diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlxsw')
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/Makefile | 3 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/cmd.h | 75 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/core.c | 30 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/core.h | 17 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/pci.c | 78 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/reg.h | 1386 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2268 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 264 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c | 91 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 1814 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 446 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/switchx2.c | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/trap.h | 5 |
13 files changed, 5564 insertions, 914 deletions
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index 9b5ebf84c051..d20ae1838a64 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -7,5 +7,6 @@ obj-$(CONFIG_MLXSW_SWITCHX2) += mlxsw_switchx2.o mlxsw_switchx2-objs := switchx2.o obj-$(CONFIG_MLXSW_SPECTRUM) += mlxsw_spectrum.o mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \ - spectrum_switchdev.o + spectrum_switchdev.o spectrum_router.o \ + spectrum_kvdl.o mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h index cd63b8263688..28271bedd957 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h +++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h @@ -105,6 +105,7 @@ enum mlxsw_cmd_opcode { MLXSW_CMD_OPCODE_SW2HW_EQ = 0x013, MLXSW_CMD_OPCODE_HW2SW_EQ = 0x014, MLXSW_CMD_OPCODE_QUERY_EQ = 0x015, + MLXSW_CMD_OPCODE_QUERY_RESOURCES = 0x101, }; static inline const char *mlxsw_cmd_opcode_str(u16 opcode) @@ -144,6 +145,8 @@ static inline const char *mlxsw_cmd_opcode_str(u16 opcode) return "HW2SW_EQ"; case MLXSW_CMD_OPCODE_QUERY_EQ: return "QUERY_EQ"; + case MLXSW_CMD_OPCODE_QUERY_RESOURCES: + return "QUERY_RESOURCES"; default: return "*UNKNOWN*"; } @@ -500,6 +503,35 @@ static inline int mlxsw_cmd_unmap_fa(struct mlxsw_core *mlxsw_core) return mlxsw_cmd_exec_none(mlxsw_core, MLXSW_CMD_OPCODE_UNMAP_FA, 0, 0); } +/* QUERY_RESOURCES - Query chip resources + * -------------------------------------- + * OpMod == 0 (N/A) , INMmod is index + * ---------------------------------- + * The QUERY_RESOURCES command retrieves information related to chip resources + * by resource ID. Every command returns 32 entries. INmod is being use as base. + * for example, index 1 will return entries 32-63. When the tables end and there + * are no more sources in the table, will return resource id 0xFFF to indicate + * it. + */ +static inline int mlxsw_cmd_query_resources(struct mlxsw_core *mlxsw_core, + char *out_mbox, int index) +{ + return mlxsw_cmd_exec_out(mlxsw_core, MLXSW_CMD_OPCODE_QUERY_RESOURCES, + 0, index, false, out_mbox, + MLXSW_CMD_MBOX_SIZE); +} + +/* cmd_mbox_query_resource_id + * The resource id. 0xFFFF indicates table's end. + */ +MLXSW_ITEM32_INDEXED(cmd_mbox, query_resource, id, 0x00, 16, 16, 0x8, 0, false); + +/* cmd_mbox_query_resource_data + * The resource + */ +MLXSW_ITEM64_INDEXED(cmd_mbox, query_resource, data, + 0x00, 0, 40, 0x8, 0, false); + /* CONFIG_PROFILE (Set) - Configure Switch Profile * ------------------------------ * OpMod == 1 (Set), INMmod == 0 (N/A) @@ -607,6 +639,24 @@ MLXSW_ITEM32(cmd_mbox, config_profile, */ MLXSW_ITEM32(cmd_mbox, config_profile, set_ar_sec, 0x0C, 15, 1); +/* cmd_mbox_config_set_kvd_linear_size + * Capability bit. Setting a bit to 1 configures the profile + * according to the mailbox contents. + */ +MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_linear_size, 0x0C, 24, 1); + +/* cmd_mbox_config_set_kvd_hash_single_size + * Capability bit. Setting a bit to 1 configures the profile + * according to the mailbox contents. + */ +MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_single_size, 0x0C, 25, 1); + +/* cmd_mbox_config_set_kvd_hash_double_size + * Capability bit. Setting a bit to 1 configures the profile + * according to the mailbox contents. + */ +MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_double_size, 0x0C, 26, 1); + /* cmd_mbox_config_profile_max_vepa_channels * Maximum number of VEPA channels per port (0 through 16) * 0 - multi-channel VEPA is disabled @@ -733,6 +783,31 @@ 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_kvd_linear_size + * KVD Linear Size + * Valid for Spectrum only + * Allowed values are 128*N where N=0 or higher + */ +MLXSW_ITEM32(cmd_mbox, config_profile, kvd_linear_size, 0x54, 0, 24); + +/* cmd_mbox_config_kvd_hash_single_size + * KVD Hash single-entries size + * Valid for Spectrum only + * Allowed values are 128*N where N=0 or higher + * Must be greater or equal to cap_min_kvd_hash_single_size + * Must be smaller or equal to cap_kvd_size - kvd_linear_size + */ +MLXSW_ITEM32(cmd_mbox, config_profile, kvd_hash_single_size, 0x58, 0, 24); + +/* cmd_mbox_config_kvd_hash_double_size + * KVD Hash double-entries size (units of single-size entries) + * Valid for Spectrum only + * Allowed values are 128*N where N=0 or higher + * Must be either 0 or greater or equal to cap_min_kvd_hash_double_size + * Must be smaller or equal to cap_kvd_size - kvd_linear_size + */ +MLXSW_ITEM32(cmd_mbox, config_profile, kvd_hash_double_size, 0x5C, 0, 24); + /* cmd_mbox_config_profile_swid_config_mask * Modify Switch Partition Configuration mask. When set, the configu- * ration value for the Switch Partition are taken from the mailbox. diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index b0a0b01bb4ef..068ee65a960b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -58,6 +58,7 @@ #include <linux/workqueue.h> #include <asm/byteorder.h> #include <net/devlink.h> +#include <trace/events/devlink.h> #include "core.h" #include "item.h" @@ -110,6 +111,7 @@ struct mlxsw_core { struct { u8 *mapping; /* lag_id+port_index to local_port mapping */ } lag; + struct mlxsw_resources resources; struct mlxsw_hwmon *hwmon; unsigned long driver_priv[0]; /* driver_priv has to be always the last item */ @@ -447,6 +449,10 @@ static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core, if (!skb) return -ENOMEM; + trace_devlink_hwmsg(priv_to_devlink(mlxsw_core), false, 0, + skb->data + mlxsw_core->driver->txhdr_len, + skb->len - mlxsw_core->driver->txhdr_len); + atomic_set(&trans->active, 1); err = mlxsw_core_skb_transmit(mlxsw_core, skb, &trans->tx_info); if (err) { @@ -529,6 +535,9 @@ static void mlxsw_emad_rx_listener_func(struct sk_buff *skb, u8 local_port, struct mlxsw_core *mlxsw_core = priv; struct mlxsw_reg_trans *trans; + trace_devlink_hwmsg(priv_to_devlink(mlxsw_core), true, 0, + skb->data, skb->len); + if (!mlxsw_emad_is_resp(skb)) goto free_skb; @@ -1102,7 +1111,8 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, } } - err = mlxsw_bus->init(bus_priv, mlxsw_core, mlxsw_driver->profile); + err = mlxsw_bus->init(bus_priv, mlxsw_core, mlxsw_driver->profile, + &mlxsw_core->resources); if (err) goto err_bus_init; @@ -1110,14 +1120,14 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, if (err) goto err_emad_init; - err = mlxsw_hwmon_init(mlxsw_core, mlxsw_bus_info, &mlxsw_core->hwmon); - if (err) - goto err_hwmon_init; - err = devlink_register(devlink, mlxsw_bus_info->dev); if (err) goto err_devlink_register; + err = mlxsw_hwmon_init(mlxsw_core, mlxsw_bus_info, &mlxsw_core->hwmon); + if (err) + goto err_hwmon_init; + err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info); if (err) goto err_driver_init; @@ -1131,9 +1141,9 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, err_debugfs_init: mlxsw_core->driver->fini(mlxsw_core); err_driver_init: +err_hwmon_init: devlink_unregister(devlink); err_devlink_register: -err_hwmon_init: mlxsw_emad_fini(mlxsw_core); err_emad_init: mlxsw_bus->fini(bus_priv); @@ -1644,6 +1654,12 @@ void mlxsw_core_lag_mapping_clear(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_lag_mapping_clear); +struct mlxsw_resources *mlxsw_core_resources_get(struct mlxsw_core *mlxsw_core) +{ + return &mlxsw_core->resources; +} +EXPORT_SYMBOL(mlxsw_core_resources_get); + int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, struct mlxsw_core_port *mlxsw_core_port, u8 local_port, struct net_device *dev, bool split, u32 split_group) @@ -1736,7 +1752,7 @@ static int __init mlxsw_core_module_init(void) { int err; - mlxsw_wq = create_workqueue(mlxsw_core_driver_name); + mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_MEM_RECLAIM, 0); if (!mlxsw_wq) return -ENOMEM; mlxsw_core_dbg_root = debugfs_create_dir(mlxsw_core_driver_name, NULL); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 436bc49df6ab..d3476ead9982 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -190,7 +190,8 @@ struct mlxsw_config_profile { used_max_ib_mc:1, used_max_pkey:1, used_ar_sec:1, - used_adaptive_routing_group_cap:1; + used_adaptive_routing_group_cap:1, + used_kvd_sizes:1; u8 max_vepa_channels; u16 max_lag; u16 max_port_per_lag; @@ -211,6 +212,10 @@ struct mlxsw_config_profile { u8 ar_sec; u16 adaptive_routing_group_cap; u8 arn; + u32 kvd_linear_size; + u32 kvd_hash_single_size; + u32 kvd_hash_double_size; + u8 resource_query_enable; struct mlxsw_swid_config swid_config[MLXSW_CONFIG_PROFILE_SWID_COUNT]; }; @@ -262,10 +267,18 @@ struct mlxsw_driver { const struct mlxsw_config_profile *profile; }; +struct mlxsw_resources { + u8 max_span_valid:1; + u8 max_span; +}; + +struct mlxsw_resources *mlxsw_core_resources_get(struct mlxsw_core *mlxsw_core); + struct mlxsw_bus { const char *kind; int (*init)(void *bus_priv, struct mlxsw_core *mlxsw_core, - const struct mlxsw_config_profile *profile); + const struct mlxsw_config_profile *profile, + struct mlxsw_resources *resources); void (*fini)(void *bus_priv); bool (*skb_transmit_busy)(void *bus_priv, const struct mlxsw_tx_info *tx_info); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 7f4173c8eda3..1d1360c178bb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1154,6 +1154,61 @@ mlxsw_pci_config_profile_swid_config(struct mlxsw_pci *mlxsw_pci, mlxsw_cmd_mbox_config_profile_swid_config_mask_set(mbox, index, mask); } +#define MLXSW_RESOURCES_TABLE_END_ID 0xffff +#define MLXSW_MAX_SPAN_ID 0x2420 +#define MLXSW_RESOURCES_QUERY_MAX_QUERIES 100 +#define MLXSW_RESOURCES_PER_QUERY 32 + +static void mlxsw_pci_resources_query_parse(int id, u64 val, + struct mlxsw_resources *resources) +{ + switch (id) { + case MLXSW_MAX_SPAN_ID: + resources->max_span = val; + resources->max_span_valid = 1; + break; + default: + break; + } +} + +static int mlxsw_pci_resources_query(struct mlxsw_pci *mlxsw_pci, char *mbox, + struct mlxsw_resources *resources, + u8 query_enabled) +{ + int index, i; + u64 data; + u16 id; + int err; + + /* Not all the versions support resources query */ + if (!query_enabled) + return 0; + + mlxsw_cmd_mbox_zero(mbox); + + for (index = 0; index < MLXSW_RESOURCES_QUERY_MAX_QUERIES; index++) { + err = mlxsw_cmd_query_resources(mlxsw_pci->core, mbox, index); + if (err) + return err; + + for (i = 0; i < MLXSW_RESOURCES_PER_QUERY; i++) { + id = mlxsw_cmd_mbox_query_resource_id_get(mbox, i); + data = mlxsw_cmd_mbox_query_resource_data_get(mbox, i); + + if (id == MLXSW_RESOURCES_TABLE_END_ID) + return 0; + + mlxsw_pci_resources_query_parse(id, data, resources); + } + } + + /* If after MLXSW_RESOURCES_QUERY_MAX_QUERIES we still didn't get + * MLXSW_RESOURCES_TABLE_END_ID, something went bad in the FW. + */ + return -EIO; +} + static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox, const struct mlxsw_config_profile *profile) { @@ -1255,6 +1310,20 @@ static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox, mlxsw_cmd_mbox_config_profile_adaptive_routing_group_cap_set( mbox, profile->adaptive_routing_group_cap); } + if (profile->used_kvd_sizes) { + mlxsw_cmd_mbox_config_profile_set_kvd_linear_size_set( + mbox, 1); + mlxsw_cmd_mbox_config_profile_kvd_linear_size_set( + mbox, profile->kvd_linear_size); + mlxsw_cmd_mbox_config_profile_set_kvd_hash_single_size_set( + mbox, 1); + mlxsw_cmd_mbox_config_profile_kvd_hash_single_size_set( + mbox, profile->kvd_hash_single_size); + mlxsw_cmd_mbox_config_profile_set_kvd_hash_double_size_set( + mbox, 1); + mlxsw_cmd_mbox_config_profile_kvd_hash_double_size_set( + mbox, profile->kvd_hash_double_size); + } for (i = 0; i < MLXSW_CONFIG_PROFILE_SWID_COUNT; i++) mlxsw_pci_config_profile_swid_config(mlxsw_pci, mbox, i, @@ -1390,7 +1459,8 @@ static void mlxsw_pci_mbox_free(struct mlxsw_pci *mlxsw_pci, } static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, - const struct mlxsw_config_profile *profile) + const struct mlxsw_config_profile *profile, + struct mlxsw_resources *resources) { struct mlxsw_pci *mlxsw_pci = bus_priv; struct pci_dev *pdev = mlxsw_pci->pdev; @@ -1449,6 +1519,11 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, if (err) goto err_boardinfo; + err = mlxsw_pci_resources_query(mlxsw_pci, mbox, resources, + profile->resource_query_enable); + if (err) + goto err_query_resources; + err = mlxsw_pci_config_profile(mlxsw_pci, mbox, profile); if (err) goto err_config_profile; @@ -1471,6 +1546,7 @@ err_request_eq_irq: mlxsw_pci_aqs_fini(mlxsw_pci); err_aqs_init: err_config_profile: +err_query_resources: err_boardinfo: mlxsw_pci_fw_area_fini(mlxsw_pci); err_fw_area_init: diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 57d48da709fb..7ca9201f7dcb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -1,9 +1,10 @@ /* * drivers/net/ethernet/mellanox/mlxsw/reg.h * Copyright (c) 2015 Mellanox Technologies. All rights reserved. - * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com> + * Copyright (c) 2015-2016 Ido Schimmel <idosch@mellanox.com> * Copyright (c) 2015 Elad Raz <eladr@mellanox.com> - * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com> + * Copyright (c) 2015-2016 Jiri Pirko <jiri@mellanox.com> + * Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -386,7 +387,9 @@ enum mlxsw_reg_sfd_rec_action { /* forward and trap, trap_id is FDB_TRAP */ MLXSW_REG_SFD_REC_ACTION_MIRROR_TO_CPU = 1, /* trap and do not forward, trap_id is FDB_TRAP */ - MLXSW_REG_SFD_REC_ACTION_TRAP = 3, + MLXSW_REG_SFD_REC_ACTION_TRAP = 2, + /* forward to IP router */ + MLXSW_REG_SFD_REC_ACTION_FORWARD_IP_ROUTER = 3, MLXSW_REG_SFD_REC_ACTION_DISCARD_ERROR = 15, }; @@ -2500,6 +2503,7 @@ MLXSW_ITEM32(reg, ppcnt, pnat, 0x00, 14, 2); enum mlxsw_reg_ppcnt_grp { MLXSW_REG_PPCNT_IEEE_8023_CNT = 0x0, MLXSW_REG_PPCNT_PRIO_CNT = 0x10, + MLXSW_REG_PPCNT_TC_CNT = 0x11, }; /* reg_ppcnt_grp @@ -2700,6 +2704,23 @@ MLXSW_ITEM64(reg, ppcnt, tx_pause_duration, 0x08 + 0x68, 0, 64); */ MLXSW_ITEM64(reg, ppcnt, tx_pause_transition, 0x08 + 0x70, 0, 64); +/* Ethernet Per Traffic Group Counters */ + +/* reg_ppcnt_tc_transmit_queue + * Contains the transmit queue depth in cells of traffic class + * selected by prio_tc and the port selected by local_port. + * The field cannot be cleared. + * Access: RO + */ +MLXSW_ITEM64(reg, ppcnt, tc_transmit_queue, 0x08 + 0x00, 0, 64); + +/* reg_ppcnt_tc_no_buffer_discard_uc + * The number of unicast packets dropped due to lack of shared + * buffer resources. + * Access: RO + */ +MLXSW_ITEM64(reg, ppcnt, tc_no_buffer_discard_uc, 0x08 + 0x08, 0, 64); + static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port, enum mlxsw_reg_ppcnt_grp grp, u8 prio_tc) @@ -3201,6 +3222,1183 @@ static inline void mlxsw_reg_hpkt_pack(char *payload, u8 action, u16 trap_id) mlxsw_reg_hpkt_ctrl_set(payload, MLXSW_REG_HPKT_CTRL_PACKET_DEFAULT); } +/* RGCR - Router General Configuration Register + * -------------------------------------------- + * The register is used for setting up the router configuration. + */ +#define MLXSW_REG_RGCR_ID 0x8001 +#define MLXSW_REG_RGCR_LEN 0x28 + +static const struct mlxsw_reg_info mlxsw_reg_rgcr = { + .id = MLXSW_REG_RGCR_ID, + .len = MLXSW_REG_RGCR_LEN, +}; + +/* reg_rgcr_ipv4_en + * IPv4 router enable. + * Access: RW + */ +MLXSW_ITEM32(reg, rgcr, ipv4_en, 0x00, 31, 1); + +/* reg_rgcr_ipv6_en + * IPv6 router enable. + * Access: RW + */ +MLXSW_ITEM32(reg, rgcr, ipv6_en, 0x00, 30, 1); + +/* reg_rgcr_max_router_interfaces + * Defines the maximum number of active router interfaces for all virtual + * routers. + * Access: RW + */ +MLXSW_ITEM32(reg, rgcr, max_router_interfaces, 0x10, 0, 16); + +/* reg_rgcr_usp + * Update switch priority and packet color. + * 0 - Preserve the value of Switch Priority and packet color. + * 1 - Recalculate the value of Switch Priority and packet color. + * Access: RW + * + * Note: Not supported by SwitchX and SwitchX-2. + */ +MLXSW_ITEM32(reg, rgcr, usp, 0x18, 20, 1); + +/* reg_rgcr_pcp_rw + * Indicates how to handle the pcp_rewrite_en value: + * 0 - Preserve the value of pcp_rewrite_en. + * 2 - Disable PCP rewrite. + * 3 - Enable PCP rewrite. + * Access: RW + * + * Note: Not supported by SwitchX and SwitchX-2. + */ +MLXSW_ITEM32(reg, rgcr, pcp_rw, 0x18, 16, 2); + +/* reg_rgcr_activity_dis + * Activity disable: + * 0 - Activity will be set when an entry is hit (default). + * 1 - Activity will not be set when an entry is hit. + * + * Bit 0 - Disable activity bit in Router Algorithmic LPM Unicast Entry + * (RALUE). + * Bit 1 - Disable activity bit in Router Algorithmic LPM Unicast Host + * Entry (RAUHT). + * Bits 2:7 are reserved. + * Access: RW + * + * Note: Not supported by SwitchX, SwitchX-2 and Switch-IB. + */ +MLXSW_ITEM32(reg, rgcr, activity_dis, 0x20, 0, 8); + +static inline void mlxsw_reg_rgcr_pack(char *payload, bool ipv4_en) +{ + MLXSW_REG_ZERO(rgcr, payload); + mlxsw_reg_rgcr_ipv4_en_set(payload, ipv4_en); +} + +/* RITR - Router Interface Table Register + * -------------------------------------- + * The register is used to configure the router interface table. + */ +#define MLXSW_REG_RITR_ID 0x8002 +#define MLXSW_REG_RITR_LEN 0x40 + +static const struct mlxsw_reg_info mlxsw_reg_ritr = { + .id = MLXSW_REG_RITR_ID, + .len = MLXSW_REG_RITR_LEN, +}; + +/* reg_ritr_enable + * Enables routing on the router interface. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, enable, 0x00, 31, 1); + +/* reg_ritr_ipv4 + * IPv4 routing enable. Enables routing of IPv4 traffic on the router + * interface. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, ipv4, 0x00, 29, 1); + +/* reg_ritr_ipv6 + * IPv6 routing enable. Enables routing of IPv6 traffic on the router + * interface. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, ipv6, 0x00, 28, 1); + +enum mlxsw_reg_ritr_if_type { + MLXSW_REG_RITR_VLAN_IF, + MLXSW_REG_RITR_FID_IF, + MLXSW_REG_RITR_SP_IF, +}; + +/* reg_ritr_type + * Router interface type. + * 0 - VLAN interface. + * 1 - FID interface. + * 2 - Sub-port interface. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, type, 0x00, 23, 3); + +enum { + MLXSW_REG_RITR_RIF_CREATE, + MLXSW_REG_RITR_RIF_DEL, +}; + +/* reg_ritr_op + * Opcode: + * 0 - Create or edit RIF. + * 1 - Delete RIF. + * Reserved for SwitchX-2. For Spectrum, editing of interface properties + * is not supported. An interface must be deleted and re-created in order + * to update properties. + * Access: WO + */ +MLXSW_ITEM32(reg, ritr, op, 0x00, 20, 2); + +/* reg_ritr_rif + * Router interface index. A pointer to the Router Interface Table. + * Access: Index + */ +MLXSW_ITEM32(reg, ritr, rif, 0x00, 0, 16); + +/* reg_ritr_ipv4_fe + * IPv4 Forwarding Enable. + * Enables routing of IPv4 traffic on the router interface. When disabled, + * forwarding is blocked but local traffic (traps and IP2ME) will be enabled. + * Not supported in SwitchX-2. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, ipv4_fe, 0x04, 29, 1); + +/* reg_ritr_ipv6_fe + * IPv6 Forwarding Enable. + * Enables routing of IPv6 traffic on the router interface. When disabled, + * forwarding is blocked but local traffic (traps and IP2ME) will be enabled. + * Not supported in SwitchX-2. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, ipv6_fe, 0x04, 28, 1); + +/* reg_ritr_virtual_router + * Virtual router ID associated with the router interface. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, virtual_router, 0x04, 0, 16); + +/* reg_ritr_mtu + * Router interface MTU. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, mtu, 0x34, 0, 16); + +/* reg_ritr_if_swid + * Switch partition ID. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, if_swid, 0x08, 24, 8); + +/* reg_ritr_if_mac + * Router interface MAC address. + * In Spectrum, all MAC addresses must have the same 38 MSBits. + * Access: RW + */ +MLXSW_ITEM_BUF(reg, ritr, if_mac, 0x12, 6); + +/* VLAN Interface */ + +/* reg_ritr_vlan_if_vid + * VLAN ID. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, vlan_if_vid, 0x08, 0, 12); + +/* FID Interface */ + +/* reg_ritr_fid_if_fid + * Filtering ID. Used to connect a bridge to the router. Only FIDs from + * the vFID range are supported. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, fid_if_fid, 0x08, 0, 16); + +static inline void mlxsw_reg_ritr_fid_set(char *payload, + enum mlxsw_reg_ritr_if_type rif_type, + u16 fid) +{ + if (rif_type == MLXSW_REG_RITR_FID_IF) + mlxsw_reg_ritr_fid_if_fid_set(payload, fid); + else + mlxsw_reg_ritr_vlan_if_vid_set(payload, fid); +} + +/* Sub-port Interface */ + +/* reg_ritr_sp_if_lag + * LAG indication. When this bit is set the system_port field holds the + * LAG identifier. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, sp_if_lag, 0x08, 24, 1); + +/* reg_ritr_sp_system_port + * Port unique indentifier. When lag bit is set, this field holds the + * lag_id in bits 0:9. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, sp_if_system_port, 0x08, 0, 16); + +/* reg_ritr_sp_if_vid + * VLAN ID. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, sp_if_vid, 0x18, 0, 12); + +static inline void mlxsw_reg_ritr_rif_pack(char *payload, u16 rif) +{ + MLXSW_REG_ZERO(ritr, payload); + mlxsw_reg_ritr_rif_set(payload, rif); +} + +static inline void mlxsw_reg_ritr_sp_if_pack(char *payload, bool lag, + u16 system_port, u16 vid) +{ + mlxsw_reg_ritr_sp_if_lag_set(payload, lag); + mlxsw_reg_ritr_sp_if_system_port_set(payload, system_port); + mlxsw_reg_ritr_sp_if_vid_set(payload, vid); +} + +static inline void mlxsw_reg_ritr_pack(char *payload, bool enable, + enum mlxsw_reg_ritr_if_type type, + u16 rif, u16 mtu, const char *mac) +{ + bool op = enable ? MLXSW_REG_RITR_RIF_CREATE : MLXSW_REG_RITR_RIF_DEL; + + MLXSW_REG_ZERO(ritr, payload); + mlxsw_reg_ritr_enable_set(payload, enable); + mlxsw_reg_ritr_ipv4_set(payload, 1); + mlxsw_reg_ritr_type_set(payload, type); + mlxsw_reg_ritr_op_set(payload, op); + mlxsw_reg_ritr_rif_set(payload, rif); + mlxsw_reg_ritr_ipv4_fe_set(payload, 1); + mlxsw_reg_ritr_mtu_set(payload, mtu); + mlxsw_reg_ritr_if_mac_memcpy_to(payload, mac); +} + +/* RATR - Router Adjacency Table Register + * -------------------------------------- + * The RATR register is used to configure the Router Adjacency (next-hop) + * Table. + */ +#define MLXSW_REG_RATR_ID 0x8008 +#define MLXSW_REG_RATR_LEN 0x2C + +static const struct mlxsw_reg_info mlxsw_reg_ratr = { + .id = MLXSW_REG_RATR_ID, + .len = MLXSW_REG_RATR_LEN, +}; + +enum mlxsw_reg_ratr_op { + /* Read */ + MLXSW_REG_RATR_OP_QUERY_READ = 0, + /* Read and clear activity */ + MLXSW_REG_RATR_OP_QUERY_READ_CLEAR = 2, + /* Write Adjacency entry */ + MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY = 1, + /* Write Adjacency entry only if the activity is cleared. + * The write may not succeed if the activity is set. There is not + * direct feedback if the write has succeeded or not, however + * the get will reveal the actual entry (SW can compare the get + * response to the set command). + */ + MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY_ON_ACTIVITY = 3, +}; + +/* reg_ratr_op + * Note that Write operation may also be used for updating + * counter_set_type and counter_index. In this case all other + * fields must not be updated. + * Access: OP + */ +MLXSW_ITEM32(reg, ratr, op, 0x00, 28, 4); + +/* reg_ratr_v + * Valid bit. Indicates if the adjacency entry is valid. + * Note: the device may need some time before reusing an invalidated + * entry. During this time the entry can not be reused. It is + * recommended to use another entry before reusing an invalidated + * entry (e.g. software can put it at the end of the list for + * reusing). Trying to access an invalidated entry not yet cleared + * by the device results with failure indicating "Try Again" status. + * When valid is '0' then egress_router_interface,trap_action, + * adjacency_parameters and counters are reserved + * Access: RW + */ +MLXSW_ITEM32(reg, ratr, v, 0x00, 24, 1); + +/* reg_ratr_a + * Activity. Set for new entries. Set if a packet lookup has hit on + * the specific entry. To clear the a bit, use "clear activity". + * Access: RO + */ +MLXSW_ITEM32(reg, ratr, a, 0x00, 16, 1); + +/* reg_ratr_adjacency_index_low + * Bits 15:0 of index into the adjacency table. + * For SwitchX and SwitchX-2, the adjacency table is linear and + * used for adjacency entries only. + * For Spectrum, the index is to the KVD linear. + * Access: Index + */ +MLXSW_ITEM32(reg, ratr, adjacency_index_low, 0x04, 0, 16); + +/* reg_ratr_egress_router_interface + * Range is 0 .. cap_max_router_interfaces - 1 + * Access: RW + */ +MLXSW_ITEM32(reg, ratr, egress_router_interface, 0x08, 0, 16); + +enum mlxsw_reg_ratr_trap_action { + MLXSW_REG_RATR_TRAP_ACTION_NOP, + MLXSW_REG_RATR_TRAP_ACTION_TRAP, + MLXSW_REG_RATR_TRAP_ACTION_MIRROR_TO_CPU, + MLXSW_REG_RATR_TRAP_ACTION_MIRROR, + MLXSW_REG_RATR_TRAP_ACTION_DISCARD_ERRORS, +}; + +/* reg_ratr_trap_action + * see mlxsw_reg_ratr_trap_action + * Access: RW + */ +MLXSW_ITEM32(reg, ratr, trap_action, 0x0C, 28, 4); + +enum mlxsw_reg_ratr_trap_id { + MLXSW_REG_RATR_TRAP_ID_RTR_EGRESS0 = 0, + MLXSW_REG_RATR_TRAP_ID_RTR_EGRESS1 = 1, +}; + +/* reg_ratr_adjacency_index_high + * Bits 23:16 of the adjacency_index. + * Access: Index + */ +MLXSW_ITEM32(reg, ratr, adjacency_index_high, 0x0C, 16, 8); + +/* reg_ratr_trap_id + * Trap ID to be reported to CPU. + * Trap-ID is RTR_EGRESS0 or RTR_EGRESS1. + * For trap_action of NOP, MIRROR and DISCARD_ERROR + * Access: RW + */ +MLXSW_ITEM32(reg, ratr, trap_id, 0x0C, 0, 8); + +/* reg_ratr_eth_destination_mac + * MAC address of the destination next-hop. + * Access: RW + */ +MLXSW_ITEM_BUF(reg, ratr, eth_destination_mac, 0x12, 6); + +static inline void +mlxsw_reg_ratr_pack(char *payload, + enum mlxsw_reg_ratr_op op, bool valid, + u32 adjacency_index, u16 egress_rif) +{ + MLXSW_REG_ZERO(ratr, payload); + mlxsw_reg_ratr_op_set(payload, op); + mlxsw_reg_ratr_v_set(payload, valid); + mlxsw_reg_ratr_adjacency_index_low_set(payload, adjacency_index); + mlxsw_reg_ratr_adjacency_index_high_set(payload, adjacency_index >> 16); + mlxsw_reg_ratr_egress_router_interface_set(payload, egress_rif); +} + +static inline void mlxsw_reg_ratr_eth_entry_pack(char *payload, + const char *dest_mac) +{ + mlxsw_reg_ratr_eth_destination_mac_memcpy_to(payload, dest_mac); +} + +/* RALTA - Router Algorithmic LPM Tree Allocation Register + * ------------------------------------------------------- + * RALTA is used to allocate the LPM trees of the SHSPM method. + */ +#define MLXSW_REG_RALTA_ID 0x8010 +#define MLXSW_REG_RALTA_LEN 0x04 + +static const struct mlxsw_reg_info mlxsw_reg_ralta = { + .id = MLXSW_REG_RALTA_ID, + .len = MLXSW_REG_RALTA_LEN, +}; + +/* reg_ralta_op + * opcode (valid for Write, must be 0 on Read) + * 0 - allocate a tree + * 1 - deallocate a tree + * Access: OP + */ +MLXSW_ITEM32(reg, ralta, op, 0x00, 28, 2); + +enum mlxsw_reg_ralxx_protocol { + MLXSW_REG_RALXX_PROTOCOL_IPV4, + MLXSW_REG_RALXX_PROTOCOL_IPV6, +}; + +/* reg_ralta_protocol + * Protocol. + * Deallocation opcode: Reserved. + * Access: RW + */ +MLXSW_ITEM32(reg, ralta, protocol, 0x00, 24, 4); + +/* reg_ralta_tree_id + * An identifier (numbered from 1..cap_shspm_max_trees-1) representing + * the tree identifier (managed by software). + * Note that tree_id 0 is allocated for a default-route tree. + * Access: Index + */ +MLXSW_ITEM32(reg, ralta, tree_id, 0x00, 0, 8); + +static inline void mlxsw_reg_ralta_pack(char *payload, bool alloc, + enum mlxsw_reg_ralxx_protocol protocol, + u8 tree_id) +{ + MLXSW_REG_ZERO(ralta, payload); + mlxsw_reg_ralta_op_set(payload, !alloc); + mlxsw_reg_ralta_protocol_set(payload, protocol); + mlxsw_reg_ralta_tree_id_set(payload, tree_id); +} + +/* RALST - Router Algorithmic LPM Structure Tree Register + * ------------------------------------------------------ + * RALST is used to set and query the structure of an LPM tree. + * The structure of the tree must be sorted as a sorted binary tree, while + * each node is a bin that is tagged as the length of the prefixes the lookup + * will refer to. Therefore, bin X refers to a set of entries with prefixes + * of X bits to match with the destination address. The bin 0 indicates + * the default action, when there is no match of any prefix. + */ +#define MLXSW_REG_RALST_ID 0x8011 +#define MLXSW_REG_RALST_LEN 0x104 + +static const struct mlxsw_reg_info mlxsw_reg_ralst = { + .id = MLXSW_REG_RALST_ID, + .len = MLXSW_REG_RALST_LEN, +}; + +/* reg_ralst_root_bin + * The bin number of the root bin. + * 0<root_bin=<(length of IP address) + * For a default-route tree configure 0xff + * Access: RW + */ +MLXSW_ITEM32(reg, ralst, root_bin, 0x00, 16, 8); + +/* reg_ralst_tree_id + * Tree identifier numbered from 1..(cap_shspm_max_trees-1). + * Access: Index + */ +MLXSW_ITEM32(reg, ralst, tree_id, 0x00, 0, 8); + +#define MLXSW_REG_RALST_BIN_NO_CHILD 0xff +#define MLXSW_REG_RALST_BIN_OFFSET 0x04 +#define MLXSW_REG_RALST_BIN_COUNT 128 + +/* reg_ralst_left_child_bin + * Holding the children of the bin according to the stored tree's structure. + * For trees composed of less than 4 blocks, the bins in excess are reserved. + * Note that tree_id 0 is allocated for a default-route tree, bins are 0xff + * Access: RW + */ +MLXSW_ITEM16_INDEXED(reg, ralst, left_child_bin, 0x04, 8, 8, 0x02, 0x00, false); + +/* reg_ralst_right_child_bin + * Holding the children of the bin according to the stored tree's structure. + * For trees composed of less than 4 blocks, the bins in excess are reserved. + * Note that tree_id 0 is allocated for a default-route tree, bins are 0xff + * Access: RW + */ +MLXSW_ITEM16_INDEXED(reg, ralst, right_child_bin, 0x04, 0, 8, 0x02, 0x00, + false); + +static inline void mlxsw_reg_ralst_pack(char *payload, u8 root_bin, u8 tree_id) +{ + MLXSW_REG_ZERO(ralst, payload); + + /* Initialize all bins to have no left or right child */ + memset(payload + MLXSW_REG_RALST_BIN_OFFSET, + MLXSW_REG_RALST_BIN_NO_CHILD, MLXSW_REG_RALST_BIN_COUNT * 2); + + mlxsw_reg_ralst_root_bin_set(payload, root_bin); + mlxsw_reg_ralst_tree_id_set(payload, tree_id); +} + +static inline void mlxsw_reg_ralst_bin_pack(char *payload, u8 bin_number, + u8 left_child_bin, + u8 right_child_bin) +{ + int bin_index = bin_number - 1; + + mlxsw_reg_ralst_left_child_bin_set(payload, bin_index, left_child_bin); + mlxsw_reg_ralst_right_child_bin_set(payload, bin_index, + right_child_bin); +} + +/* RALTB - Router Algorithmic LPM Tree Binding Register + * ---------------------------------------------------- + * RALTB is used to bind virtual router and protocol to an allocated LPM tree. + */ +#define MLXSW_REG_RALTB_ID 0x8012 +#define MLXSW_REG_RALTB_LEN 0x04 + +static const struct mlxsw_reg_info mlxsw_reg_raltb = { + .id = MLXSW_REG_RALTB_ID, + .len = MLXSW_REG_RALTB_LEN, +}; + +/* reg_raltb_virtual_router + * Virtual Router ID + * Range is 0..cap_max_virtual_routers-1 + * Access: Index + */ +MLXSW_ITEM32(reg, raltb, virtual_router, 0x00, 16, 16); + +/* reg_raltb_protocol + * Protocol. + * Access: Index + */ +MLXSW_ITEM32(reg, raltb, protocol, 0x00, 12, 4); + +/* reg_raltb_tree_id + * Tree to be used for the {virtual_router, protocol} + * Tree identifier numbered from 1..(cap_shspm_max_trees-1). + * By default, all Unicast IPv4 and IPv6 are bound to tree_id 0. + * Access: RW + */ +MLXSW_ITEM32(reg, raltb, tree_id, 0x00, 0, 8); + +static inline void mlxsw_reg_raltb_pack(char *payload, u16 virtual_router, + enum mlxsw_reg_ralxx_protocol protocol, + u8 tree_id) +{ + MLXSW_REG_ZERO(raltb, payload); + mlxsw_reg_raltb_virtual_router_set(payload, virtual_router); + mlxsw_reg_raltb_protocol_set(payload, protocol); + mlxsw_reg_raltb_tree_id_set(payload, tree_id); +} + +/* RALUE - Router Algorithmic LPM Unicast Entry Register + * ----------------------------------------------------- + * RALUE is used to configure and query LPM entries that serve + * the Unicast protocols. + */ +#define MLXSW_REG_RALUE_ID 0x8013 +#define MLXSW_REG_RALUE_LEN 0x38 + +static const struct mlxsw_reg_info mlxsw_reg_ralue = { + .id = MLXSW_REG_RALUE_ID, + .len = MLXSW_REG_RALUE_LEN, +}; + +/* reg_ralue_protocol + * Protocol. + * Access: Index + */ +MLXSW_ITEM32(reg, ralue, protocol, 0x00, 24, 4); + +enum mlxsw_reg_ralue_op { + /* Read operation. If entry doesn't exist, the operation fails. */ + MLXSW_REG_RALUE_OP_QUERY_READ = 0, + /* Clear on read operation. Used to read entry and + * clear Activity bit. + */ + MLXSW_REG_RALUE_OP_QUERY_CLEAR = 1, + /* Write operation. Used to write a new entry to the table. All RW + * fields are written for new entry. Activity bit is set + * for new entries. + */ + MLXSW_REG_RALUE_OP_WRITE_WRITE = 0, + /* Update operation. Used to update an existing route entry and + * only update the RW fields that are detailed in the field + * op_u_mask. If entry doesn't exist, the operation fails. + */ + MLXSW_REG_RALUE_OP_WRITE_UPDATE = 1, + /* Clear activity. The Activity bit (the field a) is cleared + * for the entry. + */ + MLXSW_REG_RALUE_OP_WRITE_CLEAR = 2, + /* Delete operation. Used to delete an existing entry. If entry + * doesn't exist, the operation fails. + */ + MLXSW_REG_RALUE_OP_WRITE_DELETE = 3, +}; + +/* reg_ralue_op + * Operation. + * Access: OP + */ +MLXSW_ITEM32(reg, ralue, op, 0x00, 20, 3); + +/* reg_ralue_a + * Activity. Set for new entries. Set if a packet lookup has hit on the + * specific entry, only if the entry is a route. To clear the a bit, use + * "clear activity" op. + * Enabled by activity_dis in RGCR + * Access: RO + */ +MLXSW_ITEM32(reg, ralue, a, 0x00, 16, 1); + +/* reg_ralue_virtual_router + * Virtual Router ID + * Range is 0..cap_max_virtual_routers-1 + * Access: Index + */ +MLXSW_ITEM32(reg, ralue, virtual_router, 0x04, 16, 16); + +#define MLXSW_REG_RALUE_OP_U_MASK_ENTRY_TYPE BIT(0) +#define MLXSW_REG_RALUE_OP_U_MASK_BMP_LEN BIT(1) +#define MLXSW_REG_RALUE_OP_U_MASK_ACTION BIT(2) + +/* reg_ralue_op_u_mask + * opcode update mask. + * On read operation, this field is reserved. + * This field is valid for update opcode, otherwise - reserved. + * This field is a bitmask of the fields that should be updated. + * Access: WO + */ +MLXSW_ITEM32(reg, ralue, op_u_mask, 0x04, 8, 3); + +/* reg_ralue_prefix_len + * Number of bits in the prefix of the LPM route. + * Note that for IPv6 prefixes, if prefix_len>64 the entry consumes + * two entries in the physical HW table. + * Access: Index + */ +MLXSW_ITEM32(reg, ralue, prefix_len, 0x08, 0, 8); + +/* reg_ralue_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 list significant bits must be '0' if the prefix_len is smaller + * than 128 for IPv6 or smaller than 32 for IPv4. + * IPv4 address uses bits dip[31:0] and bits dip[127:32] are reserved. + * Access: Index + */ +MLXSW_ITEM32(reg, ralue, dip4, 0x18, 0, 32); + +enum mlxsw_reg_ralue_entry_type { + MLXSW_REG_RALUE_ENTRY_TYPE_MARKER_ENTRY = 1, + MLXSW_REG_RALUE_ENTRY_TYPE_ROUTE_ENTRY = 2, + MLXSW_REG_RALUE_ENTRY_TYPE_MARKER_AND_ROUTE_ENTRY = 3, +}; + +/* reg_ralue_entry_type + * Entry type. + * Note - for Marker entries, the action_type and action fields are reserved. + * Access: RW + */ +MLXSW_ITEM32(reg, ralue, entry_type, 0x1C, 30, 2); + +/* reg_ralue_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 + * Note for any update operation with entry_type modification this + * field must be set. + * Access: RW + */ +MLXSW_ITEM32(reg, ralue, bmp_len, 0x1C, 16, 8); + +enum mlxsw_reg_ralue_action_type { + MLXSW_REG_RALUE_ACTION_TYPE_REMOTE, + MLXSW_REG_RALUE_ACTION_TYPE_LOCAL, + MLXSW_REG_RALUE_ACTION_TYPE_IP2ME, +}; + +/* reg_ralue_action_type + * Action Type + * Indicates how the IP address is connected. + * It can be connected to a local subnet through local_erif or can be + * on a remote subnet connected through a next-hop router, + * or transmitted to the CPU. + * Reserved when entry_type = MARKER_ENTRY + * Access: RW + */ +MLXSW_ITEM32(reg, ralue, action_type, 0x1C, 0, 2); + +enum mlxsw_reg_ralue_trap_action { + MLXSW_REG_RALUE_TRAP_ACTION_NOP, + MLXSW_REG_RALUE_TRAP_ACTION_TRAP, + MLXSW_REG_RALUE_TRAP_ACTION_MIRROR_TO_CPU, + MLXSW_REG_RALUE_TRAP_ACTION_MIRROR, + MLXSW_REG_RALUE_TRAP_ACTION_DISCARD_ERROR, +}; + +/* reg_ralue_trap_action + * Trap action. + * For IP2ME action, only NOP and MIRROR are possible. + * Access: RW + */ +MLXSW_ITEM32(reg, ralue, trap_action, 0x20, 28, 4); + +/* reg_ralue_trap_id + * Trap ID to be reported to CPU. + * Trap ID is RTR_INGRESS0 or RTR_INGRESS1. + * For trap_action of NOP, MIRROR and DISCARD_ERROR, trap_id is reserved. + * Access: RW + */ +MLXSW_ITEM32(reg, ralue, trap_id, 0x20, 0, 9); + +/* reg_ralue_adjacency_index + * Points to the first entry of the group-based ECMP. + * Only relevant in case of REMOTE action. + * Access: RW + */ +MLXSW_ITEM32(reg, ralue, adjacency_index, 0x24, 0, 24); + +/* reg_ralue_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. + * Reserved when trap_action is TRAP or DISCARD_ERROR. + * Only relevant in case of REMOTE action. + * Access: RW + */ +MLXSW_ITEM32(reg, ralue, ecmp_size, 0x28, 0, 13); + +/* reg_ralue_local_erif + * Egress Router Interface. + * Only relevant in case of LOCAL action. + * Access: RW + */ +MLXSW_ITEM32(reg, ralue, local_erif, 0x24, 0, 16); + +/* reg_ralue_v + * Valid bit for the tunnel_ptr field. + * If valid = 0 then trap to CPU as IP2ME trap ID. + * If valid = 1 and the packet format allows NVE or IPinIP tunnel + * decapsulation then tunnel decapsulation is done. + * If valid = 1 and packet format does not allow NVE or IPinIP tunnel + * decapsulation then trap as IP2ME trap ID. + * Only relevant in case of IP2ME action. + * Access: RW + */ +MLXSW_ITEM32(reg, ralue, v, 0x24, 31, 1); + +/* reg_ralue_tunnel_ptr + * Tunnel Pointer for NVE or IPinIP tunnel decapsulation. + * For Spectrum, pointer to KVD Linear. + * Only relevant in case of IP2ME action. + * Access: RW + */ +MLXSW_ITEM32(reg, ralue, tunnel_ptr, 0x24, 0, 24); + +static inline void mlxsw_reg_ralue_pack(char *payload, + enum mlxsw_reg_ralxx_protocol protocol, + enum mlxsw_reg_ralue_op op, + u16 virtual_router, u8 prefix_len) +{ + MLXSW_REG_ZERO(ralue, payload); + mlxsw_reg_ralue_protocol_set(payload, protocol); + mlxsw_reg_ralue_virtual_router_set(payload, virtual_router); + mlxsw_reg_ralue_prefix_len_set(payload, prefix_len); + mlxsw_reg_ralue_entry_type_set(payload, + MLXSW_REG_RALUE_ENTRY_TYPE_ROUTE_ENTRY); + mlxsw_reg_ralue_bmp_len_set(payload, prefix_len); +} + +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) +{ + mlxsw_reg_ralue_pack(payload, protocol, op, virtual_router, prefix_len); + mlxsw_reg_ralue_dip4_set(payload, dip); +} + +static inline void +mlxsw_reg_ralue_act_remote_pack(char *payload, + enum mlxsw_reg_ralue_trap_action trap_action, + u16 trap_id, u32 adjacency_index, u16 ecmp_size) +{ + mlxsw_reg_ralue_action_type_set(payload, + MLXSW_REG_RALUE_ACTION_TYPE_REMOTE); + mlxsw_reg_ralue_trap_action_set(payload, trap_action); + mlxsw_reg_ralue_trap_id_set(payload, trap_id); + mlxsw_reg_ralue_adjacency_index_set(payload, adjacency_index); + mlxsw_reg_ralue_ecmp_size_set(payload, ecmp_size); +} + +static inline void +mlxsw_reg_ralue_act_local_pack(char *payload, + enum mlxsw_reg_ralue_trap_action trap_action, + u16 trap_id, u16 local_erif) +{ + mlxsw_reg_ralue_action_type_set(payload, + MLXSW_REG_RALUE_ACTION_TYPE_LOCAL); + mlxsw_reg_ralue_trap_action_set(payload, trap_action); + mlxsw_reg_ralue_trap_id_set(payload, trap_id); + mlxsw_reg_ralue_local_erif_set(payload, local_erif); +} + +static inline void +mlxsw_reg_ralue_act_ip2me_pack(char *payload) +{ + mlxsw_reg_ralue_action_type_set(payload, + MLXSW_REG_RALUE_ACTION_TYPE_IP2ME); +} + +/* RAUHT - Router Algorithmic LPM Unicast Host Table Register + * ---------------------------------------------------------- + * The RAUHT register is used to configure and query the Unicast Host table in + * devices that implement the Algorithmic LPM. + */ +#define MLXSW_REG_RAUHT_ID 0x8014 +#define MLXSW_REG_RAUHT_LEN 0x74 + +static const struct mlxsw_reg_info mlxsw_reg_rauht = { + .id = MLXSW_REG_RAUHT_ID, + .len = MLXSW_REG_RAUHT_LEN, +}; + +enum mlxsw_reg_rauht_type { + MLXSW_REG_RAUHT_TYPE_IPV4, + MLXSW_REG_RAUHT_TYPE_IPV6, +}; + +/* reg_rauht_type + * Access: Index + */ +MLXSW_ITEM32(reg, rauht, type, 0x00, 24, 2); + +enum mlxsw_reg_rauht_op { + MLXSW_REG_RAUHT_OP_QUERY_READ = 0, + /* Read operation */ + MLXSW_REG_RAUHT_OP_QUERY_CLEAR_ON_READ = 1, + /* Clear on read operation. Used to read entry and clear + * activity bit. + */ + MLXSW_REG_RAUHT_OP_WRITE_ADD = 0, + /* Add. Used to write a new entry to the table. All R/W fields are + * relevant for new entry. Activity bit is set for new entries. + */ + MLXSW_REG_RAUHT_OP_WRITE_UPDATE = 1, + /* Update action. Used to update an existing route entry and + * only update the following fields: + * trap_action, trap_id, mac, counter_set_type, counter_index + */ + MLXSW_REG_RAUHT_OP_WRITE_CLEAR_ACTIVITY = 2, + /* Clear activity. A bit is cleared for the entry. */ + MLXSW_REG_RAUHT_OP_WRITE_DELETE = 3, + /* Delete entry */ + MLXSW_REG_RAUHT_OP_WRITE_DELETE_ALL = 4, + /* Delete all host entries on a RIF. In this command, dip + * field is reserved. + */ +}; + +/* reg_rauht_op + * Access: OP + */ +MLXSW_ITEM32(reg, rauht, op, 0x00, 20, 3); + +/* reg_rauht_a + * Activity. Set for new entries. Set if a packet lookup has hit on + * the specific entry. + * To clear the a bit, use "clear activity" op. + * Enabled by activity_dis in RGCR + * Access: RO + */ +MLXSW_ITEM32(reg, rauht, a, 0x00, 16, 1); + +/* reg_rauht_rif + * Router Interface + * Access: Index + */ +MLXSW_ITEM32(reg, rauht, rif, 0x00, 0, 16); + +/* reg_rauht_dip* + * Destination address. + * Access: Index + */ +MLXSW_ITEM32(reg, rauht, dip4, 0x1C, 0x0, 32); + +enum mlxsw_reg_rauht_trap_action { + MLXSW_REG_RAUHT_TRAP_ACTION_NOP, + MLXSW_REG_RAUHT_TRAP_ACTION_TRAP, + MLXSW_REG_RAUHT_TRAP_ACTION_MIRROR_TO_CPU, + MLXSW_REG_RAUHT_TRAP_ACTION_MIRROR, + MLXSW_REG_RAUHT_TRAP_ACTION_DISCARD_ERRORS, +}; + +/* reg_rauht_trap_action + * Access: RW + */ +MLXSW_ITEM32(reg, rauht, trap_action, 0x60, 28, 4); + +enum mlxsw_reg_rauht_trap_id { + MLXSW_REG_RAUHT_TRAP_ID_RTR_EGRESS0, + MLXSW_REG_RAUHT_TRAP_ID_RTR_EGRESS1, +}; + +/* reg_rauht_trap_id + * Trap ID to be reported to CPU. + * Trap-ID is RTR_EGRESS0 or RTR_EGRESS1. + * For trap_action of NOP, MIRROR and DISCARD_ERROR, + * trap_id is reserved. + * Access: RW + */ +MLXSW_ITEM32(reg, rauht, trap_id, 0x60, 0, 9); + +/* reg_rauht_counter_set_type + * Counter set type for flow counters + * Access: RW + */ +MLXSW_ITEM32(reg, rauht, counter_set_type, 0x68, 24, 8); + +/* reg_rauht_counter_index + * Counter index for flow counters + * Access: RW + */ +MLXSW_ITEM32(reg, rauht, counter_index, 0x68, 0, 24); + +/* reg_rauht_mac + * MAC address. + * Access: RW + */ +MLXSW_ITEM_BUF(reg, rauht, mac, 0x6E, 6); + +static inline void mlxsw_reg_rauht_pack(char *payload, + enum mlxsw_reg_rauht_op op, u16 rif, + const char *mac) +{ + MLXSW_REG_ZERO(rauht, payload); + mlxsw_reg_rauht_op_set(payload, op); + mlxsw_reg_rauht_rif_set(payload, rif); + mlxsw_reg_rauht_mac_memcpy_to(payload, mac); +} + +static inline void mlxsw_reg_rauht_pack4(char *payload, + enum mlxsw_reg_rauht_op op, u16 rif, + const char *mac, u32 dip) +{ + mlxsw_reg_rauht_pack(payload, op, rif, mac); + mlxsw_reg_rauht_dip4_set(payload, dip); +} + +/* RALEU - Router Algorithmic LPM ECMP Update Register + * --------------------------------------------------- + * The register enables updating the ECMP section in the action for multiple + * LPM Unicast entries in a single operation. The update is executed to + * all entries of a {virtual router, protocol} tuple using the same ECMP group. + */ +#define MLXSW_REG_RALEU_ID 0x8015 +#define MLXSW_REG_RALEU_LEN 0x28 + +static const struct mlxsw_reg_info mlxsw_reg_raleu = { + .id = MLXSW_REG_RALEU_ID, + .len = MLXSW_REG_RALEU_LEN, +}; + +/* reg_raleu_protocol + * Protocol. + * Access: Index + */ +MLXSW_ITEM32(reg, raleu, protocol, 0x00, 24, 4); + +/* reg_raleu_virtual_router + * Virtual Router ID + * Range is 0..cap_max_virtual_routers-1 + * Access: Index + */ +MLXSW_ITEM32(reg, raleu, virtual_router, 0x00, 0, 16); + +/* reg_raleu_adjacency_index + * Adjacency Index used for matching on the existing entries. + * Access: Index + */ +MLXSW_ITEM32(reg, raleu, adjacency_index, 0x10, 0, 24); + +/* reg_raleu_ecmp_size + * ECMP Size used for matching on the existing entries. + * Access: Index + */ +MLXSW_ITEM32(reg, raleu, ecmp_size, 0x14, 0, 13); + +/* reg_raleu_new_adjacency_index + * New Adjacency Index. + * Access: WO + */ +MLXSW_ITEM32(reg, raleu, new_adjacency_index, 0x20, 0, 24); + +/* reg_raleu_new_ecmp_size + * New ECMP Size. + * Access: WO + */ +MLXSW_ITEM32(reg, raleu, new_ecmp_size, 0x24, 0, 13); + +static inline void mlxsw_reg_raleu_pack(char *payload, + enum mlxsw_reg_ralxx_protocol protocol, + u16 virtual_router, + u32 adjacency_index, u16 ecmp_size, + u32 new_adjacency_index, + u16 new_ecmp_size) +{ + MLXSW_REG_ZERO(raleu, payload); + mlxsw_reg_raleu_protocol_set(payload, protocol); + mlxsw_reg_raleu_virtual_router_set(payload, virtual_router); + mlxsw_reg_raleu_adjacency_index_set(payload, adjacency_index); + mlxsw_reg_raleu_ecmp_size_set(payload, ecmp_size); + mlxsw_reg_raleu_new_adjacency_index_set(payload, new_adjacency_index); + mlxsw_reg_raleu_new_ecmp_size_set(payload, new_ecmp_size); +} + +/* RAUHTD - Router Algorithmic LPM Unicast Host Table Dump Register + * ---------------------------------------------------------------- + * The RAUHTD register allows dumping entries from the Router Unicast Host + * Table. For a given session an entry is dumped no more than one time. The + * first RAUHTD access after reset is a new session. A session ends when the + * num_rec response is smaller than num_rec request or for IPv4 when the + * num_entries is smaller than 4. The clear activity affect the current session + * or the last session if a new session has not started. + */ +#define MLXSW_REG_RAUHTD_ID 0x8018 +#define MLXSW_REG_RAUHTD_BASE_LEN 0x20 +#define MLXSW_REG_RAUHTD_REC_LEN 0x20 +#define MLXSW_REG_RAUHTD_REC_MAX_NUM 32 +#define MLXSW_REG_RAUHTD_LEN (MLXSW_REG_RAUHTD_BASE_LEN + \ + MLXSW_REG_RAUHTD_REC_MAX_NUM * MLXSW_REG_RAUHTD_REC_LEN) +#define MLXSW_REG_RAUHTD_IPV4_ENT_PER_REC 4 + +static const struct mlxsw_reg_info mlxsw_reg_rauhtd = { + .id = MLXSW_REG_RAUHTD_ID, + .len = MLXSW_REG_RAUHTD_LEN, +}; + +#define MLXSW_REG_RAUHTD_FILTER_A BIT(0) +#define MLXSW_REG_RAUHTD_FILTER_RIF BIT(3) + +/* reg_rauhtd_filter_fields + * if a bit is '0' then the relevant field is ignored and dump is done + * regardless of the field value + * Bit0 - filter by activity: entry_a + * Bit3 - filter by entry rip: entry_rif + * Access: Index + */ +MLXSW_ITEM32(reg, rauhtd, filter_fields, 0x00, 0, 8); + +enum mlxsw_reg_rauhtd_op { + MLXSW_REG_RAUHTD_OP_DUMP, + MLXSW_REG_RAUHTD_OP_DUMP_AND_CLEAR, +}; + +/* reg_rauhtd_op + * Access: OP + */ +MLXSW_ITEM32(reg, rauhtd, op, 0x04, 24, 2); + +/* reg_rauhtd_num_rec + * At request: number of records requested + * At response: number of records dumped + * For IPv4, each record has 4 entries at request and up to 4 entries + * at response + * Range is 0..MLXSW_REG_RAUHTD_REC_MAX_NUM + * Access: Index + */ +MLXSW_ITEM32(reg, rauhtd, num_rec, 0x04, 0, 8); + +/* reg_rauhtd_entry_a + * Dump only if activity has value of entry_a + * Reserved if filter_fields bit0 is '0' + * Access: Index + */ +MLXSW_ITEM32(reg, rauhtd, entry_a, 0x08, 16, 1); + +enum mlxsw_reg_rauhtd_type { + MLXSW_REG_RAUHTD_TYPE_IPV4, + MLXSW_REG_RAUHTD_TYPE_IPV6, +}; + +/* reg_rauhtd_type + * Dump only if record type is: + * 0 - IPv4 + * 1 - IPv6 + * Access: Index + */ +MLXSW_ITEM32(reg, rauhtd, type, 0x08, 0, 4); + +/* reg_rauhtd_entry_rif + * Dump only if RIF has value of entry_rif + * Reserved if filter_fields bit3 is '0' + * Access: Index + */ +MLXSW_ITEM32(reg, rauhtd, entry_rif, 0x0C, 0, 16); + +static inline void mlxsw_reg_rauhtd_pack(char *payload, + enum mlxsw_reg_rauhtd_type type) +{ + MLXSW_REG_ZERO(rauhtd, payload); + mlxsw_reg_rauhtd_filter_fields_set(payload, MLXSW_REG_RAUHTD_FILTER_A); + mlxsw_reg_rauhtd_op_set(payload, MLXSW_REG_RAUHTD_OP_DUMP_AND_CLEAR); + mlxsw_reg_rauhtd_num_rec_set(payload, MLXSW_REG_RAUHTD_REC_MAX_NUM); + mlxsw_reg_rauhtd_entry_a_set(payload, 1); + mlxsw_reg_rauhtd_type_set(payload, type); +} + +/* reg_rauhtd_ipv4_rec_num_entries + * Number of valid entries in this record: + * 0 - 1 valid entry + * 1 - 2 valid entries + * 2 - 3 valid entries + * 3 - 4 valid entries + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, rauhtd, ipv4_rec_num_entries, + MLXSW_REG_RAUHTD_BASE_LEN, 28, 2, + MLXSW_REG_RAUHTD_REC_LEN, 0x00, false); + +/* reg_rauhtd_rec_type + * Record type. + * 0 - IPv4 + * 1 - IPv6 + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, rauhtd, rec_type, MLXSW_REG_RAUHTD_BASE_LEN, 24, 2, + MLXSW_REG_RAUHTD_REC_LEN, 0x00, false); + +#define MLXSW_REG_RAUHTD_IPV4_ENT_LEN 0x8 + +/* reg_rauhtd_ipv4_ent_a + * Activity. Set for new entries. Set if a packet lookup has hit on the + * specific entry. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, rauhtd, ipv4_ent_a, MLXSW_REG_RAUHTD_BASE_LEN, 16, 1, + MLXSW_REG_RAUHTD_IPV4_ENT_LEN, 0x00, false); + +/* reg_rauhtd_ipv4_ent_rif + * Router interface. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, rauhtd, ipv4_ent_rif, MLXSW_REG_RAUHTD_BASE_LEN, 0, + 16, MLXSW_REG_RAUHTD_IPV4_ENT_LEN, 0x00, false); + +/* reg_rauhtd_ipv4_ent_dip + * Destination IPv4 address. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, rauhtd, ipv4_ent_dip, MLXSW_REG_RAUHTD_BASE_LEN, 0, + 32, MLXSW_REG_RAUHTD_IPV4_ENT_LEN, 0x04, false); + +static inline void mlxsw_reg_rauhtd_ent_ipv4_unpack(char *payload, + int ent_index, u16 *p_rif, + u32 *p_dip) +{ + *p_rif = mlxsw_reg_rauhtd_ipv4_ent_rif_get(payload, ent_index); + *p_dip = mlxsw_reg_rauhtd_ipv4_ent_dip_get(payload, ent_index); +} + /* MFCR - Management Fan Control Register * -------------------------------------- * This register controls the settings of the Fan Speed PWM mechanism. @@ -3435,6 +4633,123 @@ static inline void mlxsw_reg_mtmp_unpack(char *payload, unsigned int *p_temp, mlxsw_reg_mtmp_sensor_name_memcpy_from(payload, sensor_name); } +/* MPAT - Monitoring Port Analyzer Table + * ------------------------------------- + * MPAT Register is used to query and configure the Switch PortAnalyzer Table. + * For an enabled analyzer, all fields except e (enable) cannot be modified. + */ +#define MLXSW_REG_MPAT_ID 0x901A +#define MLXSW_REG_MPAT_LEN 0x78 + +static const struct mlxsw_reg_info mlxsw_reg_mpat = { + .id = MLXSW_REG_MPAT_ID, + .len = MLXSW_REG_MPAT_LEN, +}; + +/* reg_mpat_pa_id + * Port Analyzer ID. + * Access: Index + */ +MLXSW_ITEM32(reg, mpat, pa_id, 0x00, 28, 4); + +/* reg_mpat_system_port + * A unique port identifier for the final destination of the packet. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, system_port, 0x00, 0, 16); + +/* reg_mpat_e + * Enable. Indicating the Port Analyzer is enabled. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, e, 0x04, 31, 1); + +/* reg_mpat_qos + * Quality Of Service Mode. + * 0: CONFIGURED - QoS parameters (Switch Priority, and encapsulation + * PCP, DEI, DSCP or VL) are configured. + * 1: MAINTAIN - QoS parameters (Switch Priority, Color) are the + * same as in the original packet that has triggered the mirroring. For + * SPAN also the pcp,dei are maintained. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, qos, 0x04, 26, 1); + +/* reg_mpat_be + * Best effort mode. Indicates mirroring traffic should not cause packet + * drop or back pressure, but will discard the mirrored packets. Mirrored + * packets will be forwarded on a best effort manner. + * 0: Do not discard mirrored packets + * 1: Discard mirrored packets if causing congestion + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, be, 0x04, 25, 1); + +static inline void mlxsw_reg_mpat_pack(char *payload, u8 pa_id, + u16 system_port, bool e) +{ + MLXSW_REG_ZERO(mpat, payload); + mlxsw_reg_mpat_pa_id_set(payload, pa_id); + mlxsw_reg_mpat_system_port_set(payload, system_port); + mlxsw_reg_mpat_e_set(payload, e); + mlxsw_reg_mpat_qos_set(payload, 1); + mlxsw_reg_mpat_be_set(payload, 1); +} + +/* MPAR - Monitoring Port Analyzer Register + * ---------------------------------------- + * MPAR register is used to query and configure the port analyzer port mirroring + * properties. + */ +#define MLXSW_REG_MPAR_ID 0x901B +#define MLXSW_REG_MPAR_LEN 0x08 + +static const struct mlxsw_reg_info mlxsw_reg_mpar = { + .id = MLXSW_REG_MPAR_ID, + .len = MLXSW_REG_MPAR_LEN, +}; + +/* reg_mpar_local_port + * The local port to mirror the packets from. + * Access: Index + */ +MLXSW_ITEM32(reg, mpar, local_port, 0x00, 16, 8); + +enum mlxsw_reg_mpar_i_e { + MLXSW_REG_MPAR_TYPE_EGRESS, + MLXSW_REG_MPAR_TYPE_INGRESS, +}; + +/* reg_mpar_i_e + * Ingress/Egress + * Access: Index + */ +MLXSW_ITEM32(reg, mpar, i_e, 0x00, 0, 4); + +/* reg_mpar_enable + * Enable mirroring + * By default, port mirroring is disabled for all ports. + * Access: RW + */ +MLXSW_ITEM32(reg, mpar, enable, 0x04, 31, 1); + +/* reg_mpar_pa_id + * Port Analyzer ID. + * Access: RW + */ +MLXSW_ITEM32(reg, mpar, pa_id, 0x04, 0, 4); + +static inline void mlxsw_reg_mpar_pack(char *payload, u8 local_port, + enum mlxsw_reg_mpar_i_e i_e, + bool enable, u8 pa_id) +{ + MLXSW_REG_ZERO(mpar, payload); + mlxsw_reg_mpar_local_port_set(payload, local_port); + mlxsw_reg_mpar_enable_set(payload, enable); + mlxsw_reg_mpar_i_e_set(payload, i_e); + mlxsw_reg_mpar_pa_id_set(payload, pa_id); +} + /* MLCR - Management LED Control Register * -------------------------------------- * Controls the system LEDs. @@ -3864,6 +5179,45 @@ static inline void mlxsw_reg_sbsr_rec_unpack(char *payload, int rec_index, mlxsw_reg_sbsr_rec_max_buff_occupancy_get(payload, rec_index); } +/* SBIB - Shared Buffer Internal Buffer Register + * --------------------------------------------- + * The SBIB register configures per port buffers for internal use. The internal + * buffers consume memory on the port buffers (note that the port buffers are + * used also by PBMC). + * + * For Spectrum this is used for egress mirroring. + */ +#define MLXSW_REG_SBIB_ID 0xB006 +#define MLXSW_REG_SBIB_LEN 0x10 + +static const struct mlxsw_reg_info mlxsw_reg_sbib = { + .id = MLXSW_REG_SBIB_ID, + .len = MLXSW_REG_SBIB_LEN, +}; + +/* reg_sbib_local_port + * Local port number + * Not supported for CPU port and router port + * Access: Index + */ +MLXSW_ITEM32(reg, sbib, local_port, 0x00, 16, 8); + +/* reg_sbib_buff_size + * Units represented in cells + * Allowed range is 0 to (cap_max_headroom_size - 1) + * Default is 0 + * Access: RW + */ +MLXSW_ITEM32(reg, sbib, buff_size, 0x08, 0, 24); + +static inline void mlxsw_reg_sbib_pack(char *payload, u8 local_port, + u32 buff_size) +{ + MLXSW_REG_ZERO(sbib, payload); + mlxsw_reg_sbib_local_port_set(payload, local_port); + mlxsw_reg_sbib_buff_size_set(payload, buff_size); +} + static inline const char *mlxsw_reg_id_str(u16 reg_id) { switch (reg_id) { @@ -3939,6 +5293,26 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id) return "HTGT"; case MLXSW_REG_HPKT_ID: return "HPKT"; + case MLXSW_REG_RGCR_ID: + return "RGCR"; + case MLXSW_REG_RITR_ID: + return "RITR"; + case MLXSW_REG_RATR_ID: + return "RATR"; + case MLXSW_REG_RALTA_ID: + return "RALTA"; + case MLXSW_REG_RALST_ID: + return "RALST"; + case MLXSW_REG_RALTB_ID: + return "RALTB"; + case MLXSW_REG_RALUE_ID: + return "RALUE"; + case MLXSW_REG_RAUHT_ID: + return "RAUHT"; + case MLXSW_REG_RALEU_ID: + return "RALEU"; + case MLXSW_REG_RAUHTD_ID: + return "RAUHTD"; case MLXSW_REG_MFCR_ID: return "MFCR"; case MLXSW_REG_MFSC_ID: @@ -3947,6 +5321,10 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id) return "MFSM"; case MLXSW_REG_MTCAP_ID: return "MTCAP"; + case MLXSW_REG_MPAT_ID: + return "MPAT"; + case MLXSW_REG_MPAR_ID: + return "MPAR"; case MLXSW_REG_MTMP_ID: return "MTMP"; case MLXSW_REG_MLCR_ID: @@ -3961,6 +5339,8 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id) return "SBMM"; case MLXSW_REG_SBSR_ID: return "SBSR"; + case MLXSW_REG_SBIB_ID: + return "SBIB"; default: return "*UNKNOWN*"; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 374080027b2f..c3e61500819d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -49,9 +49,13 @@ #include <linux/jiffies.h> #include <linux/bitops.h> #include <linux/list.h> +#include <linux/notifier.h> #include <linux/dcbnl.h> +#include <linux/inetdevice.h> #include <net/switchdev.h> #include <generated/utsrelease.h> +#include <net/pkt_cls.h> +#include <net/tc_act/tc_mirred.h> #include "spectrum.h" #include "core.h" @@ -131,6 +135,8 @@ MLXSW_ITEM32(tx, hdr, fid, 0x08, 0, 16); */ MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4); +static bool mlxsw_sp_port_dev_check(const struct net_device *dev); + static void mlxsw_sp_txhdr_construct(struct sk_buff *skb, const struct mlxsw_tx_info *tx_info) { @@ -159,6 +165,303 @@ static int mlxsw_sp_base_mac_get(struct mlxsw_sp *mlxsw_sp) return 0; } +static int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_resources *resources; + int i; + + resources = mlxsw_core_resources_get(mlxsw_sp->core); + if (!resources->max_span_valid) + return -EIO; + + mlxsw_sp->span.entries_count = resources->max_span; + mlxsw_sp->span.entries = kcalloc(mlxsw_sp->span.entries_count, + sizeof(struct mlxsw_sp_span_entry), + GFP_KERNEL); + if (!mlxsw_sp->span.entries) + return -ENOMEM; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) + INIT_LIST_HEAD(&mlxsw_sp->span.entries[i].bound_ports_list); + + return 0; +} + +static void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp) +{ + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + WARN_ON_ONCE(!list_empty(&curr->bound_ports_list)); + } + kfree(mlxsw_sp->span.entries); +} + +static struct mlxsw_sp_span_entry * +mlxsw_sp_span_entry_create(struct mlxsw_sp_port *port) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + struct mlxsw_sp_span_entry *span_entry; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + u8 local_port = port->local_port; + int index; + int i; + int err; + + /* find a free entry to use */ + index = -1; + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + if (!mlxsw_sp->span.entries[i].used) { + index = i; + span_entry = &mlxsw_sp->span.entries[i]; + break; + } + } + if (index < 0) + return NULL; + + /* create a new port analayzer entry for local_port */ + mlxsw_reg_mpat_pack(mpat_pl, index, local_port, true); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); + if (err) + return NULL; + + span_entry->used = true; + span_entry->id = index; + span_entry->ref_count = 0; + span_entry->local_port = local_port; + return span_entry; +} + +static void mlxsw_sp_span_entry_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_span_entry *span_entry) +{ + u8 local_port = span_entry->local_port; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + int pa_id = span_entry->id; + + mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, false); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); + span_entry->used = false; +} + +struct mlxsw_sp_span_entry *mlxsw_sp_span_entry_find(struct mlxsw_sp_port *port) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + if (curr->used && curr->local_port == port->local_port) + return curr; + } + return NULL; +} + +struct mlxsw_sp_span_entry *mlxsw_sp_span_entry_get(struct mlxsw_sp_port *port) +{ + struct mlxsw_sp_span_entry *span_entry; + + span_entry = mlxsw_sp_span_entry_find(port); + if (span_entry) { + span_entry->ref_count++; + return span_entry; + } + + return mlxsw_sp_span_entry_create(port); +} + +static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_span_entry *span_entry) +{ + if (--span_entry->ref_count == 0) + mlxsw_sp_span_entry_destroy(mlxsw_sp, span_entry); + return 0; +} + +static bool mlxsw_sp_span_is_egress_mirror(struct mlxsw_sp_port *port) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + struct mlxsw_sp_span_inspected_port *p; + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + list_for_each_entry(p, &curr->bound_ports_list, list) + if (p->local_port == port->local_port && + p->type == MLXSW_SP_SPAN_EGRESS) + return true; + } + + return false; +} + +static int mlxsw_sp_span_mtu_to_buffsize(int mtu) +{ + return MLXSW_SP_BYTES_TO_CELLS(mtu * 5 / 2) + 1; +} + +static int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char sbib_pl[MLXSW_REG_SBIB_LEN]; + int err; + + /* If port is egress mirrored, the shared buffer size should be + * updated according to the mtu value + */ + if (mlxsw_sp_span_is_egress_mirror(port)) { + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, + mlxsw_sp_span_mtu_to_buffsize(mtu)); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + if (err) { + netdev_err(port->dev, "Could not update shared buffer for mirroring\n"); + return err; + } + } + + return 0; +} + +static struct mlxsw_sp_span_inspected_port * +mlxsw_sp_span_entry_bound_port_find(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry) +{ + struct mlxsw_sp_span_inspected_port *p; + + list_for_each_entry(p, &span_entry->bound_ports_list, list) + if (port->local_port == p->local_port) + return p; + return NULL; +} + +static int +mlxsw_sp_span_inspected_port_bind(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry, + enum mlxsw_sp_span_type type) +{ + struct mlxsw_sp_span_inspected_port *inspected_port; + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char mpar_pl[MLXSW_REG_MPAR_LEN]; + char sbib_pl[MLXSW_REG_SBIB_LEN]; + int pa_id = span_entry->id; + int err; + + /* if it is an egress SPAN, bind a shared buffer to it */ + if (type == MLXSW_SP_SPAN_EGRESS) { + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, + mlxsw_sp_span_mtu_to_buffsize(port->dev->mtu)); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + if (err) { + netdev_err(port->dev, "Could not create shared buffer for mirroring\n"); + return err; + } + } + + /* bind the port to the SPAN entry */ + mlxsw_reg_mpar_pack(mpar_pl, port->local_port, type, true, pa_id); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpar), mpar_pl); + if (err) + goto err_mpar_reg_write; + + inspected_port = kzalloc(sizeof(*inspected_port), GFP_KERNEL); + if (!inspected_port) { + err = -ENOMEM; + goto err_inspected_port_alloc; + } + inspected_port->local_port = port->local_port; + inspected_port->type = type; + list_add_tail(&inspected_port->list, &span_entry->bound_ports_list); + + return 0; + +err_mpar_reg_write: +err_inspected_port_alloc: + if (type == MLXSW_SP_SPAN_EGRESS) { + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + } + return err; +} + +static void +mlxsw_sp_span_inspected_port_unbind(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry, + enum mlxsw_sp_span_type type) +{ + struct mlxsw_sp_span_inspected_port *inspected_port; + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char mpar_pl[MLXSW_REG_MPAR_LEN]; + char sbib_pl[MLXSW_REG_SBIB_LEN]; + int pa_id = span_entry->id; + + inspected_port = mlxsw_sp_span_entry_bound_port_find(port, span_entry); + if (!inspected_port) + return; + + /* remove the inspected port */ + mlxsw_reg_mpar_pack(mpar_pl, port->local_port, type, false, pa_id); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpar), mpar_pl); + + /* remove the SBIB buffer if it was egress SPAN */ + if (type == MLXSW_SP_SPAN_EGRESS) { + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + } + + mlxsw_sp_span_entry_put(mlxsw_sp, span_entry); + + list_del(&inspected_port->list); + kfree(inspected_port); +} + +static int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, + struct mlxsw_sp_port *to, + enum mlxsw_sp_span_type type) +{ + struct mlxsw_sp *mlxsw_sp = from->mlxsw_sp; + struct mlxsw_sp_span_entry *span_entry; + int err; + + span_entry = mlxsw_sp_span_entry_get(to); + if (!span_entry) + return -ENOENT; + + netdev_dbg(from->dev, "Adding inspected port to SPAN entry %d\n", + span_entry->id); + + err = mlxsw_sp_span_inspected_port_bind(from, span_entry, type); + if (err) + goto err_port_bind; + + return 0; + +err_port_bind: + mlxsw_sp_span_entry_put(mlxsw_sp, span_entry); + return err; +} + +static void mlxsw_sp_span_mirror_remove(struct mlxsw_sp_port *from, + struct mlxsw_sp_port *to, + enum mlxsw_sp_span_type type) +{ + struct mlxsw_sp_span_entry *span_entry; + + span_entry = mlxsw_sp_span_entry_find(to); + if (!span_entry) { + netdev_err(from->dev, "no span entry found\n"); + return; + } + + netdev_dbg(from->dev, "removing inspected port from SPAN entry %d\n", + span_entry->id); + mlxsw_sp_span_inspected_port_unbind(from, span_entry, type); +} + static int mlxsw_sp_port_admin_status_set(struct mlxsw_sp_port *mlxsw_sp_port, bool is_up) { @@ -192,23 +495,6 @@ static int mlxsw_sp_port_dev_addr_init(struct mlxsw_sp_port *mlxsw_sp_port) return mlxsw_sp_port_dev_addr_set(mlxsw_sp_port, addr); } -static int mlxsw_sp_port_stp_state_set(struct mlxsw_sp_port *mlxsw_sp_port, - u16 vid, enum mlxsw_reg_spms_state state) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - char *spms_pl; - int err; - - spms_pl = kmalloc(MLXSW_REG_SPMS_LEN, GFP_KERNEL); - if (!spms_pl) - return -ENOMEM; - mlxsw_reg_spms_pack(spms_pl, mlxsw_sp_port->local_port); - mlxsw_reg_spms_vid_pack(spms_pl, vid, state); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spms), spms_pl); - kfree(spms_pl); - return err; -} - static int mlxsw_sp_port_mtu_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; @@ -508,6 +794,9 @@ static int mlxsw_sp_port_change_mtu(struct net_device *dev, int mtu) err = mlxsw_sp_port_headroom_set(mlxsw_sp_port, mtu, pause_en); if (err) return err; + err = mlxsw_sp_span_port_mtu_update(mlxsw_sp_port, mtu); + if (err) + goto err_span_port_mtu_update; err = mlxsw_sp_port_mtu_set(mlxsw_sp_port, mtu); if (err) goto err_port_mtu_set; @@ -515,6 +804,8 @@ static int mlxsw_sp_port_change_mtu(struct net_device *dev, int mtu) return 0; err_port_mtu_set: + mlxsw_sp_span_port_mtu_update(mlxsw_sp_port, dev->mtu); +err_span_port_mtu_update: mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu, pause_en); return err; } @@ -619,94 +910,8 @@ static int mlxsw_sp_port_vlan_mode_trans(struct mlxsw_sp_port *mlxsw_sp_port) return 0; } -static struct mlxsw_sp_vfid * -mlxsw_sp_vfid_find(const struct mlxsw_sp *mlxsw_sp, u16 vid) -{ - struct mlxsw_sp_vfid *vfid; - - list_for_each_entry(vfid, &mlxsw_sp->port_vfids.list, list) { - if (vfid->vid == vid) - return vfid; - } - - return NULL; -} - -static u16 mlxsw_sp_avail_vfid_get(const struct mlxsw_sp *mlxsw_sp) -{ - return find_first_zero_bit(mlxsw_sp->port_vfids.mapped, - MLXSW_SP_VFID_PORT_MAX); -} - -static int __mlxsw_sp_vfid_create(struct mlxsw_sp *mlxsw_sp, u16 vfid) -{ - u16 fid = mlxsw_sp_vfid_to_fid(vfid); - char sfmr_pl[MLXSW_REG_SFMR_LEN]; - - mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_CREATE_FID, fid, 0); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl); -} - -static void __mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp, u16 vfid) -{ - u16 fid = mlxsw_sp_vfid_to_fid(vfid); - char sfmr_pl[MLXSW_REG_SFMR_LEN]; - - mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_DESTROY_FID, fid, 0); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl); -} - -static struct mlxsw_sp_vfid *mlxsw_sp_vfid_create(struct mlxsw_sp *mlxsw_sp, - u16 vid) -{ - struct device *dev = mlxsw_sp->bus_info->dev; - struct mlxsw_sp_vfid *vfid; - u16 n_vfid; - int err; - - n_vfid = mlxsw_sp_avail_vfid_get(mlxsw_sp); - if (n_vfid == MLXSW_SP_VFID_PORT_MAX) { - dev_err(dev, "No available vFIDs\n"); - return ERR_PTR(-ERANGE); - } - - err = __mlxsw_sp_vfid_create(mlxsw_sp, n_vfid); - if (err) { - dev_err(dev, "Failed to create vFID=%d\n", n_vfid); - return ERR_PTR(err); - } - - vfid = kzalloc(sizeof(*vfid), GFP_KERNEL); - if (!vfid) - goto err_allocate_vfid; - - vfid->vfid = n_vfid; - vfid->vid = vid; - - list_add(&vfid->list, &mlxsw_sp->port_vfids.list); - set_bit(n_vfid, mlxsw_sp->port_vfids.mapped); - - return vfid; - -err_allocate_vfid: - __mlxsw_sp_vfid_destroy(mlxsw_sp, n_vfid); - return ERR_PTR(-ENOMEM); -} - -static void mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vfid *vfid) -{ - clear_bit(vfid->vfid, mlxsw_sp->port_vfids.mapped); - list_del(&vfid->list); - - __mlxsw_sp_vfid_destroy(mlxsw_sp, vfid->vfid); - - kfree(vfid); -} - static struct mlxsw_sp_port * -mlxsw_sp_port_vport_create(struct mlxsw_sp_port *mlxsw_sp_port, - struct mlxsw_sp_vfid *vfid) +mlxsw_sp_port_vport_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) { struct mlxsw_sp_port *mlxsw_sp_vport; @@ -724,8 +929,7 @@ mlxsw_sp_port_vport_create(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_vport->stp_state = BR_STATE_FORWARDING; mlxsw_sp_vport->lagged = mlxsw_sp_port->lagged; mlxsw_sp_vport->lag_id = mlxsw_sp_port->lag_id; - mlxsw_sp_vport->vport.vfid = vfid; - mlxsw_sp_vport->vport.vid = vfid->vid; + mlxsw_sp_vport->vport.vid = vid; list_add(&mlxsw_sp_vport->vport.list, &mlxsw_sp_port->vports_list); @@ -742,9 +946,8 @@ int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, u16 vid) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_port *mlxsw_sp_vport; - struct mlxsw_sp_vfid *vfid; + bool untagged = vid == 1; int err; /* VLAN 0 is added to HW filter when device goes up, but it is @@ -758,31 +961,10 @@ int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, return 0; } - vfid = mlxsw_sp_vfid_find(mlxsw_sp, vid); - if (!vfid) { - vfid = mlxsw_sp_vfid_create(mlxsw_sp, vid); - if (IS_ERR(vfid)) { - netdev_err(dev, "Failed to create vFID for VID=%d\n", - vid); - return PTR_ERR(vfid); - } - } - - mlxsw_sp_vport = mlxsw_sp_port_vport_create(mlxsw_sp_port, vfid); + mlxsw_sp_vport = mlxsw_sp_port_vport_create(mlxsw_sp_port, vid); if (!mlxsw_sp_vport) { netdev_err(dev, "Failed to create vPort for VID=%d\n", vid); - err = -ENOMEM; - goto err_port_vport_create; - } - - if (!vfid->nr_vports) { - err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, - true, false); - if (err) { - netdev_err(dev, "Failed to setup flooding for vFID=%d\n", - vfid->vfid); - goto err_vport_flood_set; - } + return -ENOMEM; } /* When adding the first VLAN interface on a bridged port we need to @@ -797,70 +979,37 @@ int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, } } - err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, - MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, - true, - mlxsw_sp_vfid_to_fid(vfid->vfid), - vid); - if (err) { - netdev_err(dev, "Failed to map {Port, VID=%d} to vFID=%d\n", - vid, vfid->vfid); - goto err_port_vid_to_fid_set; - } - err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false); if (err) { netdev_err(dev, "Failed to disable learning for VID=%d\n", vid); goto err_port_vid_learning_set; } - err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, true, false); + err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, true, untagged); if (err) { netdev_err(dev, "Failed to set VLAN membership for VID=%d\n", vid); goto err_port_add_vid; } - err = mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid, - MLXSW_REG_SPMS_STATE_FORWARDING); - if (err) { - netdev_err(dev, "Failed to set STP state for VID=%d\n", vid); - goto err_port_stp_state_set; - } - - vfid->nr_vports++; - return 0; -err_port_stp_state_set: - mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, false, false); err_port_add_vid: mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true); err_port_vid_learning_set: - mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, - MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, false, - mlxsw_sp_vfid_to_fid(vfid->vfid), vid); -err_port_vid_to_fid_set: if (list_is_singular(&mlxsw_sp_port->vports_list)) mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port); err_port_vp_mode_trans: - if (!vfid->nr_vports) - mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, false, - false); -err_vport_flood_set: mlxsw_sp_port_vport_destroy(mlxsw_sp_vport); -err_port_vport_create: - if (!vfid->nr_vports) - mlxsw_sp_vfid_destroy(mlxsw_sp, vfid); return err; } -int mlxsw_sp_port_kill_vid(struct net_device *dev, - __be16 __always_unused proto, u16 vid) +static int mlxsw_sp_port_kill_vid(struct net_device *dev, + __be16 __always_unused proto, u16 vid) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct mlxsw_sp_port *mlxsw_sp_vport; - struct mlxsw_sp_vfid *vfid; + struct mlxsw_sp_fid *f; int err; /* VLAN 0 is removed from HW filter when device goes down, but @@ -875,15 +1024,6 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev, return 0; } - vfid = mlxsw_sp_vport->vport.vfid; - - err = mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid, - MLXSW_REG_SPMS_STATE_DISCARDING); - if (err) { - netdev_err(dev, "Failed to set STP state for VID=%d\n", vid); - return err; - } - err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, false, false); if (err) { netdev_err(dev, "Failed to set VLAN membership for VID=%d\n", @@ -897,16 +1037,12 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev, return err; } - err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, - MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, - false, - mlxsw_sp_vfid_to_fid(vfid->vfid), - vid); - if (err) { - netdev_err(dev, "Failed to invalidate {Port, VID=%d} to vFID=%d mapping\n", - vid, vfid->vfid); - return err; - } + /* Drop FID reference. If this was the last reference the + * resources will be freed. + */ + f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); + if (f && !WARN_ON(!f->leave)) + f->leave(mlxsw_sp_vport); /* When removing the last VLAN interface on a bridged port we need to * transition all active 802.1Q bridge VLANs to use VID to FID @@ -920,13 +1056,8 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev, } } - vfid->nr_vports--; mlxsw_sp_port_vport_destroy(mlxsw_sp_vport); - /* Destroy the vFID if no vPorts are assigned to it anymore. */ - if (!vfid->nr_vports) - mlxsw_sp_vfid_destroy(mlxsw_sp_port->mlxsw_sp, vfid); - return 0; } @@ -951,16 +1082,162 @@ static int mlxsw_sp_port_get_phys_port_name(struct net_device *dev, char *name, return 0; } +static struct mlxsw_sp_port_mall_tc_entry * +mlxsw_sp_port_mirror_entry_find(struct mlxsw_sp_port *port, + unsigned long cookie) { + struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry; + + list_for_each_entry(mall_tc_entry, &port->mall_tc_list, list) + if (mall_tc_entry->cookie == cookie) + return mall_tc_entry; + + return NULL; +} + +static int +mlxsw_sp_port_add_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port, + struct tc_cls_matchall_offload *cls, + const struct tc_action *a, + bool ingress) +{ + struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry; + struct net *net = dev_net(mlxsw_sp_port->dev); + enum mlxsw_sp_span_type span_type; + struct mlxsw_sp_port *to_port; + struct net_device *to_dev; + int ifindex; + int err; + + ifindex = tcf_mirred_ifindex(a); + to_dev = __dev_get_by_index(net, ifindex); + if (!to_dev) { + netdev_err(mlxsw_sp_port->dev, "Could not find requested device\n"); + return -EINVAL; + } + + if (!mlxsw_sp_port_dev_check(to_dev)) { + netdev_err(mlxsw_sp_port->dev, "Cannot mirror to a non-spectrum port"); + return -ENOTSUPP; + } + to_port = netdev_priv(to_dev); + + mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); + if (!mall_tc_entry) + return -ENOMEM; + + mall_tc_entry->cookie = cls->cookie; + mall_tc_entry->type = MLXSW_SP_PORT_MALL_MIRROR; + mall_tc_entry->mirror.to_local_port = to_port->local_port; + mall_tc_entry->mirror.ingress = ingress; + list_add_tail(&mall_tc_entry->list, &mlxsw_sp_port->mall_tc_list); + + span_type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS; + err = mlxsw_sp_span_mirror_add(mlxsw_sp_port, to_port, span_type); + if (err) + goto err_mirror_add; + return 0; + +err_mirror_add: + list_del(&mall_tc_entry->list); + kfree(mall_tc_entry); + return err; +} + +static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, + __be16 protocol, + struct tc_cls_matchall_offload *cls, + bool ingress) +{ + const struct tc_action *a; + int err; + + if (!tc_single_action(cls->exts)) { + netdev_err(mlxsw_sp_port->dev, "only singular actions are supported\n"); + return -ENOTSUPP; + } + + tc_for_each_action(a, cls->exts) { + if (!is_tcf_mirred_mirror(a) || protocol != htons(ETH_P_ALL)) + return -ENOTSUPP; + + err = mlxsw_sp_port_add_cls_matchall_mirror(mlxsw_sp_port, cls, + a, ingress); + if (err) + return err; + } + + return 0; +} + +static void mlxsw_sp_port_del_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, + struct tc_cls_matchall_offload *cls) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry; + enum mlxsw_sp_span_type span_type; + struct mlxsw_sp_port *to_port; + + mall_tc_entry = mlxsw_sp_port_mirror_entry_find(mlxsw_sp_port, + cls->cookie); + if (!mall_tc_entry) { + netdev_dbg(mlxsw_sp_port->dev, "tc entry not found on port\n"); + return; + } + + switch (mall_tc_entry->type) { + case MLXSW_SP_PORT_MALL_MIRROR: + to_port = mlxsw_sp->ports[mall_tc_entry->mirror.to_local_port]; + span_type = mall_tc_entry->mirror.ingress ? + MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS; + + mlxsw_sp_span_mirror_remove(mlxsw_sp_port, to_port, span_type); + break; + default: + WARN_ON(1); + } + + list_del(&mall_tc_entry->list); + kfree(mall_tc_entry); +} + +static int mlxsw_sp_setup_tc(struct net_device *dev, u32 handle, + __be16 proto, struct tc_to_netdev *tc) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + bool ingress = TC_H_MAJ(handle) == TC_H_MAJ(TC_H_INGRESS); + + if (tc->type == TC_SETUP_MATCHALL) { + switch (tc->cls_mall->command) { + case TC_CLSMATCHALL_REPLACE: + return mlxsw_sp_port_add_cls_matchall(mlxsw_sp_port, + proto, + tc->cls_mall, + ingress); + case TC_CLSMATCHALL_DESTROY: + mlxsw_sp_port_del_cls_matchall(mlxsw_sp_port, + tc->cls_mall); + return 0; + default: + return -EINVAL; + } + } + + return -ENOTSUPP; +} + static const struct net_device_ops mlxsw_sp_port_netdev_ops = { .ndo_open = mlxsw_sp_port_open, .ndo_stop = mlxsw_sp_port_stop, .ndo_start_xmit = mlxsw_sp_port_xmit, + .ndo_setup_tc = mlxsw_sp_setup_tc, .ndo_set_rx_mode = mlxsw_sp_set_rx_mode, .ndo_set_mac_address = mlxsw_sp_port_set_mac_address, .ndo_change_mtu = mlxsw_sp_port_change_mtu, .ndo_get_stats64 = mlxsw_sp_port_get_stats64, .ndo_vlan_rx_add_vid = mlxsw_sp_port_add_vid, .ndo_vlan_rx_kill_vid = mlxsw_sp_port_kill_vid, + .ndo_neigh_construct = mlxsw_sp_router_neigh_construct, + .ndo_neigh_destroy = mlxsw_sp_router_neigh_destroy, .ndo_fdb_add = switchdev_port_fdb_add, .ndo_fdb_del = switchdev_port_fdb_del, .ndo_fdb_dump = switchdev_port_fdb_dump, @@ -1055,7 +1332,7 @@ struct mlxsw_sp_port_hw_stats { u64 (*getter)(char *payload); }; -static const struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = { +static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = { { .str = "a_frames_transmitted_ok", .getter = mlxsw_reg_ppcnt_a_frames_transmitted_ok_get, @@ -1136,6 +1413,90 @@ static const struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = { #define MLXSW_SP_PORT_HW_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_stats) +static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_prio_stats[] = { + { + .str = "rx_octets_prio", + .getter = mlxsw_reg_ppcnt_rx_octets_get, + }, + { + .str = "rx_frames_prio", + .getter = mlxsw_reg_ppcnt_rx_frames_get, + }, + { + .str = "tx_octets_prio", + .getter = mlxsw_reg_ppcnt_tx_octets_get, + }, + { + .str = "tx_frames_prio", + .getter = mlxsw_reg_ppcnt_tx_frames_get, + }, + { + .str = "rx_pause_prio", + .getter = mlxsw_reg_ppcnt_rx_pause_get, + }, + { + .str = "rx_pause_duration_prio", + .getter = mlxsw_reg_ppcnt_rx_pause_duration_get, + }, + { + .str = "tx_pause_prio", + .getter = mlxsw_reg_ppcnt_tx_pause_get, + }, + { + .str = "tx_pause_duration_prio", + .getter = mlxsw_reg_ppcnt_tx_pause_duration_get, + }, +}; + +#define MLXSW_SP_PORT_HW_PRIO_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_prio_stats) + +static u64 mlxsw_reg_ppcnt_tc_transmit_queue_bytes_get(char *ppcnt_pl) +{ + u64 transmit_queue = mlxsw_reg_ppcnt_tc_transmit_queue_get(ppcnt_pl); + + return MLXSW_SP_CELLS_TO_BYTES(transmit_queue); +} + +static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = { + { + .str = "tc_transmit_queue_tc", + .getter = mlxsw_reg_ppcnt_tc_transmit_queue_bytes_get, + }, + { + .str = "tc_no_buffer_discard_uc_tc", + .getter = mlxsw_reg_ppcnt_tc_no_buffer_discard_uc_get, + }, +}; + +#define MLXSW_SP_PORT_HW_TC_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_tc_stats) + +#define MLXSW_SP_PORT_ETHTOOL_STATS_LEN (MLXSW_SP_PORT_HW_STATS_LEN + \ + (MLXSW_SP_PORT_HW_PRIO_STATS_LEN + \ + MLXSW_SP_PORT_HW_TC_STATS_LEN) * \ + IEEE_8021QAZ_MAX_TCS) + +static void mlxsw_sp_port_get_prio_strings(u8 **p, int prio) +{ + int i; + + for (i = 0; i < MLXSW_SP_PORT_HW_PRIO_STATS_LEN; i++) { + snprintf(*p, ETH_GSTRING_LEN, "%s_%d", + mlxsw_sp_port_hw_prio_stats[i].str, prio); + *p += ETH_GSTRING_LEN; + } +} + +static void mlxsw_sp_port_get_tc_strings(u8 **p, int tc) +{ + int i; + + for (i = 0; i < MLXSW_SP_PORT_HW_TC_STATS_LEN; i++) { + snprintf(*p, ETH_GSTRING_LEN, "%s_%d", + mlxsw_sp_port_hw_tc_stats[i].str, tc); + *p += ETH_GSTRING_LEN; + } +} + static void mlxsw_sp_port_get_strings(struct net_device *dev, u32 stringset, u8 *data) { @@ -1149,6 +1510,13 @@ static void mlxsw_sp_port_get_strings(struct net_device *dev, ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; } + + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + mlxsw_sp_port_get_prio_strings(&p, i); + + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + mlxsw_sp_port_get_tc_strings(&p, i); + break; } } @@ -1176,27 +1544,80 @@ static int mlxsw_sp_port_set_phys_id(struct net_device *dev, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mlcr), mlcr_pl); } -static void mlxsw_sp_port_get_stats(struct net_device *dev, - struct ethtool_stats *stats, u64 *data) +static int +mlxsw_sp_get_hw_stats_by_group(struct mlxsw_sp_port_hw_stats **p_hw_stats, + int *p_len, enum mlxsw_reg_ppcnt_grp grp) +{ + switch (grp) { + case MLXSW_REG_PPCNT_IEEE_8023_CNT: + *p_hw_stats = mlxsw_sp_port_hw_stats; + *p_len = MLXSW_SP_PORT_HW_STATS_LEN; + break; + case MLXSW_REG_PPCNT_PRIO_CNT: + *p_hw_stats = mlxsw_sp_port_hw_prio_stats; + *p_len = MLXSW_SP_PORT_HW_PRIO_STATS_LEN; + break; + case MLXSW_REG_PPCNT_TC_CNT: + *p_hw_stats = mlxsw_sp_port_hw_tc_stats; + *p_len = MLXSW_SP_PORT_HW_TC_STATS_LEN; + break; + default: + WARN_ON(1); + return -ENOTSUPP; + } + return 0; +} + +static void __mlxsw_sp_port_get_stats(struct net_device *dev, + enum mlxsw_reg_ppcnt_grp grp, int prio, + u64 *data, int data_index) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_port_hw_stats *hw_stats; char ppcnt_pl[MLXSW_REG_PPCNT_LEN]; - int i; + int i, len; int err; - mlxsw_reg_ppcnt_pack(ppcnt_pl, mlxsw_sp_port->local_port, - MLXSW_REG_PPCNT_IEEE_8023_CNT, 0); + err = mlxsw_sp_get_hw_stats_by_group(&hw_stats, &len, grp); + if (err) + return; + mlxsw_reg_ppcnt_pack(ppcnt_pl, mlxsw_sp_port->local_port, grp, prio); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ppcnt), ppcnt_pl); - for (i = 0; i < MLXSW_SP_PORT_HW_STATS_LEN; i++) - data[i] = !err ? mlxsw_sp_port_hw_stats[i].getter(ppcnt_pl) : 0; + for (i = 0; i < len; i++) + data[data_index + i] = !err ? hw_stats[i].getter(ppcnt_pl) : 0; +} + +static void mlxsw_sp_port_get_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + int i, data_index = 0; + + /* IEEE 802.3 Counters */ + __mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_IEEE_8023_CNT, 0, + data, data_index); + data_index = MLXSW_SP_PORT_HW_STATS_LEN; + + /* Per-Priority Counters */ + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + __mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_PRIO_CNT, i, + data, data_index); + data_index += MLXSW_SP_PORT_HW_PRIO_STATS_LEN; + } + + /* Per-TC Counters */ + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + __mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_TC_CNT, i, + data, data_index); + data_index += MLXSW_SP_PORT_HW_TC_STATS_LEN; + } } static int mlxsw_sp_port_get_sset_count(struct net_device *dev, int sset) { switch (sset) { case ETH_SS_STATS: - return MLXSW_SP_PORT_HW_STATS_LEN; + return MLXSW_SP_PORT_ETHTOOL_STATS_LEN; default: return -EOPNOTSUPP; } @@ -1686,6 +2107,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, goto err_port_untagged_vlans_alloc; } INIT_LIST_HEAD(&mlxsw_sp_port->vports_list); + INIT_LIST_HEAD(&mlxsw_sp_port->mall_tc_list); mlxsw_sp_port->pcpu_stats = netdev_alloc_pcpu_stats(struct mlxsw_sp_port_pcpu_stats); @@ -1707,7 +2129,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, netif_carrier_off(dev); dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_LLTX | NETIF_F_SG | - NETIF_F_HW_VLAN_CTAG_FILTER; + NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_TC; + dev->hw_features |= NETIF_F_HW_TC; /* Each packet needs to have a Tx header (metadata) on top all other * headers. @@ -1816,23 +2239,6 @@ err_port_active_vlans_alloc: return err; } -static void mlxsw_sp_port_vports_fini(struct mlxsw_sp_port *mlxsw_sp_port) -{ - struct net_device *dev = mlxsw_sp_port->dev; - struct mlxsw_sp_port *mlxsw_sp_vport, *tmp; - - list_for_each_entry_safe(mlxsw_sp_vport, tmp, - &mlxsw_sp_port->vports_list, vport.list) { - u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); - - /* vPorts created for VLAN devices should already be gone - * by now, since we unregistered the port netdev. - */ - WARN_ON(is_vlan_dev(mlxsw_sp_vport->dev)); - mlxsw_sp_port_kill_vid(dev, 0, vid); - } -} - static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) { struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port]; @@ -1843,13 +2249,14 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) mlxsw_core_port_fini(&mlxsw_sp_port->core_port); unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */ mlxsw_sp_port_dcb_fini(mlxsw_sp_port); - mlxsw_sp_port_vports_fini(mlxsw_sp_port); + mlxsw_sp_port_kill_vid(mlxsw_sp_port->dev, 0, 1); mlxsw_sp_port_switchdev_fini(mlxsw_sp_port); mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT); mlxsw_sp_port_module_unmap(mlxsw_sp, mlxsw_sp_port->local_port); free_percpu(mlxsw_sp_port->pcpu_stats); kfree(mlxsw_sp_port->untagged_vlans); kfree(mlxsw_sp_port->active_vlans); + WARN_ON_ONCE(!list_empty(&mlxsw_sp_port->vports_list)); free_netdev(mlxsw_sp_port->dev); } @@ -2086,11 +2493,8 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg, local_port = mlxsw_reg_pude_local_port_get(pude_pl); mlxsw_sp_port = mlxsw_sp->ports[local_port]; - if (!mlxsw_sp_port) { - dev_warn(mlxsw_sp->bus_info->dev, "Port %d: Link event received for non-existent port\n", - local_port); + if (!mlxsw_sp_port) return; - } status = mlxsw_reg_pude_oper_status_get(pude_pl); if (status == MLXSW_PORT_OPER_STATUS_UP) { @@ -2245,6 +2649,31 @@ static const struct mlxsw_rx_listener mlxsw_sp_rx_listener[] = { .local_port = MLXSW_PORT_DONT_CARE, .trap_id = MLXSW_TRAP_ID_IGMP_V3_REPORT, }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_ARPBC, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_ARPUC, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_IP2ME, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_RTR_INGRESS0, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_HOST_MISS_IPV4, + }, }; static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp) @@ -2285,7 +2714,7 @@ err_rx_trap_set: mlxsw_sp); err_rx_listener_register: for (i--; i >= 0; i--) { - mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD, + mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_DISCARD, mlxsw_sp_rx_listener[i].trap_id); mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(hpkt), hpkt_pl); @@ -2302,7 +2731,7 @@ static void mlxsw_sp_traps_fini(struct mlxsw_sp *mlxsw_sp) int i; for (i = 0; i < ARRAY_SIZE(mlxsw_sp_rx_listener); i++) { - mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD, + mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_DISCARD, mlxsw_sp_rx_listener[i].trap_id); mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(hpkt), hpkt_pl); @@ -2381,8 +2810,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, mlxsw_sp->core = mlxsw_core; mlxsw_sp->bus_info = mlxsw_bus_info; - INIT_LIST_HEAD(&mlxsw_sp->port_vfids.list); - INIT_LIST_HEAD(&mlxsw_sp->br_vfids.list); + INIT_LIST_HEAD(&mlxsw_sp->fids); + INIT_LIST_HEAD(&mlxsw_sp->vfids.list); INIT_LIST_HEAD(&mlxsw_sp->br_mids.list); err = mlxsw_sp_base_mac_get(mlxsw_sp); @@ -2391,16 +2820,10 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, return err; } - err = mlxsw_sp_ports_create(mlxsw_sp); - if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Failed to create ports\n"); - return err; - } - err = mlxsw_sp_event_register(mlxsw_sp, MLXSW_TRAP_ID_PUDE); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to register for PUDE events\n"); - goto err_event_register; + return err; } err = mlxsw_sp_traps_init(mlxsw_sp); @@ -2433,8 +2856,32 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_switchdev_init; } + err = mlxsw_sp_router_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize router\n"); + goto err_router_init; + } + + err = mlxsw_sp_span_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n"); + goto err_span_init; + } + + err = mlxsw_sp_ports_create(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to create ports\n"); + goto err_ports_create; + } + return 0; +err_ports_create: + mlxsw_sp_span_fini(mlxsw_sp); +err_span_init: + mlxsw_sp_router_fini(mlxsw_sp); +err_router_init: + mlxsw_sp_switchdev_fini(mlxsw_sp); err_switchdev_init: err_lag_init: mlxsw_sp_buffers_fini(mlxsw_sp); @@ -2443,20 +2890,25 @@ err_flood_init: mlxsw_sp_traps_fini(mlxsw_sp); err_rx_listener_register: mlxsw_sp_event_unregister(mlxsw_sp, MLXSW_TRAP_ID_PUDE); -err_event_register: - mlxsw_sp_ports_remove(mlxsw_sp); return err; } static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + int i; + mlxsw_sp_ports_remove(mlxsw_sp); + mlxsw_sp_span_fini(mlxsw_sp); + mlxsw_sp_router_fini(mlxsw_sp); mlxsw_sp_switchdev_fini(mlxsw_sp); mlxsw_sp_buffers_fini(mlxsw_sp); mlxsw_sp_traps_fini(mlxsw_sp); mlxsw_sp_event_unregister(mlxsw_sp, MLXSW_TRAP_ID_PUDE); - mlxsw_sp_ports_remove(mlxsw_sp); + WARN_ON(!list_empty(&mlxsw_sp->vfids.list)); + WARN_ON(!list_empty(&mlxsw_sp->fids)); + for (i = 0; i < MLXSW_SP_RIF_MAX; i++) + WARN_ON_ONCE(mlxsw_sp->rifs[i]); } static struct mlxsw_config_profile mlxsw_sp_config_profile = { @@ -2487,12 +2939,17 @@ static struct mlxsw_config_profile mlxsw_sp_config_profile = { .max_ib_mc = 0, .used_max_pkey = 1, .max_pkey = 0, + .used_kvd_sizes = 1, + .kvd_linear_size = MLXSW_SP_KVD_LINEAR_SIZE, + .kvd_hash_single_size = MLXSW_SP_KVD_HASH_SINGLE_SIZE, + .kvd_hash_double_size = MLXSW_SP_KVD_HASH_DOUBLE_SIZE, .swid_config = { { .used_type = 1, .type = MLXSW_PORT_SWID_TYPE_ETH, } }, + .resource_query_enable = 1, }; static struct mlxsw_driver mlxsw_sp_driver = { @@ -2518,16 +2975,590 @@ static struct mlxsw_driver mlxsw_sp_driver = { .profile = &mlxsw_sp_config_profile, }; -static int -mlxsw_sp_port_fdb_flush_by_port(const struct mlxsw_sp_port *mlxsw_sp_port) +static bool mlxsw_sp_port_dev_check(const struct net_device *dev) +{ + return dev->netdev_ops == &mlxsw_sp_port_netdev_ops; +} + +static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev) +{ + struct net_device *lower_dev; + struct list_head *iter; + + if (mlxsw_sp_port_dev_check(dev)) + return netdev_priv(dev); + + netdev_for_each_all_lower_dev(dev, lower_dev, iter) { + if (mlxsw_sp_port_dev_check(lower_dev)) + return netdev_priv(lower_dev); + } + return NULL; +} + +static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) +{ + struct mlxsw_sp_port *mlxsw_sp_port; + + mlxsw_sp_port = mlxsw_sp_port_dev_lower_find(dev); + return mlxsw_sp_port ? mlxsw_sp_port->mlxsw_sp : NULL; +} + +static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev) +{ + struct net_device *lower_dev; + struct list_head *iter; + + if (mlxsw_sp_port_dev_check(dev)) + return netdev_priv(dev); + + netdev_for_each_all_lower_dev_rcu(dev, lower_dev, iter) { + if (mlxsw_sp_port_dev_check(lower_dev)) + return netdev_priv(lower_dev); + } + return NULL; +} + +struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev) +{ + struct mlxsw_sp_port *mlxsw_sp_port; + + rcu_read_lock(); + mlxsw_sp_port = mlxsw_sp_port_dev_lower_find_rcu(dev); + if (mlxsw_sp_port) + dev_hold(mlxsw_sp_port->dev); + rcu_read_unlock(); + return mlxsw_sp_port; +} + +void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port) +{ + dev_put(mlxsw_sp_port->dev); +} + +static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *r, + unsigned long event) +{ + switch (event) { + case NETDEV_UP: + if (!r) + return true; + r->ref_count++; + return false; + case NETDEV_DOWN: + if (r && --r->ref_count == 0) + return true; + /* It is possible we already removed the RIF ourselves + * if it was assigned to a netdev that is now a bridge + * or LAG slave. + */ + return false; + } + + return false; +} + +static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp) +{ + int i; + + for (i = 0; i < MLXSW_SP_RIF_MAX; i++) + if (!mlxsw_sp->rifs[i]) + return i; + + return MLXSW_SP_RIF_MAX; +} + +static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport, + bool *p_lagged, u16 *p_system_port) +{ + u8 local_port = mlxsw_sp_vport->local_port; + + *p_lagged = mlxsw_sp_vport->lagged; + *p_system_port = *p_lagged ? mlxsw_sp_vport->lag_id : local_port; +} + +static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *l3_dev, u16 rif, + bool create) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + bool lagged = mlxsw_sp_vport->lagged; + char ritr_pl[MLXSW_REG_RITR_LEN]; + u16 system_port; + + mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif, + l3_dev->mtu, l3_dev->dev_addr); + + mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port); + mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port, + mlxsw_sp_vport_vid_get(mlxsw_sp_vport)); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport); + +static struct mlxsw_sp_fid * +mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev) +{ + struct mlxsw_sp_fid *f; + + f = kzalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + f->leave = mlxsw_sp_vport_rif_sp_leave; + f->ref_count = 0; + f->dev = l3_dev; + f->fid = fid; + + return f; +} + +static struct mlxsw_sp_rif * +mlxsw_sp_rif_alloc(u16 rif, struct net_device *l3_dev, struct mlxsw_sp_fid *f) +{ + struct mlxsw_sp_rif *r; + + r = kzalloc(sizeof(*r), GFP_KERNEL); + if (!r) + return NULL; + + ether_addr_copy(r->addr, l3_dev->dev_addr); + r->mtu = l3_dev->mtu; + r->ref_count = 1; + r->dev = l3_dev; + r->rif = rif; + r->f = f; + + return r; +} + +static struct mlxsw_sp_rif * +mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *l3_dev) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + struct mlxsw_sp_fid *f; + struct mlxsw_sp_rif *r; + u16 fid, rif; + int err; + + rif = mlxsw_sp_avail_rif_get(mlxsw_sp); + if (rif == MLXSW_SP_RIF_MAX) + return ERR_PTR(-ERANGE); + + err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, true); + if (err) + return ERR_PTR(err); + + fid = mlxsw_sp_rif_sp_to_fid(rif); + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true); + if (err) + goto err_rif_fdb_op; + + f = mlxsw_sp_rfid_alloc(fid, l3_dev); + if (!f) { + err = -ENOMEM; + goto err_rfid_alloc; + } + + r = mlxsw_sp_rif_alloc(rif, l3_dev, f); + if (!r) { + err = -ENOMEM; + goto err_rif_alloc; + } + + f->r = r; + mlxsw_sp->rifs[rif] = r; + + return r; + +err_rif_alloc: + kfree(f); +err_rfid_alloc: + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); +err_rif_fdb_op: + mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false); + return ERR_PTR(err); +} + +static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport, + struct mlxsw_sp_rif *r) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + struct net_device *l3_dev = r->dev; + struct mlxsw_sp_fid *f = r->f; + u16 fid = f->fid; + u16 rif = r->rif; + + mlxsw_sp->rifs[rif] = NULL; + f->r = NULL; + + kfree(r); + + kfree(f); + + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); + + mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false); +} + +static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *l3_dev) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + struct mlxsw_sp_rif *r; + + r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev); + if (!r) { + r = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev); + if (IS_ERR(r)) + return PTR_ERR(r); + } + + mlxsw_sp_vport_fid_set(mlxsw_sp_vport, r->f); + r->f->ref_count++; + + netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", r->f->fid); + + return 0; +} + +static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport) +{ + struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); + + netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid); + + mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL); + if (--f->ref_count == 0) + mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->r); +} + +static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev, + struct net_device *port_dev, + unsigned long event, u16 vid) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev); + struct mlxsw_sp_port *mlxsw_sp_vport; + + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); + if (WARN_ON(!mlxsw_sp_vport)) + return -EINVAL; + + switch (event) { + case NETDEV_UP: + return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, l3_dev); + case NETDEV_DOWN: + mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport); + break; + } + + return 0; +} + +static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev, + unsigned long event) +{ + if (netif_is_bridge_port(port_dev) || netif_is_lag_port(port_dev)) + return 0; + + return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1); +} + +static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev, + struct net_device *lag_dev, + unsigned long event, u16 vid) +{ + struct net_device *port_dev; + struct list_head *iter; + int err; + + netdev_for_each_lower_dev(lag_dev, port_dev, iter) { + if (mlxsw_sp_port_dev_check(port_dev)) { + err = mlxsw_sp_inetaddr_vport_event(l3_dev, port_dev, + event, vid); + if (err) + return err; + } + } + + return 0; +} + +static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev, + unsigned long event) +{ + if (netif_is_bridge_port(lag_dev)) + return 0; + + return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1); +} + +static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev) +{ + u16 fid; + + if (is_vlan_dev(l3_dev)) + fid = vlan_dev_vlan_id(l3_dev); + else if (mlxsw_sp->master_bridge.dev == l3_dev) + fid = 1; + else + return mlxsw_sp_vfid_find(mlxsw_sp, l3_dev); + + return mlxsw_sp_fid_find(mlxsw_sp, fid); +} + +static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid) +{ + if (mlxsw_sp_fid_is_vfid(fid)) + return MLXSW_REG_RITR_FID_IF; + else + return MLXSW_REG_RITR_VLAN_IF; +} + +static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev, + u16 fid, u16 rif, + bool create) +{ + enum mlxsw_reg_ritr_if_type rif_type; + char ritr_pl[MLXSW_REG_RITR_LEN]; + + rif_type = mlxsw_sp_rif_type_get(fid); + mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, l3_dev->mtu, + l3_dev->dev_addr); + mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev, + struct mlxsw_sp_fid *f) +{ + struct mlxsw_sp_rif *r; + u16 rif; + int err; + + rif = mlxsw_sp_avail_rif_get(mlxsw_sp); + if (rif == MLXSW_SP_RIF_MAX) + return -ERANGE; + + err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true); + if (err) + return err; + + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true); + if (err) + goto err_rif_fdb_op; + + r = mlxsw_sp_rif_alloc(rif, l3_dev, f); + if (!r) { + err = -ENOMEM; + goto err_rif_alloc; + } + + f->r = r; + mlxsw_sp->rifs[rif] = r; + + netdev_dbg(l3_dev, "RIF=%d created\n", rif); + + return 0; + +err_rif_alloc: + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); +err_rif_fdb_op: + mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); + return err; +} + +void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *r) +{ + struct net_device *l3_dev = r->dev; + struct mlxsw_sp_fid *f = r->f; + u16 rif = r->rif; + + mlxsw_sp->rifs[rif] = NULL; + f->r = NULL; + + kfree(r); + + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); + + mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); + + netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif); +} + +static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev, + struct net_device *br_dev, + unsigned long event) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev); + struct mlxsw_sp_fid *f; + + /* FID can either be an actual FID if the L3 device is the + * VLAN-aware bridge or a VLAN device on top. Otherwise, the + * L3 device is a VLAN-unaware bridge and we get a vFID. + */ + f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev); + if (WARN_ON(!f)) + return -EINVAL; + + switch (event) { + case NETDEV_UP: + return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f); + case NETDEV_DOWN: + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); + break; + } + + return 0; +} + +static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev, + unsigned long event) +{ + struct net_device *real_dev = vlan_dev_real_dev(vlan_dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev); + u16 vid = vlan_dev_vlan_id(vlan_dev); + + if (mlxsw_sp_port_dev_check(real_dev)) + return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event, + vid); + else if (netif_is_lag_master(real_dev)) + return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event, + vid); + else if (netif_is_bridge_master(real_dev) && + mlxsw_sp->master_bridge.dev == real_dev) + return mlxsw_sp_inetaddr_bridge_event(vlan_dev, real_dev, + event); + + return 0; +} + +static int mlxsw_sp_inetaddr_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct in_ifaddr *ifa = (struct in_ifaddr *) ptr; + struct net_device *dev = ifa->ifa_dev->dev; + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_rif *r; + int err = 0; + + mlxsw_sp = mlxsw_sp_lower_get(dev); + if (!mlxsw_sp) + goto out; + + r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!mlxsw_sp_rif_should_config(r, event)) + goto out; + + if (mlxsw_sp_port_dev_check(dev)) + err = mlxsw_sp_inetaddr_port_event(dev, event); + else if (netif_is_lag_master(dev)) + err = mlxsw_sp_inetaddr_lag_event(dev, event); + else if (netif_is_bridge_master(dev)) + err = mlxsw_sp_inetaddr_bridge_event(dev, dev, event); + else if (is_vlan_dev(dev)) + err = mlxsw_sp_inetaddr_vlan_event(dev, event); + +out: + return notifier_from_errno(err); +} + +static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif, + const char *mac, int mtu) +{ + char ritr_pl[MLXSW_REG_RITR_LEN]; + int err; + + mlxsw_reg_ritr_rif_pack(ritr_pl, rif); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); + if (err) + return err; + + mlxsw_reg_ritr_mtu_set(ritr_pl, mtu); + mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac); + mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +static int mlxsw_sp_netdevice_router_port_event(struct net_device *dev) +{ + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_rif *r; + int err; + + mlxsw_sp = mlxsw_sp_lower_get(dev); + if (!mlxsw_sp) + return 0; + + r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!r) + return 0; + + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, false); + if (err) + return err; + + err = mlxsw_sp_rif_edit(mlxsw_sp, r->rif, dev->dev_addr, dev->mtu); + if (err) + goto err_rif_edit; + + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, r->f->fid, true); + if (err) + goto err_rif_fdb_op; + + ether_addr_copy(r->addr, dev->dev_addr); + r->mtu = dev->mtu; + + netdev_dbg(dev, "Updated RIF=%d\n", r->rif); + + return 0; + +err_rif_fdb_op: + mlxsw_sp_rif_edit(mlxsw_sp, r->rif, r->addr, r->mtu); +err_rif_edit: + mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, true); + return err; +} + +static bool mlxsw_sp_lag_port_fid_member(struct mlxsw_sp_port *lag_port, + u16 fid) +{ + if (mlxsw_sp_fid_is_vfid(fid)) + return mlxsw_sp_port_vport_find_by_fid(lag_port, fid); + else + return test_bit(fid, lag_port->active_vlans); +} + +static bool mlxsw_sp_port_fdb_should_flush(struct mlxsw_sp_port *mlxsw_sp_port, + u16 fid) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - char sfdf_pl[MLXSW_REG_SFDF_LEN]; + u8 local_port = mlxsw_sp_port->local_port; + u16 lag_id = mlxsw_sp_port->lag_id; + int i, count = 0; - mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_PORT); - mlxsw_reg_sfdf_system_port_set(sfdf_pl, mlxsw_sp_port->local_port); + if (!mlxsw_sp_port->lagged) + return true; - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl); + for (i = 0; i < MLXSW_SP_PORT_PER_LAG_MAX; i++) { + struct mlxsw_sp_port *lag_port; + + lag_port = mlxsw_sp_port_lagged_get(mlxsw_sp, lag_id, i); + if (!lag_port || lag_port->local_port == local_port) + continue; + if (mlxsw_sp_lag_port_fid_member(lag_port, fid)) + count++; + } + + return !count; } static int @@ -2542,17 +3573,8 @@ mlxsw_sp_port_fdb_flush_by_port_fid(const struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_reg_sfdf_port_fid_system_port_set(sfdf_pl, mlxsw_sp_port->local_port); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl); -} - -static int -mlxsw_sp_port_fdb_flush_by_lag_id(const struct mlxsw_sp_port *mlxsw_sp_port) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - char sfdf_pl[MLXSW_REG_SFDF_LEN]; - - mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_LAG); - mlxsw_reg_sfdf_lag_id_set(sfdf_pl, mlxsw_sp_port->lag_id); + netdev_dbg(mlxsw_sp_port->dev, "FDB flushed using Port=%d, FID=%d\n", + mlxsw_sp_port->local_port, fid); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl); } @@ -2568,71 +3590,64 @@ mlxsw_sp_port_fdb_flush_by_lag_id_fid(const struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_reg_sfdf_fid_set(sfdf_pl, fid); mlxsw_reg_sfdf_lag_fid_lag_id_set(sfdf_pl, mlxsw_sp_port->lag_id); + netdev_dbg(mlxsw_sp_port->dev, "FDB flushed using LAG ID=%d, FID=%d\n", + mlxsw_sp_port->lag_id, fid); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl); } -static int -__mlxsw_sp_port_fdb_flush(const struct mlxsw_sp_port *mlxsw_sp_port) +int mlxsw_sp_port_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid) { - int err, last_err = 0; - u16 vid; - - for (vid = 1; vid < VLAN_N_VID - 1; vid++) { - err = mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_port, vid); - if (err) - last_err = err; - } + if (!mlxsw_sp_port_fdb_should_flush(mlxsw_sp_port, fid)) + return 0; - return last_err; + if (mlxsw_sp_port->lagged) + return mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_port, + fid); + else + return mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_port, fid); } -static int -__mlxsw_sp_port_fdb_flush_lagged(const struct mlxsw_sp_port *mlxsw_sp_port) +static void mlxsw_sp_master_bridge_gone_sync(struct mlxsw_sp *mlxsw_sp) { - int err, last_err = 0; - u16 vid; - - for (vid = 1; vid < VLAN_N_VID - 1; vid++) { - err = mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_port, vid); - if (err) - last_err = err; - } + struct mlxsw_sp_fid *f, *tmp; - return last_err; + list_for_each_entry_safe(f, tmp, &mlxsw_sp->fids, list) + if (--f->ref_count == 0) + mlxsw_sp_fid_destroy(mlxsw_sp, f); + else + WARN_ON_ONCE(1); } -static int mlxsw_sp_port_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_port) +static bool mlxsw_sp_master_bridge_check(struct mlxsw_sp *mlxsw_sp, + struct net_device *br_dev) { - if (!list_empty(&mlxsw_sp_port->vports_list)) - if (mlxsw_sp_port->lagged) - return __mlxsw_sp_port_fdb_flush_lagged(mlxsw_sp_port); - else - return __mlxsw_sp_port_fdb_flush(mlxsw_sp_port); - else - if (mlxsw_sp_port->lagged) - return mlxsw_sp_port_fdb_flush_by_lag_id(mlxsw_sp_port); - else - return mlxsw_sp_port_fdb_flush_by_port(mlxsw_sp_port); + return !mlxsw_sp->master_bridge.dev || + mlxsw_sp->master_bridge.dev == br_dev; } -static int mlxsw_sp_vport_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_vport) +static void mlxsw_sp_master_bridge_inc(struct mlxsw_sp *mlxsw_sp, + struct net_device *br_dev) { - u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_vport); - u16 fid = mlxsw_sp_vfid_to_fid(vfid); - - if (mlxsw_sp_vport->lagged) - return mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_vport, - fid); - else - return mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_vport, fid); + mlxsw_sp->master_bridge.dev = br_dev; + mlxsw_sp->master_bridge.ref_count++; } -static bool mlxsw_sp_port_dev_check(const struct net_device *dev) +static void mlxsw_sp_master_bridge_dec(struct mlxsw_sp *mlxsw_sp) { - return dev->netdev_ops == &mlxsw_sp_port_netdev_ops; + if (--mlxsw_sp->master_bridge.ref_count == 0) { + mlxsw_sp->master_bridge.dev = NULL; + /* It's possible upper VLAN devices are still holding + * references to underlying FIDs. Drop the reference + * and release the resources if it was the last one. + * If it wasn't, then something bad happened. + */ + mlxsw_sp_master_bridge_gone_sync(mlxsw_sp); + } } -static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port) +static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port, + struct net_device *br_dev) { struct net_device *dev = mlxsw_sp_port->dev; int err; @@ -2646,6 +3661,8 @@ static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port) if (err) return err; + mlxsw_sp_master_bridge_inc(mlxsw_sp_port->mlxsw_sp, br_dev); + mlxsw_sp_port->learning = 1; mlxsw_sp_port->learning_sync = 1; mlxsw_sp_port->uc_flood = 1; @@ -2654,16 +3671,14 @@ static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port) return 0; } -static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port, - bool flush_fdb) +static void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port) { struct net_device *dev = mlxsw_sp_port->dev; - if (flush_fdb && mlxsw_sp_port_fdb_flush(mlxsw_sp_port)) - netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n"); - mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1); + mlxsw_sp_master_bridge_dec(mlxsw_sp_port->mlxsw_sp); + mlxsw_sp_port->learning = 0; mlxsw_sp_port->learning_sync = 0; mlxsw_sp_port->uc_flood = 0; @@ -2672,28 +3687,7 @@ static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port, /* Add implicit VLAN interface in the device, so that untagged * packets will be classified to the default vFID. */ - return mlxsw_sp_port_add_vid(dev, 0, 1); -} - -static bool mlxsw_sp_master_bridge_check(struct mlxsw_sp *mlxsw_sp, - struct net_device *br_dev) -{ - return !mlxsw_sp->master_bridge.dev || - mlxsw_sp->master_bridge.dev == br_dev; -} - -static void mlxsw_sp_master_bridge_inc(struct mlxsw_sp *mlxsw_sp, - struct net_device *br_dev) -{ - mlxsw_sp->master_bridge.dev = br_dev; - mlxsw_sp->master_bridge.ref_count++; -} - -static void mlxsw_sp_master_bridge_dec(struct mlxsw_sp *mlxsw_sp, - struct net_device *br_dev) -{ - if (--mlxsw_sp->master_bridge.ref_count == 0) - mlxsw_sp->master_bridge.dev = NULL; + mlxsw_sp_port_add_vid(dev, 0, 1); } static int mlxsw_sp_lag_create(struct mlxsw_sp *mlxsw_sp, u16 lag_id) @@ -2809,6 +3803,45 @@ static int mlxsw_sp_port_lag_index_get(struct mlxsw_sp *mlxsw_sp, return -EBUSY; } +static void +mlxsw_sp_port_pvid_vport_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, + u16 lag_id) +{ + struct mlxsw_sp_port *mlxsw_sp_vport; + struct mlxsw_sp_fid *f; + + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, 1); + if (WARN_ON(!mlxsw_sp_vport)) + return; + + /* If vPort is assigned a RIF, then leave it since it's no + * longer valid. + */ + f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); + if (f) + f->leave(mlxsw_sp_vport); + + mlxsw_sp_vport->lag_id = lag_id; + mlxsw_sp_vport->lagged = 1; +} + +static void +mlxsw_sp_port_pvid_vport_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp_port *mlxsw_sp_vport; + struct mlxsw_sp_fid *f; + + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, 1); + if (WARN_ON(!mlxsw_sp_vport)) + return; + + f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); + if (f) + f->leave(mlxsw_sp_vport); + + mlxsw_sp_vport->lagged = 0; +} + static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *lag_dev) { @@ -2844,6 +3877,9 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_port->lag_id = lag_id; mlxsw_sp_port->lagged = 1; lag->ref_count++; + + mlxsw_sp_port_pvid_vport_lag_join(mlxsw_sp_port, lag_id); + return 0; err_col_port_enable: @@ -2854,65 +3890,35 @@ err_col_port_add: return err; } -static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, - struct net_device *br_dev, - bool flush_fdb); - -static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, - struct net_device *lag_dev) +static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, + struct net_device *lag_dev) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - struct mlxsw_sp_port *mlxsw_sp_vport; - struct mlxsw_sp_upper *lag; u16 lag_id = mlxsw_sp_port->lag_id; - int err; + struct mlxsw_sp_upper *lag; if (!mlxsw_sp_port->lagged) - return 0; + return; lag = mlxsw_sp_lag_get(mlxsw_sp, lag_id); WARN_ON(lag->ref_count == 0); - err = mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, lag_id); - if (err) - return err; - err = mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id); - if (err) - return err; - - /* In case we leave a LAG device that has bridges built on top, - * then their teardown sequence is never issued and we need to - * invoke the necessary cleanup routines ourselves. - */ - list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list, - vport.list) { - struct net_device *br_dev; - - if (!mlxsw_sp_vport->bridged) - continue; - - br_dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport); - mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev, false); - } + mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, lag_id); + mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id); if (mlxsw_sp_port->bridged) { mlxsw_sp_port_active_vlans_del(mlxsw_sp_port); - mlxsw_sp_port_bridge_leave(mlxsw_sp_port, false); - mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL); + mlxsw_sp_port_bridge_leave(mlxsw_sp_port); } - if (lag->ref_count == 1) { - if (mlxsw_sp_port_fdb_flush_by_lag_id(mlxsw_sp_port)) - netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n"); - err = mlxsw_sp_lag_destroy(mlxsw_sp, lag_id); - if (err) - return err; - } + if (lag->ref_count == 1) + mlxsw_sp_lag_destroy(mlxsw_sp, lag_id); mlxsw_core_lag_mapping_clear(mlxsw_sp->core, lag_id, mlxsw_sp_port->local_port); mlxsw_sp_port->lagged = 0; lag->ref_count--; - return 0; + + mlxsw_sp_port_pvid_vport_lag_leave(mlxsw_sp_port); } static int mlxsw_sp_lag_dist_port_add(struct mlxsw_sp_port *mlxsw_sp_port, @@ -2961,42 +3967,25 @@ static int mlxsw_sp_port_vlan_link(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid = vlan_dev_vlan_id(vlan_dev); mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); - if (!mlxsw_sp_vport) { - WARN_ON(!mlxsw_sp_vport); + if (WARN_ON(!mlxsw_sp_vport)) return -EINVAL; - } mlxsw_sp_vport->dev = vlan_dev; return 0; } -static int mlxsw_sp_port_vlan_unlink(struct mlxsw_sp_port *mlxsw_sp_port, - struct net_device *vlan_dev) +static void mlxsw_sp_port_vlan_unlink(struct mlxsw_sp_port *mlxsw_sp_port, + struct net_device *vlan_dev) { struct mlxsw_sp_port *mlxsw_sp_vport; u16 vid = vlan_dev_vlan_id(vlan_dev); mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); - if (!mlxsw_sp_vport) { - WARN_ON(!mlxsw_sp_vport); - return -EINVAL; - } - - /* When removing a VLAN device while still bridged we should first - * remove it from the bridge, as we receive the bridge's notification - * when the vPort is already gone. - */ - if (mlxsw_sp_vport->bridged) { - struct net_device *br_dev; - - br_dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport); - mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev, true); - } + if (WARN_ON(!mlxsw_sp_vport)) + return; mlxsw_sp_vport->dev = mlxsw_sp_port->dev; - - return 0; } static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, @@ -3006,7 +3995,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, struct mlxsw_sp_port *mlxsw_sp_port; struct net_device *upper_dev; struct mlxsw_sp *mlxsw_sp; - int err; + int err = 0; mlxsw_sp_port = netdev_priv(dev); mlxsw_sp = mlxsw_sp_port->mlxsw_sp; @@ -3015,73 +4004,56 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, switch (event) { case NETDEV_PRECHANGEUPPER: upper_dev = info->upper_dev; - if (!info->master || !info->linking) + if (!is_vlan_dev(upper_dev) && + !netif_is_lag_master(upper_dev) && + !netif_is_bridge_master(upper_dev)) + return -EINVAL; + if (!info->linking) break; /* HW limitation forbids to put ports to multiple bridges. */ if (netif_is_bridge_master(upper_dev) && !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev)) - return NOTIFY_BAD; + return -EINVAL; if (netif_is_lag_master(upper_dev) && !mlxsw_sp_master_lag_check(mlxsw_sp, upper_dev, info->upper_info)) - return NOTIFY_BAD; + return -EINVAL; + if (netif_is_lag_master(upper_dev) && vlan_uses_dev(dev)) + return -EINVAL; + if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) && + !netif_is_lag_master(vlan_dev_real_dev(upper_dev))) + return -EINVAL; break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; if (is_vlan_dev(upper_dev)) { - if (info->linking) { + if (info->linking) err = mlxsw_sp_port_vlan_link(mlxsw_sp_port, upper_dev); - if (err) { - netdev_err(dev, "Failed to link VLAN device\n"); - return NOTIFY_BAD; - } - } else { - err = mlxsw_sp_port_vlan_unlink(mlxsw_sp_port, - upper_dev); - if (err) { - netdev_err(dev, "Failed to unlink VLAN device\n"); - return NOTIFY_BAD; - } - } + else + mlxsw_sp_port_vlan_unlink(mlxsw_sp_port, + upper_dev); } else if (netif_is_bridge_master(upper_dev)) { - if (info->linking) { - err = mlxsw_sp_port_bridge_join(mlxsw_sp_port); - if (err) { - netdev_err(dev, "Failed to join bridge\n"); - return NOTIFY_BAD; - } - mlxsw_sp_master_bridge_inc(mlxsw_sp, upper_dev); - } else { - err = mlxsw_sp_port_bridge_leave(mlxsw_sp_port, - true); - mlxsw_sp_master_bridge_dec(mlxsw_sp, upper_dev); - if (err) { - netdev_err(dev, "Failed to leave bridge\n"); - return NOTIFY_BAD; - } - } + if (info->linking) + err = mlxsw_sp_port_bridge_join(mlxsw_sp_port, + upper_dev); + else + mlxsw_sp_port_bridge_leave(mlxsw_sp_port); } else if (netif_is_lag_master(upper_dev)) { - if (info->linking) { + if (info->linking) err = mlxsw_sp_port_lag_join(mlxsw_sp_port, upper_dev); - if (err) { - netdev_err(dev, "Failed to join link aggregation\n"); - return NOTIFY_BAD; - } - } else { - err = mlxsw_sp_port_lag_leave(mlxsw_sp_port, - upper_dev); - if (err) { - netdev_err(dev, "Failed to leave link aggregation\n"); - return NOTIFY_BAD; - } - } + else + mlxsw_sp_port_lag_leave(mlxsw_sp_port, + upper_dev); + } else { + err = -EINVAL; + WARN_ON(1); } break; } - return NOTIFY_DONE; + return err; } static int mlxsw_sp_netdevice_port_lower_event(struct net_device *dev, @@ -3105,7 +4077,7 @@ static int mlxsw_sp_netdevice_port_lower_event(struct net_device *dev, break; } - return NOTIFY_DONE; + return 0; } static int mlxsw_sp_netdevice_port_event(struct net_device *dev, @@ -3119,7 +4091,7 @@ static int mlxsw_sp_netdevice_port_event(struct net_device *dev, return mlxsw_sp_netdevice_port_lower_event(dev, event, ptr); } - return NOTIFY_DONE; + return 0; } static int mlxsw_sp_netdevice_lag_event(struct net_device *lag_dev, @@ -3132,218 +4104,230 @@ static int mlxsw_sp_netdevice_lag_event(struct net_device *lag_dev, netdev_for_each_lower_dev(lag_dev, dev, iter) { if (mlxsw_sp_port_dev_check(dev)) { ret = mlxsw_sp_netdevice_port_event(dev, event, ptr); - if (ret == NOTIFY_BAD) + if (ret) return ret; } } - return NOTIFY_DONE; + return 0; } -static struct mlxsw_sp_vfid * -mlxsw_sp_br_vfid_find(const struct mlxsw_sp *mlxsw_sp, - const struct net_device *br_dev) +static int mlxsw_sp_master_bridge_vlan_link(struct mlxsw_sp *mlxsw_sp, + struct net_device *vlan_dev) { - struct mlxsw_sp_vfid *vfid; + u16 fid = vlan_dev_vlan_id(vlan_dev); + struct mlxsw_sp_fid *f; - list_for_each_entry(vfid, &mlxsw_sp->br_vfids.list, list) { - if (vfid->br_dev == br_dev) - return vfid; + f = mlxsw_sp_fid_find(mlxsw_sp, fid); + if (!f) { + f = mlxsw_sp_fid_create(mlxsw_sp, fid); + if (IS_ERR(f)) + return PTR_ERR(f); } - return NULL; + f->ref_count++; + + return 0; +} + +static void mlxsw_sp_master_bridge_vlan_unlink(struct mlxsw_sp *mlxsw_sp, + struct net_device *vlan_dev) +{ + u16 fid = vlan_dev_vlan_id(vlan_dev); + struct mlxsw_sp_fid *f; + + f = mlxsw_sp_fid_find(mlxsw_sp, fid); + if (f && f->r) + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); + if (f && --f->ref_count == 0) + mlxsw_sp_fid_destroy(mlxsw_sp, f); } -static u16 mlxsw_sp_vfid_to_br_vfid(u16 vfid) +static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev, + unsigned long event, void *ptr) { - return vfid - MLXSW_SP_VFID_PORT_MAX; + struct netdev_notifier_changeupper_info *info; + struct net_device *upper_dev; + struct mlxsw_sp *mlxsw_sp; + int err; + + mlxsw_sp = mlxsw_sp_lower_get(br_dev); + if (!mlxsw_sp) + return 0; + if (br_dev != mlxsw_sp->master_bridge.dev) + return 0; + + info = ptr; + + switch (event) { + case NETDEV_CHANGEUPPER: + upper_dev = info->upper_dev; + if (!is_vlan_dev(upper_dev)) + break; + if (info->linking) { + err = mlxsw_sp_master_bridge_vlan_link(mlxsw_sp, + upper_dev); + if (err) + return err; + } else { + mlxsw_sp_master_bridge_vlan_unlink(mlxsw_sp, upper_dev); + } + break; + } + + return 0; } -static u16 mlxsw_sp_br_vfid_to_vfid(u16 br_vfid) +static u16 mlxsw_sp_avail_vfid_get(const struct mlxsw_sp *mlxsw_sp) { - return MLXSW_SP_VFID_PORT_MAX + br_vfid; + return find_first_zero_bit(mlxsw_sp->vfids.mapped, + MLXSW_SP_VFID_MAX); } -static u16 mlxsw_sp_avail_br_vfid_get(const struct mlxsw_sp *mlxsw_sp) +static int mlxsw_sp_vfid_op(struct mlxsw_sp *mlxsw_sp, u16 fid, bool create) { - return find_first_zero_bit(mlxsw_sp->br_vfids.mapped, - MLXSW_SP_VFID_BR_MAX); + char sfmr_pl[MLXSW_REG_SFMR_LEN]; + + mlxsw_reg_sfmr_pack(sfmr_pl, !create, fid, 0); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl); } -static struct mlxsw_sp_vfid *mlxsw_sp_br_vfid_create(struct mlxsw_sp *mlxsw_sp, - struct net_device *br_dev) +static void mlxsw_sp_vport_vfid_leave(struct mlxsw_sp_port *mlxsw_sp_vport); + +static struct mlxsw_sp_fid *mlxsw_sp_vfid_create(struct mlxsw_sp *mlxsw_sp, + struct net_device *br_dev) { struct device *dev = mlxsw_sp->bus_info->dev; - struct mlxsw_sp_vfid *vfid; - u16 n_vfid; + struct mlxsw_sp_fid *f; + u16 vfid, fid; int err; - n_vfid = mlxsw_sp_br_vfid_to_vfid(mlxsw_sp_avail_br_vfid_get(mlxsw_sp)); - if (n_vfid == MLXSW_SP_VFID_MAX) { + vfid = mlxsw_sp_avail_vfid_get(mlxsw_sp); + if (vfid == MLXSW_SP_VFID_MAX) { dev_err(dev, "No available vFIDs\n"); return ERR_PTR(-ERANGE); } - err = __mlxsw_sp_vfid_create(mlxsw_sp, n_vfid); + fid = mlxsw_sp_vfid_to_fid(vfid); + err = mlxsw_sp_vfid_op(mlxsw_sp, fid, true); if (err) { - dev_err(dev, "Failed to create vFID=%d\n", n_vfid); + dev_err(dev, "Failed to create FID=%d\n", fid); return ERR_PTR(err); } - vfid = kzalloc(sizeof(*vfid), GFP_KERNEL); - if (!vfid) + f = kzalloc(sizeof(*f), GFP_KERNEL); + if (!f) goto err_allocate_vfid; - vfid->vfid = n_vfid; - vfid->br_dev = br_dev; + f->leave = mlxsw_sp_vport_vfid_leave; + f->fid = fid; + f->dev = br_dev; - list_add(&vfid->list, &mlxsw_sp->br_vfids.list); - set_bit(mlxsw_sp_vfid_to_br_vfid(n_vfid), mlxsw_sp->br_vfids.mapped); + list_add(&f->list, &mlxsw_sp->vfids.list); + set_bit(vfid, mlxsw_sp->vfids.mapped); - return vfid; + return f; err_allocate_vfid: - __mlxsw_sp_vfid_destroy(mlxsw_sp, n_vfid); + mlxsw_sp_vfid_op(mlxsw_sp, fid, false); return ERR_PTR(-ENOMEM); } -static void mlxsw_sp_br_vfid_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vfid *vfid) +static void mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fid *f) { - u16 br_vfid = mlxsw_sp_vfid_to_br_vfid(vfid->vfid); + u16 vfid = mlxsw_sp_fid_to_vfid(f->fid); + u16 fid = f->fid; + + clear_bit(vfid, mlxsw_sp->vfids.mapped); + list_del(&f->list); - clear_bit(br_vfid, mlxsw_sp->br_vfids.mapped); - list_del(&vfid->list); + if (f->r) + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); - __mlxsw_sp_vfid_destroy(mlxsw_sp, vfid->vfid); + kfree(f); - kfree(vfid); + mlxsw_sp_vfid_op(mlxsw_sp, fid, false); } -static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, - struct net_device *br_dev, - bool flush_fdb) +static int mlxsw_sp_vport_fid_map(struct mlxsw_sp_port *mlxsw_sp_vport, u16 fid, + bool valid) { - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + enum mlxsw_reg_svfa_mt mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID; u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); - struct net_device *dev = mlxsw_sp_vport->dev; - struct mlxsw_sp_vfid *vfid, *new_vfid; - int err; - vfid = mlxsw_sp_br_vfid_find(mlxsw_sp, br_dev); - if (!vfid) { - WARN_ON(!vfid); - return -EINVAL; - } - - /* We need a vFID to go back to after leaving the bridge's vFID. */ - new_vfid = mlxsw_sp_vfid_find(mlxsw_sp, vid); - if (!new_vfid) { - new_vfid = mlxsw_sp_vfid_create(mlxsw_sp, vid); - if (IS_ERR(new_vfid)) { - netdev_err(dev, "Failed to create vFID for VID=%d\n", - vid); - return PTR_ERR(new_vfid); - } - } - - /* Invalidate existing {Port, VID} to vFID mapping and create a new - * one for the new vFID. - */ - err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, - MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, - false, - mlxsw_sp_vfid_to_fid(vfid->vfid), - vid); - if (err) { - netdev_err(dev, "Failed to invalidate {Port, VID} to vFID=%d mapping\n", - vfid->vfid); - goto err_port_vid_to_fid_invalidate; - } + return mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, mt, valid, fid, + vid); +} - err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, - MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, - true, - mlxsw_sp_vfid_to_fid(new_vfid->vfid), - vid); - if (err) { - netdev_err(dev, "Failed to map {Port, VID} to vFID=%d\n", - new_vfid->vfid); - goto err_port_vid_to_fid_validate; - } +static int mlxsw_sp_vport_vfid_join(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *br_dev) +{ + struct mlxsw_sp_fid *f; + int err; - err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false); - if (err) { - netdev_err(dev, "Failed to disable learning\n"); - goto err_port_vid_learning_set; + f = mlxsw_sp_vfid_find(mlxsw_sp_vport->mlxsw_sp, br_dev); + if (!f) { + f = mlxsw_sp_vfid_create(mlxsw_sp_vport->mlxsw_sp, br_dev); + if (IS_ERR(f)) + return PTR_ERR(f); } - err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, false, - false); - if (err) { - netdev_err(dev, "Failed clear to clear flooding\n"); + err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, f->fid, true); + if (err) goto err_vport_flood_set; - } - - err = mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid, - MLXSW_REG_SPMS_STATE_FORWARDING); - if (err) { - netdev_err(dev, "Failed to set STP state\n"); - goto err_port_stp_state_set; - } - if (flush_fdb && mlxsw_sp_vport_fdb_flush(mlxsw_sp_vport)) - netdev_err(dev, "Failed to flush FDB\n"); + err = mlxsw_sp_vport_fid_map(mlxsw_sp_vport, f->fid, true); + if (err) + goto err_vport_fid_map; - /* Switch between the vFIDs and destroy the old one if needed. */ - new_vfid->nr_vports++; - mlxsw_sp_vport->vport.vfid = new_vfid; - vfid->nr_vports--; - if (!vfid->nr_vports) - mlxsw_sp_br_vfid_destroy(mlxsw_sp, vfid); + mlxsw_sp_vport_fid_set(mlxsw_sp_vport, f); + f->ref_count++; - mlxsw_sp_vport->learning = 0; - mlxsw_sp_vport->learning_sync = 0; - mlxsw_sp_vport->uc_flood = 0; - mlxsw_sp_vport->bridged = 0; + netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", f->fid); return 0; -err_port_stp_state_set: +err_vport_fid_map: + mlxsw_sp_vport_flood_set(mlxsw_sp_vport, f->fid, false); err_vport_flood_set: -err_port_vid_learning_set: -err_port_vid_to_fid_validate: -err_port_vid_to_fid_invalidate: - /* Rollback vFID only if new. */ - if (!new_vfid->nr_vports) - mlxsw_sp_vfid_destroy(mlxsw_sp, new_vfid); + if (!f->ref_count) + mlxsw_sp_vfid_destroy(mlxsw_sp_vport->mlxsw_sp, f); return err; } +static void mlxsw_sp_vport_vfid_leave(struct mlxsw_sp_port *mlxsw_sp_vport) +{ + struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); + + netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid); + + mlxsw_sp_vport_fid_map(mlxsw_sp_vport, f->fid, false); + + mlxsw_sp_vport_flood_set(mlxsw_sp_vport, f->fid, false); + + mlxsw_sp_port_fdb_flush(mlxsw_sp_vport, f->fid); + + mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL); + if (--f->ref_count == 0) + mlxsw_sp_vfid_destroy(mlxsw_sp_vport->mlxsw_sp, f); +} + static int mlxsw_sp_vport_bridge_join(struct mlxsw_sp_port *mlxsw_sp_vport, struct net_device *br_dev) { - struct mlxsw_sp_vfid *old_vfid = mlxsw_sp_vport->vport.vfid; - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); struct net_device *dev = mlxsw_sp_vport->dev; - struct mlxsw_sp_vfid *vfid; int err; - vfid = mlxsw_sp_br_vfid_find(mlxsw_sp, br_dev); - if (!vfid) { - vfid = mlxsw_sp_br_vfid_create(mlxsw_sp, br_dev); - if (IS_ERR(vfid)) { - netdev_err(dev, "Failed to create bridge vFID\n"); - return PTR_ERR(vfid); - } - } + if (f && !WARN_ON(!f->leave)) + f->leave(mlxsw_sp_vport); - err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, true, false); + err = mlxsw_sp_vport_vfid_join(mlxsw_sp_vport, br_dev); if (err) { - netdev_err(dev, "Failed to setup flooding for vFID=%d\n", - vfid->vfid); - goto err_port_flood_set; + netdev_err(dev, "Failed to join vFID\n"); + return err; } err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true); @@ -3352,38 +4336,6 @@ static int mlxsw_sp_vport_bridge_join(struct mlxsw_sp_port *mlxsw_sp_vport, goto err_port_vid_learning_set; } - /* We need to invalidate existing {Port, VID} to vFID mapping and - * create a new one for the bridge's vFID. - */ - err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, - MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, - false, - mlxsw_sp_vfid_to_fid(old_vfid->vfid), - vid); - if (err) { - netdev_err(dev, "Failed to invalidate {Port, VID} to vFID=%d mapping\n", - old_vfid->vfid); - goto err_port_vid_to_fid_invalidate; - } - - err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, - MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, - true, - mlxsw_sp_vfid_to_fid(vfid->vfid), - vid); - if (err) { - netdev_err(dev, "Failed to map {Port, VID} to vFID=%d\n", - vfid->vfid); - goto err_port_vid_to_fid_validate; - } - - /* Switch between the vFIDs and destroy the old one if needed. */ - vfid->nr_vports++; - mlxsw_sp_vport->vport.vfid = vfid; - old_vfid->nr_vports--; - if (!old_vfid->nr_vports) - mlxsw_sp_vfid_destroy(mlxsw_sp, old_vfid); - mlxsw_sp_vport->learning = 1; mlxsw_sp_vport->learning_sync = 1; mlxsw_sp_vport->uc_flood = 1; @@ -3391,20 +4343,25 @@ static int mlxsw_sp_vport_bridge_join(struct mlxsw_sp_port *mlxsw_sp_vport, return 0; -err_port_vid_to_fid_validate: - mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, - MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, false, - mlxsw_sp_vfid_to_fid(old_vfid->vfid), vid); -err_port_vid_to_fid_invalidate: - mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false); err_port_vid_learning_set: - mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, false, false); -err_port_flood_set: - if (!vfid->nr_vports) - mlxsw_sp_br_vfid_destroy(mlxsw_sp, vfid); + mlxsw_sp_vport_vfid_leave(mlxsw_sp_vport); return err; } +static void mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport) +{ + u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); + + mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false); + + mlxsw_sp_vport_vfid_leave(mlxsw_sp_vport); + + mlxsw_sp_vport->learning = 0; + mlxsw_sp_vport->learning_sync = 0; + mlxsw_sp_vport->uc_flood = 0; + mlxsw_sp_vport->bridged = 0; +} + static bool mlxsw_sp_port_master_bridge_check(const struct mlxsw_sp_port *mlxsw_sp_port, const struct net_device *br_dev) @@ -3413,7 +4370,9 @@ mlxsw_sp_port_master_bridge_check(const struct mlxsw_sp_port *mlxsw_sp_port, list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list, vport.list) { - if (mlxsw_sp_vport_br_get(mlxsw_sp_vport) == br_dev) + struct net_device *dev = mlxsw_sp_vport_dev_get(mlxsw_sp_vport); + + if (dev && dev == br_dev) return false; } @@ -3428,56 +4387,39 @@ static int mlxsw_sp_netdevice_vport_event(struct net_device *dev, struct netdev_notifier_changeupper_info *info = ptr; struct mlxsw_sp_port *mlxsw_sp_vport; struct net_device *upper_dev; - int err; + int err = 0; mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); switch (event) { case NETDEV_PRECHANGEUPPER: upper_dev = info->upper_dev; - if (!info->master || !info->linking) - break; if (!netif_is_bridge_master(upper_dev)) - return NOTIFY_BAD; + return -EINVAL; + if (!info->linking) + break; /* We can't have multiple VLAN interfaces configured on * the same port and being members in the same bridge. */ if (!mlxsw_sp_port_master_bridge_check(mlxsw_sp_port, upper_dev)) - return NOTIFY_BAD; + return -EINVAL; break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; - if (!info->master) - break; if (info->linking) { - if (!mlxsw_sp_vport) { - WARN_ON(!mlxsw_sp_vport); - return NOTIFY_BAD; - } + if (WARN_ON(!mlxsw_sp_vport)) + return -EINVAL; err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport, upper_dev); - if (err) { - netdev_err(dev, "Failed to join bridge\n"); - return NOTIFY_BAD; - } } else { - /* We ignore bridge's unlinking notifications if vPort - * is gone, since we already left the bridge when the - * VLAN device was unlinked from the real device. - */ if (!mlxsw_sp_vport) - return NOTIFY_DONE; - err = mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, - upper_dev, true); - if (err) { - netdev_err(dev, "Failed to leave bridge\n"); - return NOTIFY_BAD; - } + return 0; + mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport); } } - return NOTIFY_DONE; + return err; } static int mlxsw_sp_netdevice_lag_vport_event(struct net_device *lag_dev, @@ -3492,12 +4434,12 @@ static int mlxsw_sp_netdevice_lag_vport_event(struct net_device *lag_dev, if (mlxsw_sp_port_dev_check(dev)) { ret = mlxsw_sp_netdevice_vport_event(dev, event, ptr, vid); - if (ret == NOTIFY_BAD) + if (ret) return ret; } } - return NOTIFY_DONE; + return 0; } static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev, @@ -3513,35 +4455,44 @@ static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev, return mlxsw_sp_netdevice_lag_vport_event(real_dev, event, ptr, vid); - return NOTIFY_DONE; + return 0; } static int mlxsw_sp_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + int err = 0; - if (mlxsw_sp_port_dev_check(dev)) - return mlxsw_sp_netdevice_port_event(dev, event, ptr); - - if (netif_is_lag_master(dev)) - return mlxsw_sp_netdevice_lag_event(dev, event, ptr); + if (event == NETDEV_CHANGEADDR || event == NETDEV_CHANGEMTU) + err = mlxsw_sp_netdevice_router_port_event(dev); + else if (mlxsw_sp_port_dev_check(dev)) + err = mlxsw_sp_netdevice_port_event(dev, event, ptr); + else if (netif_is_lag_master(dev)) + err = mlxsw_sp_netdevice_lag_event(dev, event, ptr); + else if (netif_is_bridge_master(dev)) + err = mlxsw_sp_netdevice_bridge_event(dev, event, ptr); + else if (is_vlan_dev(dev)) + err = mlxsw_sp_netdevice_vlan_event(dev, event, ptr); - if (is_vlan_dev(dev)) - return mlxsw_sp_netdevice_vlan_event(dev, event, ptr); - - return NOTIFY_DONE; + return notifier_from_errno(err); } static struct notifier_block mlxsw_sp_netdevice_nb __read_mostly = { .notifier_call = mlxsw_sp_netdevice_event, }; +static struct notifier_block mlxsw_sp_inetaddr_nb __read_mostly = { + .notifier_call = mlxsw_sp_inetaddr_event, + .priority = 10, /* Must be called before FIB notifier block */ +}; + static int __init mlxsw_sp_module_init(void) { int err; register_netdevice_notifier(&mlxsw_sp_netdevice_nb); + register_inetaddr_notifier(&mlxsw_sp_inetaddr_nb); err = mlxsw_core_driver_register(&mlxsw_sp_driver); if (err) goto err_core_driver_register; @@ -3555,6 +4506,7 @@ err_core_driver_register: static void __exit mlxsw_sp_module_exit(void) { mlxsw_core_driver_unregister(&mlxsw_sp_driver); + unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb); unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 13b30eaa13d4..f69aa37d1521 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -39,19 +39,22 @@ #include <linux/types.h> #include <linux/netdevice.h> +#include <linux/rhashtable.h> #include <linux/bitops.h> #include <linux/if_vlan.h> #include <linux/list.h> #include <linux/dcbnl.h> +#include <linux/in6.h> #include <net/switchdev.h> #include "port.h" #include "core.h" #define MLXSW_SP_VFID_BASE VLAN_N_VID -#define MLXSW_SP_VFID_PORT_MAX 512 /* Non-bridged VLAN interfaces */ -#define MLXSW_SP_VFID_BR_MAX 6144 /* Bridged VLAN interfaces */ -#define MLXSW_SP_VFID_MAX (MLXSW_SP_VFID_PORT_MAX + MLXSW_SP_VFID_BR_MAX) +#define MLXSW_SP_VFID_MAX 6656 /* Bridged VLAN interfaces */ + +#define MLXSW_SP_RFID_BASE 15360 +#define MLXSW_SP_RIF_MAX 800 #define MLXSW_SP_LAG_MAX 64 #define MLXSW_SP_PORT_PER_LAG_MAX 16 @@ -60,6 +63,12 @@ #define MLXSW_SP_PORTS_PER_CLUSTER_MAX 4 +#define MLXSW_SP_LPM_TREE_MIN 2 /* trees 0 and 1 are reserved */ +#define MLXSW_SP_LPM_TREE_MAX 22 +#define MLXSW_SP_LPM_TREE_COUNT (MLXSW_SP_LPM_TREE_MAX - MLXSW_SP_LPM_TREE_MIN) + +#define MLXSW_SP_VIRTUAL_ROUTER_MAX 256 + #define MLXSW_SP_PORT_BASE_SPEED 25000 /* Mb/s */ #define MLXSW_SP_BYTES_PER_CELL 96 @@ -67,6 +76,10 @@ #define MLXSW_SP_BYTES_TO_CELLS(b) DIV_ROUND_UP(b, MLXSW_SP_BYTES_PER_CELL) #define MLXSW_SP_CELLS_TO_BYTES(c) (c * MLXSW_SP_BYTES_PER_CELL) +#define MLXSW_SP_KVD_LINEAR_SIZE 65536 /* entries */ +#define MLXSW_SP_KVD_HASH_SINGLE_SIZE 163840 /* entries */ +#define MLXSW_SP_KVD_HASH_DOUBLE_SIZE 32768 /* entries */ + /* Maximum delay buffer needed in case of PAUSE frames, in cells. * Assumes 100m cable and maximum MTU. */ @@ -87,12 +100,22 @@ struct mlxsw_sp_upper { unsigned int ref_count; }; -struct mlxsw_sp_vfid { +struct mlxsw_sp_fid { + void (*leave)(struct mlxsw_sp_port *mlxsw_sp_vport); struct list_head list; - u16 nr_vports; - u16 vfid; /* Starting at 0 */ - struct net_device *br_dev; - u16 vid; + unsigned int ref_count; + struct net_device *dev; + struct mlxsw_sp_rif *r; + u16 fid; +}; + +struct mlxsw_sp_rif { + struct net_device *dev; + unsigned int ref_count; + struct mlxsw_sp_fid *f; + unsigned char addr[ETH_ALEN]; + int mtu; + u16 rif; }; struct mlxsw_sp_mid { @@ -115,7 +138,17 @@ static inline u16 mlxsw_sp_fid_to_vfid(u16 fid) static inline bool mlxsw_sp_fid_is_vfid(u16 fid) { - return fid >= MLXSW_SP_VFID_BASE; + return fid >= MLXSW_SP_VFID_BASE && fid < MLXSW_SP_RFID_BASE; +} + +static inline bool mlxsw_sp_fid_is_rfid(u16 fid) +{ + return fid >= MLXSW_SP_RFID_BASE; +} + +static inline u16 mlxsw_sp_rif_sp_to_fid(u16 rif) +{ + return MLXSW_SP_RFID_BASE + rif; } struct mlxsw_sp_sb_pr { @@ -152,20 +185,97 @@ struct mlxsw_sp_sb { } ports[MLXSW_PORT_MAX_PORTS]; }; -struct mlxsw_sp { +#define MLXSW_SP_PREFIX_COUNT (sizeof(struct in6_addr) * BITS_PER_BYTE) + +struct mlxsw_sp_prefix_usage { + DECLARE_BITMAP(b, MLXSW_SP_PREFIX_COUNT); +}; + +enum mlxsw_sp_l3proto { + MLXSW_SP_L3_PROTO_IPV4, + MLXSW_SP_L3_PROTO_IPV6, +}; + +struct mlxsw_sp_lpm_tree { + u8 id; /* tree ID */ + unsigned int ref_count; + enum mlxsw_sp_l3proto proto; + struct mlxsw_sp_prefix_usage prefix_usage; +}; + +struct mlxsw_sp_fib; + +struct mlxsw_sp_vr { + u16 id; /* virtual router ID */ + bool used; + enum mlxsw_sp_l3proto proto; + u32 tb_id; /* kernel fib table id */ + struct mlxsw_sp_lpm_tree *lpm_tree; + struct mlxsw_sp_fib *fib; +}; + +enum mlxsw_sp_span_type { + MLXSW_SP_SPAN_EGRESS, + MLXSW_SP_SPAN_INGRESS +}; + +struct mlxsw_sp_span_inspected_port { + struct list_head list; + enum mlxsw_sp_span_type type; + u8 local_port; +}; + +struct mlxsw_sp_span_entry { + u8 local_port; + bool used; + struct list_head bound_ports_list; + int ref_count; + int id; +}; + +enum mlxsw_sp_port_mall_action_type { + MLXSW_SP_PORT_MALL_MIRROR, +}; + +struct mlxsw_sp_port_mall_mirror_tc_entry { + u8 to_local_port; + bool ingress; +}; + +struct mlxsw_sp_port_mall_tc_entry { + struct list_head list; + unsigned long cookie; + enum mlxsw_sp_port_mall_action_type type; + union { + struct mlxsw_sp_port_mall_mirror_tc_entry mirror; + }; +}; + +struct mlxsw_sp_router { + struct mlxsw_sp_lpm_tree lpm_trees[MLXSW_SP_LPM_TREE_COUNT]; + struct mlxsw_sp_vr vrs[MLXSW_SP_VIRTUAL_ROUTER_MAX]; + struct rhashtable neigh_ht; struct { - struct list_head list; - unsigned long mapped[BITS_TO_LONGS(MLXSW_SP_VFID_PORT_MAX)]; - } port_vfids; + struct delayed_work dw; + unsigned long interval; /* ms */ + } neighs_update; + struct delayed_work nexthop_probe_dw; +#define MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL 5000 /* ms */ + struct list_head nexthop_group_list; + struct list_head nexthop_neighs_list; +}; + +struct mlxsw_sp { struct { struct list_head list; - unsigned long mapped[BITS_TO_LONGS(MLXSW_SP_VFID_BR_MAX)]; - } br_vfids; + DECLARE_BITMAP(mapped, MLXSW_SP_VFID_MAX); + } vfids; struct { struct list_head list; - unsigned long mapped[BITS_TO_LONGS(MLXSW_SP_MID_MAX)]; + DECLARE_BITMAP(mapped, MLXSW_SP_MID_MAX); } br_mids; - unsigned long active_fids[BITS_TO_LONGS(VLAN_N_VID)]; + struct list_head fids; /* VLAN-aware bridge FIDs */ + struct mlxsw_sp_rif *rifs[MLXSW_SP_RIF_MAX]; struct mlxsw_sp_port **ports; struct mlxsw_core *core; const struct mlxsw_bus_info *bus_info; @@ -183,6 +293,15 @@ struct mlxsw_sp { struct mlxsw_sp_upper lags[MLXSW_SP_LAG_MAX]; u8 port_to_module[MLXSW_PORT_MAX_PORTS]; struct mlxsw_sp_sb sb; + struct mlxsw_sp_router router; + struct { + DECLARE_BITMAP(usage, MLXSW_SP_KVD_LINEAR_SIZE); + } kvdl; + + struct { + struct mlxsw_sp_span_entry *entries; + int entries_count; + } span; }; static inline struct mlxsw_sp_upper * @@ -217,7 +336,7 @@ struct mlxsw_sp_port { u16 lag_id; struct { struct list_head list; - struct mlxsw_sp_vfid *vfid; + struct mlxsw_sp_fid *f; u16 vid; } vport; struct { @@ -239,8 +358,13 @@ struct mlxsw_sp_port { unsigned long *untagged_vlans; /* VLAN interfaces */ struct list_head vports_list; + /* TC handles */ + struct list_head mall_tc_list; }; +struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev); +void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port); + static inline bool mlxsw_sp_port_is_pause_en(const struct mlxsw_sp_port *mlxsw_sp_port) { @@ -259,28 +383,38 @@ mlxsw_sp_port_lagged_get(struct mlxsw_sp *mlxsw_sp, u16 lag_id, u8 port_index) return mlxsw_sp_port && mlxsw_sp_port->lagged ? mlxsw_sp_port : NULL; } +static inline u16 +mlxsw_sp_vport_vid_get(const struct mlxsw_sp_port *mlxsw_sp_vport) +{ + return mlxsw_sp_vport->vport.vid; +} + static inline bool mlxsw_sp_port_is_vport(const struct mlxsw_sp_port *mlxsw_sp_port) { - return mlxsw_sp_port->vport.vfid; + u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_port); + + return vid != 0; } -static inline struct net_device * -mlxsw_sp_vport_br_get(const struct mlxsw_sp_port *mlxsw_sp_vport) +static inline void mlxsw_sp_vport_fid_set(struct mlxsw_sp_port *mlxsw_sp_vport, + struct mlxsw_sp_fid *f) { - return mlxsw_sp_vport->vport.vfid->br_dev; + mlxsw_sp_vport->vport.f = f; } -static inline u16 -mlxsw_sp_vport_vid_get(const struct mlxsw_sp_port *mlxsw_sp_vport) +static inline struct mlxsw_sp_fid * +mlxsw_sp_vport_fid_get(const struct mlxsw_sp_port *mlxsw_sp_vport) { - return mlxsw_sp_vport->vport.vid; + return mlxsw_sp_vport->vport.f; } -static inline u16 -mlxsw_sp_vport_vfid_get(const struct mlxsw_sp_port *mlxsw_sp_vport) +static inline struct net_device * +mlxsw_sp_vport_dev_get(const struct mlxsw_sp_port *mlxsw_sp_vport) { - return mlxsw_sp_vport->vport.vfid->vfid; + struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); + + return f ? f->dev : NULL; } static inline struct mlxsw_sp_port * @@ -298,20 +432,60 @@ mlxsw_sp_port_vport_find(const struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) } static inline struct mlxsw_sp_port * -mlxsw_sp_port_vport_find_by_vfid(const struct mlxsw_sp_port *mlxsw_sp_port, - u16 vfid) +mlxsw_sp_port_vport_find_by_fid(const struct mlxsw_sp_port *mlxsw_sp_port, + u16 fid) { struct mlxsw_sp_port *mlxsw_sp_vport; list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list, vport.list) { - if (mlxsw_sp_vport_vfid_get(mlxsw_sp_vport) == vfid) + struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); + + if (f && f->fid == fid) return mlxsw_sp_vport; } return NULL; } +static inline struct mlxsw_sp_fid *mlxsw_sp_fid_find(struct mlxsw_sp *mlxsw_sp, + u16 fid) +{ + struct mlxsw_sp_fid *f; + + list_for_each_entry(f, &mlxsw_sp->fids, list) + if (f->fid == fid) + return f; + + return NULL; +} + +static inline struct mlxsw_sp_fid * +mlxsw_sp_vfid_find(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *br_dev) +{ + struct mlxsw_sp_fid *f; + + list_for_each_entry(f, &mlxsw_sp->vfids.list, list) + if (f->dev == br_dev) + return f; + + return NULL; +} + +static inline struct mlxsw_sp_rif * +mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev) +{ + int i; + + for (i = 0; i < MLXSW_SP_RIF_MAX; i++) + if (mlxsw_sp->rifs[i] && mlxsw_sp->rifs[i]->dev == dev) + return mlxsw_sp->rifs[i]; + + return NULL; +} + enum mlxsw_sp_flood_table { MLXSW_SP_FLOOD_TABLE_UC, MLXSW_SP_FLOOD_TABLE_BM, @@ -364,12 +538,17 @@ int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin, u16 vid_end, bool is_member, bool untagged); int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, u16 vid); -int mlxsw_sp_port_kill_vid(struct net_device *dev, - __be16 __always_unused proto, u16 vid); -int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid, - bool set, bool only_uc); +int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 fid, + bool set); void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port); int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid); +int mlxsw_sp_port_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid); +int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid, + bool adding); +struct mlxsw_sp_fid *mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid); +void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f); +void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *r); int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port, enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index, bool dwrr, u8 dwrr_weight); @@ -399,4 +578,19 @@ static inline void mlxsw_sp_port_dcb_fini(struct mlxsw_sp_port *mlxsw_sp_port) #endif +int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp); +void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp); +int mlxsw_sp_router_fib4_add(struct mlxsw_sp_port *mlxsw_sp_port, + const struct switchdev_obj_ipv4_fib *fib4, + struct switchdev_trans *trans); +int mlxsw_sp_router_fib4_del(struct mlxsw_sp_port *mlxsw_sp_port, + const struct switchdev_obj_ipv4_fib *fib4); +int mlxsw_sp_router_neigh_construct(struct net_device *dev, + struct neighbour *n); +void mlxsw_sp_router_neigh_destroy(struct net_device *dev, + struct neighbour *n); + +int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count); +void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index); + #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c new file mode 100644 index 000000000000..ac321e8e5c1a --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c @@ -0,0 +1,91 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/kernel.h> +#include <linux/bitops.h> + +#include "spectrum.h" + +#define MLXSW_SP_KVDL_SINGLE_BASE 0 +#define MLXSW_SP_KVDL_SINGLE_SIZE 16384 +#define MLXSW_SP_KVDL_CHUNKS_BASE \ + (MLXSW_SP_KVDL_SINGLE_BASE + MLXSW_SP_KVDL_SINGLE_SIZE) +#define MLXSW_SP_KVDL_CHUNKS_SIZE \ + (MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP_KVDL_CHUNKS_BASE) +#define MLXSW_SP_CHUNK_MAX 32 + +int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count) +{ + int entry_index; + int size; + int type_base; + int type_size; + int type_entries; + + if (entry_count == 0 || entry_count > MLXSW_SP_CHUNK_MAX) { + return -EINVAL; + } else if (entry_count == 1) { + type_base = MLXSW_SP_KVDL_SINGLE_BASE; + type_size = MLXSW_SP_KVDL_SINGLE_SIZE; + type_entries = 1; + } else { + type_base = MLXSW_SP_KVDL_CHUNKS_BASE; + type_size = MLXSW_SP_KVDL_CHUNKS_SIZE; + type_entries = MLXSW_SP_CHUNK_MAX; + } + + entry_index = type_base; + size = type_base + type_size; + for_each_clear_bit_from(entry_index, mlxsw_sp->kvdl.usage, size) { + int i; + + for (i = 0; i < type_entries; i++) + set_bit(entry_index + i, mlxsw_sp->kvdl.usage); + return entry_index; + } + return -ENOBUFS; +} + +void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index) +{ + int type_entries; + int i; + + if (entry_index < MLXSW_SP_KVDL_CHUNKS_BASE) + type_entries = 1; + else + type_entries = MLXSW_SP_CHUNK_MAX; + for (i = 0; i < type_entries; i++) + clear_bit(entry_index + i, mlxsw_sp->kvdl.usage); +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c new file mode 100644 index 000000000000..81418d629231 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -0,0 +1,1814 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> + * Copyright (c) 2016 Ido Schimmel <idosch@mellanox.com> + * Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/rhashtable.h> +#include <linux/bitops.h> +#include <linux/in6.h> +#include <linux/notifier.h> +#include <net/netevent.h> +#include <net/neighbour.h> +#include <net/arp.h> + +#include "spectrum.h" +#include "core.h" +#include "reg.h" + +#define mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) \ + for_each_set_bit(prefix, (prefix_usage)->b, MLXSW_SP_PREFIX_COUNT) + +static bool +mlxsw_sp_prefix_usage_subset(struct mlxsw_sp_prefix_usage *prefix_usage1, + struct mlxsw_sp_prefix_usage *prefix_usage2) +{ + unsigned char prefix; + + mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage1) { + if (!test_bit(prefix, prefix_usage2->b)) + return false; + } + return true; +} + +static bool +mlxsw_sp_prefix_usage_eq(struct mlxsw_sp_prefix_usage *prefix_usage1, + struct mlxsw_sp_prefix_usage *prefix_usage2) +{ + return !memcmp(prefix_usage1, prefix_usage2, sizeof(*prefix_usage1)); +} + +static bool +mlxsw_sp_prefix_usage_none(struct mlxsw_sp_prefix_usage *prefix_usage) +{ + struct mlxsw_sp_prefix_usage prefix_usage_none = {{ 0 } }; + + return mlxsw_sp_prefix_usage_eq(prefix_usage, &prefix_usage_none); +} + +static void +mlxsw_sp_prefix_usage_cpy(struct mlxsw_sp_prefix_usage *prefix_usage1, + struct mlxsw_sp_prefix_usage *prefix_usage2) +{ + memcpy(prefix_usage1, prefix_usage2, sizeof(*prefix_usage1)); +} + +static void +mlxsw_sp_prefix_usage_zero(struct mlxsw_sp_prefix_usage *prefix_usage) +{ + memset(prefix_usage, 0, sizeof(*prefix_usage)); +} + +static void +mlxsw_sp_prefix_usage_set(struct mlxsw_sp_prefix_usage *prefix_usage, + unsigned char prefix_len) +{ + set_bit(prefix_len, prefix_usage->b); +} + +static void +mlxsw_sp_prefix_usage_clear(struct mlxsw_sp_prefix_usage *prefix_usage, + unsigned char prefix_len) +{ + clear_bit(prefix_len, prefix_usage->b); +} + +struct mlxsw_sp_fib_key { + unsigned char addr[sizeof(struct in6_addr)]; + unsigned char prefix_len; +}; + +enum mlxsw_sp_fib_entry_type { + MLXSW_SP_FIB_ENTRY_TYPE_REMOTE, + MLXSW_SP_FIB_ENTRY_TYPE_LOCAL, + MLXSW_SP_FIB_ENTRY_TYPE_TRAP, +}; + +struct mlxsw_sp_nexthop_group; + +struct mlxsw_sp_fib_entry { + struct rhash_head ht_node; + struct mlxsw_sp_fib_key key; + enum mlxsw_sp_fib_entry_type type; + u8 added:1; + u16 rif; /* used for action local */ + struct mlxsw_sp_vr *vr; + struct list_head nexthop_group_node; + struct mlxsw_sp_nexthop_group *nh_group; +}; + +struct mlxsw_sp_fib { + struct rhashtable ht; + unsigned long prefix_ref_count[MLXSW_SP_PREFIX_COUNT]; + struct mlxsw_sp_prefix_usage prefix_usage; +}; + +static const struct rhashtable_params mlxsw_sp_fib_ht_params = { + .key_offset = offsetof(struct mlxsw_sp_fib_entry, key), + .head_offset = offsetof(struct mlxsw_sp_fib_entry, ht_node), + .key_len = sizeof(struct mlxsw_sp_fib_key), + .automatic_shrinking = true, +}; + +static int mlxsw_sp_fib_entry_insert(struct mlxsw_sp_fib *fib, + struct mlxsw_sp_fib_entry *fib_entry) +{ + unsigned char prefix_len = fib_entry->key.prefix_len; + int err; + + err = rhashtable_insert_fast(&fib->ht, &fib_entry->ht_node, + mlxsw_sp_fib_ht_params); + if (err) + return err; + if (fib->prefix_ref_count[prefix_len]++ == 0) + mlxsw_sp_prefix_usage_set(&fib->prefix_usage, prefix_len); + return 0; +} + +static void mlxsw_sp_fib_entry_remove(struct mlxsw_sp_fib *fib, + struct mlxsw_sp_fib_entry *fib_entry) +{ + unsigned char prefix_len = fib_entry->key.prefix_len; + + if (--fib->prefix_ref_count[prefix_len] == 0) + mlxsw_sp_prefix_usage_clear(&fib->prefix_usage, prefix_len); + rhashtable_remove_fast(&fib->ht, &fib_entry->ht_node, + mlxsw_sp_fib_ht_params); +} + +static struct mlxsw_sp_fib_entry * +mlxsw_sp_fib_entry_create(struct mlxsw_sp_fib *fib, const void *addr, + size_t addr_len, unsigned char prefix_len) +{ + struct mlxsw_sp_fib_entry *fib_entry; + + fib_entry = kzalloc(sizeof(*fib_entry), GFP_KERNEL); + if (!fib_entry) + return NULL; + memcpy(fib_entry->key.addr, addr, addr_len); + fib_entry->key.prefix_len = prefix_len; + return fib_entry; +} + +static void mlxsw_sp_fib_entry_destroy(struct mlxsw_sp_fib_entry *fib_entry) +{ + kfree(fib_entry); +} + +static struct mlxsw_sp_fib_entry * +mlxsw_sp_fib_entry_lookup(struct mlxsw_sp_fib *fib, const void *addr, + size_t addr_len, unsigned char prefix_len) +{ + struct mlxsw_sp_fib_key key = {{ 0 } }; + + memcpy(key.addr, addr, addr_len); + key.prefix_len = prefix_len; + return rhashtable_lookup_fast(&fib->ht, &key, mlxsw_sp_fib_ht_params); +} + +static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void) +{ + struct mlxsw_sp_fib *fib; + int err; + + fib = kzalloc(sizeof(*fib), GFP_KERNEL); + if (!fib) + return ERR_PTR(-ENOMEM); + err = rhashtable_init(&fib->ht, &mlxsw_sp_fib_ht_params); + if (err) + goto err_rhashtable_init; + return fib; + +err_rhashtable_init: + kfree(fib); + return ERR_PTR(err); +} + +static void mlxsw_sp_fib_destroy(struct mlxsw_sp_fib *fib) +{ + rhashtable_destroy(&fib->ht); + kfree(fib); +} + +static struct mlxsw_sp_lpm_tree * +mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp, bool one_reserved) +{ + static struct mlxsw_sp_lpm_tree *lpm_tree; + int i; + + for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) { + lpm_tree = &mlxsw_sp->router.lpm_trees[i]; + if (lpm_tree->ref_count == 0) { + if (one_reserved) + one_reserved = false; + else + return lpm_tree; + } + } + return NULL; +} + +static int mlxsw_sp_lpm_tree_alloc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_lpm_tree *lpm_tree) +{ + char ralta_pl[MLXSW_REG_RALTA_LEN]; + + mlxsw_reg_ralta_pack(ralta_pl, true, lpm_tree->proto, lpm_tree->id); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); +} + +static int mlxsw_sp_lpm_tree_free(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_lpm_tree *lpm_tree) +{ + char ralta_pl[MLXSW_REG_RALTA_LEN]; + + mlxsw_reg_ralta_pack(ralta_pl, false, lpm_tree->proto, lpm_tree->id); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); +} + +static int +mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_prefix_usage *prefix_usage, + struct mlxsw_sp_lpm_tree *lpm_tree) +{ + char ralst_pl[MLXSW_REG_RALST_LEN]; + u8 root_bin = 0; + u8 prefix; + u8 last_prefix = MLXSW_REG_RALST_BIN_NO_CHILD; + + mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) + root_bin = prefix; + + mlxsw_reg_ralst_pack(ralst_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); + last_prefix = prefix; + } + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), ralst_pl); +} + +static struct mlxsw_sp_lpm_tree * +mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_prefix_usage *prefix_usage, + enum mlxsw_sp_l3proto proto, bool one_reserved) +{ + struct mlxsw_sp_lpm_tree *lpm_tree; + int err; + + lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp, one_reserved); + if (!lpm_tree) + return ERR_PTR(-EBUSY); + lpm_tree->proto = proto; + err = mlxsw_sp_lpm_tree_alloc(mlxsw_sp, lpm_tree); + if (err) + return ERR_PTR(err); + + err = mlxsw_sp_lpm_tree_left_struct_set(mlxsw_sp, prefix_usage, + lpm_tree); + if (err) + goto err_left_struct_set; + return lpm_tree; + +err_left_struct_set: + mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree); + return ERR_PTR(err); +} + +static int mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_lpm_tree *lpm_tree) +{ + return mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree); +} + +static struct mlxsw_sp_lpm_tree * +mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_prefix_usage *prefix_usage, + enum mlxsw_sp_l3proto proto, bool one_reserved) +{ + struct mlxsw_sp_lpm_tree *lpm_tree; + int i; + + for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) { + lpm_tree = &mlxsw_sp->router.lpm_trees[i]; + if (lpm_tree->proto == proto && + mlxsw_sp_prefix_usage_eq(&lpm_tree->prefix_usage, + prefix_usage)) + goto inc_ref_count; + } + lpm_tree = mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage, + proto, one_reserved); + if (IS_ERR(lpm_tree)) + return lpm_tree; + +inc_ref_count: + lpm_tree->ref_count++; + return lpm_tree; +} + +static int mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_lpm_tree *lpm_tree) +{ + if (--lpm_tree->ref_count == 0) + return mlxsw_sp_lpm_tree_destroy(mlxsw_sp, lpm_tree); + return 0; +} + +static void mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_lpm_tree *lpm_tree; + int i; + + for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) { + lpm_tree = &mlxsw_sp->router.lpm_trees[i]; + lpm_tree->id = i + MLXSW_SP_LPM_TREE_MIN; + } +} + +static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_vr *vr; + int i; + + for (i = 0; i < MLXSW_SP_VIRTUAL_ROUTER_MAX; i++) { + vr = &mlxsw_sp->router.vrs[i]; + if (!vr->used) + return vr; + } + return NULL; +} + +static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_vr *vr) +{ + char raltb_pl[MLXSW_REG_RALTB_LEN]; + + mlxsw_reg_raltb_pack(raltb_pl, vr->id, vr->proto, vr->lpm_tree->id); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); +} + +static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_vr *vr) +{ + char raltb_pl[MLXSW_REG_RALTB_LEN]; + + /* Bind to tree 0 which is default */ + mlxsw_reg_raltb_pack(raltb_pl, vr->id, vr->proto, 0); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); +} + +static u32 mlxsw_sp_fix_tb_id(u32 tb_id) +{ + /* For our purpose, squash main and local table into one */ + if (tb_id == RT_TABLE_LOCAL) + tb_id = RT_TABLE_MAIN; + return tb_id; +} + +static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp, + u32 tb_id, + enum mlxsw_sp_l3proto proto) +{ + struct mlxsw_sp_vr *vr; + int i; + + tb_id = mlxsw_sp_fix_tb_id(tb_id); + for (i = 0; i < MLXSW_SP_VIRTUAL_ROUTER_MAX; i++) { + vr = &mlxsw_sp->router.vrs[i]; + if (vr->used && vr->proto == proto && vr->tb_id == tb_id) + return vr; + } + return NULL; +} + +static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, + unsigned char prefix_len, + u32 tb_id, + enum mlxsw_sp_l3proto proto) +{ + struct mlxsw_sp_prefix_usage req_prefix_usage; + struct mlxsw_sp_lpm_tree *lpm_tree; + struct mlxsw_sp_vr *vr; + int err; + + vr = mlxsw_sp_vr_find_unused(mlxsw_sp); + if (!vr) + return ERR_PTR(-EBUSY); + vr->fib = mlxsw_sp_fib_create(); + if (IS_ERR(vr->fib)) + return ERR_CAST(vr->fib); + + vr->proto = proto; + vr->tb_id = tb_id; + mlxsw_sp_prefix_usage_zero(&req_prefix_usage); + mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len); + lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, + proto, true); + if (IS_ERR(lpm_tree)) { + err = PTR_ERR(lpm_tree); + goto err_tree_get; + } + vr->lpm_tree = lpm_tree; + err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); + if (err) + goto err_tree_bind; + + vr->used = true; + return vr; + +err_tree_bind: + mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree); +err_tree_get: + mlxsw_sp_fib_destroy(vr->fib); + + return ERR_PTR(err); +} + +static void mlxsw_sp_vr_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_vr *vr) +{ + mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr); + mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree); + mlxsw_sp_fib_destroy(vr->fib); + vr->used = false; +} + +static int +mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, + struct mlxsw_sp_prefix_usage *req_prefix_usage) +{ + struct mlxsw_sp_lpm_tree *lpm_tree; + + if (mlxsw_sp_prefix_usage_eq(req_prefix_usage, + &vr->lpm_tree->prefix_usage)) + return 0; + + lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage, + vr->proto, false); + if (IS_ERR(lpm_tree)) { + /* We failed to get a tree according to the required + * prefix usage. However, the current tree might be still good + * for us if our requirement is subset of the prefixes used + * in the tree. + */ + if (mlxsw_sp_prefix_usage_subset(req_prefix_usage, + &vr->lpm_tree->prefix_usage)) + return 0; + return PTR_ERR(lpm_tree); + } + + mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr); + mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree); + vr->lpm_tree = lpm_tree; + return mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); +} + +static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, + unsigned char prefix_len, + u32 tb_id, + enum mlxsw_sp_l3proto proto) +{ + struct mlxsw_sp_vr *vr; + int err; + + tb_id = mlxsw_sp_fix_tb_id(tb_id); + vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id, proto); + if (!vr) { + vr = mlxsw_sp_vr_create(mlxsw_sp, prefix_len, tb_id, proto); + if (IS_ERR(vr)) + return vr; + } else { + struct mlxsw_sp_prefix_usage req_prefix_usage; + + mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, + &vr->fib->prefix_usage); + mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len); + /* Need to replace LPM tree in case new prefix is required. */ + err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr, + &req_prefix_usage); + if (err) + return ERR_PTR(err); + } + return vr; +} + +static void mlxsw_sp_vr_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr) +{ + /* Destroy virtual router entity in case the associated FIB is empty + * and allow it to be used for other tables in future. Otherwise, + * check if some prefix usage did not disappear and change tree if + * that is the case. Note that in case new, smaller tree cannot be + * allocated, the original one will be kept being used. + */ + if (mlxsw_sp_prefix_usage_none(&vr->fib->prefix_usage)) + mlxsw_sp_vr_destroy(mlxsw_sp, vr); + else + mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr, + &vr->fib->prefix_usage); +} + +static void mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_vr *vr; + int i; + + for (i = 0; i < MLXSW_SP_VIRTUAL_ROUTER_MAX; i++) { + vr = &mlxsw_sp->router.vrs[i]; + vr->id = i; + } +} + +struct mlxsw_sp_neigh_key { + unsigned char addr[sizeof(struct in6_addr)]; + struct net_device *dev; +}; + +struct mlxsw_sp_neigh_entry { + struct rhash_head ht_node; + struct mlxsw_sp_neigh_key key; + u16 rif; + struct neighbour *n; + bool offloaded; + struct delayed_work dw; + struct mlxsw_sp_port *mlxsw_sp_port; + unsigned char ha[ETH_ALEN]; + struct list_head nexthop_list; /* list of nexthops using + * this neigh entry + */ + struct list_head nexthop_neighs_list_node; +}; + +static const struct rhashtable_params mlxsw_sp_neigh_ht_params = { + .key_offset = offsetof(struct mlxsw_sp_neigh_entry, key), + .head_offset = offsetof(struct mlxsw_sp_neigh_entry, ht_node), + .key_len = sizeof(struct mlxsw_sp_neigh_key), +}; + +static int +mlxsw_sp_neigh_entry_insert(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_neigh_entry *neigh_entry) +{ + return rhashtable_insert_fast(&mlxsw_sp->router.neigh_ht, + &neigh_entry->ht_node, + mlxsw_sp_neigh_ht_params); +} + +static void +mlxsw_sp_neigh_entry_remove(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_neigh_entry *neigh_entry) +{ + rhashtable_remove_fast(&mlxsw_sp->router.neigh_ht, + &neigh_entry->ht_node, + mlxsw_sp_neigh_ht_params); +} + +static void mlxsw_sp_router_neigh_update_hw(struct work_struct *work); + +static struct mlxsw_sp_neigh_entry * +mlxsw_sp_neigh_entry_create(const void *addr, size_t addr_len, + struct net_device *dev, u16 rif, + struct neighbour *n) +{ + struct mlxsw_sp_neigh_entry *neigh_entry; + + neigh_entry = kzalloc(sizeof(*neigh_entry), GFP_ATOMIC); + if (!neigh_entry) + return NULL; + memcpy(neigh_entry->key.addr, addr, addr_len); + neigh_entry->key.dev = dev; + neigh_entry->rif = rif; + neigh_entry->n = n; + INIT_DELAYED_WORK(&neigh_entry->dw, mlxsw_sp_router_neigh_update_hw); + INIT_LIST_HEAD(&neigh_entry->nexthop_list); + return neigh_entry; +} + +static void +mlxsw_sp_neigh_entry_destroy(struct mlxsw_sp_neigh_entry *neigh_entry) +{ + kfree(neigh_entry); +} + +static struct mlxsw_sp_neigh_entry * +mlxsw_sp_neigh_entry_lookup(struct mlxsw_sp *mlxsw_sp, const void *addr, + size_t addr_len, struct net_device *dev) +{ + struct mlxsw_sp_neigh_key key = {{ 0 } }; + + memcpy(key.addr, addr, addr_len); + key.dev = dev; + return rhashtable_lookup_fast(&mlxsw_sp->router.neigh_ht, + &key, mlxsw_sp_neigh_ht_params); +} + +int mlxsw_sp_router_neigh_construct(struct net_device *dev, + struct neighbour *n) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_neigh_entry *neigh_entry; + struct mlxsw_sp_rif *r; + u32 dip; + int err; + + if (n->tbl != &arp_tbl) + return 0; + + dip = ntohl(*((__be32 *) n->primary_key)); + neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &dip, sizeof(dip), + n->dev); + if (neigh_entry) { + WARN_ON(neigh_entry->n != n); + return 0; + } + + r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (WARN_ON(!r)) + return -EINVAL; + + neigh_entry = mlxsw_sp_neigh_entry_create(&dip, sizeof(dip), n->dev, + r->rif, n); + if (!neigh_entry) + return -ENOMEM; + err = mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry); + if (err) + goto err_neigh_entry_insert; + return 0; + +err_neigh_entry_insert: + mlxsw_sp_neigh_entry_destroy(neigh_entry); + return err; +} + +void mlxsw_sp_router_neigh_destroy(struct net_device *dev, + struct neighbour *n) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_neigh_entry *neigh_entry; + u32 dip; + + if (n->tbl != &arp_tbl) + return; + + dip = ntohl(*((__be32 *) n->primary_key)); + neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &dip, sizeof(dip), + n->dev); + if (!neigh_entry) + return; + mlxsw_sp_neigh_entry_remove(mlxsw_sp, neigh_entry); + mlxsw_sp_neigh_entry_destroy(neigh_entry); +} + +static void +mlxsw_sp_router_neighs_update_interval_init(struct mlxsw_sp *mlxsw_sp) +{ + unsigned long interval = NEIGH_VAR(&arp_tbl.parms, DELAY_PROBE_TIME); + + mlxsw_sp->router.neighs_update.interval = jiffies_to_msecs(interval); +} + +static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp, + char *rauhtd_pl, + int ent_index) +{ + struct net_device *dev; + struct neighbour *n; + __be32 dipn; + u32 dip; + u16 rif; + + mlxsw_reg_rauhtd_ent_ipv4_unpack(rauhtd_pl, ent_index, &rif, &dip); + + if (!mlxsw_sp->rifs[rif]) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect RIF in neighbour entry\n"); + return; + } + + dipn = htonl(dip); + dev = mlxsw_sp->rifs[rif]->dev; + n = neigh_lookup(&arp_tbl, &dipn, dev); + if (!n) { + netdev_err(dev, "Failed to find matching neighbour for IP=%pI4h\n", + &dip); + return; + } + + netdev_dbg(dev, "Updating neighbour with IP=%pI4h\n", &dip); + neigh_event_send(n, NULL); + neigh_release(n); +} + +static void mlxsw_sp_router_neigh_rec_ipv4_process(struct mlxsw_sp *mlxsw_sp, + char *rauhtd_pl, + int rec_index) +{ + u8 num_entries; + int i; + + num_entries = mlxsw_reg_rauhtd_ipv4_rec_num_entries_get(rauhtd_pl, + rec_index); + /* Hardware starts counting at 0, so add 1. */ + num_entries++; + + /* Each record consists of several neighbour entries. */ + for (i = 0; i < num_entries; i++) { + int ent_index; + + ent_index = rec_index * MLXSW_REG_RAUHTD_IPV4_ENT_PER_REC + i; + mlxsw_sp_router_neigh_ent_ipv4_process(mlxsw_sp, rauhtd_pl, + ent_index); + } + +} + +static void mlxsw_sp_router_neigh_rec_process(struct mlxsw_sp *mlxsw_sp, + char *rauhtd_pl, int rec_index) +{ + switch (mlxsw_reg_rauhtd_rec_type_get(rauhtd_pl, rec_index)) { + case MLXSW_REG_RAUHTD_TYPE_IPV4: + mlxsw_sp_router_neigh_rec_ipv4_process(mlxsw_sp, rauhtd_pl, + rec_index); + break; + case MLXSW_REG_RAUHTD_TYPE_IPV6: + WARN_ON_ONCE(1); + break; + } +} + +static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp) +{ + char *rauhtd_pl; + u8 num_rec; + int i, err; + + rauhtd_pl = kmalloc(MLXSW_REG_RAUHTD_LEN, GFP_KERNEL); + if (!rauhtd_pl) + return -ENOMEM; + + /* Make sure the neighbour's netdev isn't removed in the + * process. + */ + rtnl_lock(); + do { + mlxsw_reg_rauhtd_pack(rauhtd_pl, MLXSW_REG_RAUHTD_TYPE_IPV4); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(rauhtd), + rauhtd_pl); + if (err) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to dump neighbour talbe\n"); + break; + } + num_rec = mlxsw_reg_rauhtd_num_rec_get(rauhtd_pl); + for (i = 0; i < num_rec; i++) + mlxsw_sp_router_neigh_rec_process(mlxsw_sp, rauhtd_pl, + i); + } while (num_rec); + rtnl_unlock(); + + kfree(rauhtd_pl); + return err; +} + +static void mlxsw_sp_router_neighs_update_nh(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_neigh_entry *neigh_entry; + + /* Take RTNL mutex here to prevent lists from changes */ + rtnl_lock(); + list_for_each_entry(neigh_entry, &mlxsw_sp->router.nexthop_neighs_list, + nexthop_neighs_list_node) { + /* If this neigh have nexthops, make the kernel think this neigh + * is active regardless of the traffic. + */ + if (!list_empty(&neigh_entry->nexthop_list)) + neigh_event_send(neigh_entry->n, NULL); + } + rtnl_unlock(); +} + +static void +mlxsw_sp_router_neighs_update_work_schedule(struct mlxsw_sp *mlxsw_sp) +{ + unsigned long interval = mlxsw_sp->router.neighs_update.interval; + + mlxsw_core_schedule_dw(&mlxsw_sp->router.neighs_update.dw, + msecs_to_jiffies(interval)); +} + +static void mlxsw_sp_router_neighs_update_work(struct work_struct *work) +{ + struct mlxsw_sp *mlxsw_sp = container_of(work, struct mlxsw_sp, + router.neighs_update.dw.work); + int err; + + err = mlxsw_sp_router_neighs_update_rauhtd(mlxsw_sp); + if (err) + dev_err(mlxsw_sp->bus_info->dev, "Could not update kernel for neigh activity"); + + mlxsw_sp_router_neighs_update_nh(mlxsw_sp); + + mlxsw_sp_router_neighs_update_work_schedule(mlxsw_sp); +} + +static void mlxsw_sp_router_probe_unresolved_nexthops(struct work_struct *work) +{ + struct mlxsw_sp_neigh_entry *neigh_entry; + struct mlxsw_sp *mlxsw_sp = container_of(work, struct mlxsw_sp, + router.nexthop_probe_dw.work); + + /* Iterate over nexthop neighbours, find those who are unresolved and + * send arp on them. This solves the chicken-egg problem when + * the nexthop wouldn't get offloaded until the neighbor is resolved + * but it wouldn't get resolved ever in case traffic is flowing in HW + * using different nexthop. + * + * Take RTNL mutex here to prevent lists from changes. + */ + rtnl_lock(); + list_for_each_entry(neigh_entry, &mlxsw_sp->router.nexthop_neighs_list, + nexthop_neighs_list_node) { + if (!(neigh_entry->n->nud_state & NUD_VALID) && + !list_empty(&neigh_entry->nexthop_list)) + neigh_event_send(neigh_entry->n, NULL); + } + rtnl_unlock(); + + mlxsw_core_schedule_dw(&mlxsw_sp->router.nexthop_probe_dw, + MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL); +} + +static void +mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_neigh_entry *neigh_entry, + bool removing); + +static void mlxsw_sp_router_neigh_update_hw(struct work_struct *work) +{ + struct mlxsw_sp_neigh_entry *neigh_entry = + container_of(work, struct mlxsw_sp_neigh_entry, dw.work); + struct neighbour *n = neigh_entry->n; + struct mlxsw_sp_port *mlxsw_sp_port = neigh_entry->mlxsw_sp_port; + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char rauht_pl[MLXSW_REG_RAUHT_LEN]; + struct net_device *dev; + bool entry_connected; + u8 nud_state; + bool updating; + bool removing; + bool adding; + u32 dip; + int err; + + read_lock_bh(&n->lock); + dip = ntohl(*((__be32 *) n->primary_key)); + memcpy(neigh_entry->ha, n->ha, sizeof(neigh_entry->ha)); + nud_state = n->nud_state; + dev = n->dev; + read_unlock_bh(&n->lock); + + entry_connected = nud_state & NUD_VALID; + adding = (!neigh_entry->offloaded) && entry_connected; + updating = neigh_entry->offloaded && entry_connected; + removing = neigh_entry->offloaded && !entry_connected; + + if (adding || updating) { + mlxsw_reg_rauht_pack4(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_ADD, + neigh_entry->rif, + neigh_entry->ha, dip); + err = mlxsw_reg_write(mlxsw_sp->core, + MLXSW_REG(rauht), rauht_pl); + if (err) { + netdev_err(dev, "Could not add neigh %pI4h\n", &dip); + neigh_entry->offloaded = false; + } else { + neigh_entry->offloaded = true; + } + mlxsw_sp_nexthop_neigh_update(mlxsw_sp, neigh_entry, false); + } else if (removing) { + mlxsw_reg_rauht_pack4(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_DELETE, + neigh_entry->rif, + neigh_entry->ha, dip); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), + rauht_pl); + if (err) { + netdev_err(dev, "Could not delete neigh %pI4h\n", &dip); + neigh_entry->offloaded = true; + } else { + neigh_entry->offloaded = false; + } + mlxsw_sp_nexthop_neigh_update(mlxsw_sp, neigh_entry, true); + } + + neigh_release(n); + mlxsw_sp_port_dev_put(mlxsw_sp_port); +} + +static int mlxsw_sp_router_netevent_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct mlxsw_sp_neigh_entry *neigh_entry; + struct mlxsw_sp_port *mlxsw_sp_port; + struct mlxsw_sp *mlxsw_sp; + unsigned long interval; + struct net_device *dev; + struct neigh_parms *p; + struct neighbour *n; + u32 dip; + + switch (event) { + case NETEVENT_DELAY_PROBE_TIME_UPDATE: + p = ptr; + + /* We don't care about changes in the default table. */ + if (!p->dev || p->tbl != &arp_tbl) + return NOTIFY_DONE; + + /* We are in atomic context and can't take RTNL mutex, + * so use RCU variant to walk the device chain. + */ + mlxsw_sp_port = mlxsw_sp_port_lower_dev_hold(p->dev); + if (!mlxsw_sp_port) + return NOTIFY_DONE; + + mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + interval = jiffies_to_msecs(NEIGH_VAR(p, DELAY_PROBE_TIME)); + mlxsw_sp->router.neighs_update.interval = interval; + + mlxsw_sp_port_dev_put(mlxsw_sp_port); + break; + case NETEVENT_NEIGH_UPDATE: + n = ptr; + dev = n->dev; + + if (n->tbl != &arp_tbl) + return NOTIFY_DONE; + + mlxsw_sp_port = mlxsw_sp_port_lower_dev_hold(dev); + if (!mlxsw_sp_port) + return NOTIFY_DONE; + + mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + dip = ntohl(*((__be32 *) n->primary_key)); + neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, + &dip, + sizeof(__be32), + dev); + if (WARN_ON(!neigh_entry) || WARN_ON(neigh_entry->n != n)) { + mlxsw_sp_port_dev_put(mlxsw_sp_port); + return NOTIFY_DONE; + } + neigh_entry->mlxsw_sp_port = mlxsw_sp_port; + + /* Take a reference to ensure the neighbour won't be + * destructed until we drop the reference in delayed + * work. + */ + neigh_clone(n); + if (!mlxsw_core_schedule_dw(&neigh_entry->dw, 0)) { + neigh_release(n); + mlxsw_sp_port_dev_put(mlxsw_sp_port); + } + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block mlxsw_sp_router_netevent_nb __read_mostly = { + .notifier_call = mlxsw_sp_router_netevent_event, +}; + +static int mlxsw_sp_neigh_init(struct mlxsw_sp *mlxsw_sp) +{ + int err; + + err = rhashtable_init(&mlxsw_sp->router.neigh_ht, + &mlxsw_sp_neigh_ht_params); + if (err) + return err; + + /* Initialize the polling interval according to the default + * table. + */ + mlxsw_sp_router_neighs_update_interval_init(mlxsw_sp); + + err = register_netevent_notifier(&mlxsw_sp_router_netevent_nb); + if (err) + goto err_register_netevent_notifier; + + /* Create the delayed works for the activity_update */ + INIT_DELAYED_WORK(&mlxsw_sp->router.neighs_update.dw, + mlxsw_sp_router_neighs_update_work); + INIT_DELAYED_WORK(&mlxsw_sp->router.nexthop_probe_dw, + mlxsw_sp_router_probe_unresolved_nexthops); + mlxsw_core_schedule_dw(&mlxsw_sp->router.neighs_update.dw, 0); + mlxsw_core_schedule_dw(&mlxsw_sp->router.nexthop_probe_dw, 0); + return 0; + +err_register_netevent_notifier: + rhashtable_destroy(&mlxsw_sp->router.neigh_ht); + return err; +} + +static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp) +{ + cancel_delayed_work_sync(&mlxsw_sp->router.neighs_update.dw); + cancel_delayed_work_sync(&mlxsw_sp->router.nexthop_probe_dw); + unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb); + rhashtable_destroy(&mlxsw_sp->router.neigh_ht); +} + +struct mlxsw_sp_nexthop { + struct list_head neigh_list_node; /* member of neigh entry list */ + struct mlxsw_sp_nexthop_group *nh_grp; /* pointer back to the group + * this belongs to + */ + u8 should_offload:1, /* set indicates this neigh is connected and + * should be put to KVD linear area of this group. + */ + 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 + * updated in HW + */ + struct mlxsw_sp_neigh_entry *neigh_entry; +}; + +struct mlxsw_sp_nexthop_group { + struct list_head list; /* node in mlxsw->router.nexthop_group_list */ + struct list_head fib_list; /* list of fib entries that use this group */ + u8 adj_index_valid:1; + u32 adj_index; + u16 ecmp_size; + u16 count; + struct mlxsw_sp_nexthop nexthops[0]; +}; + +static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_vr *vr, + u32 adj_index, u16 ecmp_size, + u32 new_adj_index, + u16 new_ecmp_size) +{ + char raleu_pl[MLXSW_REG_RALEU_LEN]; + + mlxsw_reg_raleu_pack(raleu_pl, vr->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); +} + +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_vr *vr = NULL; + int err; + + list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) { + if (vr == fib_entry->vr) + continue; + vr = fib_entry->vr; + err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, vr, + old_adj_index, + old_ecmp_size, + nh_grp->adj_index, + nh_grp->ecmp_size); + if (err) + return err; + } + return 0; +} + +static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, + struct mlxsw_sp_nexthop *nh) +{ + struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry; + char ratr_pl[MLXSW_REG_RATR_LEN]; + + mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, + true, adj_index, neigh_entry->rif); + mlxsw_reg_ratr_eth_entry_pack(ratr_pl, neigh_entry->ha); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); +} + +static int +mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp) +{ + u32 adj_index = nh_grp->adj_index; /* base */ + struct mlxsw_sp_nexthop *nh; + int i; + int err; + + for (i = 0; i < nh_grp->count; i++) { + nh = &nh_grp->nexthops[i]; + + if (!nh->should_offload) { + nh->offloaded = 0; + continue; + } + + if (nh->update) { + err = mlxsw_sp_nexthop_mac_update(mlxsw_sp, + adj_index, nh); + if (err) + return err; + nh->update = 0; + nh->offloaded = 1; + } + adj_index++; + } + return 0; +} + +static int mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry); + +static int +mlxsw_sp_nexthop_fib_entries_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp) +{ + struct mlxsw_sp_fib_entry *fib_entry; + int err; + + list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) { + err = mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry); + if (err) + return err; + } + return 0; +} + +static void +mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp) +{ + struct mlxsw_sp_nexthop *nh; + bool offload_change = false; + u32 adj_index; + u16 ecmp_size = 0; + bool old_adj_index_valid; + u32 old_adj_index; + u16 old_ecmp_size; + int ret; + int i; + int err; + + for (i = 0; i < nh_grp->count; i++) { + nh = &nh_grp->nexthops[i]; + + if (nh->should_offload ^ nh->offloaded) { + offload_change = true; + if (nh->should_offload) + nh->update = 1; + } + if (nh->should_offload) + ecmp_size++; + } + if (!offload_change) { + /* Nothing was added or removed, so no need to reallocate. Just + * update MAC on existing adjacency indexes. + */ + err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp); + if (err) { + dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n"); + goto set_trap; + } + return; + } + if (!ecmp_size) + /* No neigh of this group is connected so we just set + * the trap and let everthing flow through kernel. + */ + goto set_trap; + + ret = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size); + if (ret < 0) { + /* We ran out of KVD linear space, just set the + * trap and let everything flow through kernel. + */ + dev_warn(mlxsw_sp->bus_info->dev, "Failed to allocate KVD linear area for nexthop group.\n"); + goto set_trap; + } + adj_index = ret; + 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; + err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp); + if (err) { + dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n"); + goto set_trap; + } + + if (!old_adj_index_valid) { + /* The trap was set for fib entries, so we have to call + * fib entry update to unset it and use adjacency index. + */ + err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp); + if (err) { + dev_warn(mlxsw_sp->bus_info->dev, "Failed to add adjacency index to fib entries.\n"); + goto set_trap; + } + return; + } + + err = mlxsw_sp_adj_index_mass_update(mlxsw_sp, nh_grp, + old_adj_index, old_ecmp_size); + mlxsw_sp_kvdl_free(mlxsw_sp, old_adj_index); + if (err) { + dev_warn(mlxsw_sp->bus_info->dev, "Failed to mass-update adjacency index for nexthop group.\n"); + goto set_trap; + } + return; + +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]; + nh->offloaded = 0; + } + err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp); + if (err) + dev_warn(mlxsw_sp->bus_info->dev, "Failed to set traps for fib entries.\n"); + if (old_adj_index_valid) + mlxsw_sp_kvdl_free(mlxsw_sp, nh_grp->adj_index); +} + +static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh, + bool removing) +{ + if (!removing && !nh->should_offload) + nh->should_offload = 1; + else if (removing && nh->offloaded) + nh->should_offload = 0; + nh->update = 1; +} + +static void +mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_neigh_entry *neigh_entry, + bool removing) +{ + struct mlxsw_sp_nexthop *nh; + + /* Take RTNL mutex here to prevent lists from changes */ + rtnl_lock(); + 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); + } + rtnl_unlock(); +} + +static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp, + struct mlxsw_sp_nexthop *nh, + struct fib_nh *fib_nh) +{ + struct mlxsw_sp_neigh_entry *neigh_entry; + u32 gwip = ntohl(fib_nh->nh_gw); + struct net_device *dev = fib_nh->nh_dev; + struct neighbour *n; + u8 nud_state; + + neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &gwip, + sizeof(gwip), dev); + if (!neigh_entry) { + __be32 gwipn = htonl(gwip); + + n = neigh_create(&arp_tbl, &gwipn, dev); + if (IS_ERR(n)) + return PTR_ERR(n); + neigh_event_send(n, NULL); + neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &gwip, + sizeof(gwip), dev); + if (!neigh_entry) { + neigh_release(n); + return -EINVAL; + } + } else { + /* Take a reference of neigh here ensuring that neigh would + * not be detructed before the nexthop entry is finished. + * The second branch takes the reference in neith_create() + */ + n = neigh_entry->n; + neigh_clone(n); + } + + /* If that is the first nexthop connected to that neigh, add to + * nexthop_neighs_list + */ + if (list_empty(&neigh_entry->nexthop_list)) + list_add_tail(&neigh_entry->nexthop_neighs_list_node, + &mlxsw_sp->router.nexthop_neighs_list); + + nh->nh_grp = nh_grp; + nh->neigh_entry = neigh_entry; + list_add_tail(&nh->neigh_list_node, &neigh_entry->nexthop_list); + read_lock_bh(&n->lock); + nud_state = n->nud_state; + read_unlock_bh(&n->lock); + __mlxsw_sp_nexthop_neigh_update(nh, !(nud_state & NUD_VALID)); + + return 0; +} + +static void mlxsw_sp_nexthop_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry; + + list_del(&nh->neigh_list_node); + + /* If that is the last nexthop connected to that neigh, remove from + * nexthop_neighs_list + */ + if (list_empty(&nh->neigh_entry->nexthop_list)) + list_del(&nh->neigh_entry->nexthop_neighs_list_node); + + neigh_release(neigh_entry->n); +} + +static struct mlxsw_sp_nexthop_group * +mlxsw_sp_nexthop_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi) +{ + struct mlxsw_sp_nexthop_group *nh_grp; + struct mlxsw_sp_nexthop *nh; + struct fib_nh *fib_nh; + size_t alloc_size; + int i; + int err; + + alloc_size = sizeof(*nh_grp) + + fi->fib_nhs * sizeof(struct mlxsw_sp_nexthop); + nh_grp = kzalloc(alloc_size, GFP_KERNEL); + if (!nh_grp) + return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&nh_grp->fib_list); + nh_grp->count = fi->fib_nhs; + for (i = 0; i < nh_grp->count; i++) { + nh = &nh_grp->nexthops[i]; + fib_nh = &fi->fib_nh[i]; + err = mlxsw_sp_nexthop_init(mlxsw_sp, nh_grp, nh, fib_nh); + if (err) + goto err_nexthop_init; + } + list_add_tail(&nh_grp->list, &mlxsw_sp->router.nexthop_group_list); + mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); + return nh_grp; + +err_nexthop_init: + for (i--; i >= 0; i--) + mlxsw_sp_nexthop_fini(mlxsw_sp, nh); + kfree(nh_grp); + return ERR_PTR(err); +} + +static void +mlxsw_sp_nexthop_group_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp) +{ + struct mlxsw_sp_nexthop *nh; + int i; + + list_del(&nh_grp->list); + for (i = 0; i < nh_grp->count; i++) { + nh = &nh_grp->nexthops[i]; + mlxsw_sp_nexthop_fini(mlxsw_sp, nh); + } + kfree(nh_grp); +} + +static bool mlxsw_sp_nexthop_match(struct mlxsw_sp_nexthop *nh, + struct fib_info *fi) +{ + int i; + + for (i = 0; i < fi->fib_nhs; i++) { + struct fib_nh *fib_nh = &fi->fib_nh[i]; + u32 gwip = ntohl(fib_nh->nh_gw); + + if (memcmp(nh->neigh_entry->key.addr, + &gwip, sizeof(u32)) == 0 && + nh->neigh_entry->key.dev == fib_nh->nh_dev) + return true; + } + return false; +} + +static bool mlxsw_sp_nexthop_group_match(struct mlxsw_sp_nexthop_group *nh_grp, + struct fib_info *fi) +{ + int i; + + if (nh_grp->count != fi->fib_nhs) + return false; + for (i = 0; i < nh_grp->count; i++) { + struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i]; + + if (!mlxsw_sp_nexthop_match(nh, fi)) + return false; + } + return true; +} + +static struct mlxsw_sp_nexthop_group * +mlxsw_sp_nexthop_group_find(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi) +{ + struct mlxsw_sp_nexthop_group *nh_grp; + + list_for_each_entry(nh_grp, &mlxsw_sp->router.nexthop_group_list, + list) { + if (mlxsw_sp_nexthop_group_match(nh_grp, fi)) + return nh_grp; + } + return NULL; +} + +static int mlxsw_sp_nexthop_group_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + struct fib_info *fi) +{ + struct mlxsw_sp_nexthop_group *nh_grp; + + nh_grp = mlxsw_sp_nexthop_group_find(mlxsw_sp, fi); + if (!nh_grp) { + nh_grp = mlxsw_sp_nexthop_group_create(mlxsw_sp, fi); + if (IS_ERR(nh_grp)) + return PTR_ERR(nh_grp); + } + list_add_tail(&fib_entry->nexthop_group_node, &nh_grp->fib_list); + fib_entry->nh_group = nh_grp; + return 0; +} + +static void mlxsw_sp_nexthop_group_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) +{ + struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group; + + list_del(&fib_entry->nexthop_group_node); + if (!list_empty(&nh_grp->fib_list)) + return; + mlxsw_sp_nexthop_group_destroy(mlxsw_sp, nh_grp); +} + +static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) +{ + char rgcr_pl[MLXSW_REG_RGCR_LEN]; + + mlxsw_reg_rgcr_pack(rgcr_pl, true); + mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, MLXSW_SP_RIF_MAX); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); +} + +static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) +{ + char rgcr_pl[MLXSW_REG_RGCR_LEN]; + + mlxsw_reg_rgcr_pack(rgcr_pl, false); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); +} + +int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) +{ + int err; + + INIT_LIST_HEAD(&mlxsw_sp->router.nexthop_neighs_list); + INIT_LIST_HEAD(&mlxsw_sp->router.nexthop_group_list); + err = __mlxsw_sp_router_init(mlxsw_sp); + if (err) + return err; + mlxsw_sp_lpm_init(mlxsw_sp); + mlxsw_sp_vrs_init(mlxsw_sp); + return mlxsw_sp_neigh_init(mlxsw_sp); +} + +void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) +{ + mlxsw_sp_neigh_fini(mlxsw_sp); + __mlxsw_sp_router_fini(mlxsw_sp); +} + +static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) +{ + char ralue_pl[MLXSW_REG_RALUE_LEN]; + u32 *p_dip = (u32 *) fib_entry->key.addr; + struct mlxsw_sp_vr *vr = fib_entry->vr; + enum mlxsw_reg_ralue_trap_action trap_action; + u16 trap_id = 0; + u32 adjacency_index = 0; + u16 ecmp_size = 0; + + /* In case the nexthop group adjacency index is valid, use it + * with provided ECMP size. Otherwise, setup trap and pass + * traffic to kernel. + */ + if (fib_entry->nh_group->adj_index_valid) { + 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 { + trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP; + trap_id = MLXSW_TRAP_ID_RTR_INGRESS0; + } + + mlxsw_reg_ralue_pack4(ralue_pl, vr->proto, op, vr->id, + fib_entry->key.prefix_len, *p_dip); + 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); +} + +static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) +{ + char ralue_pl[MLXSW_REG_RALUE_LEN]; + u32 *p_dip = (u32 *) fib_entry->key.addr; + struct mlxsw_sp_vr *vr = fib_entry->vr; + + mlxsw_reg_ralue_pack4(ralue_pl, vr->proto, op, vr->id, + fib_entry->key.prefix_len, *p_dip); + mlxsw_reg_ralue_act_local_pack(ralue_pl, + MLXSW_REG_RALUE_TRAP_ACTION_NOP, 0, + fib_entry->rif); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); +} + +static int mlxsw_sp_fib_entry_op4_trap(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) +{ + char ralue_pl[MLXSW_REG_RALUE_LEN]; + u32 *p_dip = (u32 *) fib_entry->key.addr; + struct mlxsw_sp_vr *vr = fib_entry->vr; + + mlxsw_reg_ralue_pack4(ralue_pl, vr->proto, op, vr->id, + fib_entry->key.prefix_len, *p_dip); + mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); +} + +static int mlxsw_sp_fib_entry_op4(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) +{ + switch (fib_entry->type) { + case MLXSW_SP_FIB_ENTRY_TYPE_REMOTE: + return mlxsw_sp_fib_entry_op4_remote(mlxsw_sp, fib_entry, op); + case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL: + return mlxsw_sp_fib_entry_op4_local(mlxsw_sp, fib_entry, op); + case MLXSW_SP_FIB_ENTRY_TYPE_TRAP: + return mlxsw_sp_fib_entry_op4_trap(mlxsw_sp, fib_entry, op); + } + return -EINVAL; +} + +static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) +{ + switch (fib_entry->vr->proto) { + case MLXSW_SP_L3_PROTO_IPV4: + return mlxsw_sp_fib_entry_op4(mlxsw_sp, fib_entry, op); + case MLXSW_SP_L3_PROTO_IPV6: + return -EINVAL; + } + return -EINVAL; +} + +static int mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) +{ + enum mlxsw_reg_ralue_op op; + + op = !fib_entry->added ? MLXSW_REG_RALUE_OP_WRITE_WRITE : + MLXSW_REG_RALUE_OP_WRITE_UPDATE; + return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, op); +} + +static int mlxsw_sp_fib_entry_del(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_DELETE); +} + +struct mlxsw_sp_router_fib4_add_info { + struct switchdev_trans_item tritem; + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_fib_entry *fib_entry; +}; + +static void mlxsw_sp_router_fib4_add_info_destroy(void const *data) +{ + const struct mlxsw_sp_router_fib4_add_info *info = data; + struct mlxsw_sp_fib_entry *fib_entry = info->fib_entry; + struct mlxsw_sp *mlxsw_sp = info->mlxsw_sp; + + mlxsw_sp_fib_entry_destroy(fib_entry); + mlxsw_sp_vr_put(mlxsw_sp, fib_entry->vr); + kfree(info); +} + +static int +mlxsw_sp_router_fib4_entry_init(struct mlxsw_sp *mlxsw_sp, + const struct switchdev_obj_ipv4_fib *fib4, + struct mlxsw_sp_fib_entry *fib_entry) +{ + struct fib_info *fi = fib4->fi; + + if (fib4->type == RTN_LOCAL || fib4->type == RTN_BROADCAST) { + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; + return 0; + } + if (fib4->type != RTN_UNICAST) + return -EINVAL; + + if (fi->fib_scope != RT_SCOPE_UNIVERSE) { + struct mlxsw_sp_rif *r; + + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; + r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fi->fib_dev); + if (!r) + return -EINVAL; + fib_entry->rif = r->rif; + return 0; + } + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; + return mlxsw_sp_nexthop_group_get(mlxsw_sp, fib_entry, fi); +} + +static void +mlxsw_sp_router_fib4_entry_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) +{ + if (fib_entry->type != MLXSW_SP_FIB_ENTRY_TYPE_REMOTE) + return; + mlxsw_sp_nexthop_group_put(mlxsw_sp, fib_entry); +} + +static int +mlxsw_sp_router_fib4_add_prepare(struct mlxsw_sp_port *mlxsw_sp_port, + const struct switchdev_obj_ipv4_fib *fib4, + struct switchdev_trans *trans) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_router_fib4_add_info *info; + struct mlxsw_sp_fib_entry *fib_entry; + struct mlxsw_sp_vr *vr; + int err; + + vr = mlxsw_sp_vr_get(mlxsw_sp, fib4->dst_len, fib4->tb_id, + MLXSW_SP_L3_PROTO_IPV4); + if (IS_ERR(vr)) + return PTR_ERR(vr); + + fib_entry = mlxsw_sp_fib_entry_create(vr->fib, &fib4->dst, + sizeof(fib4->dst), fib4->dst_len); + if (!fib_entry) { + err = -ENOMEM; + goto err_fib_entry_create; + } + fib_entry->vr = vr; + + err = mlxsw_sp_router_fib4_entry_init(mlxsw_sp, fib4, fib_entry); + if (err) + goto err_fib4_entry_init; + + info = kmalloc(sizeof(*info), GFP_KERNEL); + if (!info) { + err = -ENOMEM; + goto err_alloc_info; + } + info->mlxsw_sp = mlxsw_sp; + info->fib_entry = fib_entry; + switchdev_trans_item_enqueue(trans, info, + mlxsw_sp_router_fib4_add_info_destroy, + &info->tritem); + return 0; + +err_alloc_info: + mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry); +err_fib4_entry_init: + mlxsw_sp_fib_entry_destroy(fib_entry); +err_fib_entry_create: + mlxsw_sp_vr_put(mlxsw_sp, vr); + return err; +} + +static int +mlxsw_sp_router_fib4_add_commit(struct mlxsw_sp_port *mlxsw_sp_port, + const struct switchdev_obj_ipv4_fib *fib4, + struct switchdev_trans *trans) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_router_fib4_add_info *info; + struct mlxsw_sp_fib_entry *fib_entry; + struct mlxsw_sp_vr *vr; + int err; + + info = switchdev_trans_item_dequeue(trans); + fib_entry = info->fib_entry; + kfree(info); + + vr = fib_entry->vr; + err = mlxsw_sp_fib_entry_insert(fib_entry->vr->fib, fib_entry); + if (err) + goto err_fib_entry_insert; + err = mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry); + if (err) + goto err_fib_entry_add; + return 0; + +err_fib_entry_add: + mlxsw_sp_fib_entry_remove(vr->fib, fib_entry); +err_fib_entry_insert: + mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry); + mlxsw_sp_fib_entry_destroy(fib_entry); + mlxsw_sp_vr_put(mlxsw_sp, vr); + return err; +} + +int mlxsw_sp_router_fib4_add(struct mlxsw_sp_port *mlxsw_sp_port, + const struct switchdev_obj_ipv4_fib *fib4, + struct switchdev_trans *trans) +{ + if (switchdev_trans_ph_prepare(trans)) + return mlxsw_sp_router_fib4_add_prepare(mlxsw_sp_port, + fib4, trans); + return mlxsw_sp_router_fib4_add_commit(mlxsw_sp_port, + fib4, trans); +} + +int mlxsw_sp_router_fib4_del(struct mlxsw_sp_port *mlxsw_sp_port, + const struct switchdev_obj_ipv4_fib *fib4) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_fib_entry *fib_entry; + struct mlxsw_sp_vr *vr; + + vr = mlxsw_sp_vr_find(mlxsw_sp, fib4->tb_id, MLXSW_SP_L3_PROTO_IPV4); + if (!vr) { + dev_warn(mlxsw_sp->bus_info->dev, "Failed to find virtual router for FIB4 entry being removed.\n"); + return -ENOENT; + } + fib_entry = mlxsw_sp_fib_entry_lookup(vr->fib, &fib4->dst, + sizeof(fib4->dst), fib4->dst_len); + if (!fib_entry) { + dev_warn(mlxsw_sp->bus_info->dev, "Failed to find FIB4 entry being removed.\n"); + return -ENOENT; + } + mlxsw_sp_fib_entry_del(mlxsw_sp_port->mlxsw_sp, fib_entry); + mlxsw_sp_fib_entry_remove(vr->fib, fib_entry); + mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry); + mlxsw_sp_fib_entry_destroy(fib_entry); + mlxsw_sp_vr_put(mlxsw_sp, vr); + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 3710f19ed6bb..a1ad5e6bdfa8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -55,13 +55,10 @@ static u16 mlxsw_sp_port_vid_to_fid_get(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) { + struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_port); u16 fid = vid; - if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) { - u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_port); - - fid = mlxsw_sp_vfid_to_fid(vfid); - } + fid = f ? f->fid : fid; if (!fid) fid = mlxsw_sp_port->pvid; @@ -169,11 +166,6 @@ static int mlxsw_sp_port_attr_stp_state_set(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_sp_port_stp_state_set(mlxsw_sp_port, state); } -static bool mlxsw_sp_vfid_is_vport_br(u16 vfid) -{ - return vfid >= MLXSW_SP_VFID_PORT_MAX; -} - static int __mlxsw_sp_port_flood_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 idx_begin, u16 idx_end, bool set, bool only_uc) @@ -185,15 +177,10 @@ static int __mlxsw_sp_port_flood_set(struct mlxsw_sp_port *mlxsw_sp_port, char *sftr_pl; int err; - if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) { + if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) table_type = MLXSW_REG_SFGC_TABLE_TYPE_FID; - if (mlxsw_sp_vfid_is_vport_br(idx_begin)) - local_port = mlxsw_sp_port->local_port; - else - local_port = MLXSW_PORT_CPU_PORT; - } else { + else table_type = MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST; - } sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); if (!sftr_pl) @@ -236,7 +223,8 @@ static int mlxsw_sp_port_uc_flood_set(struct mlxsw_sp_port *mlxsw_sp_port, int err; if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) { - u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_port); + u16 fid = mlxsw_sp_vport_fid_get(mlxsw_sp_port)->fid; + u16 vfid = mlxsw_sp_fid_to_vfid(fid); return __mlxsw_sp_port_flood_set(mlxsw_sp_port, vfid, vfid, set, true); @@ -260,14 +248,17 @@ err_port_flood_set: return err; } -int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid, - bool set, bool only_uc) +int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 fid, + bool set) { + u16 vfid; + /* In case of vFIDs, index into the flooding table is relative to * the start of the vFIDs range. */ + vfid = mlxsw_sp_fid_to_vfid(fid); return __mlxsw_sp_port_flood_set(mlxsw_sp_vport, vfid, vfid, set, - only_uc); + false); } static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port, @@ -383,6 +374,187 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev, return err; } +static int mlxsw_sp_fid_op(struct mlxsw_sp *mlxsw_sp, u16 fid, bool create) +{ + char sfmr_pl[MLXSW_REG_SFMR_LEN]; + + mlxsw_reg_sfmr_pack(sfmr_pl, !create, fid, fid); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl); +} + +static int mlxsw_sp_fid_map(struct mlxsw_sp *mlxsw_sp, u16 fid, bool valid) +{ + enum mlxsw_reg_svfa_mt mt = MLXSW_REG_SVFA_MT_VID_TO_FID; + char svfa_pl[MLXSW_REG_SVFA_LEN]; + + mlxsw_reg_svfa_pack(svfa_pl, 0, mt, valid, fid, fid); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(svfa), svfa_pl); +} + +static struct mlxsw_sp_fid *mlxsw_sp_fid_alloc(u16 fid) +{ + struct mlxsw_sp_fid *f; + + f = kzalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + f->fid = fid; + + return f; +} + +struct mlxsw_sp_fid *mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid) +{ + struct mlxsw_sp_fid *f; + int err; + + err = mlxsw_sp_fid_op(mlxsw_sp, fid, true); + if (err) + return ERR_PTR(err); + + /* Although all the ports member in the FID might be using a + * {Port, VID} to FID mapping, we create a global VID-to-FID + * mapping. This allows a port to transition to VLAN mode, + * knowing the global mapping exists. + */ + err = mlxsw_sp_fid_map(mlxsw_sp, fid, true); + if (err) + goto err_fid_map; + + f = mlxsw_sp_fid_alloc(fid); + if (!f) { + err = -ENOMEM; + goto err_allocate_fid; + } + + list_add(&f->list, &mlxsw_sp->fids); + + return f; + +err_allocate_fid: + mlxsw_sp_fid_map(mlxsw_sp, fid, false); +err_fid_map: + mlxsw_sp_fid_op(mlxsw_sp, fid, false); + return ERR_PTR(err); +} + +void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f) +{ + u16 fid = f->fid; + + list_del(&f->list); + + if (f->r) + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); + + kfree(f); + + mlxsw_sp_fid_op(mlxsw_sp, fid, false); +} + +static int __mlxsw_sp_port_fid_join(struct mlxsw_sp_port *mlxsw_sp_port, + u16 fid) +{ + struct mlxsw_sp_fid *f; + + f = mlxsw_sp_fid_find(mlxsw_sp_port->mlxsw_sp, fid); + if (!f) { + f = mlxsw_sp_fid_create(mlxsw_sp_port->mlxsw_sp, fid); + if (IS_ERR(f)) + return PTR_ERR(f); + } + + f->ref_count++; + + netdev_dbg(mlxsw_sp_port->dev, "Joined FID=%d\n", fid); + + return 0; +} + +static void __mlxsw_sp_port_fid_leave(struct mlxsw_sp_port *mlxsw_sp_port, + u16 fid) +{ + struct mlxsw_sp_fid *f; + + f = mlxsw_sp_fid_find(mlxsw_sp_port->mlxsw_sp, fid); + if (WARN_ON(!f)) + return; + + netdev_dbg(mlxsw_sp_port->dev, "Left FID=%d\n", fid); + + mlxsw_sp_port_fdb_flush(mlxsw_sp_port, fid); + + if (--f->ref_count == 0) + mlxsw_sp_fid_destroy(mlxsw_sp_port->mlxsw_sp, f); +} + +static int mlxsw_sp_port_fid_map(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid, + bool valid) +{ + enum mlxsw_reg_svfa_mt mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID; + + /* If port doesn't have vPorts, then it can use the global + * VID-to-FID mapping. + */ + if (list_empty(&mlxsw_sp_port->vports_list)) + return 0; + + return mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt, valid, fid, fid); +} + +static int mlxsw_sp_port_fid_join(struct mlxsw_sp_port *mlxsw_sp_port, + u16 fid_begin, u16 fid_end) +{ + int fid, err; + + for (fid = fid_begin; fid <= fid_end; fid++) { + err = __mlxsw_sp_port_fid_join(mlxsw_sp_port, fid); + if (err) + goto err_port_fid_join; + } + + err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, fid_begin, fid_end, + true, false); + if (err) + goto err_port_flood_set; + + for (fid = fid_begin; fid <= fid_end; fid++) { + err = mlxsw_sp_port_fid_map(mlxsw_sp_port, fid, true); + if (err) + goto err_port_fid_map; + } + + return 0; + +err_port_fid_map: + for (fid--; fid >= fid_begin; fid--) + mlxsw_sp_port_fid_map(mlxsw_sp_port, fid, false); + __mlxsw_sp_port_flood_set(mlxsw_sp_port, fid_begin, fid_end, false, + false); +err_port_flood_set: + fid = fid_end; +err_port_fid_join: + for (fid--; fid >= fid_begin; fid--) + __mlxsw_sp_port_fid_leave(mlxsw_sp_port, fid); + return err; +} + +static void mlxsw_sp_port_fid_leave(struct mlxsw_sp_port *mlxsw_sp_port, + u16 fid_begin, u16 fid_end) +{ + int fid; + + for (fid = fid_begin; fid <= fid_end; fid++) + mlxsw_sp_port_fid_map(mlxsw_sp_port, fid, false); + + __mlxsw_sp_port_flood_set(mlxsw_sp_port, fid_begin, fid_end, false, + false); + + for (fid = fid_begin; fid <= fid_end; fid++) + __mlxsw_sp_port_fid_leave(mlxsw_sp_port, fid); +} + static int __mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) { @@ -440,74 +612,6 @@ err_port_allow_untagged_set: return err; } -static int mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid) -{ - char sfmr_pl[MLXSW_REG_SFMR_LEN]; - int err; - - mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_CREATE_FID, fid, fid); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl); - - if (err) - return err; - - set_bit(fid, mlxsw_sp->active_fids); - return 0; -} - -static void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, u16 fid) -{ - char sfmr_pl[MLXSW_REG_SFMR_LEN]; - - clear_bit(fid, mlxsw_sp->active_fids); - - mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_DESTROY_FID, - fid, fid); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl); -} - -static int mlxsw_sp_port_fid_map(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid) -{ - enum mlxsw_reg_svfa_mt mt; - - if (!list_empty(&mlxsw_sp_port->vports_list)) - mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID; - else - mt = MLXSW_REG_SVFA_MT_VID_TO_FID; - - return mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt, true, fid, fid); -} - -static int mlxsw_sp_port_fid_unmap(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid) -{ - enum mlxsw_reg_svfa_mt mt; - - if (list_empty(&mlxsw_sp_port->vports_list)) - return 0; - - mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID; - return mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt, false, fid, fid); -} - -static int mlxsw_sp_port_add_vids(struct net_device *dev, u16 vid_begin, - u16 vid_end) -{ - u16 vid; - int err; - - for (vid = vid_begin; vid <= vid_end; vid++) { - err = mlxsw_sp_port_add_vid(dev, 0, vid); - if (err) - goto err_port_add_vid; - } - return 0; - -err_port_add_vid: - for (vid--; vid >= vid_begin; vid--) - mlxsw_sp_port_kill_vid(dev, 0, vid); - return err; -} - static int __mlxsw_sp_port_vlans_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin, u16 vid_end, bool is_member, bool untagged) @@ -533,57 +637,17 @@ static int __mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin, u16 vid_end, bool flag_untagged, bool flag_pvid) { - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct net_device *dev = mlxsw_sp_port->dev; - u16 vid, last_visited_vid, old_pvid; - enum mlxsw_reg_svfa_mt mt; + u16 vid, old_pvid; int err; - /* In case this is invoked with BRIDGE_FLAGS_SELF and port is - * not bridged, then packets ingressing through the port with - * the specified VIDs will be directed to CPU. - */ if (!mlxsw_sp_port->bridged) - return mlxsw_sp_port_add_vids(dev, vid_begin, vid_end); - - for (vid = vid_begin; vid <= vid_end; vid++) { - if (!test_bit(vid, mlxsw_sp->active_fids)) { - err = mlxsw_sp_fid_create(mlxsw_sp, vid); - if (err) { - netdev_err(dev, "Failed to create FID=%d\n", - vid); - return err; - } - - /* When creating a FID, we set a VID to FID mapping - * regardless of the port's mode. - */ - mt = MLXSW_REG_SVFA_MT_VID_TO_FID; - err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt, - true, vid, vid); - if (err) { - netdev_err(dev, "Failed to create FID=VID=%d mapping\n", - vid); - goto err_port_vid_to_fid_set; - } - } - } - - /* Set FID mapping according to port's mode */ - for (vid = vid_begin; vid <= vid_end; vid++) { - err = mlxsw_sp_port_fid_map(mlxsw_sp_port, vid); - if (err) { - netdev_err(dev, "Failed to map FID=%d", vid); - last_visited_vid = --vid; - goto err_port_fid_map; - } - } + return -EINVAL; - err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, vid_begin, vid_end, - true, false); + err = mlxsw_sp_port_fid_join(mlxsw_sp_port, vid_begin, vid_end); if (err) { - netdev_err(dev, "Failed to configure flooding\n"); - goto err_port_flood_set; + netdev_err(dev, "Failed to join FIDs\n"); + return err; } err = __mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end, @@ -628,10 +692,6 @@ static int __mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port, return 0; -err_port_vid_to_fid_set: - mlxsw_sp_fid_destroy(mlxsw_sp, vid); - return err; - err_port_stp_state_set: for (vid = vid_begin; vid <= vid_end; vid++) clear_bit(vid, mlxsw_sp_port->active_vlans); @@ -641,13 +701,7 @@ err_port_pvid_set: __mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end, false, false); err_port_vlans_set: - __mlxsw_sp_port_flood_set(mlxsw_sp_port, vid_begin, vid_end, false, - false); -err_port_flood_set: - last_visited_vid = vid_end; -err_port_fid_map: - for (vid = last_visited_vid; vid >= vid_begin; vid--) - mlxsw_sp_port_fid_unmap(mlxsw_sp_port, vid); + mlxsw_sp_port_fid_leave(mlxsw_sp_port, vid_begin, vid_end); return err; } @@ -678,9 +732,10 @@ static enum mlxsw_reg_sfd_op mlxsw_sp_sfd_op(bool adding) MLXSW_REG_SFD_OP_WRITE_REMOVE; } -static int mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port, - const char *mac, u16 fid, bool adding, - bool dynamic) +static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port, + const char *mac, u16 fid, bool adding, + enum mlxsw_reg_sfd_rec_action action, + bool dynamic) { char *sfd_pl; int err; @@ -691,14 +746,29 @@ static int mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port, mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0); mlxsw_reg_sfd_uc_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic), - mac, fid, MLXSW_REG_SFD_REC_ACTION_NOP, - local_port); + mac, fid, action, local_port); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl); kfree(sfd_pl); return err; } +static int mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port, + const char *mac, u16 fid, bool adding, + bool dynamic) +{ + return __mlxsw_sp_port_fdb_uc_op(mlxsw_sp, local_port, mac, fid, adding, + MLXSW_REG_SFD_REC_ACTION_NOP, dynamic); +} + +int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid, + bool adding) +{ + return __mlxsw_sp_port_fdb_uc_op(mlxsw_sp, 0, mac, fid, adding, + MLXSW_REG_SFD_REC_ACTION_FORWARD_IP_ROUTER, + false); +} + static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id, const char *mac, u16 fid, u16 lag_vid, bool adding, bool dynamic) @@ -903,6 +973,11 @@ static int mlxsw_sp_port_obj_add(struct net_device *dev, SWITCHDEV_OBJ_PORT_VLAN(obj), trans); break; + case SWITCHDEV_OBJ_ID_IPV4_FIB: + err = mlxsw_sp_router_fib4_add(mlxsw_sp_port, + SWITCHDEV_OBJ_IPV4_FIB(obj), + trans); + break; case SWITCHDEV_OBJ_ID_PORT_FDB: err = mlxsw_sp_port_fdb_static_add(mlxsw_sp_port, SWITCHDEV_OBJ_PORT_FDB(obj), @@ -921,21 +996,6 @@ static int mlxsw_sp_port_obj_add(struct net_device *dev, return err; } -static int mlxsw_sp_port_kill_vids(struct net_device *dev, u16 vid_begin, - u16 vid_end) -{ - u16 vid; - int err; - - for (vid = vid_begin; vid <= vid_end; vid++) { - err = mlxsw_sp_port_kill_vid(dev, 0, vid); - if (err) - return err; - } - - return 0; -} - static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin, u16 vid_end, bool init) { @@ -943,12 +1003,8 @@ static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, pvid; int err; - /* In case this is invoked with BRIDGE_FLAGS_SELF and port is - * not bridged, then prevent packets ingressing through the - * port with the specified VIDs from being trapped to CPU. - */ if (!init && !mlxsw_sp_port->bridged) - return mlxsw_sp_port_kill_vids(dev, vid_begin, vid_end); + return -EINVAL; err = __mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end, false, false); @@ -970,21 +1026,7 @@ static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, } } - err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, vid_begin, vid_end, - false, false); - if (err) { - netdev_err(dev, "Failed to clear flooding\n"); - return err; - } - - for (vid = vid_begin; vid <= vid_end; vid++) { - /* Remove FID mapping in case of Virtual mode */ - err = mlxsw_sp_port_fid_unmap(mlxsw_sp_port, vid); - if (err) { - netdev_err(dev, "Failed to unmap FID=%d", vid); - return err; - } - } + mlxsw_sp_port_fid_leave(mlxsw_sp_port, vid_begin, vid_end); out: /* Changing activity bits only if HW operation succeded */ @@ -1081,6 +1123,10 @@ static int mlxsw_sp_port_obj_del(struct net_device *dev, err = mlxsw_sp_port_vlans_del(mlxsw_sp_port, SWITCHDEV_OBJ_PORT_VLAN(obj)); break; + case SWITCHDEV_OBJ_ID_IPV4_FIB: + err = mlxsw_sp_router_fib4_del(mlxsw_sp_port, + SWITCHDEV_OBJ_IPV4_FIB(obj)); + break; case SWITCHDEV_OBJ_ID_PORT_FDB: err = mlxsw_sp_port_fdb_static_del(mlxsw_sp_port, SWITCHDEV_OBJ_PORT_FDB(obj)); @@ -1118,7 +1164,8 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_port *tmp; - u16 vport_fid = 0; + struct mlxsw_sp_fid *f; + u16 vport_fid; char *sfd_pl; char mac[ETH_ALEN]; u16 fid; @@ -1133,12 +1180,8 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, if (!sfd_pl) return -ENOMEM; - if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) { - u16 tmp; - - tmp = mlxsw_sp_vport_vfid_get(mlxsw_sp_port); - vport_fid = mlxsw_sp_vfid_to_fid(tmp); - } + f = mlxsw_sp_vport_fid_get(mlxsw_sp_port); + vport_fid = f ? f->fid : 0; mlxsw_reg_sfd_pack(sfd_pl, MLXSW_REG_SFD_OP_QUERY_DUMP, 0); do { @@ -1310,11 +1353,10 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, } if (mlxsw_sp_fid_is_vfid(fid)) { - u16 vfid = mlxsw_sp_fid_to_vfid(fid); struct mlxsw_sp_port *mlxsw_sp_vport; - mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_vfid(mlxsw_sp_port, - vfid); + mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_fid(mlxsw_sp_port, + fid); if (!mlxsw_sp_vport) { netdev_err(mlxsw_sp_port->dev, "Failed to find a matching vPort following FDB notification\n"); goto just_remove; @@ -1370,11 +1412,10 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp, } if (mlxsw_sp_fid_is_vfid(fid)) { - u16 vfid = mlxsw_sp_fid_to_vfid(fid); struct mlxsw_sp_port *mlxsw_sp_vport; - mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_vfid(mlxsw_sp_port, - vfid); + mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_fid(mlxsw_sp_port, + fid); if (!mlxsw_sp_vport) { netdev_err(mlxsw_sp_port->dev, "Failed to find a matching vPort following FDB notification\n"); goto just_remove; @@ -1495,14 +1536,6 @@ static void mlxsw_sp_fdb_fini(struct mlxsw_sp *mlxsw_sp) cancel_delayed_work_sync(&mlxsw_sp->fdb_notify.dw); } -static void mlxsw_sp_fids_fini(struct mlxsw_sp *mlxsw_sp) -{ - u16 fid; - - for_each_set_bit(fid, mlxsw_sp->active_fids, VLAN_N_VID) - mlxsw_sp_fid_destroy(mlxsw_sp, fid); -} - int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp) { return mlxsw_sp_fdb_init(mlxsw_sp); @@ -1511,7 +1544,6 @@ int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp) void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp) { mlxsw_sp_fdb_fini(mlxsw_sp); - mlxsw_sp_fids_fini(mlxsw_sp); } int mlxsw_sp_port_vlan_init(struct mlxsw_sp_port *mlxsw_sp_port) diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 25f658b3849a..377daa4d509c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -1541,6 +1541,7 @@ static struct mlxsw_config_profile mlxsw_sx_config_profile = { .type = MLXSW_PORT_SWID_TYPE_ETH, } }, + .resource_query_enable = 0, }; static struct mlxsw_driver mlxsw_sx_driver = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 53a9550be75e..470d7696e9fe 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -54,6 +54,11 @@ enum { MLXSW_TRAP_ID_IGMP_V2_REPORT = 0x32, MLXSW_TRAP_ID_IGMP_V2_LEAVE = 0x33, MLXSW_TRAP_ID_IGMP_V3_REPORT = 0x34, + MLXSW_TRAP_ID_ARPBC = 0x50, + MLXSW_TRAP_ID_ARPUC = 0x51, + MLXSW_TRAP_ID_IP2ME = 0x5F, + MLXSW_TRAP_ID_RTR_INGRESS0 = 0x70, + MLXSW_TRAP_ID_HOST_MISS_IPV4 = 0x90, MLXSW_TRAP_ID_MAX = 0x1FF }; |