mlxsw_sp_bridge_device *bridge_device, + struct mlxsw_sp_bridge_port *bridge_port, + struct mlxsw_sp_port *mlxsw_sp_port, + struct netlink_ext_ack *extack) +{ + int err; + + err = mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, true, false); + if (err) + return err; + + err = mlxsw_sp_bridge_vlan_aware_port_join(bridge_port, mlxsw_sp_port, + extack); + if (err) + goto err_bridge_vlan_aware_port_join; + + return 0; + +err_bridge_vlan_aware_port_join: + mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, false, true); + return err; +} + +static void +mlxsw_sp_bridge_8021ad_port_leave(struct mlxsw_sp_bridge_device *bridge_device, + struct mlxsw_sp_bridge_port *bridge_port, + struct mlxsw_sp_port *mlxsw_sp_port) +{ + mlxsw_sp_bridge_vlan_aware_port_leave(mlxsw_sp_port); + mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, false, true); +} + +static int +mlxsw_sp_bridge_8021ad_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device, + const struct net_device *vxlan_dev, u16 vid, + struct netlink_ext_ack *extack) +{ + return mlxsw_sp_bridge_vlan_aware_vxlan_join(bridge_device, vxlan_dev, + vid, ETH_P_8021AD, extack); +} + +static const struct mlxsw_sp_bridge_ops mlxsw_sp_bridge_8021ad_ops = { + .port_join = mlxsw_sp_bridge_8021ad_port_join, + .port_leave = mlxsw_sp_bridge_8021ad_port_leave, + .vxlan_join = mlxsw_sp_bridge_8021ad_vxlan_join, + .fid_get = mlxsw_sp_bridge_8021q_fid_get, + .fid_lookup = mlxsw_sp_bridge_8021q_fid_lookup, + .fid_vid = mlxsw_sp_bridge_8021q_fid_vid, +}; + int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *brport_dev, struct net_device *br_dev, @@ -3206,8 +3320,8 @@ mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp, if (!fid) { if (!flag_untagged || !flag_pvid) return 0; - return mlxsw_sp_bridge_8021q_vxlan_join(bridge_device, - vxlan_dev, vid, extack); + return bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, + vid, extack); } /* Second case: FID is associated with the VNI and the VLAN associated @@ -3246,16 +3360,14 @@ mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp, if (!flag_untagged) return 0; - err = mlxsw_sp_bridge_8021q_vxlan_join(bridge_device, vxlan_dev, vid, - extack); + err = bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, vid, extack); if (err) goto err_vxlan_join; return 0; err_vxlan_join: - mlxsw_sp_bridge_8021q_vxlan_join(bridge_device, vxlan_dev, old_vid, - NULL); + bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, old_vid, NULL); return err; } @@ -3507,6 +3619,7 @@ int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp) bridge->bridge_8021q_ops = &mlxsw_sp_bridge_8021q_ops; bridge->bridge_8021d_ops = &mlxsw_sp_bridge_8021d_ops; + bridge->bridge_8021ad_ops = &mlxsw_sp_bridge_8021ad_ops; return mlxsw_sp_fdb_init(mlxsw_sp); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index 433f14ade464..4ef12e3e021a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -617,7 +617,7 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = { TRAP_TO_CPU), MLXSW_SP_RXL_EXCEPTION(HOST_MISS_IPV6, L3_EXCEPTIONS, TRAP_TO_CPU), - MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER3, L3_EXCEPTIONS, + MLXSW_SP_RXL_EXCEPTION(RTR_EGRESS0, L3_EXCEPTIONS, TRAP_EXCEPTION_TO_CPU), }, }, @@ -1007,6 +1007,12 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = { false), }, }, + { + .trap = MLXSW_SP_TRAP_DROP(BLACKHOLE_NEXTHOP, L3_DROPS), + .listeners_arr = { + MLXSW_SP_RXL_DISCARD(ROUTER3, L3_DISCARDS), + }, + }, }; static struct mlxsw_sp_trap_policer_item * diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 5023d91269f4..40e2e79d4517 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -6,6 +6,7 @@ #include <linux/types.h> #include <linux/pci.h> #include <linux/netdevice.h> +#include <linux/ethtool.h> #include <linux/etherdevice.h> #include <linux/slab.h> #include <linux/device.h> diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 57f9e24602d0..9e070ab3ed76 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -52,6 +52,7 @@ enum { MLXSW_TRAP_ID_RTR_INGRESS1 = 0x71, MLXSW_TRAP_ID_IPV6_PIM = 0x79, MLXSW_TRAP_ID_IPV6_VRRP = 0x7A, + MLXSW_TRAP_ID_RTR_EGRESS0 = 0x80, MLXSW_TRAP_ID_IPV4_BGP = 0x88, MLXSW_TRAP_ID_IPV6_BGP = 0x89, MLXSW_TRAP_ID_L3_IPV6_ROUTER_SOLICITATION = 0x8A, |