diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ice')
68 files changed, 3861 insertions, 2212 deletions
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 3307d551f431..9e0d9f710441 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -32,7 +32,8 @@ ice-y := ice_main.o \ ice_parser_rt.o \ ice_idc.o \ devlink/devlink.o \ - devlink/devlink_port.o \ + devlink/health.o \ + devlink/port.o \ ice_sf_eth.o \ ice_sf_vsi_vlan_ops.o \ ice_ddp.o \ diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index 415445cefdb2..4af60e2f37df 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -6,7 +6,7 @@ #include "ice.h" #include "ice_lib.h" #include "devlink.h" -#include "devlink_port.h" +#include "port.h" #include "ice_eswitch.h" #include "ice_fw_update.h" #include "ice_dcb_lib.h" @@ -368,14 +368,18 @@ static int ice_devlink_info_get(struct devlink *devlink, } break; case ICE_VERSION_RUNNING: - err = devlink_info_version_running_put(req, key, ctx->buf); + err = devlink_info_version_running_put_ext(req, key, + ctx->buf, + DEVLINK_INFO_VERSION_TYPE_COMPONENT); if (err) { NL_SET_ERR_MSG_MOD(extack, "Unable to set running version"); goto out_free_ctx; } break; case ICE_VERSION_STORED: - err = devlink_info_version_stored_put(req, key, ctx->buf); + err = devlink_info_version_stored_put_ext(req, key, + ctx->buf, + DEVLINK_INFO_VERSION_TYPE_COMPONENT); if (err) { NL_SET_ERR_MSG_MOD(extack, "Unable to set stored version"); goto out_free_ctx; @@ -977,6 +981,9 @@ static int ice_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv /* preallocate memory for ice_sched_node */ node = devm_kzalloc(ice_hw_to_dev(pi->hw), sizeof(*node), GFP_KERNEL); + if (!node) + return -ENOMEM; + *priv = node; return 0; @@ -1198,6 +1205,25 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate, return status; } +static void ice_set_min_max_msix(struct ice_pf *pf) +{ + struct devlink *devlink = priv_to_devlink(pf); + union devlink_param_value val; + int err; + + err = devl_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, + &val); + if (!err) + pf->msix.min = val.vu32; + + err = devl_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, + &val); + if (!err) + pf->msix.max = val.vu32; +} + /** * ice_devlink_reinit_up - do reinit of the given PF * @pf: pointer to the PF struct @@ -1207,9 +1233,18 @@ static int ice_devlink_reinit_up(struct ice_pf *pf) struct ice_vsi *vsi = ice_get_main_vsi(pf); int err; + err = ice_init_hw(&pf->hw); + if (err) { + dev_err(ice_pf_to_dev(pf), "ice_init_hw failed: %d\n", err); + return err; + } + + /* load MSI-X values */ + ice_set_min_max_msix(pf); + err = ice_init_dev(pf); if (err) - return err; + goto unroll_hw_init; vsi->flags = ICE_VSI_FLAG_INIT; @@ -1232,6 +1267,8 @@ err_load: rtnl_unlock(); err_vsi_cfg: ice_deinit_dev(pf); +unroll_hw_init: + ice_deinit_hw(&pf->hw); return err; } @@ -1302,8 +1339,13 @@ ice_devlink_enable_roce_get(struct devlink *devlink, u32 id, struct devlink_param_gset_ctx *ctx) { struct ice_pf *pf = devlink_priv(devlink); + struct iidc_rdma_core_dev_info *cdev; + + cdev = pf->cdev_info; + if (!cdev) + return -ENODEV; - ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ? true : false; + ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2); return 0; } @@ -1313,19 +1355,24 @@ static int ice_devlink_enable_roce_set(struct devlink *devlink, u32 id, struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); + struct iidc_rdma_core_dev_info *cdev; bool roce_ena = ctx->val.vbool; int ret; + cdev = pf->cdev_info; + if (!cdev) + return -ENODEV; + if (!roce_ena) { ice_unplug_aux_dev(pf); - pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2; + cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_ROCEV2; return 0; } - pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2; + cdev->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2; ret = ice_plug_aux_dev(pf); if (ret) - pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2; + cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_ROCEV2; return ret; } @@ -1336,11 +1383,16 @@ ice_devlink_enable_roce_validate(struct devlink *devlink, u32 id, struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); + struct iidc_rdma_core_dev_info *cdev; + + cdev = pf->cdev_info; + if (!cdev) + return -ENODEV; if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) return -EOPNOTSUPP; - if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP) { + if (cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP) { NL_SET_ERR_MSG_MOD(extack, "iWARP is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously"); return -EOPNOTSUPP; } @@ -1353,8 +1405,13 @@ ice_devlink_enable_iw_get(struct devlink *devlink, u32 id, struct devlink_param_gset_ctx *ctx) { struct ice_pf *pf = devlink_priv(devlink); + struct iidc_rdma_core_dev_info *cdev; - ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP; + cdev = pf->cdev_info; + if (!cdev) + return -ENODEV; + + ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP); return 0; } @@ -1364,19 +1421,24 @@ static int ice_devlink_enable_iw_set(struct devlink *devlink, u32 id, struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); + struct iidc_rdma_core_dev_info *cdev; bool iw_ena = ctx->val.vbool; int ret; + cdev = pf->cdev_info; + if (!cdev) + return -ENODEV; + if (!iw_ena) { ice_unplug_aux_dev(pf); - pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP; + cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_IWARP; return 0; } - pf->rdma_mode |= IIDC_RDMA_PROTOCOL_IWARP; + cdev->rdma_protocol |= IIDC_RDMA_PROTOCOL_IWARP; ret = ice_plug_aux_dev(pf); if (ret) - pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP; + cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_IWARP; return ret; } @@ -1391,7 +1453,7 @@ ice_devlink_enable_iw_validate(struct devlink *devlink, u32 id, if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) return -EOPNOTSUPP; - if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2) { + if (pf->cdev_info->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2) { NL_SET_ERR_MSG_MOD(extack, "RoCEv2 is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously"); return -EOPNOTSUPP; } @@ -1518,6 +1580,43 @@ static int ice_devlink_local_fwd_validate(struct devlink *devlink, u32 id, return 0; } +static int +ice_devlink_msix_max_pf_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + + if (val.vu32 > pf->hw.func_caps.common_cap.num_msix_vectors) + return -EINVAL; + + return 0; +} + +static int +ice_devlink_msix_min_pf_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + if (val.vu32 < ICE_MIN_MSIX) + return -EINVAL; + + return 0; +} + +static int ice_devlink_enable_rdma_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + bool new_state = val.vbool; + + if (new_state && !test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + return -EOPNOTSUPP; + + return 0; +} + enum ice_param_id { ICE_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS, @@ -1533,6 +1632,17 @@ static const struct devlink_param ice_dvl_rdma_params[] = { ice_devlink_enable_iw_get, ice_devlink_enable_iw_set, ice_devlink_enable_iw_validate), + DEVLINK_PARAM_GENERIC(ENABLE_RDMA, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, ice_devlink_enable_rdma_validate), +}; + +static const struct devlink_param ice_dvl_msix_params[] = { + DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MAX, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, ice_devlink_msix_max_pf_validate), + DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MIN, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, ice_devlink_msix_min_pf_validate), }; static const struct devlink_param ice_dvl_sched_params[] = { @@ -1636,6 +1746,7 @@ void ice_devlink_unregister(struct ice_pf *pf) int ice_devlink_register_params(struct ice_pf *pf) { struct devlink *devlink = priv_to_devlink(pf); + union devlink_param_value value; struct ice_hw *hw = &pf->hw; int status; @@ -1644,10 +1755,39 @@ int ice_devlink_register_params(struct ice_pf *pf) if (status) return status; + status = devl_params_register(devlink, ice_dvl_msix_params, + ARRAY_SIZE(ice_dvl_msix_params)); + if (status) + goto unregister_rdma_params; + if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) status = devl_params_register(devlink, ice_dvl_sched_params, ARRAY_SIZE(ice_dvl_sched_params)); + if (status) + goto unregister_msix_params; + + value.vu32 = pf->msix.max; + devl_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, + value); + value.vu32 = pf->msix.min; + devl_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, + value); + + value.vbool = test_bit(ICE_FLAG_RDMA_ENA, pf->flags); + devl_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, + value); + return 0; + +unregister_msix_params: + devl_params_unregister(devlink, ice_dvl_msix_params, + ARRAY_SIZE(ice_dvl_msix_params)); +unregister_rdma_params: + devl_params_unregister(devlink, ice_dvl_rdma_params, + ARRAY_SIZE(ice_dvl_rdma_params)); return status; } @@ -1658,6 +1798,8 @@ void ice_devlink_unregister_params(struct ice_pf *pf) devl_params_unregister(devlink, ice_dvl_rdma_params, ARRAY_SIZE(ice_dvl_rdma_params)); + devl_params_unregister(devlink, ice_dvl_msix_params, + ARRAY_SIZE(ice_dvl_msix_params)); if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) devl_params_unregister(devlink, ice_dvl_sched_params, diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c new file mode 100644 index 000000000000..19c3d37aa768 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/devlink/health.c @@ -0,0 +1,550 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024, Intel Corporation. */ + +#include "ice.h" +#include "ice_adminq_cmd.h" /* for enum ice_aqc_health_status_elem */ +#include "health.h" + +#define ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, obj, name) \ + devlink_fmsg_put(fmsg, #name, (obj)->name) + +#define ICE_HEALTH_STATUS_DATA_SIZE 2 + +struct ice_health_status { + enum ice_aqc_health_status code; + const char *description; + const char *solution; + const char *data_label[ICE_HEALTH_STATUS_DATA_SIZE]; +}; + +/* + * In addition to the health status codes provided below, the firmware might + * generate Health Status Codes that are not pertinent to the end-user. + * For instance, Health Code 0x1002 is triggered when the command fails. + * Such codes should be disregarded by the end-user. + * The below lookup requires to be sorted by code. + */ + +static const char ice_common_port_solutions[] = + "Check your cable connection. Change or replace the module or cable. Manually set speed and duplex."; +static const char ice_port_number_label[] = "Port Number"; +static const char ice_update_nvm_solution[] = "Update to the latest NVM image."; + +static const struct ice_health_status ice_health_status_lookup[] = { + {ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT, "An unsupported module was detected.", + ice_common_port_solutions, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE, "Module type is not supported.", + "Change or replace the module or cable.", {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL, "Module is not qualified.", + ice_common_port_solutions, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM, + "Device cannot communicate with the module.", + "Check your cable connection. Change or replace the module or cable. Manually set speed and duplex.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT, "Unresolved module conflict.", + "Manually set speed/duplex or change the port option. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT, "Module is not present.", + "Check that the module is inserted correctly. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED, "Underutilized module.", + "Change or replace the module or cable. Change the port option.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT, "An unsupported module was detected.", + ice_common_port_solutions, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG, "Invalid link configuration.", + NULL, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS, "Port hardware access error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE, "A port is unreachable.", + "Change the port option. Update to the latest NVM image."}, + {ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED, "Port speed is limited due to module.", + "Change the module or configure the port option to match the current module speed. Change the port option.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT, + "All configured link modes were attempted but failed to establish link. The device will restart the process to establish link.", + "Check link partner connection and configuration.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED, + "Port speed is limited by PHY capabilities.", + "Change the module to align to port option.", {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO, "LOM topology netlist is corrupted.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_NETLIST, "Unrecoverable netlist error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT, "Port topology conflict.", + "Change the port option. Update to the latest NVM image."}, + {ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS, "Unrecoverable hardware access error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME, "Unrecoverable runtime error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT, "Link management engine failed to initialize.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD, + "Failed to load the firmware image in the external PHY.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_INFO_RECOVERY, "The device is in firmware recovery mode.", + ice_update_nvm_solution, {"Extended Error"}}, + {ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS, "The flash chip cannot be accessed.", + "If issue persists, call customer support.", {"Access Type"}}, + {ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH, "NVM authentication failed.", + ice_update_nvm_solution}, + {ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH, "Option ROM authentication failed.", + ice_update_nvm_solution}, + {ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH, "DDP package authentication failed.", + "Update to latest base driver and DDP package."}, + {ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT, "NVM image is incompatible.", + ice_update_nvm_solution}, + {ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT, "Option ROM is incompatible.", + ice_update_nvm_solution, {"Expected PCI Device ID", "Expected Module ID"}}, + {ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB, + "Supplied MIB file is invalid. DCB reverted to default configuration.", + "Disable FW-LLDP and check DCBx system configuration.", + {ice_port_number_label, "MIB ID"}}, +}; + +static int ice_health_status_lookup_compare(const void *a, const void *b) +{ + return ((struct ice_health_status *)a)->code - ((struct ice_health_status *)b)->code; +} + +static const struct ice_health_status *ice_get_health_status(u16 code) +{ + struct ice_health_status key = { .code = code }; + + return bsearch(&key, ice_health_status_lookup, ARRAY_SIZE(ice_health_status_lookup), + sizeof(struct ice_health_status), ice_health_status_lookup_compare); +} + +static void ice_describe_status_code(struct devlink_fmsg *fmsg, + struct ice_aqc_health_status_elem *hse) +{ + static const char *const aux_label[] = { "Aux Data 1", "Aux Data 2" }; + const struct ice_health_status *health_code; + u32 internal_data[2]; + u16 status_code; + + status_code = le16_to_cpu(hse->health_status_code); + + devlink_fmsg_put(fmsg, "Syndrome", status_code); + if (status_code) { + internal_data[0] = le32_to_cpu(hse->internal_data1); + internal_data[1] = le32_to_cpu(hse->internal_data2); + + health_code = ice_get_health_status(status_code); + if (!health_code) + return; + + devlink_fmsg_string_pair_put(fmsg, "Description", health_code->description); + if (health_code->solution) + devlink_fmsg_string_pair_put(fmsg, "Possible Solution", + health_code->solution); + + for (size_t i = 0; i < ICE_HEALTH_STATUS_DATA_SIZE; i++) { + if (internal_data[i] != ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA) + devlink_fmsg_u32_pair_put(fmsg, + health_code->data_label[i] ? + health_code->data_label[i] : + aux_label[i], + internal_data[i]); + } + } +} + +static int +ice_port_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.port_status); + return 0; +} + +static int +ice_port_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + void *priv_ctx, struct netlink_ext_ack __always_unused *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.port_status); + return 0; +} + +static int +ice_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.fw_status); + return 0; +} + +static int +ice_fw_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + void *priv_ctx, struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.fw_status); + return 0; +} + +static void ice_config_health_events(struct ice_pf *pf, bool enable) +{ + u8 enable_bits = 0; + int ret; + + if (enable) + enable_bits = ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK | + ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK; + + ret = ice_aq_set_health_status_cfg(&pf->hw, enable_bits); + if (ret) + dev_err(ice_pf_to_dev(pf), "Failed to %s firmware health events, err %d aq_err %s\n", + str_enable_disable(enable), ret, + ice_aq_str(pf->hw.adminq.sq_last_status)); +} + +/** + * ice_process_health_status_event - Process the health status event from FW + * @pf: pointer to the PF structure + * @event: event structure containing the Health Status Event opcode + * + * Decode the Health Status Events and print the associated messages + */ +void ice_process_health_status_event(struct ice_pf *pf, struct ice_rq_event_info *event) +{ + const struct ice_aqc_health_status_elem *health_info; + u16 count; + + health_info = (struct ice_aqc_health_status_elem *)event->msg_buf; + count = le16_to_cpu(event->desc.params.get_health_status.health_status_count); + + if (count > (event->buf_len / sizeof(*health_info))) { + dev_err(ice_pf_to_dev(pf), "Received a health status event with invalid element count\n"); + return; + } + + for (size_t i = 0; i < count; i++) { + const struct ice_health_status *health_code; + u16 status_code; + + status_code = le16_to_cpu(health_info->health_status_code); + health_code = ice_get_health_status(status_code); + + if (health_code) { + switch (le16_to_cpu(health_info->event_source)) { + case ICE_AQC_HEALTH_STATUS_GLOBAL: + pf->health_reporters.fw_status = *health_info; + devlink_health_report(pf->health_reporters.fw, + "FW syndrome reported", NULL); + break; + case ICE_AQC_HEALTH_STATUS_PF: + case ICE_AQC_HEALTH_STATUS_PORT: + pf->health_reporters.port_status = *health_info; + devlink_health_report(pf->health_reporters.port, + "Port syndrome reported", NULL); + break; + default: + dev_err(ice_pf_to_dev(pf), "Health code with unknown source\n"); + } + } else { + u32 data1, data2; + u16 source; + + source = le16_to_cpu(health_info->event_source); + data1 = le32_to_cpu(health_info->internal_data1); + data2 = le32_to_cpu(health_info->internal_data2); + dev_dbg(ice_pf_to_dev(pf), + "Received internal health status code 0x%08x, source: 0x%08x, data1: 0x%08x, data2: 0x%08x", + status_code, source, data1, data2); + } + health_info++; + } +} + +/** + * ice_devlink_health_report - boilerplate to call given @reporter + * + * @reporter: devlink health reporter to call, do nothing on NULL + * @msg: message to pass up, "event name" is fine + * @priv_ctx: typically some event struct + */ +static void ice_devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx) +{ + if (!reporter) + return; + + /* We do not do auto recovering, so return value of the below function + * will always be 0, thus we do ignore it. + */ + devlink_health_report(reporter, msg, priv_ctx); +} + +struct ice_mdd_event { + enum ice_mdd_src src; + u16 vf_num; + u16 queue; + u8 pf_num; + u8 event; +}; + +static const char *ice_mdd_src_to_str(enum ice_mdd_src src) +{ + switch (src) { + case ICE_MDD_SRC_TX_PQM: + return "tx_pqm"; + case ICE_MDD_SRC_TX_TCLAN: + return "tx_tclan"; + case ICE_MDD_SRC_TX_TDPU: + return "tx_tdpu"; + case ICE_MDD_SRC_RX: + return "rx"; + default: + return "invalid"; + } +} + +static int +ice_mdd_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) +{ + struct ice_mdd_event *mdd_event = priv_ctx; + const char *src; + + if (!mdd_event) + return 0; + + src = ice_mdd_src_to_str(mdd_event->src); + + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_put(fmsg, "src", src); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, pf_num); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, vf_num); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, event); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, queue); + devlink_fmsg_obj_nest_end(fmsg); + + return 0; +} + +/** + * ice_report_mdd_event - Report an MDD event through devlink health + * @pf: the PF device structure + * @src: the HW block that was the source of this MDD event + * @pf_num: the pf_num on which the MDD event occurred + * @vf_num: the vf_num on which the MDD event occurred + * @event: the event type of the MDD event + * @queue: the queue on which the MDD event occurred + * + * Report an MDD event that has occurred on this PF. + */ +void ice_report_mdd_event(struct ice_pf *pf, enum ice_mdd_src src, u8 pf_num, + u16 vf_num, u8 event, u16 queue) +{ + struct ice_mdd_event ev = { + .src = src, + .pf_num = pf_num, + .vf_num = vf_num, + .event = event, + .queue = queue, + }; + + ice_devlink_health_report(pf->health_reporters.mdd, "MDD event", &ev); +} + +/** + * ice_fmsg_put_ptr - put hex value of pointer into fmsg + * + * @fmsg: devlink fmsg under construction + * @name: name to pass + * @ptr: 64 bit value to print as hex and put into fmsg + */ +static void ice_fmsg_put_ptr(struct devlink_fmsg *fmsg, const char *name, + void *ptr) +{ + char buf[sizeof(ptr) * 3]; + + sprintf(buf, "%p", ptr); + devlink_fmsg_put(fmsg, name, buf); +} + +struct ice_tx_hang_event { + u32 head; + u32 intr; + u16 vsi_num; + u16 queue; + u16 next_to_clean; + u16 next_to_use; + struct ice_tx_ring *tx_ring; +}; + +static int ice_tx_hang_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) +{ + struct ice_tx_hang_event *event = priv_ctx; + struct sk_buff *skb; + + if (!event) + return 0; + + skb = event->tx_ring->tx_buf->skb; + devlink_fmsg_obj_nest_start(fmsg); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, head); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, intr); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, vsi_num); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, queue); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, next_to_clean); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, next_to_use); + devlink_fmsg_put(fmsg, "irq-mapping", event->tx_ring->q_vector->name); + ice_fmsg_put_ptr(fmsg, "desc-ptr", event->tx_ring->desc); + ice_fmsg_put_ptr(fmsg, "dma-ptr", (void *)(long)event->tx_ring->dma); + ice_fmsg_put_ptr(fmsg, "skb-ptr", skb); + devlink_fmsg_binary_pair_put(fmsg, "desc", event->tx_ring->desc, + event->tx_ring->count * sizeof(struct ice_tx_desc)); + devlink_fmsg_dump_skb(fmsg, skb); + devlink_fmsg_obj_nest_end(fmsg); + + return 0; +} + +void ice_prep_tx_hang_report(struct ice_pf *pf, struct ice_tx_ring *tx_ring, + u16 vsi_num, u32 head, u32 intr) +{ + struct ice_health_tx_hang_buf *buf = &pf->health_reporters.tx_hang_buf; + + buf->tx_ring = tx_ring; + buf->vsi_num = vsi_num; + buf->head = head; + buf->intr = intr; +} + +void ice_report_tx_hang(struct ice_pf *pf) +{ + struct ice_health_tx_hang_buf *buf = &pf->health_reporters.tx_hang_buf; + struct ice_tx_ring *tx_ring = buf->tx_ring; + + struct ice_tx_hang_event ev = { + .head = buf->head, + .intr = buf->intr, + .vsi_num = buf->vsi_num, + .queue = tx_ring->q_index, + .next_to_clean = tx_ring->next_to_clean, + .next_to_use = tx_ring->next_to_use, + .tx_ring = tx_ring, + }; + + ice_devlink_health_report(pf->health_reporters.tx_hang, "Tx hang", &ev); +} + +static struct devlink_health_reporter * +ice_init_devlink_rep(struct ice_pf *pf, + const struct devlink_health_reporter_ops *ops) +{ + struct devlink *devlink = priv_to_devlink(pf); + struct devlink_health_reporter *rep; + const u64 graceful_period = 0; + + rep = devl_health_reporter_create(devlink, ops, graceful_period, pf); + if (IS_ERR(rep)) { + struct device *dev = ice_pf_to_dev(pf); + + dev_err(dev, "failed to create devlink %s health report er", + ops->name); + return NULL; + } + return rep; +} + +#define ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field) \ + ._field = ice_##_name##_reporter_##_field, + +#define ICE_DEFINE_HEALTH_REPORTER_OPS_1(_name, _field1) \ + static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \ + .name = #_name, \ + ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \ + } + +#define ICE_DEFINE_HEALTH_REPORTER_OPS_2(_name, _field1, _field2) \ + static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \ + .name = #_name, \ + ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \ + ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field2) \ + } + +ICE_DEFINE_HEALTH_REPORTER_OPS_1(mdd, dump); +ICE_DEFINE_HEALTH_REPORTER_OPS_1(tx_hang, dump); +ICE_DEFINE_HEALTH_REPORTER_OPS_2(fw, dump, diagnose); +ICE_DEFINE_HEALTH_REPORTER_OPS_2(port, dump, diagnose); + +/** + * ice_health_init - allocate and init all ice devlink health reporters and + * accompanied data + * + * @pf: PF struct + */ +void ice_health_init(struct ice_pf *pf) +{ + struct ice_health *reps = &pf->health_reporters; + + reps->mdd = ice_init_devlink_rep(pf, &ice_mdd_reporter_ops); + reps->tx_hang = ice_init_devlink_rep(pf, &ice_tx_hang_reporter_ops); + + if (ice_is_fw_health_report_supported(&pf->hw)) { + reps->fw = ice_init_devlink_rep(pf, &ice_fw_reporter_ops); + reps->port = ice_init_devlink_rep(pf, &ice_port_reporter_ops); + ice_config_health_events(pf, true); + } +} + +/** + * ice_deinit_devl_reporter - destroy given devlink health reporter + * @reporter: reporter to destroy + */ +static void ice_deinit_devl_reporter(struct devlink_health_reporter *reporter) +{ + if (reporter) + devl_health_reporter_destroy(reporter); +} + +/** + * ice_health_deinit - deallocate all ice devlink health reporters and + * accompanied data + * + * @pf: PF struct + */ +void ice_health_deinit(struct ice_pf *pf) +{ + ice_deinit_devl_reporter(pf->health_reporters.mdd); + ice_deinit_devl_reporter(pf->health_reporters.tx_hang); + if (ice_is_fw_health_report_supported(&pf->hw)) { + ice_deinit_devl_reporter(pf->health_reporters.fw); + ice_deinit_devl_reporter(pf->health_reporters.port); + ice_config_health_events(pf, false); + } +} + +static +void ice_health_assign_healthy_state(struct devlink_health_reporter *reporter) +{ + if (reporter) + devlink_health_reporter_state_update(reporter, + DEVLINK_HEALTH_REPORTER_STATE_HEALTHY); +} + +/** + * ice_health_clear - clear devlink health issues after a reset + * @pf: the PF device structure + * + * Mark the PF in healthy state again after a reset has completed. + */ +void ice_health_clear(struct ice_pf *pf) +{ + ice_health_assign_healthy_state(pf->health_reporters.mdd); + ice_health_assign_healthy_state(pf->health_reporters.tx_hang); +} diff --git a/drivers/net/ethernet/intel/ice/devlink/health.h b/drivers/net/ethernet/intel/ice/devlink/health.h new file mode 100644 index 000000000000..5edfc4d2adce --- /dev/null +++ b/drivers/net/ethernet/intel/ice/devlink/health.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024, Intel Corporation. */ + +#ifndef _HEALTH_H_ +#define _HEALTH_H_ + +#include <linux/types.h> + +/** + * DOC: health.h + * + * This header file stores everything that is needed for broadly understood + * devlink health mechanism for ice driver. + */ + +struct ice_aqc_health_status_elem; +struct ice_pf; +struct ice_tx_ring; +struct ice_rq_event_info; + +enum ice_mdd_src { + ICE_MDD_SRC_TX_PQM, + ICE_MDD_SRC_TX_TCLAN, + ICE_MDD_SRC_TX_TDPU, + ICE_MDD_SRC_RX, +}; + +/** + * struct ice_health - stores ice devlink health reporters and accompanied data + * @fw: devlink health reporter for FW Health Status events + * @mdd: devlink health reporter for MDD detection event + * @port: devlink health reporter for Port Health Status events + * @tx_hang: devlink health reporter for tx_hang event + * @tx_hang_buf: pre-allocated place to put info for Tx hang reporter from + * non-sleeping context + * @tx_ring: ring that the hang occurred on + * @head: descriptor head + * @intr: interrupt register value + * @vsi_num: VSI owning the queue that the hang occurred on + * @fw_status: buffer for last received FW Status event + * @port_status: buffer for last received Port Status event + */ +struct ice_health { + struct devlink_health_reporter *fw; + struct devlink_health_reporter *mdd; + struct devlink_health_reporter *port; + struct devlink_health_reporter *tx_hang; + struct_group_tagged(ice_health_tx_hang_buf, tx_hang_buf, + struct ice_tx_ring *tx_ring; + u32 head; + u32 intr; + u16 vsi_num; + ); + struct ice_aqc_health_status_elem fw_status; + struct ice_aqc_health_status_elem port_status; +}; + +void ice_process_health_status_event(struct ice_pf *pf, + struct ice_rq_event_info *event); + +void ice_health_init(struct ice_pf *pf); +void ice_health_deinit(struct ice_pf *pf); +void ice_health_clear(struct ice_pf *pf); + +void ice_prep_tx_hang_report(struct ice_pf *pf, struct ice_tx_ring *tx_ring, + u16 vsi_num, u32 head, u32 intr); +void ice_report_mdd_event(struct ice_pf *pf, enum ice_mdd_src src, u8 pf_num, + u16 vf_num, u8 event, u16 queue); +void ice_report_tx_hang(struct ice_pf *pf); + +#endif /* _HEALTH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/port.c index c6779d9dffff..767419a67fef 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c +++ b/drivers/net/ethernet/intel/ice/devlink/port.c @@ -5,7 +5,7 @@ #include "ice.h" #include "devlink.h" -#include "devlink_port.h" +#include "port.h" #include "ice_lib.h" #include "ice_fltr.h" diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h b/drivers/net/ethernet/intel/ice/devlink/port.h index d60efc340945..d60efc340945 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h +++ b/drivers/net/ethernet/intel/ice/devlink/port.h diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 2f5d6f974185..ddd0ad68185b 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -78,6 +78,7 @@ #include "ice_irq.h" #include "ice_dpll.h" #include "ice_adapter.h" +#include "devlink/health.h" #define ICE_BAR0 0 #define ICE_REQ_DESC_MULTIPLE 32 @@ -96,9 +97,6 @@ #define ICE_MIN_LAN_OICR_MSIX 1 #define ICE_MIN_MSIX (ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX) #define ICE_FDIR_MSIX 2 -#define ICE_RDMA_NUM_AEQ_MSIX 4 -#define ICE_MIN_RDMA_MSIX 2 -#define ICE_ESWITCH_MSIX 1 #define ICE_NO_VSI 0xffff #define ICE_VSI_MAP_CONTIG 0 #define ICE_VSI_MAP_SCATTER 1 @@ -195,14 +193,13 @@ #define ice_pf_to_dev(pf) (&((pf)->pdev->dev)) -#define ice_pf_src_tmr_owned(pf) ((pf)->hw.func_caps.ts_func_info.src_tmr_owned) - enum ice_feature { ICE_F_DSCP, ICE_F_PHY_RCLK, ICE_F_SMA_CTRL, ICE_F_CGU, ICE_F_GNSS, + ICE_F_GCS, ICE_F_ROCE_LAG, ICE_F_SRIOV_LAG, ICE_F_MBX_LIMIT, @@ -402,7 +399,6 @@ struct ice_vsi { u16 req_rxq; /* User requested Rx queues */ u16 num_rx_desc; u16 num_tx_desc; - u16 qset_handle[ICE_MAX_TRAFFIC_CLASS]; struct ice_tc_cfg tc_cfg; struct bpf_prog *xdp_prog; struct ice_tx_ring **xdp_rings; /* XDP ring array */ @@ -477,9 +473,6 @@ struct ice_q_vector { struct ice_ring_container rx; struct ice_ring_container tx; - cpumask_t affinity_mask; - struct irq_affinity_notify affinity_notify; - struct ice_channel *ch; char name[ICE_INT_NAME_STR_LEN]; @@ -519,6 +512,7 @@ enum ice_pf_flags { ICE_FLAG_MTU_CHANGED, ICE_FLAG_GNSS, /* GNSS successfully initialized */ ICE_FLAG_DPLL, /* SyncE/PTP dplls initialized */ + ICE_FLAG_LLDP_AQ_FLTR, ICE_PF_FLAGS_NBITS /* must be last */ }; @@ -541,6 +535,14 @@ struct ice_agg_node { u8 valid; }; +struct ice_pf_msix { + u32 cur; + u32 min; + u32 max; + u32 total; + u32 rest; +}; + struct ice_pf { struct pci_dev *pdev; struct ice_adapter *adapter; @@ -553,15 +555,8 @@ struct ice_pf { struct devlink_port devlink_port; /* OS reserved IRQ details */ - struct msix_entry *msix_entries; struct ice_irq_tracker irq_tracker; - /* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the - * number of MSIX vectors needed for all SR-IOV VFs from the number of - * MSIX vectors allowed on this PF. - */ - u16 sriov_base_vector; - unsigned long *sriov_irq_bm; /* bitmap to track irq usage */ - u16 sriov_irq_size; /* size of the irq_bm bitmap */ + struct ice_virt_irq_tracker virt_irq_tracker; u16 ctrl_vsi_idx; /* control VSI index in pf->vsi array */ @@ -594,7 +589,6 @@ struct ice_pf { struct gnss_serial *gnss_serial; struct gnss_device *gnss_dev; u16 num_rdma_msix; /* Total MSIX vectors for RDMA driver */ - u16 rdma_base_vector; /* spinlock to protect the AdminQ wait list */ spinlock_t aq_wait_lock; @@ -611,7 +605,7 @@ struct ice_pf { struct msi_map ll_ts_irq; /* LL_TS interrupt MSIX vector */ u16 max_pf_txqs; /* Total Tx queues PF wide */ u16 max_pf_rxqs; /* Total Rx queues PF wide */ - u16 num_lan_msix; /* Total MSIX vectors for base driver */ + struct ice_pf_msix msix; u16 num_lan_tx; /* num LAN Tx queues setup */ u16 num_lan_rx; /* num LAN Rx queues setup */ u16 next_vsi; /* Next free slot in pf->vsi[] - 0-based! */ @@ -627,14 +621,12 @@ struct ice_pf { struct ice_hw_port_stats stats_prev; struct ice_hw hw; u8 stat_prev_loaded:1; /* has previous stats been loaded */ - u8 rdma_mode; u16 dcbx_cap; u32 tx_timeout_count; unsigned long tx_timeout_last_recovery; u32 tx_timeout_recovery_level; char int_name[ICE_INT_NAME_STR_LEN]; char int_name_ll_ts[ICE_INT_NAME_STR_LEN]; - struct auxiliary_device *adev; int aux_idx; u32 sw_int_count; /* count of tc_flower filters specific to channel (aka where filter @@ -665,6 +657,8 @@ struct ice_pf { struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES]; struct ice_dplls dplls; struct device *hwmon_dev; + struct ice_health health_reporters; + struct iidc_rdma_core_dev_info *cdev_info; u8 num_quanta_prof_used; }; @@ -1045,10 +1039,63 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf) clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); } -static inline enum ice_phy_model ice_get_phy_model(const struct ice_hw *hw) +extern const struct xdp_metadata_ops ice_xdp_md_ops; + +/** + * ice_is_dual - Check if given config is multi-NAC + * @hw: pointer to HW structure + * + * Return: true if the device is running in mutli-NAC (Network + * Acceleration Complex) configuration variant, false otherwise + * (always false for non-E825 devices). + */ +static inline bool ice_is_dual(struct ice_hw *hw) { - return hw->ptp.phy_model; + return hw->mac_type == ICE_MAC_GENERIC_3K_E825 && + (hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_DUAL_M); } -extern const struct xdp_metadata_ops ice_xdp_md_ops; +/** + * ice_is_primary - Check if given device belongs to the primary complex + * @hw: pointer to HW structure + * + * Check if given PF/HW is running on primary complex in multi-NAC + * configuration. + * + * Return: true if the device is dual, false otherwise (always true + * for non-E825 devices). + */ +static inline bool ice_is_primary(struct ice_hw *hw) +{ + return hw->mac_type != ICE_MAC_GENERIC_3K_E825 || + !ice_is_dual(hw) || + (hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M); +} + +/** + * ice_pf_src_tmr_owned - Check if a primary timer is owned by PF + * @pf: pointer to PF structure + * + * Return: true if PF owns primary timer, false otherwise. + */ +static inline bool ice_pf_src_tmr_owned(struct ice_pf *pf) +{ + return pf->hw.func_caps.ts_func_info.src_tmr_owned && + ice_is_primary(&pf->hw); +} + +/** + * ice_get_primary_hw - Get pointer to primary ice_hw structure + * @pf: pointer to PF structure + * + * Return: A pointer to ice_hw structure with access to timesync + * register space. + */ +static inline struct ice_hw *ice_get_primary_hw(struct ice_pf *pf) +{ + if (!pf->adapter->ctrl_pf) + return &pf->hw; + else + return &pf->adapter->ctrl_pf->hw; +} #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c index 01a08cfd0090..66e070095d1b 100644 --- a/drivers/net/ethernet/intel/ice/ice_adapter.c +++ b/drivers/net/ethernet/intel/ice/ice_adapter.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only // SPDX-FileCopyrightText: Copyright Red Hat -#include <linux/bitfield.h> #include <linux/cleanup.h> #include <linux/mutex.h> #include <linux/pci.h> @@ -14,32 +13,16 @@ static DEFINE_XARRAY(ice_adapters); static DEFINE_MUTEX(ice_adapters_mutex); -/* PCI bus number is 8 bits. Slot is 5 bits. Domain can have the rest. */ -#define INDEX_FIELD_DOMAIN GENMASK(BITS_PER_LONG - 1, 13) -#define INDEX_FIELD_DEV GENMASK(31, 16) -#define INDEX_FIELD_BUS GENMASK(12, 5) -#define INDEX_FIELD_SLOT GENMASK(4, 0) - -static unsigned long ice_adapter_index(const struct pci_dev *pdev) +static unsigned long ice_adapter_index(u64 dsn) { - unsigned int domain = pci_domain_nr(pdev->bus); - - WARN_ON(domain > FIELD_MAX(INDEX_FIELD_DOMAIN)); - - switch (pdev->device) { - case ICE_DEV_ID_E825C_BACKPLANE: - case ICE_DEV_ID_E825C_QSFP: - case ICE_DEV_ID_E825C_SFP: - case ICE_DEV_ID_E825C_SGMII: - return FIELD_PREP(INDEX_FIELD_DEV, pdev->device); - default: - return FIELD_PREP(INDEX_FIELD_DOMAIN, domain) | - FIELD_PREP(INDEX_FIELD_BUS, pdev->bus->number) | - FIELD_PREP(INDEX_FIELD_SLOT, PCI_SLOT(pdev->devfn)); - } +#if BITS_PER_LONG == 64 + return dsn; +#else + return (u32)dsn ^ (u32)(dsn >> 32); +#endif } -static struct ice_adapter *ice_adapter_new(void) +static struct ice_adapter *ice_adapter_new(u64 dsn) { struct ice_adapter *adapter; @@ -47,6 +30,7 @@ static struct ice_adapter *ice_adapter_new(void) if (!adapter) return NULL; + adapter->device_serial_number = dsn; spin_lock_init(&adapter->ptp_gltsyn_time_lock); refcount_set(&adapter->refcount, 1); @@ -77,23 +61,26 @@ static void ice_adapter_free(struct ice_adapter *adapter) * Return: Pointer to ice_adapter on success. * ERR_PTR() on error. -ENOMEM is the only possible error. */ -struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev) +struct ice_adapter *ice_adapter_get(struct pci_dev *pdev) { - unsigned long index = ice_adapter_index(pdev); + u64 dsn = pci_get_dsn(pdev); struct ice_adapter *adapter; + unsigned long index; int err; + index = ice_adapter_index(dsn); scoped_guard(mutex, &ice_adapters_mutex) { err = xa_insert(&ice_adapters, index, NULL, GFP_KERNEL); if (err == -EBUSY) { adapter = xa_load(&ice_adapters, index); refcount_inc(&adapter->refcount); + WARN_ON_ONCE(adapter->device_serial_number != dsn); return adapter; } if (err) return ERR_PTR(err); - adapter = ice_adapter_new(); + adapter = ice_adapter_new(dsn); if (!adapter) return ERR_PTR(-ENOMEM); xa_store(&ice_adapters, index, adapter, GFP_KERNEL); @@ -110,11 +97,13 @@ struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev) * * Context: Process, may sleep. */ -void ice_adapter_put(const struct pci_dev *pdev) +void ice_adapter_put(struct pci_dev *pdev) { - unsigned long index = ice_adapter_index(pdev); + u64 dsn = pci_get_dsn(pdev); struct ice_adapter *adapter; + unsigned long index; + index = ice_adapter_index(dsn); scoped_guard(mutex, &ice_adapters_mutex) { adapter = xa_load(&ice_adapters, index); if (WARN_ON(!adapter)) diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h index e233225848b3..ac15c0d2bc1a 100644 --- a/drivers/net/ethernet/intel/ice/ice_adapter.h +++ b/drivers/net/ethernet/intel/ice/ice_adapter.h @@ -32,6 +32,7 @@ struct ice_port_list { * @refcount: Reference count. struct ice_pf objects hold the references. * @ctrl_pf: Control PF of the adapter * @ports: Ports list + * @device_serial_number: DSN cached for collision detection on 32bit systems */ struct ice_adapter { refcount_t refcount; @@ -40,9 +41,10 @@ struct ice_adapter { struct ice_pf *ctrl_pf; struct ice_port_list ports; + u64 device_serial_number; }; -struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev); -void ice_adapter_put(const struct pci_dev *pdev); +struct ice_adapter *ice_adapter_get(struct pci_dev *pdev); +void ice_adapter_put(struct pci_dev *pdev); #endif /* _ICE_ADAPTER_H */ diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 46f9726d9a8a..bdee499f991a 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -12,6 +12,13 @@ #define ICE_AQC_TOPO_MAX_LEVEL_NUM 0x9 #define ICE_AQ_SET_MAC_FRAME_SIZE_MAX 9728 +#define ICE_RXQ_CTX_SIZE_DWORDS 8 +#define ICE_RXQ_CTX_SZ (ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32)) +#define ICE_TXQ_CTX_SZ 22 + +typedef struct __packed { u8 buf[ICE_RXQ_CTX_SZ]; } ice_rxq_ctx_buf_t; +typedef struct __packed { u8 buf[ICE_TXQ_CTX_SZ]; } ice_txq_ctx_buf_t; + struct ice_aqc_generic { __le32 param0; __le32 param1; @@ -1491,7 +1498,6 @@ struct ice_aqc_dnl_equa_param { #define ICE_AQC_RX_EQU_POST1 (0x12 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_BFLF (0x13 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_BFHF (0x14 << ICE_AQC_RX_EQU_SHIFT) -#define ICE_AQC_RX_EQU_DRATE (0x15 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_CTLE_GAINHF (0x20 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_CTLE_GAINLF (0x21 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_CTLE_GAINDC (0x22 << ICE_AQC_RX_EQU_SHIFT) @@ -1808,6 +1814,7 @@ struct ice_aqc_nvm_pass_comp_tbl { #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED 0x0 #define ICE_AQ_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE 0x1 #define ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED 0x2 +#define ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK 0x3 u8 component_response_code; /* Response only */ #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED_CODE 0x0 #define ICE_AQ_NVM_PASS_COMP_STAMP_IDENTICAL_CODE 0x1 @@ -2085,10 +2092,10 @@ struct ice_aqc_add_txqs_perq { __le16 txq_id; u8 rsvd[2]; __le32 q_teid; - u8 txq_ctx[22]; + ice_txq_ctx_buf_t txq_ctx; u8 rsvd2[2]; struct ice_aqc_txsched_elem info; -}; +} __packed; /* The format of the command buffer for Add Tx LAN Queues (0x0C30) * is an array of the following structs. Please note that the length of @@ -2511,6 +2518,87 @@ enum ice_aqc_fw_logging_mod { ICE_AQC_FW_LOG_ID_MAX, }; +enum ice_aqc_health_status_mask { + ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK = BIT(0), + ICE_AQC_HEALTH_STATUS_SET_ALL_PF_MASK = BIT(1), + ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK = BIT(2), +}; + +/* Set Health Status (direct 0xFF20) */ +struct ice_aqc_set_health_status_cfg { + u8 event_source; + u8 reserved[15]; +}; + +enum ice_aqc_health_status { + ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT = 0x101, + ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE = 0x102, + ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL = 0x103, + ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM = 0x104, + ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT = 0x105, + ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT = 0x106, + ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED = 0x107, + ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT = 0x108, + ICE_AQC_HEALTH_STATUS_ERR_MOD_DIAGNOSTIC_FEATURE = 0x109, + ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG = 0x10B, + ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS = 0x10C, + ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE = 0x10D, + ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED = 0x10F, + ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT = 0x110, + ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED = 0x111, + ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO = 0x112, + ICE_AQC_HEALTH_STATUS_ERR_NETLIST = 0x113, + ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT = 0x114, + ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS = 0x115, + ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME = 0x116, + ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT = 0x117, + ICE_AQC_HEALTH_STATUS_ERR_PHY_NVM_PROG = 0x120, + ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD = 0x121, + ICE_AQC_HEALTH_STATUS_INFO_RECOVERY = 0x500, + ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS = 0x501, + ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH = 0x502, + ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH = 0x503, + ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH = 0x504, + ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT = 0x505, + ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT = 0x506, + ICE_AQC_HEALTH_STATUS_ERR_NVM_SEC_VIOLATION = 0x507, + ICE_AQC_HEALTH_STATUS_ERR_OROM_SEC_VIOLATION = 0x508, + ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB = 0x509, + ICE_AQC_HEALTH_STATUS_ERR_MNG_TIMEOUT = 0x50A, + ICE_AQC_HEALTH_STATUS_ERR_BMC_RESET = 0x50B, + ICE_AQC_HEALTH_STATUS_ERR_LAST_MNG_FAIL = 0x50C, + ICE_AQC_HEALTH_STATUS_ERR_RESOURCE_ALLOC_FAIL = 0x50D, + ICE_AQC_HEALTH_STATUS_ERR_FW_LOOP = 0x1000, + ICE_AQC_HEALTH_STATUS_ERR_FW_PFR_FAIL = 0x1001, + ICE_AQC_HEALTH_STATUS_ERR_LAST_FAIL_AQ = 0x1002, +}; + +/* Get Health Status (indirect 0xFF22) */ +struct ice_aqc_get_health_status { + __le16 health_status_count; + u8 reserved[6]; + __le32 addr_high; + __le32 addr_low; +}; + +enum ice_aqc_health_status_scope { + ICE_AQC_HEALTH_STATUS_PF = 0x1, + ICE_AQC_HEALTH_STATUS_PORT = 0x2, + ICE_AQC_HEALTH_STATUS_GLOBAL = 0x3, +}; + +#define ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA 0xDEADBEEF + +/* Get Health Status event buffer entry (0xFF22), + * repeated per reported health status. + */ +struct ice_aqc_health_status_elem { + __le16 health_status_code; + __le16 event_source; + __le32 internal_data1; + __le32 internal_data2; +}; + /* Set FW Logging configuration (indirect 0xFF30) * Register for FW Logging (indirect 0xFF31) * Query FW Logging (indirect 0xFF32) @@ -2651,6 +2739,8 @@ struct ice_aq_desc { struct ice_aqc_get_link_status get_link_status; struct ice_aqc_event_lan_overflow lan_overflow; struct ice_aqc_get_link_topo get_link_topo; + struct ice_aqc_set_health_status_cfg set_health_status_cfg; + struct ice_aqc_get_health_status get_health_status; struct ice_aqc_dnl_call_command dnl_call; struct ice_aqc_i2c read_write_i2c; struct ice_aqc_read_i2c_resp read_i2c_resp; @@ -2853,6 +2943,10 @@ enum ice_adminq_opc { /* Standalone Commands/Events */ ice_aqc_opc_event_lan_overflow = 0x1001, + /* System Diagnostic commands */ + ice_aqc_opc_set_health_status_cfg = 0xFF20, + ice_aqc_opc_get_health_status = 0xFF22, + /* FW Logging Commands */ ice_aqc_opc_fw_logs_config = 0xFF30, ice_aqc_opc_fw_logs_register = 0xFF31, diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 7cee365cc7d1..2bc5c7f59844 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -511,7 +511,7 @@ void ice_init_arfs(struct ice_vsi *vsi) struct hlist_head *arfs_fltr_list; unsigned int i; - if (!vsi || vsi->type != ICE_VSI_PF) + if (!vsi || vsi->type != ICE_VSI_PF || ice_is_arfs_active(vsi)) return; arfs_fltr_list = kcalloc(ICE_MAX_ARFS_LIST, sizeof(*arfs_fltr_list), @@ -571,25 +571,6 @@ void ice_clear_arfs(struct ice_vsi *vsi) } /** - * ice_free_cpu_rx_rmap - free setup CPU reverse map - * @vsi: the VSI to be forwarded to - */ -void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) -{ - struct net_device *netdev; - - if (!vsi || vsi->type != ICE_VSI_PF) - return; - - netdev = vsi->netdev; - if (!netdev || !netdev->rx_cpu_rmap) - return; - - free_irq_cpu_rmap(netdev->rx_cpu_rmap); - netdev->rx_cpu_rmap = NULL; -} - -/** * ice_set_cpu_rx_rmap - setup CPU reverse map for each queue * @vsi: the VSI to be forwarded to */ @@ -597,7 +578,6 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) { struct net_device *netdev; struct ice_pf *pf; - int i; if (!vsi || vsi->type != ICE_VSI_PF) return 0; @@ -610,18 +590,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) netdev_dbg(netdev, "Setup CPU RMAP: vsi type 0x%x, ifname %s, q_vectors %d\n", vsi->type, netdev->name, vsi->num_q_vectors); - netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(vsi->num_q_vectors); - if (unlikely(!netdev->rx_cpu_rmap)) - return -EINVAL; - - ice_for_each_q_vector(vsi, i) - if (irq_cpu_rmap_add(netdev->rx_cpu_rmap, - vsi->q_vectors[i]->irq.virq)) { - ice_free_cpu_rx_rmap(vsi); - return -EINVAL; - } - - return 0; + return netif_enable_cpu_rmap(netdev, vsi->num_q_vectors); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.h b/drivers/net/ethernet/intel/ice/ice_arfs.h index 9669ad9bf7b5..9706293128c3 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.h +++ b/drivers/net/ethernet/intel/ice/ice_arfs.h @@ -45,7 +45,6 @@ int ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb, u16 rxq_idx, u32 flow_id); void ice_clear_arfs(struct ice_vsi *vsi); -void ice_free_cpu_rx_rmap(struct ice_vsi *vsi); void ice_init_arfs(struct ice_vsi *vsi); void ice_sync_arfs_fltrs(struct ice_pf *pf); int ice_set_cpu_rx_rmap(struct ice_vsi *vsi); @@ -56,7 +55,6 @@ ice_is_arfs_using_perfect_flow(struct ice_hw *hw, enum ice_fltr_ptype flow_type); #else static inline void ice_clear_arfs(struct ice_vsi *vsi) { } -static inline void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { } static inline void ice_init_arfs(struct ice_vsi *vsi) { } static inline void ice_sync_arfs_fltrs(struct ice_pf *pf) { } static inline void ice_remove_arfs(struct ice_pf *pf) { } diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 82a9cd4ec7ae..6db4ad8fc70b 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -147,10 +147,6 @@ skip_alloc: q_vector->reg_idx = q_vector->irq.index; q_vector->vf_reg_idx = q_vector->irq.index; - /* only set affinity_mask if the CPU is online */ - if (cpu_online(v_idx)) - cpumask_set_cpu(v_idx, &q_vector->affinity_mask); - /* This will not be called in the driver load path because the netdev * will not be created yet. All other cases with register the NAPI * handler here (i.e. resume, reset/rebuild, etc.) @@ -276,7 +272,8 @@ static void ice_cfg_xps_tx_ring(struct ice_tx_ring *ring) if (test_and_set_bit(ICE_TX_XPS_INIT_DONE, ring->xps_state)) return; - netif_set_xps_queue(ring->netdev, &ring->q_vector->affinity_mask, + netif_set_xps_queue(ring->netdev, + &ring->q_vector->napi.config->affinity_mask, ring->q_index); } @@ -454,6 +451,9 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) /* Rx queue threshold in units of 64 */ rlan_ctx.lrxqthresh = 1; + /* Enable descriptor prefetch */ + rlan_ctx.prefena = 1; + /* PF acts as uplink for switchdev; set flex descriptor with src_vsi * metadata and flags to allow redirecting to PR netdev */ @@ -470,9 +470,6 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) */ if (vsi->type != ICE_VSI_VF) ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3, true); - else - ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3, - false); /* Absolute queue number out of 2K needs to be passed */ err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q); @@ -798,13 +795,11 @@ int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi) return 0; err_out: - while (v_idx--) - ice_free_q_vector(vsi, v_idx); - dev_err(dev, "Failed to allocate %d q_vector for VSI %d, ret=%d\n", - vsi->num_q_vectors, vsi->vsi_num, err); - vsi->num_q_vectors = 0; - return err; + dev_info(dev, "Failed to allocate %d q_vectors for VSI %d, new value %d", + vsi->num_q_vectors, vsi->vsi_num, v_idx); + vsi->num_q_vectors = v_idx; + return v_idx ? 0 : err; } /** @@ -910,8 +905,7 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, ice_setup_tx_ctx(ring, &tlan_ctx, pf_q); /* copy context contents into the qg_buf */ qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q); - ice_set_ctx(hw, (u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx, - ice_tlan_ctx_info); + ice_pack_txq_ctx(&tlan_ctx, &qg_buf->txqs[0].txq_ctx); /* init queue specific tail reg. It is referred as * transmit comm scheduler queue doorbell. diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 532024f34ce4..4fedf0181c4e 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -6,6 +6,7 @@ #include "ice_adminq_cmd.h" #include "ice_flow.h" #include "ice_ptp_hw.h" +#include <linux/packing.h> #define ICE_PF_RESET_WAIT_COUNT 300 #define ICE_MAX_NETLIST_SIZE 10 @@ -185,7 +186,7 @@ static int ice_set_mac_type(struct ice_hw *hw) * ice_is_generic_mac - check if device's mac_type is generic * @hw: pointer to the hardware structure * - * Return: true if mac_type is generic (with SBQ support), false if not + * Return: true if mac_type is ICE_MAC_GENERIC*, false otherwise. */ bool ice_is_generic_mac(struct ice_hw *hw) { @@ -194,117 +195,39 @@ bool ice_is_generic_mac(struct ice_hw *hw) } /** - * ice_is_e810 - * @hw: pointer to the hardware structure - * - * returns true if the device is E810 based, false if not. - */ -bool ice_is_e810(struct ice_hw *hw) -{ - return hw->mac_type == ICE_MAC_E810; -} - -/** - * ice_is_e810t - * @hw: pointer to the hardware structure + * ice_is_pf_c827 - check if pf contains c827 phy + * @hw: pointer to the hw struct * - * returns true if the device is E810T based, false if not. + * Return: true if the device has c827 phy. */ -bool ice_is_e810t(struct ice_hw *hw) +static bool ice_is_pf_c827(struct ice_hw *hw) { - switch (hw->device_id) { - case ICE_DEV_ID_E810C_SFP: - switch (hw->subsystem_device_id) { - case ICE_SUBDEV_ID_E810T: - case ICE_SUBDEV_ID_E810T2: - case ICE_SUBDEV_ID_E810T3: - case ICE_SUBDEV_ID_E810T4: - case ICE_SUBDEV_ID_E810T6: - case ICE_SUBDEV_ID_E810T7: - return true; - } - break; - case ICE_DEV_ID_E810C_QSFP: - switch (hw->subsystem_device_id) { - case ICE_SUBDEV_ID_E810T2: - case ICE_SUBDEV_ID_E810T3: - case ICE_SUBDEV_ID_E810T5: - return true; - } - break; - default: - break; - } - - return false; -} + struct ice_aqc_get_link_topo cmd = {}; + u8 node_part_number; + u16 node_handle; + int status; -/** - * ice_is_e822 - Check if a device is E822 family device - * @hw: pointer to the hardware structure - * - * Return: true if the device is E822 based, false if not. - */ -bool ice_is_e822(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E822C_BACKPLANE: - case ICE_DEV_ID_E822C_QSFP: - case ICE_DEV_ID_E822C_SFP: - case ICE_DEV_ID_E822C_10G_BASE_T: - case ICE_DEV_ID_E822C_SGMII: - case ICE_DEV_ID_E822L_BACKPLANE: - case ICE_DEV_ID_E822L_SFP: - case ICE_DEV_ID_E822L_10G_BASE_T: - case ICE_DEV_ID_E822L_SGMII: - return true; - default: + if (hw->mac_type != ICE_MAC_E810) return false; - } -} -/** - * ice_is_e823 - * @hw: pointer to the hardware structure - * - * returns true if the device is E823-L or E823-C based, false if not. - */ -bool ice_is_e823(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E823L_BACKPLANE: - case ICE_DEV_ID_E823L_SFP: - case ICE_DEV_ID_E823L_10G_BASE_T: - case ICE_DEV_ID_E823L_1GBE: - case ICE_DEV_ID_E823L_QSFP: - case ICE_DEV_ID_E823C_BACKPLANE: - case ICE_DEV_ID_E823C_QSFP: - case ICE_DEV_ID_E823C_SFP: - case ICE_DEV_ID_E823C_10G_BASE_T: - case ICE_DEV_ID_E823C_SGMII: + if (hw->device_id != ICE_DEV_ID_E810C_QSFP) return true; - default: + + cmd.addr.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) | + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT); + cmd.addr.topo_params.index = 0; + + status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number, + &node_handle); + + if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827) return false; - } -} -/** - * ice_is_e825c - Check if a device is E825C family device - * @hw: pointer to the hardware structure - * - * Return: true if the device is E825-C based, false if not. - */ -bool ice_is_e825c(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E825C_BACKPLANE: - case ICE_DEV_ID_E825C_QSFP: - case ICE_DEV_ID_E825C_SFP: - case ICE_DEV_ID_E825C_SGMII: + if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE) return true; - default: - return false; - } + + return false; } /** @@ -1025,6 +948,33 @@ static void ice_get_itr_intrl_gran(struct ice_hw *hw) } /** + * ice_wait_for_fw - wait for full FW readiness + * @hw: pointer to the hardware structure + * @timeout: milliseconds that can elapse before timing out + * + * Return: 0 on success, -ETIMEDOUT on timeout. + */ +static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout) +{ + int fw_loading; + u32 elapsed = 0; + + while (elapsed <= timeout) { + fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M; + + /* firmware was not yet loaded, we have to wait more */ + if (fw_loading) { + elapsed += 100; + msleep(100); + continue; + } + return 0; + } + + return -ETIMEDOUT; +} + +/** * ice_init_hw - main hardware initialization routine * @hw: pointer to the hardware structure */ @@ -1173,8 +1123,21 @@ int ice_init_hw(struct ice_hw *hw) mutex_init(&hw->tnl_lock); ice_init_chk_recipe_reuse_support(hw); - return 0; + /* Some cards require longer initialization times + * due to necessity of loading FW from an external source. + * This can take even half a minute. + */ + if (ice_is_pf_c827(hw)) { + status = ice_wait_for_fw(hw, 30000); + if (status) { + dev_err(ice_hw_to_dev(hw), "ice_wait_for_fw timed out"); + goto err_unroll_fltr_mgmt_struct; + } + } + hw->lane_num = ice_get_phy_lane_number(hw); + + return 0; err_unroll_fltr_mgmt_struct: ice_cleanup_fltr_mgmt_struct(hw); err_unroll_sched: @@ -1360,39 +1323,31 @@ int ice_reset(struct ice_hw *hw, enum ice_reset_req req) } /** - * ice_copy_rxq_ctx_to_hw + * ice_copy_rxq_ctx_to_hw - Copy packed Rx queue context to HW registers * @hw: pointer to the hardware structure - * @ice_rxq_ctx: pointer to the rxq context + * @rxq_ctx: pointer to the packed Rx queue context * @rxq_index: the index of the Rx queue - * - * Copies rxq context from dense structure to HW register space */ -static int -ice_copy_rxq_ctx_to_hw(struct ice_hw *hw, u8 *ice_rxq_ctx, u32 rxq_index) +static void ice_copy_rxq_ctx_to_hw(struct ice_hw *hw, + const ice_rxq_ctx_buf_t *rxq_ctx, + u32 rxq_index) { - u8 i; - - if (!ice_rxq_ctx) - return -EINVAL; - - if (rxq_index > QRX_CTRL_MAX_INDEX) - return -EINVAL; - /* Copy each dword separately to HW */ - for (i = 0; i < ICE_RXQ_CTX_SIZE_DWORDS; i++) { - wr32(hw, QRX_CONTEXT(i, rxq_index), - *((u32 *)(ice_rxq_ctx + (i * sizeof(u32))))); + for (int i = 0; i < ICE_RXQ_CTX_SIZE_DWORDS; i++) { + u32 ctx = ((const u32 *)rxq_ctx)[i]; - ice_debug(hw, ICE_DBG_QCTX, "qrxdata[%d]: %08X\n", i, - *((u32 *)(ice_rxq_ctx + (i * sizeof(u32))))); - } + wr32(hw, QRX_CONTEXT(i, rxq_index), ctx); - return 0; + ice_debug(hw, ICE_DBG_QCTX, "qrxdata[%d]: %08X\n", i, ctx); + } } +#define ICE_CTX_STORE(struct_name, struct_field, width, lsb) \ + PACKED_FIELD((lsb) + (width) - 1, (lsb), struct struct_name, struct_field) + /* LAN Rx Queue Context */ -static const struct ice_ctx_ele ice_rlan_ctx_info[] = { - /* Field Width LSB */ +static const struct packed_field_u8 ice_rlan_ctx_fields[] = { + /* Field Width LSB */ ICE_CTX_STORE(ice_rlan_ctx, head, 13, 0), ICE_CTX_STORE(ice_rlan_ctx, cpuid, 8, 13), ICE_CTX_STORE(ice_rlan_ctx, base, 57, 32), @@ -1413,35 +1368,50 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = { ICE_CTX_STORE(ice_rlan_ctx, tphhead_ena, 1, 196), ICE_CTX_STORE(ice_rlan_ctx, lrxqthresh, 3, 198), ICE_CTX_STORE(ice_rlan_ctx, prefena, 1, 201), - { 0 } }; /** - * ice_write_rxq_ctx + * ice_pack_rxq_ctx - Pack Rx queue context into a HW buffer + * @ctx: the Rx queue context to pack + * @buf: the HW buffer to pack into + * + * Pack the Rx queue context from the CPU-friendly unpacked buffer into its + * bit-packed HW layout. + */ +static void ice_pack_rxq_ctx(const struct ice_rlan_ctx *ctx, + ice_rxq_ctx_buf_t *buf) +{ + pack_fields(buf, sizeof(*buf), ctx, ice_rlan_ctx_fields, + QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST); +} + +/** + * ice_write_rxq_ctx - Write Rx Queue context to hardware * @hw: pointer to the hardware structure - * @rlan_ctx: pointer to the rxq context + * @rlan_ctx: pointer to the unpacked Rx queue context * @rxq_index: the index of the Rx queue * - * Converts rxq context from sparse to dense structure and then writes - * it to HW register space and enables the hardware to prefetch descriptors - * instead of only fetching them on demand + * Pack the sparse Rx Queue context into dense hardware format and write it + * into the HW register space. + * + * Return: 0 on success, or -EINVAL if the Rx queue index is invalid. */ int ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, u32 rxq_index) { - u8 ctx_buf[ICE_RXQ_CTX_SZ] = { 0 }; + ice_rxq_ctx_buf_t buf = {}; - if (!rlan_ctx) + if (rxq_index > QRX_CTRL_MAX_INDEX) return -EINVAL; - rlan_ctx->prefena = 1; + ice_pack_rxq_ctx(rlan_ctx, &buf); + ice_copy_rxq_ctx_to_hw(hw, &buf, rxq_index); - ice_set_ctx(hw, (u8 *)rlan_ctx, ctx_buf, ice_rlan_ctx_info); - return ice_copy_rxq_ctx_to_hw(hw, ctx_buf, rxq_index); + return 0; } /* LAN Tx Queue Context */ -const struct ice_ctx_ele ice_tlan_ctx_info[] = { +static const struct packed_field_u8 ice_tlan_ctx_fields[] = { /* Field Width LSB */ ICE_CTX_STORE(ice_tlan_ctx, base, 57, 0), ICE_CTX_STORE(ice_tlan_ctx, port_num, 3, 57), @@ -1470,10 +1440,22 @@ const struct ice_ctx_ele ice_tlan_ctx_info[] = { ICE_CTX_STORE(ice_tlan_ctx, drop_ena, 1, 165), ICE_CTX_STORE(ice_tlan_ctx, cache_prof_idx, 2, 166), ICE_CTX_STORE(ice_tlan_ctx, pkt_shaper_prof_idx, 3, 168), - ICE_CTX_STORE(ice_tlan_ctx, int_q_state, 122, 171), - { 0 } }; +/** + * ice_pack_txq_ctx - Pack Tx queue context into a HW buffer + * @ctx: the Tx queue context to pack + * @buf: the HW buffer to pack into + * + * Pack the Tx queue context from the CPU-friendly unpacked buffer into its + * bit-packed HW layout. + */ +void ice_pack_txq_ctx(const struct ice_tlan_ctx *ctx, ice_txq_ctx_buf_t *buf) +{ + pack_fields(buf, sizeof(*buf), ctx, ice_tlan_ctx_fields, + QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST); +} + /* Sideband Queue command wrappers */ /** @@ -2177,7 +2159,8 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, caps->nvm_unified_update); break; case ICE_AQC_CAPS_RDMA: - caps->rdma = (number == 1); + if (IS_ENABLED(CONFIG_INFINIBAND_IRDMA)) + caps->rdma = (number == 1); ice_debug(hw, ICE_DBG_INIT, "%s: rdma = %d\n", prefix, caps->rdma); break; case ICE_AQC_CAPS_MAX_MTU: @@ -2314,7 +2297,7 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p, info->tmr_index_owned = ((number & ICE_TS_TMR_IDX_OWND_M) != 0); info->tmr_index_assoc = ((number & ICE_TS_TMR_IDX_ASSOC_M) != 0); - if (!ice_is_e825c(hw)) { + if (hw->mac_type != ICE_MAC_GENERIC_3K_E825) { info->clk_freq = FIELD_GET(ICE_TS_CLK_FREQ_M, number); info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0); } else { @@ -2547,6 +2530,7 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, info->ts_ll_read = ((number & ICE_TS_LL_TX_TS_READ_M) != 0); info->ts_ll_int_read = ((number & ICE_TS_LL_TX_TS_INT_READ_M) != 0); + info->ll_phy_tmr_update = ((number & ICE_TS_LL_PHY_TMR_UPDATE_M) != 0); info->ena_ports = logical_id; info->tmr_own_map = phys_id; @@ -2569,6 +2553,8 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, info->ts_ll_read); ice_debug(hw, ICE_DBG_INIT, "dev caps: ts_ll_int_read = %u\n", info->ts_ll_int_read); + ice_debug(hw, ICE_DBG_INIT, "dev caps: ll_phy_tmr_update = %u\n", + info->ll_phy_tmr_update); ice_debug(hw, ICE_DBG_INIT, "dev caps: ieee_1588 ena_ports = %u\n", info->ena_ports); ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr_own_map = %u\n", @@ -2709,40 +2695,6 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, } /** - * ice_is_pf_c827 - check if pf contains c827 phy - * @hw: pointer to the hw struct - */ -bool ice_is_pf_c827(struct ice_hw *hw) -{ - struct ice_aqc_get_link_topo cmd = {}; - u8 node_part_number; - u16 node_handle; - int status; - - if (hw->mac_type != ICE_MAC_E810) - return false; - - if (hw->device_id != ICE_DEV_ID_E810C_QSFP) - return true; - - cmd.addr.topo_params.node_type_ctx = - FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) | - FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT); - cmd.addr.topo_params.index = 0; - - status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number, - &node_handle); - - if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827) - return false; - - if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE) - return true; - - return false; -} - -/** * ice_is_phy_rclk_in_netlist * @hw: pointer to the hw struct * @@ -3484,7 +3436,7 @@ int ice_aq_get_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port, msg.msg_addr_low = lower_16_bits(reg_offset); msg.msg_addr_high = receiver_id; msg.opcode = ice_sbq_msg_rd; - msg.dest_dev = rmn_0; + msg.dest_dev = ice_sbq_dev_phy_0; err = ice_sbq_rw_reg(hw, &msg, flag); if (err) @@ -4132,10 +4084,12 @@ int ice_get_phy_lane_number(struct ice_hw *hw) continue; if (hw->pf_id == lport) { + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825 && + ice_is_dual(hw) && !ice_is_primary(hw)) + lane += ICE_PORTS_PER_QUAD; kfree(options); return lane; } - lport++; } @@ -4609,205 +4563,6 @@ ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps, /* End of FW Admin Queue command wrappers */ /** - * ice_pack_ctx_byte - write a byte to a packed context structure - * @src_ctx: unpacked source context structure - * @dest_ctx: packed destination context data - * @ce_info: context element description - */ -static void ice_pack_ctx_byte(u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - u8 src_byte, dest_byte, mask; - u8 *from, *dest; - u16 shift_width; - - /* copy from the next struct field */ - from = src_ctx + ce_info->offset; - - /* prepare the bits and mask */ - shift_width = ce_info->lsb % 8; - mask = GENMASK(ce_info->width - 1 + shift_width, shift_width); - - src_byte = *from; - src_byte <<= shift_width; - src_byte &= mask; - - /* get the current bits from the target bit string */ - dest = dest_ctx + (ce_info->lsb / 8); - - memcpy(&dest_byte, dest, sizeof(dest_byte)); - - dest_byte &= ~mask; /* get the bits not changing */ - dest_byte |= src_byte; /* add in the new bits */ - - /* put it all back */ - memcpy(dest, &dest_byte, sizeof(dest_byte)); -} - -/** - * ice_pack_ctx_word - write a word to a packed context structure - * @src_ctx: unpacked source context structure - * @dest_ctx: packed destination context data - * @ce_info: context element description - */ -static void ice_pack_ctx_word(u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - u16 src_word, mask; - __le16 dest_word; - u8 *from, *dest; - u16 shift_width; - - /* copy from the next struct field */ - from = src_ctx + ce_info->offset; - - /* prepare the bits and mask */ - shift_width = ce_info->lsb % 8; - mask = GENMASK(ce_info->width - 1 + shift_width, shift_width); - - /* don't swizzle the bits until after the mask because the mask bits - * will be in a different bit position on big endian machines - */ - src_word = *(u16 *)from; - src_word <<= shift_width; - src_word &= mask; - - /* get the current bits from the target bit string */ - dest = dest_ctx + (ce_info->lsb / 8); - - memcpy(&dest_word, dest, sizeof(dest_word)); - - dest_word &= ~(cpu_to_le16(mask)); /* get the bits not changing */ - dest_word |= cpu_to_le16(src_word); /* add in the new bits */ - - /* put it all back */ - memcpy(dest, &dest_word, sizeof(dest_word)); -} - -/** - * ice_pack_ctx_dword - write a dword to a packed context structure - * @src_ctx: unpacked source context structure - * @dest_ctx: packed destination context data - * @ce_info: context element description - */ -static void ice_pack_ctx_dword(u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - u32 src_dword, mask; - __le32 dest_dword; - u8 *from, *dest; - u16 shift_width; - - /* copy from the next struct field */ - from = src_ctx + ce_info->offset; - - /* prepare the bits and mask */ - shift_width = ce_info->lsb % 8; - mask = GENMASK(ce_info->width - 1 + shift_width, shift_width); - - /* don't swizzle the bits until after the mask because the mask bits - * will be in a different bit position on big endian machines - */ - src_dword = *(u32 *)from; - src_dword <<= shift_width; - src_dword &= mask; - - /* get the current bits from the target bit string */ - dest = dest_ctx + (ce_info->lsb / 8); - - memcpy(&dest_dword, dest, sizeof(dest_dword)); - - dest_dword &= ~(cpu_to_le32(mask)); /* get the bits not changing */ - dest_dword |= cpu_to_le32(src_dword); /* add in the new bits */ - - /* put it all back */ - memcpy(dest, &dest_dword, sizeof(dest_dword)); -} - -/** - * ice_pack_ctx_qword - write a qword to a packed context structure - * @src_ctx: unpacked source context structure - * @dest_ctx: packed destination context data - * @ce_info: context element description - */ -static void ice_pack_ctx_qword(u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - u64 src_qword, mask; - __le64 dest_qword; - u8 *from, *dest; - u16 shift_width; - - /* copy from the next struct field */ - from = src_ctx + ce_info->offset; - - /* prepare the bits and mask */ - shift_width = ce_info->lsb % 8; - mask = GENMASK_ULL(ce_info->width - 1 + shift_width, shift_width); - - /* don't swizzle the bits until after the mask because the mask bits - * will be in a different bit position on big endian machines - */ - src_qword = *(u64 *)from; - src_qword <<= shift_width; - src_qword &= mask; - - /* get the current bits from the target bit string */ - dest = dest_ctx + (ce_info->lsb / 8); - - memcpy(&dest_qword, dest, sizeof(dest_qword)); - - dest_qword &= ~(cpu_to_le64(mask)); /* get the bits not changing */ - dest_qword |= cpu_to_le64(src_qword); /* add in the new bits */ - - /* put it all back */ - memcpy(dest, &dest_qword, sizeof(dest_qword)); -} - -/** - * ice_set_ctx - set context bits in packed structure - * @hw: pointer to the hardware structure - * @src_ctx: pointer to a generic non-packed context structure - * @dest_ctx: pointer to memory for the packed structure - * @ce_info: List of Rx context elements - */ -int ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - int f; - - for (f = 0; ce_info[f].width; f++) { - /* We have to deal with each element of the FW response - * using the correct size so that we are correct regardless - * of the endianness of the machine. - */ - if (ce_info[f].width > (ce_info[f].size_of * BITS_PER_BYTE)) { - ice_debug(hw, ICE_DBG_QCTX, "Field %d width of %d bits larger than size of %d byte(s) ... skipping write\n", - f, ce_info[f].width, ce_info[f].size_of); - continue; - } - switch (ce_info[f].size_of) { - case sizeof(u8): - ice_pack_ctx_byte(src_ctx, dest_ctx, &ce_info[f]); - break; - case sizeof(u16): - ice_pack_ctx_word(src_ctx, dest_ctx, &ce_info[f]); - break; - case sizeof(u32): - ice_pack_ctx_dword(src_ctx, dest_ctx, &ce_info[f]); - break; - case sizeof(u64): - ice_pack_ctx_qword(src_ctx, dest_ctx, &ce_info[f]); - break; - default: - return -EINVAL; - } - } - - return 0; -} - -/** * ice_get_lan_q_ctx - get the LAN queue context for the given VSI and TC * @hw: pointer to the HW struct * @vsi_handle: software VSI handle @@ -5901,6 +5656,96 @@ ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, } /** + * ice_get_pca9575_handle - find and return the PCA9575 controller + * @hw: pointer to the hw struct + * @pca9575_handle: GPIO controller's handle + * + * Find and return the GPIO controller's handle in the netlist. + * When found - the value will be cached in the hw structure and following calls + * will return cached value. + * + * Return: 0 on success, -ENXIO when there's no PCA9575 present. + */ +int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) +{ + struct ice_aqc_get_link_topo *cmd; + struct ice_aq_desc desc; + int err; + u8 idx; + + /* If handle was read previously return cached value */ + if (hw->io_expander_handle) { + *pca9575_handle = hw->io_expander_handle; + return 0; + } + +#define SW_PCA9575_SFP_TOPO_IDX 2 +#define SW_PCA9575_QSFP_TOPO_IDX 1 + + /* Check if the SW IO expander controlling SMA exists in the netlist. */ + if (hw->device_id == ICE_DEV_ID_E810C_SFP) + idx = SW_PCA9575_SFP_TOPO_IDX; + else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) + idx = SW_PCA9575_QSFP_TOPO_IDX; + else + return -ENXIO; + + /* If handle was not detected read it from the netlist */ + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + cmd = &desc.params.get_link_topo; + cmd->addr.topo_params.node_type_ctx = + ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL; + cmd->addr.topo_params.index = idx; + + err = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (err) + return -ENXIO; + + /* Verify if we found the right IO expander type */ + if (desc.params.get_link_topo.node_part_num != + ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) + return -ENXIO; + + /* If present save the handle and return it */ + hw->io_expander_handle = + le16_to_cpu(desc.params.get_link_topo.addr.handle); + *pca9575_handle = hw->io_expander_handle; + + return 0; +} + +/** + * ice_read_pca9575_reg - read the register from the PCA9575 controller + * @hw: pointer to the hw struct + * @offset: GPIO controller register offset + * @data: pointer to data to be read from the GPIO controller + * + * Return: 0 on success, negative error code otherwise. + */ +int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data) +{ + struct ice_aqc_link_topo_addr link_topo; + __le16 addr; + u16 handle; + int err; + + memset(&link_topo, 0, sizeof(link_topo)); + + err = ice_get_pca9575_handle(hw, &handle); + if (err) + return err; + + link_topo.handle = cpu_to_le16(handle); + link_topo.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, + ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED); + + addr = cpu_to_le16((u16)offset); + + return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL); +} + +/** * ice_aq_set_gpio * @hw: pointer to the hw struct * @gpio_ctrl_handle: GPIO controller node handle @@ -6083,6 +5928,44 @@ bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps) } /** + * ice_is_fw_health_report_supported - checks if firmware supports health events + * @hw: pointer to the hardware structure + * + * Return: true if firmware supports health status reports, + * false otherwise + */ +bool ice_is_fw_health_report_supported(struct ice_hw *hw) +{ + return ice_is_fw_api_min_ver(hw, ICE_FW_API_HEALTH_REPORT_MAJ, + ICE_FW_API_HEALTH_REPORT_MIN, + ICE_FW_API_HEALTH_REPORT_PATCH); +} + +/** + * ice_aq_set_health_status_cfg - Configure FW health events + * @hw: pointer to the HW struct + * @event_source: type of diagnostic events to enable + * + * Configure the health status event types that the firmware will send to this + * PF. The supported event types are: PF-specific, all PFs, and global. + * + * Return: 0 on success, negative error code otherwise. + */ +int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source) +{ + struct ice_aqc_set_health_status_cfg *cmd; + struct ice_aq_desc desc; + + cmd = &desc.params.set_health_status_cfg; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_health_status_cfg); + + cmd->event_source = event_source; + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** * ice_aq_set_lldp_mib - Set the LLDP MIB * @hw: pointer to the HW struct * @mib_type: Local, Remote or both Local and Remote MIBs @@ -6132,15 +6015,21 @@ bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw) /** * ice_lldp_fltr_add_remove - add or remove a LLDP Rx switch filter * @hw: pointer to HW struct - * @vsi_num: absolute HW index for VSI + * @vsi: VSI to add the filter to * @add: boolean for if adding or removing a filter + * + * Return: 0 on success, -EOPNOTSUPP if the operation cannot be performed + * with this HW or VSI, otherwise an error corresponding to + * the AQ transaction result. */ -int -ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add) +int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add) { struct ice_aqc_lldp_filter_ctrl *cmd; struct ice_aq_desc desc; + if (vsi->type != ICE_VSI_PF || !ice_fw_supports_lldp_fltr_ctrl(hw)) + return -EOPNOTSUPP; + cmd = &desc.params.lldp_filter_ctrl; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_filter_ctrl); @@ -6150,7 +6039,7 @@ ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add) else cmd->cmd_flags = ICE_AQC_LLDP_FILTER_ACTION_DELETE; - cmd->vsi_num = cpu_to_le16(vsi_num); + cmd->vsi_num = cpu_to_le16(vsi->vsi_num); return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); } diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index fe6f88cfd948..64c530b39191 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -92,9 +92,8 @@ ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle, bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq); int ice_aq_q_shutdown(struct ice_hw *hw, bool unloading); void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode); -extern const struct ice_ctx_ele ice_tlan_ctx_info[]; -int ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info); + +void ice_pack_txq_ctx(const struct ice_tlan_ctx *ctx, ice_txq_ctx_buf_t *buf); extern struct mutex ice_global_cfg_lock_sw; @@ -113,7 +112,6 @@ int ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps_data *caps, struct ice_sq_cd *cd); -bool ice_is_pf_c827(struct ice_hw *hw); bool ice_is_phy_rclk_in_netlist(struct ice_hw *hw); bool ice_is_clock_mux_in_netlist(struct ice_hw *hw); bool ice_is_cgu_in_netlist(struct ice_hw *hw); @@ -133,7 +131,6 @@ int ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags, struct ice_sq_cd *cd); bool ice_is_generic_mac(struct ice_hw *hw); -bool ice_is_e810(struct ice_hw *hw); int ice_clear_pf_cfg(struct ice_hw *hw); int ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi, @@ -143,6 +140,8 @@ int ice_get_link_default_override(struct ice_link_default_override_tlv *ldo, struct ice_port_info *pi); bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps); +bool ice_is_fw_health_report_supported(struct ice_hw *hw); +int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source); int ice_aq_get_phy_equalization(struct ice_hw *hw, u16 data_in, u16 op_code, u8 serdes_num, int *output); int @@ -276,10 +275,6 @@ ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); -bool ice_is_e810t(struct ice_hw *hw); -bool ice_is_e822(struct ice_hw *hw); -bool ice_is_e823(struct ice_hw *hw); -bool ice_is_e825c(struct ice_hw *hw); int ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, struct ice_aqc_txsched_elem_data *buf); @@ -295,8 +290,7 @@ int ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, struct ice_sq_cd *cd); bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw); -int -ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add); +int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add); int ice_lldp_execute_pending_mib(struct ice_hw *hw); int ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, @@ -306,5 +300,7 @@ int ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, u16 bus_addr, __le16 addr, u8 params, const u8 *data, struct ice_sq_cd *cd); +int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle); +int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data); bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index 74418c445cc4..64737fc62306 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -1288,7 +1288,7 @@ ice_add_dscp_up_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) tlv->ouisubtype = htonl(ouisubtype); /* bytes 0 - 63 - IPv4 DSCP2UP LUT */ - for (i = 0; i < ICE_DSCP_NUM_VAL; i++) { + for (i = 0; i < DSCP_MAX; i++) { /* IPv4 mapping */ buf[i] = dcbcfg->dscp_map[i]; /* IPv6 mapping */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index a7c510832824..533eb8930aa8 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -352,8 +352,8 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) struct ice_aqc_port_ets_elem buf = { 0 }; struct ice_dcbx_cfg *old_cfg, *curr_cfg; struct device *dev = ice_pf_to_dev(pf); + struct iidc_rdma_event *event; int ret = ICE_DCB_NO_HW_CHG; - struct iidc_event *event; struct ice_vsi *pf_vsi; curr_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; @@ -405,7 +405,7 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) goto free_cfg; } - set_bit(IIDC_EVENT_BEFORE_TC_CHANGE, event->type); + set_bit(IIDC_RDMA_EVENT_BEFORE_TC_CHANGE, event->type); ice_send_event_to_aux(pf, event); kfree(event); @@ -740,7 +740,9 @@ static int ice_dcb_noncontig_cfg(struct ice_pf *pf) void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked) { struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; - struct iidc_event *event; + struct iidc_rdma_priv_dev_info *privd; + struct iidc_rdma_core_dev_info *cdev; + struct iidc_rdma_event *event; u8 tc_map = 0; int v, ret; @@ -783,13 +785,17 @@ void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked) if (vsi->type == ICE_VSI_PF) ice_dcbnl_set_all(vsi); } - if (!locked) { + + cdev = pf->cdev_info; + if (cdev && !locked) { + privd = cdev->iidc_priv; + ice_setup_dcb_qos_info(pf, &privd->qos_info); /* Notify the AUX drivers that TC change is finished */ event = kzalloc(sizeof(*event), GFP_KERNEL); if (!event) return; - set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type); + set_bit(IIDC_RDMA_EVENT_AFTER_TC_CHANGE, event->type); ice_send_event_to_aux(pf, event); kfree(event); } @@ -846,7 +852,7 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked) goto dcb_init_err; } - ice_cfg_sw_lldp(pf_vsi, false, true); + ice_cfg_sw_rx_lldp(pf, true); pf->dcbx_cap = ice_dcb_get_mode(port_info, true); return 0; @@ -945,6 +951,37 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, } /** + * ice_setup_dcb_qos_info - Setup DCB QoS information + * @pf: ptr to ice_pf + * @qos_info: QoS param instance + */ +void ice_setup_dcb_qos_info(struct ice_pf *pf, struct iidc_rdma_qos_params *qos_info) +{ + struct ice_dcbx_cfg *dcbx_cfg; + unsigned int i; + u32 up2tc; + + if (!pf || !qos_info) + return; + + dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; + up2tc = rd32(&pf->hw, PRTDCB_TUP2TC); + + qos_info->num_tc = ice_dcb_get_num_tc(dcbx_cfg); + + for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++) + qos_info->up2tc[i] = (up2tc >> (i * 3)) & 0x7; + + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + qos_info->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i]; + + qos_info->pfc_mode = dcbx_cfg->pfc_mode; + if (qos_info->pfc_mode == IIDC_DSCP_PFC_MODE) + for (i = 0; i < DSCP_MAX; i++) + qos_info->dscp_map[i] = dcbx_cfg->dscp_map[i]; +} + +/** * ice_dcb_is_mib_change_pending - Check if MIB change is pending * @state: MIB change state */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h index 800879a88c5e..da9ba814b4e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h @@ -31,6 +31,9 @@ void ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first); void +ice_setup_dcb_qos_info(struct ice_pf *pf, + struct iidc_rdma_qos_params *qos_info); +void ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event); /** @@ -134,5 +137,11 @@ static inline void ice_update_dcb_stats(struct ice_pf *pf) { } static inline void ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event) { } static inline void ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, u8 dcb_tc) { } +static inline void +ice_setup_dcb_qos_info(struct ice_pf *pf, struct iidc_rdma_qos_params *qos_info) +{ + qos_info->num_tc = 1; + qos_info->tc_info[0].rel_bw = 100; +} #endif /* CONFIG_DCB */ #endif /* _ICE_DCB_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index 6d50b90a7359..a10c1c8d8697 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -754,7 +754,7 @@ static int ice_dcbnl_setapp(struct net_device *netdev, struct dcb_app *app) if (!ice_is_feature_supported(pf, ICE_F_DSCP)) return -EOPNOTSUPP; - if (app->protocol >= ICE_DSCP_NUM_VAL) { + if (app->protocol >= DSCP_MAX) { netdev_err(netdev, "DSCP value 0x%04X out of range\n", app->protocol); return -EINVAL; @@ -931,7 +931,7 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app) /* if the last DSCP mapping just got deleted, need to switch * to L2 VLAN QoS mode */ - if (bitmap_empty(new_cfg->dscp_mapped, ICE_DSCP_NUM_VAL) && + if (bitmap_empty(new_cfg->dscp_mapped, DSCP_MAX) && new_cfg->pfc_mode == ICE_QOS_MODE_DSCP) { ret = ice_aq_set_pfc_mode(&pf->hw, ICE_AQC_PFC_VLAN_BASED_PFC, diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index 03988be03729..59323c019544 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -2345,15 +2345,15 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size, cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM | ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW; - if (ice_is_e825c(hw)) - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); } else { ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo); cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM; - } - if (!ice_is_e825c(hw)) - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + if (hw->mac_type == ICE_MAC_E810 || + hw->mac_type == ICE_MAC_GENERIC) + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + } status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); if (status) diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 38e151c7ea23..bce3ad6ca2a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -95,7 +95,7 @@ ice_dpll_pin_freq_set(struct ice_pf *pf, struct ice_dpll_pin *pin, } if (ret) { NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to set pin freq:%u on pin:%u\n", + "err:%d %s failed to set pin freq:%u on pin:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), freq, pin->idx); @@ -322,7 +322,7 @@ ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin, } if (ret) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to enable %s pin:%u\n", + "err:%d %s failed to enable %s pin:%u", ret, ice_aq_str(hw->adminq.sq_last_status), pin_type_name[pin_type], pin->idx); @@ -367,7 +367,7 @@ ice_dpll_pin_disable(struct ice_hw *hw, struct ice_dpll_pin *pin, } if (ret) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to disable %s pin:%u\n", + "err:%d %s failed to disable %s pin:%u", ret, ice_aq_str(hw->adminq.sq_last_status), pin_type_name[pin_type], pin->idx); @@ -479,7 +479,7 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, err: if (extack) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to update %s pin:%u\n", + "err:%d %s failed to update %s pin:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), pin_type_name[pin_type], pin->idx); @@ -518,7 +518,7 @@ ice_dpll_hw_input_prio_set(struct ice_pf *pf, struct ice_dpll *dpll, (u8)prio); if (ret) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to set pin prio:%u on pin:%u\n", + "err:%d %s failed to set pin prio:%u on pin:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), prio, pin->idx); @@ -1004,7 +1004,7 @@ ice_dpll_pin_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv, mutex_unlock(&pf->dplls.lock); if (ret) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to set pin phase_adjust:%d for pin:%u on dpll:%u\n", + "err:%d %s failed to set pin phase_adjust:%d for pin:%u on dpll:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), phase_adjust, p->idx, d->dpll_idx); @@ -1362,7 +1362,7 @@ ice_dpll_rclk_state_on_pin_set(const struct dpll_pin *pin, void *pin_priv, &p->freq); if (ret) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to set pin state:%u for pin:%u on parent:%u\n", + "err:%d %s failed to set pin state:%u for pin:%u on parent:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), state, p->idx, parent->idx); @@ -2053,7 +2053,7 @@ static int ice_dpll_init_worker(struct ice_pf *pf) struct kthread_worker *kworker; kthread_init_delayed_work(&d->work, ice_dpll_periodic_work); - kworker = kthread_create_worker(0, "ice-dplls-%s", + kworker = kthread_run_worker(0, "ice-dplls-%s", dev_name(ice_pf_to_dev(pf))); if (IS_ERR(kworker)) return PTR_ERR(kworker); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index fb527434b58b..6aae03771746 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -29,6 +29,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) return -ENODEV; ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx); + ice_vsi_cfg_sw_lldp(uplink_vsi, true, false); netif_addr_lock_bh(netdev); __dev_uc_unsync(netdev, NULL); @@ -38,8 +39,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) if (ice_vsi_add_vlan_zero(uplink_vsi)) goto err_vlan_zero; - if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true, - ICE_FLTR_RX)) + if (ice_set_dflt_vsi(uplink_vsi)) goto err_def_rx; if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true, @@ -50,9 +50,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) if (vlan_ops->dis_rx_filtering(uplink_vsi)) goto err_vlan_filtering; - if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override)) - goto err_override_uplink; - if (ice_vsi_update_local_lb(uplink_vsi, true)) goto err_override_local_lb; @@ -64,8 +61,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) err_up: ice_vsi_update_local_lb(uplink_vsi, false); err_override_local_lb: - ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); -err_override_uplink: vlan_ops->ena_rx_filtering(uplink_vsi); err_vlan_filtering: ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false, @@ -251,6 +246,10 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb, u64 cd_cmd, dst_vsi; if (!dst) { + struct ethhdr *eth = (struct ethhdr *)skb_mac_header(skb); + + if (unlikely(eth->h_proto == htons(ETH_P_LLDP))) + return; cd_cmd = ICE_TX_CTX_DESC_SWTCH_UPLINK << ICE_TXD_CTX_QW1_CMD_S; off->cd_qw1 |= (cd_cmd | ICE_TX_DESC_DTYPE_CTX); } else { @@ -276,7 +275,6 @@ static void ice_eswitch_release_env(struct ice_pf *pf) vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi); ice_vsi_update_local_lb(uplink_vsi, false); - ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); vlan_ops->ena_rx_filtering(uplink_vsi); ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false, ICE_FLTR_TX); @@ -285,6 +283,7 @@ static void ice_eswitch_release_env(struct ice_pf *pf) ice_fltr_add_mac_and_broadcast(uplink_vsi, uplink_vsi->port_info->mac.perm_addr, ICE_FWD_TO_VSI); + ice_vsi_cfg_sw_lldp(uplink_vsi, true, true); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h index ac7db100e2cd..5c7dcf21b222 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h @@ -5,7 +5,7 @@ #define _ICE_ESWITCH_H_ #include <net/devlink.h> -#include "devlink/devlink_port.h" +#include "devlink/port.h" #ifdef CONFIG_ICE_SWITCHDEV void ice_eswitch_detach_vf(struct ice_pf *pf, struct ice_vf *vf); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 3072634bf049..bbf9e6fd315b 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -710,7 +710,6 @@ static int ice_get_tx_rx_equa(struct ice_hw *hw, u8 serdes_num, { ICE_AQC_RX_EQU_POST1, rx, &ptr->rx_equ_post1 }, { ICE_AQC_RX_EQU_BFLF, rx, &ptr->rx_equ_bflf }, { ICE_AQC_RX_EQU_BFHF, rx, &ptr->rx_equ_bfhf }, - { ICE_AQC_RX_EQU_DRATE, rx, &ptr->rx_equ_drate }, { ICE_AQC_RX_EQU_CTLE_GAINHF, rx, &ptr->rx_equ_ctle_gainhf }, { ICE_AQC_RX_EQU_CTLE_GAINLF, rx, &ptr->rx_equ_ctle_gainlf }, { ICE_AQC_RX_EQU_CTLE_GAINDC, rx, &ptr->rx_equ_ctle_gaindc }, @@ -1819,7 +1818,7 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) /* Remove rule to direct LLDP packets to default VSI. * The FW LLDP engine will now be consuming them. */ - ice_cfg_sw_lldp(vsi, false, false); + ice_cfg_sw_rx_lldp(vsi->back, false); /* AQ command to start FW LLDP agent will return an * error if the agent is already started @@ -3789,8 +3788,7 @@ ice_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) */ static int ice_get_max_txq(struct ice_pf *pf) { - return min3(pf->num_lan_msix, (u16)num_online_cpus(), - (u16)pf->hw.func_caps.common_cap.num_txq); + return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_txq); } /** @@ -3799,8 +3797,7 @@ static int ice_get_max_txq(struct ice_pf *pf) */ static int ice_get_max_rxq(struct ice_pf *pf) { - return min3(pf->num_lan_msix, (u16)num_online_cpus(), - (u16)pf->hw.func_caps.common_cap.num_rxq); + return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_rxq); } /** @@ -3818,8 +3815,7 @@ static u32 ice_get_combined_cnt(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, q_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[q_idx]; - if (q_vector->rx.rx_ring && q_vector->tx.tx_ring) - combined++; + combined += min(q_vector->num_ring_tx, q_vector->num_ring_rx); } return combined; @@ -3968,11 +3964,11 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) return -EINVAL; } - if (pf->adev) { + if (pf->cdev_info && pf->cdev_info->adev) { mutex_lock(&pf->adev_mutex); - device_lock(&pf->adev->dev); + device_lock(&pf->cdev_info->adev->dev); locked = true; - if (pf->adev->dev.driver) { + if (pf->cdev_info->adev->dev.driver) { netdev_err(dev, "Cannot change channels when RDMA is active\n"); ret = -EBUSY; goto adev_unlock; @@ -3991,7 +3987,7 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) adev_unlock: if (locked) { - device_unlock(&pf->adev->dev); + device_unlock(&pf->cdev_info->adev->dev); mutex_unlock(&pf->adev_mutex); } return ret; @@ -4774,7 +4770,7 @@ static const struct ethtool_ops ice_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE | ETHTOOL_COALESCE_RX_USECS_HIGH, - .cap_rss_sym_xor_supported = true, + .supported_input_xfrm = RXH_XFRM_SYM_XOR, .rxfh_per_ctx_key = true, .get_link_ksettings = ice_get_link_ksettings, .set_link_ksettings = ice_set_link_ksettings, diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.h b/drivers/net/ethernet/intel/ice/ice_ethtool.h index 8f2ad1c172c0..23b2cfbc9684 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.h +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.h @@ -15,7 +15,6 @@ struct ice_serdes_equalization_to_ethtool { int rx_equ_post1; int rx_equ_bflf; int rx_equ_bfhf; - int rx_equ_drate; int rx_equ_ctle_gainhf; int rx_equ_ctle_gainlf; int rx_equ_ctle_gaindc; diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index ee9862ddfe15..aceec184e89b 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -1605,22 +1605,19 @@ void ice_fdir_replay_fltrs(struct ice_pf *pf) */ int ice_fdir_create_dflt_rules(struct ice_pf *pf) { + static const enum ice_fltr_ptype dflt_rules[] = { + ICE_FLTR_PTYPE_NONF_IPV4_TCP, ICE_FLTR_PTYPE_NONF_IPV4_UDP, + ICE_FLTR_PTYPE_NONF_IPV6_TCP, ICE_FLTR_PTYPE_NONF_IPV6_UDP, + }; int err; /* Create perfect TCP and UDP rules in hardware. */ - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_TCP); - if (err) - return err; - - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_UDP); - if (err) - return err; + for (int i = 0; i < ARRAY_SIZE(dflt_rules); i++) { + err = ice_create_init_fdir_rule(pf, dflt_rules[i]); - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_TCP); - if (err) - return err; - - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_UDP); + if (err) + break; + } return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index 2702a0da5c3e..70c201f569ce 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -6,6 +6,7 @@ #include <linux/crc32.h> #include <linux/pldmfw.h> #include "ice.h" +#include "ice_lib.h" #include "ice_fw_update.h" struct ice_fwu_priv { @@ -125,6 +126,10 @@ ice_check_component_response(struct ice_pf *pf, u16 id, u8 response, u8 code, case ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED: dev_info(dev, "firmware has rejected updating %s\n", component); break; + case ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK: + if (ice_is_recovery_mode(&pf->hw)) + return 0; + break; } switch (code) { @@ -1004,13 +1009,20 @@ int ice_devlink_flash_update(struct devlink *devlink, return -EOPNOTSUPP; } - if (!hw->dev_caps.common_cap.nvm_unified_update) { + if (!hw->dev_caps.common_cap.nvm_unified_update && !ice_is_recovery_mode(hw)) { NL_SET_ERR_MSG_MOD(extack, "Current firmware does not support unified update"); return -EOPNOTSUPP; } memset(&priv, 0, sizeof(priv)); + if (params->component && strcmp(params->component, "fw.mgmt") == 0) { + priv.context.mode = PLDMFW_UPDATE_MODE_SINGLE_COMPONENT; + priv.context.component_identifier = NVM_COMP_ID_NVM; + } else if (params->component) { + return -EOPNOTSUPP; + } + /* the E822 device needs a slightly different ops */ if (hw->mac_type == ICE_MAC_GENERIC) priv.context.ops = &ice_fwu_ops_e822; diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index f02e8ca55375..6b26290452d4 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -182,7 +182,7 @@ static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf) pf->gnss_serial = gnss; kthread_init_delayed_work(&gnss->read_work, ice_gnss_read); - kworker = kthread_create_worker(0, "ice-gnss-%s", dev_name(dev)); + kworker = kthread_run_worker(0, "ice-gnss-%s", dev_name(dev)); if (IS_ERR(kworker)) { kfree(gnss); return NULL; @@ -381,32 +381,23 @@ void ice_gnss_exit(struct ice_pf *pf) } /** - * ice_gnss_is_gps_present - Check if GPS HW is present + * ice_gnss_is_module_present - Check if GNSS HW is present * @hw: pointer to HW struct + * + * Return: true when GNSS is present, false otherwise. */ -bool ice_gnss_is_gps_present(struct ice_hw *hw) +bool ice_gnss_is_module_present(struct ice_hw *hw) { - if (!hw->func_caps.ts_func_info.src_tmr_owned) - return false; + int err; + u8 data; - if (!ice_is_gps_in_netlist(hw)) + if (!hw->func_caps.ts_func_info.src_tmr_owned || + !ice_is_gps_in_netlist(hw)) return false; -#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) - if (ice_is_e810t(hw)) { - int err; - u8 data; - - err = ice_read_pca9575_reg(hw, ICE_PCA9575_P0_IN, &data); - if (err || !!(data & ICE_P0_GNSS_PRSNT_N)) - return false; - } else { - return false; - } -#else - if (!ice_is_e810t(hw)) + err = ice_read_pca9575_reg(hw, ICE_PCA9575_P0_IN, &data); + if (err || !!(data & ICE_P0_GNSS_PRSNT_N)) return false; -#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ return true; } diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.h b/drivers/net/ethernet/intel/ice/ice_gnss.h index 75e567ad7059..15daf603ed7b 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.h +++ b/drivers/net/ethernet/intel/ice/ice_gnss.h @@ -37,11 +37,11 @@ struct gnss_serial { #if IS_ENABLED(CONFIG_GNSS) void ice_gnss_init(struct ice_pf *pf); void ice_gnss_exit(struct ice_pf *pf); -bool ice_gnss_is_gps_present(struct ice_hw *hw); +bool ice_gnss_is_module_present(struct ice_hw *hw); #else static inline void ice_gnss_init(struct ice_pf *pf) { } static inline void ice_gnss_exit(struct ice_pf *pf) { } -static inline bool ice_gnss_is_gps_present(struct ice_hw *hw) +static inline bool ice_gnss_is_module_present(struct ice_hw *hw) { return false; } diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index dc88aea9f473..aa4bfbcf85d2 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -541,10 +541,22 @@ #define PFPM_WUS_MAG_M BIT(1) #define PFPM_WUS_MNG_M BIT(3) #define PFPM_WUS_FW_RST_WK_M BIT(31) +#define E830_PRTMAC_TS_TX_MEM_VALID_H 0x001E2020 +#define E830_PRTMAC_TS_TX_MEM_VALID_L 0x001E2000 #define E830_PRTMAC_CL01_PS_QNT 0x001E32A0 #define E830_PRTMAC_CL01_PS_QNT_CL0_M GENMASK(15, 0) #define E830_PRTMAC_CL01_QNT_THR 0x001E3320 #define E830_PRTMAC_CL01_QNT_THR_CL0_M GENMASK(15, 0) +#define E830_PRTTSYN_TXTIME_H(_i) (0x001E5800 + ((_i) * 32)) +#define E830_PRTTSYN_TXTIME_L(_i) (0x001E5000 + ((_i) * 32)) +#define E830_GLPTM_ART_CTL 0x00088B50 +#define E830_GLPTM_ART_CTL_ACTIVE_M BIT(0) +#define E830_GLPTM_ART_TIME_H 0x00088B54 +#define E830_GLPTM_ART_TIME_L 0x00088B58 +#define E830_GLTSYN_PTMTIME_H(_i) (0x00088B48 + ((_i) * 4)) +#define E830_GLTSYN_PTMTIME_L(_i) (0x00088B40 + ((_i) * 4)) +#define E830_PFPTM_SEM 0x00088B00 +#define E830_PFPTM_SEM_BUSY_M BIT(0) #define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4)) #define VFINT_DYN_CTLN_CLEARPBA_M BIT(1) #define E830_MBX_PF_IN_FLIGHT_VF_MSGS_THRESH 0x00234000 diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index 145b27f2a4ce..6ab53e430f91 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -9,22 +9,25 @@ static DEFINE_XARRAY_ALLOC1(ice_aux_id); /** - * ice_get_auxiliary_drv - retrieve iidc_auxiliary_drv struct - * @pf: pointer to PF struct + * ice_get_auxiliary_drv - retrieve iidc_rdma_core_auxiliary_drv struct + * @cdev: pointer to iidc_rdma_core_dev_info struct * * This function has to be called with a device_lock on the - * pf->adev.dev to avoid race conditions. + * cdev->adev.dev to avoid race conditions. + * + * Return: pointer to the matched auxiliary driver struct */ -static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf) +static struct iidc_rdma_core_auxiliary_drv * +ice_get_auxiliary_drv(struct iidc_rdma_core_dev_info *cdev) { struct auxiliary_device *adev; - adev = pf->adev; + adev = cdev->adev; if (!adev || !adev->dev.driver) return NULL; - return container_of(adev->dev.driver, struct iidc_auxiliary_drv, - adrv.driver); + return container_of(adev->dev.driver, + struct iidc_rdma_core_auxiliary_drv, adrv.driver); } /** @@ -32,44 +35,54 @@ static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf) * @pf: pointer to PF struct * @event: event struct */ -void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event) +void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_rdma_event *event) { - struct iidc_auxiliary_drv *iadrv; + struct iidc_rdma_core_auxiliary_drv *iadrv; + struct iidc_rdma_core_dev_info *cdev; if (WARN_ON_ONCE(!in_task())) return; + cdev = pf->cdev_info; + if (!cdev) + return; + mutex_lock(&pf->adev_mutex); - if (!pf->adev) + if (!cdev->adev) goto finish; - device_lock(&pf->adev->dev); - iadrv = ice_get_auxiliary_drv(pf); + device_lock(&cdev->adev->dev); + iadrv = ice_get_auxiliary_drv(cdev); if (iadrv && iadrv->event_handler) - iadrv->event_handler(pf, event); - device_unlock(&pf->adev->dev); + iadrv->event_handler(cdev, event); + device_unlock(&cdev->adev->dev); finish: mutex_unlock(&pf->adev_mutex); } /** * ice_add_rdma_qset - Add Leaf Node for RDMA Qset - * @pf: PF struct + * @cdev: pointer to iidc_rdma_core_dev_info struct * @qset: Resource to be allocated + * + * Return: Zero on success or error code encountered */ -int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) +int ice_add_rdma_qset(struct iidc_rdma_core_dev_info *cdev, + struct iidc_rdma_qset_params *qset) { u16 max_rdmaqs[ICE_MAX_TRAFFIC_CLASS]; struct ice_vsi *vsi; struct device *dev; + struct ice_pf *pf; u32 qset_teid; u16 qs_handle; int status; int i; - if (WARN_ON(!pf || !qset)) + if (WARN_ON(!cdev || !qset)) return -EINVAL; + pf = pci_get_drvdata(cdev->pdev); dev = ice_pf_to_dev(pf); if (!ice_is_rdma_ena(pf)) @@ -100,7 +113,6 @@ int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) dev_err(dev, "Failed VSI RDMA Qset enable\n"); return status; } - vsi->qset_handle[qset->tc] = qset->qs_handle; qset->teid = qset_teid; return 0; @@ -109,18 +121,23 @@ EXPORT_SYMBOL_GPL(ice_add_rdma_qset); /** * ice_del_rdma_qset - Delete leaf node for RDMA Qset - * @pf: PF struct + * @cdev: pointer to iidc_rdma_core_dev_info struct * @qset: Resource to be freed + * + * Return: Zero on success, error code on failure */ -int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) +int ice_del_rdma_qset(struct iidc_rdma_core_dev_info *cdev, + struct iidc_rdma_qset_params *qset) { struct ice_vsi *vsi; + struct ice_pf *pf; u32 teid; u16 q_id; - if (WARN_ON(!pf || !qset)) + if (WARN_ON(!cdev || !qset)) return -EINVAL; + pf = pci_get_drvdata(cdev->pdev); vsi = ice_find_vsi(pf, qset->vport_id); if (!vsi) { dev_err(ice_pf_to_dev(pf), "RDMA Invalid VSI\n"); @@ -130,36 +147,36 @@ int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) q_id = qset->qs_handle; teid = qset->teid; - vsi->qset_handle[qset->tc] = 0; - return ice_dis_vsi_rdma_qset(vsi->port_info, 1, &teid, &q_id); } EXPORT_SYMBOL_GPL(ice_del_rdma_qset); /** * ice_rdma_request_reset - accept request from RDMA to perform a reset - * @pf: struct for PF + * @cdev: pointer to iidc_rdma_core_dev_info struct * @reset_type: type of reset + * + * Return: Zero on success, error code on failure */ -int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type) +int ice_rdma_request_reset(struct iidc_rdma_core_dev_info *cdev, + enum iidc_rdma_reset_type reset_type) { enum ice_reset_req reset; + struct ice_pf *pf; - if (WARN_ON(!pf)) + if (WARN_ON(!cdev)) return -EINVAL; + pf = pci_get_drvdata(cdev->pdev); + switch (reset_type) { - case IIDC_PFR: + case IIDC_FUNC_RESET: reset = ICE_RESET_PFR; break; - case IIDC_CORER: + case IIDC_DEV_RESET: reset = ICE_RESET_CORER; break; - case IIDC_GLOBR: - reset = ICE_RESET_GLOBR; - break; default: - dev_err(ice_pf_to_dev(pf), "incorrect reset request\n"); return -EINVAL; } @@ -169,18 +186,23 @@ EXPORT_SYMBOL_GPL(ice_rdma_request_reset); /** * ice_rdma_update_vsi_filter - update main VSI filters for RDMA - * @pf: pointer to struct for PF + * @cdev: pointer to iidc_rdma_core_dev_info struct * @vsi_id: VSI HW idx to update filter on * @enable: bool whether to enable or disable filters + * + * Return: Zero on success, error code on failure */ -int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable) +int ice_rdma_update_vsi_filter(struct iidc_rdma_core_dev_info *cdev, + u16 vsi_id, bool enable) { struct ice_vsi *vsi; + struct ice_pf *pf; int status; - if (WARN_ON(!pf)) + if (WARN_ON(!cdev)) return -EINVAL; + pf = pci_get_drvdata(cdev->pdev); vsi = ice_find_vsi(pf, vsi_id); if (!vsi) return -EINVAL; @@ -201,88 +223,54 @@ int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable) EXPORT_SYMBOL_GPL(ice_rdma_update_vsi_filter); /** - * ice_get_qos_params - parse QoS params for RDMA consumption - * @pf: pointer to PF struct - * @qos: set of QoS values - */ -void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos) -{ - struct ice_dcbx_cfg *dcbx_cfg; - unsigned int i; - u32 up2tc; - - dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; - up2tc = rd32(&pf->hw, PRTDCB_TUP2TC); - - qos->num_tc = ice_dcb_get_num_tc(dcbx_cfg); - for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++) - qos->up2tc[i] = (up2tc >> (i * 3)) & 0x7; - - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - qos->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i]; - - qos->pfc_mode = dcbx_cfg->pfc_mode; - if (qos->pfc_mode == IIDC_DSCP_PFC_MODE) - for (i = 0; i < IIDC_MAX_DSCP_MAPPING; i++) - qos->dscp_map[i] = dcbx_cfg->dscp_map[i]; -} -EXPORT_SYMBOL_GPL(ice_get_qos_params); - -/** - * ice_alloc_rdma_qvectors - Allocate vector resources for RDMA driver - * @pf: board private structure to initialize + * ice_alloc_rdma_qvector - alloc vector resources reserved for RDMA driver + * @cdev: pointer to iidc_rdma_core_dev_info struct + * @entry: MSI-X entry to be removed + * + * Return: Zero on success, error code on failure */ -static int ice_alloc_rdma_qvectors(struct ice_pf *pf) +int ice_alloc_rdma_qvector(struct iidc_rdma_core_dev_info *cdev, + struct msix_entry *entry) { - if (ice_is_rdma_ena(pf)) { - int i; - - pf->msix_entries = kcalloc(pf->num_rdma_msix, - sizeof(*pf->msix_entries), - GFP_KERNEL); - if (!pf->msix_entries) - return -ENOMEM; + struct msi_map map; + struct ice_pf *pf; - /* RDMA is the only user of pf->msix_entries array */ - pf->rdma_base_vector = 0; + if (WARN_ON(!cdev)) + return -EINVAL; - for (i = 0; i < pf->num_rdma_msix; i++) { - struct msix_entry *entry = &pf->msix_entries[i]; - struct msi_map map; + pf = pci_get_drvdata(cdev->pdev); + map = ice_alloc_irq(pf, true); + if (map.index < 0) + return -ENOMEM; - map = ice_alloc_irq(pf, false); - if (map.index < 0) - break; + entry->entry = map.index; + entry->vector = map.virq; - entry->entry = map.index; - entry->vector = map.virq; - } - } return 0; } +EXPORT_SYMBOL_GPL(ice_alloc_rdma_qvector); /** * ice_free_rdma_qvector - free vector resources reserved for RDMA driver - * @pf: board private structure to initialize + * @cdev: pointer to iidc_rdma_core_dev_info struct + * @entry: MSI-X entry to be removed */ -static void ice_free_rdma_qvector(struct ice_pf *pf) +void ice_free_rdma_qvector(struct iidc_rdma_core_dev_info *cdev, + struct msix_entry *entry) { - int i; + struct msi_map map; + struct ice_pf *pf; - if (!pf->msix_entries) + if (WARN_ON(!cdev || !entry)) return; - for (i = 0; i < pf->num_rdma_msix; i++) { - struct msi_map map; - - map.index = pf->msix_entries[i].entry; - map.virq = pf->msix_entries[i].vector; - ice_free_irq(pf, map); - } + pf = pci_get_drvdata(cdev->pdev); - kfree(pf->msix_entries); - pf->msix_entries = NULL; + map.index = entry->entry; + map.virq = entry->vector; + ice_free_irq(pf, map); } +EXPORT_SYMBOL_GPL(ice_free_rdma_qvector); /** * ice_adev_release - function to be mapped to AUX dev's release op @@ -290,19 +278,23 @@ static void ice_free_rdma_qvector(struct ice_pf *pf) */ static void ice_adev_release(struct device *dev) { - struct iidc_auxiliary_dev *iadev; + struct iidc_rdma_core_auxiliary_dev *iadev; - iadev = container_of(dev, struct iidc_auxiliary_dev, adev.dev); + iadev = container_of(dev, struct iidc_rdma_core_auxiliary_dev, + adev.dev); kfree(iadev); } /** * ice_plug_aux_dev - allocate and register AUX device * @pf: pointer to pf struct + * + * Return: Zero on success, error code on failure */ int ice_plug_aux_dev(struct ice_pf *pf) { - struct iidc_auxiliary_dev *iadev; + struct iidc_rdma_core_auxiliary_dev *iadev; + struct iidc_rdma_core_dev_info *cdev; struct auxiliary_device *adev; int ret; @@ -312,17 +304,22 @@ int ice_plug_aux_dev(struct ice_pf *pf) if (!ice_is_rdma_ena(pf)) return 0; + cdev = pf->cdev_info; + if (!cdev) + return -ENODEV; + iadev = kzalloc(sizeof(*iadev), GFP_KERNEL); if (!iadev) return -ENOMEM; adev = &iadev->adev; - iadev->pf = pf; + iadev->cdev_info = cdev; adev->id = pf->aux_idx; adev->dev.release = ice_adev_release; adev->dev.parent = &pf->pdev->dev; - adev->name = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ? "roce" : "iwarp"; + adev->name = cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2 ? + "roce" : "iwarp"; ret = auxiliary_device_init(adev); if (ret) { @@ -337,7 +334,7 @@ int ice_plug_aux_dev(struct ice_pf *pf) } mutex_lock(&pf->adev_mutex); - pf->adev = adev; + cdev->adev = adev; mutex_unlock(&pf->adev_mutex); return 0; @@ -351,8 +348,8 @@ void ice_unplug_aux_dev(struct ice_pf *pf) struct auxiliary_device *adev; mutex_lock(&pf->adev_mutex); - adev = pf->adev; - pf->adev = NULL; + adev = pf->cdev_info->adev; + pf->cdev_info->adev = NULL; mutex_unlock(&pf->adev_mutex); if (adev) { @@ -367,7 +364,9 @@ void ice_unplug_aux_dev(struct ice_pf *pf) */ int ice_init_rdma(struct ice_pf *pf) { + struct iidc_rdma_priv_dev_info *privd; struct device *dev = &pf->pdev->dev; + struct iidc_rdma_core_dev_info *cdev; int ret; if (!ice_is_rdma_ena(pf)) { @@ -375,30 +374,50 @@ int ice_init_rdma(struct ice_pf *pf) return 0; } + cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); + if (!cdev) + return -ENOMEM; + + pf->cdev_info = cdev; + + privd = kzalloc(sizeof(*privd), GFP_KERNEL); + if (!privd) { + ret = -ENOMEM; + goto err_privd_alloc; + } + + privd->pf_id = pf->hw.pf_id; ret = xa_alloc(&ice_aux_id, &pf->aux_idx, NULL, XA_LIMIT(1, INT_MAX), GFP_KERNEL); if (ret) { dev_err(dev, "Failed to allocate device ID for AUX driver\n"); - return -ENOMEM; + ret = -ENOMEM; + goto err_alloc_xa; } - /* Reserve vector resources */ - ret = ice_alloc_rdma_qvectors(pf); - if (ret < 0) { - dev_err(dev, "failed to reserve vectors for RDMA\n"); - goto err_reserve_rdma_qvector; - } - pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2; + cdev->iidc_priv = privd; + privd->netdev = pf->vsi[0]->netdev; + + privd->hw_addr = (u8 __iomem *)pf->hw.hw_addr; + cdev->pdev = pf->pdev; + privd->vport_id = pf->vsi[0]->vsi_num; + + pf->cdev_info->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2; + ice_setup_dcb_qos_info(pf, &privd->qos_info); ret = ice_plug_aux_dev(pf); if (ret) goto err_plug_aux_dev; return 0; err_plug_aux_dev: - ice_free_rdma_qvector(pf); -err_reserve_rdma_qvector: - pf->adev = NULL; + pf->cdev_info->adev = NULL; xa_erase(&ice_aux_id, pf->aux_idx); +err_alloc_xa: + kfree(privd); +err_privd_alloc: + kfree(cdev); + pf->cdev_info = NULL; + return ret; } @@ -412,6 +431,8 @@ void ice_deinit_rdma(struct ice_pf *pf) return; ice_unplug_aux_dev(pf); - ice_free_rdma_qvector(pf); xa_erase(&ice_aux_id, pf->aux_idx); + kfree(pf->cdev_info->iidc_priv); + kfree(pf->cdev_info); + pf->cdev_info = NULL; } diff --git a/drivers/net/ethernet/intel/ice/ice_idc_int.h b/drivers/net/ethernet/intel/ice/ice_idc_int.h index 4b0c86757df9..17dbfcfb6a2a 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc_int.h +++ b/drivers/net/ethernet/intel/ice/ice_idc_int.h @@ -4,10 +4,11 @@ #ifndef _ICE_IDC_INT_H_ #define _ICE_IDC_INT_H_ -#include <linux/net/intel/iidc.h> +#include <linux/net/intel/iidc_rdma.h> +#include <linux/net/intel/iidc_rdma_ice.h> struct ice_pf; -void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event); +void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_rdma_event *event); #endif /* !_ICE_IDC_INT_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c index ad82ff7d1995..30801fd375f0 100644 --- a/drivers/net/ethernet/intel/ice/ice_irq.c +++ b/drivers/net/ethernet/intel/ice/ice_irq.c @@ -20,6 +20,19 @@ ice_init_irq_tracker(struct ice_pf *pf, unsigned int max_vectors, xa_init_flags(&pf->irq_tracker.entries, XA_FLAGS_ALLOC); } +static int +ice_init_virt_irq_tracker(struct ice_pf *pf, u32 base, u32 num_entries) +{ + pf->virt_irq_tracker.bm = bitmap_zalloc(num_entries, GFP_KERNEL); + if (!pf->virt_irq_tracker.bm) + return -ENOMEM; + + pf->virt_irq_tracker.num_entries = num_entries; + pf->virt_irq_tracker.base = base; + + return 0; +} + /** * ice_deinit_irq_tracker - free xarray tracker * @pf: board private structure @@ -29,6 +42,11 @@ static void ice_deinit_irq_tracker(struct ice_pf *pf) xa_destroy(&pf->irq_tracker.entries); } +static void ice_deinit_virt_irq_tracker(struct ice_pf *pf) +{ + bitmap_free(pf->virt_irq_tracker.bm); +} + /** * ice_free_irq_res - free a block of resources * @pf: board private structure @@ -45,7 +63,7 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index) /** * ice_get_irq_res - get an interrupt resource * @pf: board private structure - * @dyn_only: force entry to be dynamically allocated + * @dyn_allowed: allow entry to be dynamically allocated * * Allocate new irq entry in the free slot of the tracker. Since xarray * is used, always allocate new entry at the lowest possible index. Set @@ -53,11 +71,12 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index) * * Returns allocated irq entry or NULL on failure. */ -static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only) +static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, + bool dyn_allowed) { - struct xa_limit limit = { .max = pf->irq_tracker.num_entries, + struct xa_limit limit = { .max = pf->irq_tracker.num_entries - 1, .min = 0 }; - unsigned int num_static = pf->irq_tracker.num_static; + unsigned int num_static = pf->irq_tracker.num_static - 1; struct ice_irq_entry *entry; unsigned int index; int ret; @@ -66,9 +85,9 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only) if (!entry) return NULL; - /* skip preallocated entries if the caller says so */ - if (dyn_only) - limit.min = num_static; + /* only already allocated if the caller says so */ + if (!dyn_allowed) + limit.max = num_static; ret = xa_alloc(&pf->irq_tracker.entries, &index, entry, limit, GFP_KERNEL); @@ -78,161 +97,18 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only) entry = NULL; } else { entry->index = index; - entry->dynamic = index >= num_static; + entry->dynamic = index > num_static; } return entry; } -/** - * ice_reduce_msix_usage - Reduce usage of MSI-X vectors - * @pf: board private structure - * @v_remain: number of remaining MSI-X vectors to be distributed - * - * Reduce the usage of MSI-X vectors when entire request cannot be fulfilled. - * pf->num_lan_msix and pf->num_rdma_msix values are set based on number of - * remaining vectors. - */ -static void ice_reduce_msix_usage(struct ice_pf *pf, int v_remain) -{ - int v_rdma; - - if (!ice_is_rdma_ena(pf)) { - pf->num_lan_msix = v_remain; - return; - } - - /* RDMA needs at least 1 interrupt in addition to AEQ MSIX */ - v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1; - - if (v_remain < ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_RDMA_MSIX) { - dev_warn(ice_pf_to_dev(pf), "Not enough MSI-X vectors to support RDMA.\n"); - clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); - - pf->num_rdma_msix = 0; - pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX; - } else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) || - (v_remain - v_rdma < v_rdma)) { - /* Support minimum RDMA and give remaining vectors to LAN MSIX - */ - pf->num_rdma_msix = ICE_MIN_RDMA_MSIX; - pf->num_lan_msix = v_remain - ICE_MIN_RDMA_MSIX; - } else { - /* Split remaining MSIX with RDMA after accounting for AEQ MSIX - */ - pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 + - ICE_RDMA_NUM_AEQ_MSIX; - pf->num_lan_msix = v_remain - pf->num_rdma_msix; - } -} - -/** - * ice_ena_msix_range - Request a range of MSIX vectors from the OS - * @pf: board private structure - * - * Compute the number of MSIX vectors wanted and request from the OS. Adjust - * device usage if there are not enough vectors. Return the number of vectors - * reserved or negative on failure. - */ -static int ice_ena_msix_range(struct ice_pf *pf) +#define ICE_RDMA_AEQ_MSIX 1 +static int ice_get_default_msix_amount(struct ice_pf *pf) { - int num_cpus, hw_num_msix, v_other, v_wanted, v_actual; - struct device *dev = ice_pf_to_dev(pf); - int err; - - hw_num_msix = pf->hw.func_caps.common_cap.num_msix_vectors; - num_cpus = num_online_cpus(); - - /* LAN miscellaneous handler */ - v_other = ICE_MIN_LAN_OICR_MSIX; - - /* Flow Director */ - if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) - v_other += ICE_FDIR_MSIX; - - /* switchdev */ - v_other += ICE_ESWITCH_MSIX; - - v_wanted = v_other; - - /* LAN traffic */ - pf->num_lan_msix = num_cpus; - v_wanted += pf->num_lan_msix; - - /* RDMA auxiliary driver */ - if (ice_is_rdma_ena(pf)) { - pf->num_rdma_msix = num_cpus + ICE_RDMA_NUM_AEQ_MSIX; - v_wanted += pf->num_rdma_msix; - } - - if (v_wanted > hw_num_msix) { - int v_remain; - - dev_warn(dev, "not enough device MSI-X vectors. wanted = %d, available = %d\n", - v_wanted, hw_num_msix); - - if (hw_num_msix < ICE_MIN_MSIX) { - err = -ERANGE; - goto exit_err; - } - - v_remain = hw_num_msix - v_other; - if (v_remain < ICE_MIN_LAN_TXRX_MSIX) { - v_other = ICE_MIN_MSIX - ICE_MIN_LAN_TXRX_MSIX; - v_remain = ICE_MIN_LAN_TXRX_MSIX; - } - - ice_reduce_msix_usage(pf, v_remain); - v_wanted = pf->num_lan_msix + pf->num_rdma_msix + v_other; - - dev_notice(dev, "Reducing request to %d MSI-X vectors for LAN traffic.\n", - pf->num_lan_msix); - if (ice_is_rdma_ena(pf)) - dev_notice(dev, "Reducing request to %d MSI-X vectors for RDMA.\n", - pf->num_rdma_msix); - } - - /* actually reserve the vectors */ - v_actual = pci_alloc_irq_vectors(pf->pdev, ICE_MIN_MSIX, v_wanted, - PCI_IRQ_MSIX); - if (v_actual < 0) { - dev_err(dev, "unable to reserve MSI-X vectors\n"); - err = v_actual; - goto exit_err; - } - - if (v_actual < v_wanted) { - dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n", - v_wanted, v_actual); - - if (v_actual < ICE_MIN_MSIX) { - /* error if we can't get minimum vectors */ - pci_free_irq_vectors(pf->pdev); - err = -ERANGE; - goto exit_err; - } else { - int v_remain = v_actual - v_other; - - if (v_remain < ICE_MIN_LAN_TXRX_MSIX) - v_remain = ICE_MIN_LAN_TXRX_MSIX; - - ice_reduce_msix_usage(pf, v_remain); - - dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n", - pf->num_lan_msix); - - if (ice_is_rdma_ena(pf)) - dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n", - pf->num_rdma_msix); - } - } - - return v_actual; - -exit_err: - pf->num_rdma_msix = 0; - pf->num_lan_msix = 0; - return err; + return ICE_MIN_LAN_OICR_MSIX + num_online_cpus() + + (test_bit(ICE_FLAG_FD_ENA, pf->flags) ? ICE_FDIR_MSIX : 0) + + (ice_is_rdma_ena(pf) ? num_online_cpus() + ICE_RDMA_AEQ_MSIX : 0); } /** @@ -243,6 +119,7 @@ void ice_clear_interrupt_scheme(struct ice_pf *pf) { pci_free_irq_vectors(pf->pdev); ice_deinit_irq_tracker(pf); + ice_deinit_virt_irq_tracker(pf); } /** @@ -252,27 +129,38 @@ void ice_clear_interrupt_scheme(struct ice_pf *pf) int ice_init_interrupt_scheme(struct ice_pf *pf) { int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; - int vectors, max_vectors; + int vectors; - vectors = ice_ena_msix_range(pf); + /* load default PF MSI-X range */ + if (!pf->msix.min) + pf->msix.min = ICE_MIN_MSIX; - if (vectors < 0) - return -ENOMEM; + if (!pf->msix.max) + pf->msix.max = min(total_vectors, + ice_get_default_msix_amount(pf)); + + pf->msix.total = total_vectors; + pf->msix.rest = total_vectors - pf->msix.max; if (pci_msix_can_alloc_dyn(pf->pdev)) - max_vectors = total_vectors; + vectors = pf->msix.min; else - max_vectors = vectors; + vectors = pf->msix.max; + + vectors = pci_alloc_irq_vectors(pf->pdev, pf->msix.min, vectors, + PCI_IRQ_MSIX); + if (vectors < 0) + return vectors; - ice_init_irq_tracker(pf, max_vectors, vectors); + ice_init_irq_tracker(pf, pf->msix.max, vectors); - return 0; + return ice_init_virt_irq_tracker(pf, pf->msix.max, pf->msix.rest); } /** * ice_alloc_irq - Allocate new interrupt vector * @pf: board private structure - * @dyn_only: force dynamic allocation of the interrupt + * @dyn_allowed: allow dynamic allocation of the interrupt * * Allocate new interrupt vector for a given owner id. * return struct msi_map with interrupt details and track @@ -285,27 +173,22 @@ int ice_init_interrupt_scheme(struct ice_pf *pf) * interrupt will be allocated with pci_msix_alloc_irq_at. * * Some callers may only support dynamically allocated interrupts. - * This is indicated with dyn_only flag. + * This is indicated with dyn_allowed flag. * * On failure, return map with negative .index. The caller * is expected to check returned map index. * */ -struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only) +struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_allowed) { - int sriov_base_vector = pf->sriov_base_vector; struct msi_map map = { .index = -ENOENT }; struct device *dev = ice_pf_to_dev(pf); struct ice_irq_entry *entry; - entry = ice_get_irq_res(pf, dyn_only); + entry = ice_get_irq_res(pf, dyn_allowed); if (!entry) return map; - /* fail if we're about to violate SRIOV vectors space */ - if (sriov_base_vector && entry->index >= sriov_base_vector) - goto exit_free_res; - if (pci_msix_can_alloc_dyn(pf->pdev) && entry->dynamic) { map = pci_msix_alloc_irq_at(pf->pdev, entry->index, NULL); if (map.index < 0) @@ -353,26 +236,40 @@ void ice_free_irq(struct ice_pf *pf, struct msi_map map) } /** - * ice_get_max_used_msix_vector - Get the max used interrupt vector - * @pf: board private structure + * ice_virt_get_irqs - get irqs for SR-IOV usacase + * @pf: pointer to PF structure + * @needed: number of irqs to get * - * Return index of maximum used interrupt vectors with respect to the - * beginning of the MSIX table. Take into account that some interrupts - * may have been dynamically allocated after MSIX was initially enabled. + * This returns the first MSI-X vector index in PF space that is used by this + * VF. This index is used when accessing PF relative registers such as + * GLINT_VECT2FUNC and GLINT_DYN_CTL. + * This will always be the OICR index in the AVF driver so any functionality + * using vf->first_vector_idx for queue configuration_id: id of VF which will + * use this irqs */ -int ice_get_max_used_msix_vector(struct ice_pf *pf) +int ice_virt_get_irqs(struct ice_pf *pf, u32 needed) { - unsigned long start, index, max_idx; - void *entry; + int res = bitmap_find_next_zero_area(pf->virt_irq_tracker.bm, + pf->virt_irq_tracker.num_entries, + 0, needed, 0); - /* Treat all preallocated interrupts as used */ - start = pf->irq_tracker.num_static; - max_idx = start - 1; + if (res >= pf->virt_irq_tracker.num_entries) + return -ENOENT; - xa_for_each_start(&pf->irq_tracker.entries, index, entry, start) { - if (index > max_idx) - max_idx = index; - } + bitmap_set(pf->virt_irq_tracker.bm, res, needed); + + /* conversion from number in bitmap to global irq index */ + return res + pf->virt_irq_tracker.base; +} - return max_idx; +/** + * ice_virt_free_irqs - free irqs used by the VF + * @pf: pointer to PF structure + * @index: first index to be free + * @irqs: number of irqs to free + */ +void ice_virt_free_irqs(struct ice_pf *pf, u32 index, u32 irqs) +{ + bitmap_clear(pf->virt_irq_tracker.bm, index - pf->virt_irq_tracker.base, + irqs); } diff --git a/drivers/net/ethernet/intel/ice/ice_irq.h b/drivers/net/ethernet/intel/ice/ice_irq.h index f35efc08575e..b2f9dbafd57e 100644 --- a/drivers/net/ethernet/intel/ice/ice_irq.h +++ b/drivers/net/ethernet/intel/ice/ice_irq.h @@ -15,11 +15,22 @@ struct ice_irq_tracker { u16 num_static; /* preallocated entries */ }; +struct ice_virt_irq_tracker { + unsigned long *bm; /* bitmap to track irq usage */ + u32 num_entries; + /* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the + * number of MSIX vectors needed for all SR-IOV VFs from the number of + * MSIX vectors allowed on this PF. + */ + u32 base; +}; + int ice_init_interrupt_scheme(struct ice_pf *pf); void ice_clear_interrupt_scheme(struct ice_pf *pf); struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only); void ice_free_irq(struct ice_pf *pf, struct msi_map map); -int ice_get_max_used_msix_vector(struct ice_pf *pf); +int ice_virt_get_irqs(struct ice_pf *pf, u32 needed); +void ice_virt_free_irqs(struct ice_pf *pf, u32 index, u32 irqs); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 1ccb572ce285..2410aee59fb2 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -1001,6 +1001,28 @@ static void ice_lag_link(struct ice_lag *lag) } /** + * ice_lag_config_eswitch - configure eswitch to work with LAG + * @lag: lag info struct + * @netdev: active network interface device struct + * + * Updates all port representors in eswitch to use @netdev for Tx. + * + * Configures the netdev to keep dst metadata (also used in representor Tx). + * This is required for an uplink without switchdev mode configured. + */ +static void ice_lag_config_eswitch(struct ice_lag *lag, + struct net_device *netdev) +{ + struct ice_repr *repr; + unsigned long id; + + xa_for_each(&lag->pf->eswitch.reprs, id, repr) + repr->dst->u.port_info.lower_dev = netdev; + + netif_keep_dst(netdev); +} + +/** * ice_lag_unlink - handle unlink event * @lag: LAG info struct */ @@ -1021,6 +1043,9 @@ static void ice_lag_unlink(struct ice_lag *lag) ice_lag_move_vf_nodes(lag, act_port, pri_port); lag->primary = false; lag->active_port = ICE_LAG_INVALID_PORT; + + /* Config primary's eswitch back to normal operation. */ + ice_lag_config_eswitch(lag, lag->netdev); } else { struct ice_lag *primary_lag; @@ -1296,12 +1321,18 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr) */ if (!primary_lag) { lag->primary = true; + if (!ice_is_switchdev_running(lag->pf)) + return; + /* Configure primary's SWID to be shared */ ice_lag_primary_swid(lag, true); primary_lag = lag; } else { u16 swid; + if (!ice_is_switchdev_running(primary_lag->pf)) + return; + swid = primary_lag->pf->hw.port_info->sw_id; ice_lag_set_swid(swid, lag, true); ice_lag_add_prune_list(primary_lag, lag->pf); @@ -1419,6 +1450,7 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr) ice_lag_move_vf_nodes(lag, prim_port, event_port); lag->active_port = event_port; + ice_lag_config_eswitch(lag, event_netdev); return; } @@ -1428,6 +1460,7 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr) /* new active port */ ice_lag_move_vf_nodes(lag, lag->active_port, event_port); lag->active_port = event_port; + ice_lag_config_eswitch(lag, event_netdev); } else { /* port not set as currently active (e.g. new active port * has already claimed the nodes and filters diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 611577ebc29d..77ba26538b07 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -229,7 +229,7 @@ struct ice_32b_rx_flex_desc_nic { __le16 status_error1; u8 flexi_flags2; u8 ts_low; - __le16 l2tag2_1st; + __le16 raw_csum; __le16 l2tag2_2nd; /* Qword 3 */ @@ -371,29 +371,21 @@ enum ice_rx_flex_desc_status_error_1_bits { ICE_RX_FLEX_DESC_STATUS1_LAST /* this entry must be last!!! */ }; -#define ICE_RXQ_CTX_SIZE_DWORDS 8 -#define ICE_RXQ_CTX_SZ (ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32)) #define ICE_TX_CMPLTNQ_CTX_SIZE_DWORDS 22 #define ICE_TX_DRBELL_Q_CTX_SIZE_DWORDS 5 #define GLTCLAN_CQ_CNTX(i, CQ) (GLTCLAN_CQ_CNTX0(CQ) + ((i) * 0x0800)) -/* RLAN Rx queue context data - * - * The sizes of the variables may be larger than needed due to crossing byte - * boundaries. If we do not have the width of the variable set to the correct - * size then we could end up shifting bits off the top of the variable when the - * variable is at the top of a byte and crosses over into the next byte. - */ +/* RLAN Rx queue context data */ struct ice_rlan_ctx { u16 head; - u16 cpuid; /* bigger than needed, see above for reason */ + u8 cpuid; #define ICE_RLAN_BASE_S 7 u64 base; u16 qlen; #define ICE_RLAN_CTX_DBUF_S 7 - u16 dbuf; /* bigger than needed, see above for reason */ + u8 dbuf; #define ICE_RLAN_CTX_HBUF_S 6 - u16 hbuf; /* bigger than needed, see above for reason */ + u8 hbuf; u8 dtype; u8 dsize; u8 crcstrip; @@ -401,29 +393,15 @@ struct ice_rlan_ctx { u8 hsplit_0; u8 hsplit_1; u8 showiv; - u32 rxmax; /* bigger than needed, see above for reason */ + u16 rxmax; u8 tphrdesc_ena; u8 tphwdesc_ena; u8 tphdata_ena; u8 tphhead_ena; - u16 lrxqthresh; /* bigger than needed, see above for reason */ + u8 lrxqthresh; u8 prefena; /* NOTE: normally must be set to 1 at init */ }; -struct ice_ctx_ele { - u16 offset; - u16 size_of; - u16 width; - u16 lsb; -}; - -#define ICE_CTX_STORE(_struct, _ele, _width, _lsb) { \ - .offset = offsetof(struct _struct, _ele), \ - .size_of = sizeof_field(struct _struct, _ele), \ - .width = _width, \ - .lsb = _lsb, \ -} - /* for hsplit_0 field of Rx RLAN context */ enum ice_rlan_ctx_rx_hsplit_0 { ICE_RLAN_RX_HSPLIT_0_NO_SPLIT = 0, @@ -500,10 +478,15 @@ enum ice_tx_desc_len_fields { struct ice_tx_ctx_desc { __le32 tunneling_params; __le16 l2tag2; - __le16 rsvd; + __le16 gcs; __le64 qw1; }; +#define ICE_TX_GCS_DESC_START_M GENMASK(7, 0) +#define ICE_TX_GCS_DESC_OFFSET_M GENMASK(11, 8) +#define ICE_TX_GCS_DESC_TYPE_M GENMASK(14, 12) +#define ICE_TX_GCS_DESC_CSUM_PSH 1 + #define ICE_TXD_CTX_QW1_CMD_S 4 #define ICE_TXD_CTX_QW1_CMD_M (0x7FUL << ICE_TXD_CTX_QW1_CMD_S) @@ -551,18 +534,12 @@ enum ice_tx_ctx_desc_eipt_offload { #define ICE_LAN_TXQ_MAX_QGRPS 127 #define ICE_LAN_TXQ_MAX_QDIS 1023 -/* Tx queue context data - * - * The sizes of the variables may be larger than needed due to crossing byte - * boundaries. If we do not have the width of the variable set to the correct - * size then we could end up shifting bits off the top of the variable when the - * variable is at the top of a byte and crosses over into the next byte. - */ +/* Tx queue context data */ struct ice_tlan_ctx { #define ICE_TLAN_CTX_BASE_S 7 u64 base; /* base is defined in 128-byte units */ u8 port_num; - u16 cgd_num; /* bigger than needed, see above for reason */ + u8 cgd_num; u8 pf_num; u16 vmvf_num; u8 vmvf_type; @@ -573,7 +550,7 @@ struct ice_tlan_ctx { u8 tsyn_ena; u8 internal_usage_flag; u8 alt_vlan; - u16 cpuid; /* bigger than needed, see above for reason */ + u8 cpuid; u8 wb_mode; u8 tphrd_desc; u8 tphrd; @@ -582,7 +559,7 @@ struct ice_tlan_ctx { u16 qnum_in_func; u8 itr_notification_mode; u8 adjust_prof_id; - u32 qlen; /* bigger than needed, see above for reason */ + u16 qlen; u8 quanta_prof_idx; u8 tso_ena; u16 tso_qnum; @@ -590,7 +567,6 @@ struct ice_tlan_ctx { u8 drop_ena; u8 cache_prof_idx; u8 pkt_shaper_prof_idx; - u8 int_q_state; /* width not needed - internal - DO NOT WRITE!!! */ }; #endif /* _ICE_LAN_TX_RX_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index a7d45a8ce7ac..03bb16191237 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -157,6 +157,16 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) } } +static u16 ice_get_rxq_count(struct ice_pf *pf) +{ + return min(ice_get_avail_rxq_count(pf), num_online_cpus()); +} + +static u16 ice_get_txq_count(struct ice_pf *pf) +{ + return min(ice_get_avail_txq_count(pf), num_online_cpus()); +} + /** * ice_vsi_set_num_qs - Set number of queues, descriptors and vectors for a VSI * @vsi: the VSI being configured @@ -178,9 +188,7 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) vsi->alloc_txq = vsi->req_txq; vsi->num_txq = vsi->req_txq; } else { - vsi->alloc_txq = min3(pf->num_lan_msix, - ice_get_avail_txq_count(pf), - (u16)num_online_cpus()); + vsi->alloc_txq = ice_get_txq_count(pf); } pf->num_lan_tx = vsi->alloc_txq; @@ -193,17 +201,13 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) vsi->alloc_rxq = vsi->req_rxq; vsi->num_rxq = vsi->req_rxq; } else { - vsi->alloc_rxq = min3(pf->num_lan_msix, - ice_get_avail_rxq_count(pf), - (u16)num_online_cpus()); + vsi->alloc_rxq = ice_get_rxq_count(pf); } } pf->num_lan_rx = vsi->alloc_rxq; - vsi->num_q_vectors = min_t(int, pf->num_lan_msix, - max_t(int, vsi->alloc_rxq, - vsi->alloc_txq)); + vsi->num_q_vectors = max(vsi->alloc_rxq, vsi->alloc_txq); break; case ICE_VSI_SF: vsi->alloc_txq = 1; @@ -567,6 +571,8 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch) return -ENOMEM; } + vsi->irq_dyn_alloc = pci_msix_can_alloc_dyn(vsi->back->pdev); + switch (vsi->type) { case ICE_VSI_PF: case ICE_VSI_SF: @@ -827,7 +833,13 @@ bool ice_is_safe_mode(struct ice_pf *pf) */ bool ice_is_rdma_ena(struct ice_pf *pf) { - return test_bit(ICE_FLAG_RDMA_ENA, pf->flags); + union devlink_param_value value; + int err; + + err = devl_param_driverinit_value_get(priv_to_devlink(pf), + DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, + &value); + return err ? test_bit(ICE_FLAG_RDMA_ENA, pf->flags) : value.vbool; } /** @@ -1173,12 +1185,11 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) static void ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) { - struct ice_pf *pf = vsi->back; u16 qcount, qmap; u8 offset = 0; int pow; - qcount = min_t(int, vsi->num_rxq, pf->num_lan_msix); + qcount = vsi->num_rxq; pow = order_base_2(qcount); qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset); @@ -1420,6 +1431,10 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->dev = dev; ring->count = vsi->num_rx_desc; ring->cached_phctime = pf->ptp.cached_phc_time; + + if (ice_is_feature_supported(pf, ICE_F_GCS)) + ring->flags |= ICE_RX_FLAGS_RING_GCS; + WRITE_ONCE(vsi->rx_rings[i], ring); } @@ -1700,6 +1715,12 @@ bool ice_pf_state_is_nominal(struct ice_pf *pf) return true; } +#define ICE_FW_MODE_REC_M BIT(1) +bool ice_is_recovery_mode(struct ice_hw *hw) +{ + return rd32(hw, GL_MNG_FWSM) & ICE_FW_MODE_REC_M; +} + /** * ice_update_eth_stats - Update VSI-specific ethernet statistics counters * @vsi: the VSI to be updated @@ -1758,9 +1779,8 @@ void ice_update_eth_stats(struct ice_vsi *vsi) * @prio: priority for the RXDID for this queue * @ena_ts: true to enable timestamp and false to disable timestamp */ -void -ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, - bool ena_ts) +void ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, + bool ena_ts) { int regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); @@ -2045,12 +2065,15 @@ static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi) } /** - * ice_cfg_sw_lldp - Config switch rules for LLDP packet handling + * ice_vsi_cfg_sw_lldp - Config switch rules for LLDP packet handling * @vsi: the VSI being configured * @tx: bool to determine Tx or Rx rule * @create: bool to determine create or remove Rule + * + * Adding an ethtype Tx rule to the uplink VSI results in it being applied + * to the whole port, so LLDP transmission for VFs will be blocked too. */ -void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create) +void ice_vsi_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create) { int (*eth_fltr)(struct ice_vsi *v, u16 type, u16 flag, enum ice_sw_fwd_act_type act); @@ -2065,19 +2088,59 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create) status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_TX, ICE_DROP_PACKET); } else { - if (ice_fw_supports_lldp_fltr_ctrl(&pf->hw)) { - status = ice_lldp_fltr_add_remove(&pf->hw, vsi->vsi_num, - create); - } else { + if (!test_bit(ICE_FLAG_LLDP_AQ_FLTR, pf->flags)) { status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_RX, ICE_FWD_TO_VSI); + if (!status || !create) + goto report; + + dev_info(dev, + "Failed to add generic LLDP Rx filter on VSI %i error: %d, falling back to specialized AQ control\n", + vsi->vsi_num, status); } + + status = ice_lldp_fltr_add_remove(&pf->hw, vsi, create); + if (!status) + set_bit(ICE_FLAG_LLDP_AQ_FLTR, pf->flags); + } +report: if (status) - dev_dbg(dev, "Fail %s %s LLDP rule on VSI %i error: %d\n", - create ? "adding" : "removing", tx ? "TX" : "RX", - vsi->vsi_num, status); + dev_warn(dev, "Failed to %s %s LLDP rule on VSI %i error: %d\n", + create ? "add" : "remove", tx ? "Tx" : "Rx", + vsi->vsi_num, status); +} + +/** + * ice_cfg_sw_rx_lldp - Enable/disable software handling of LLDP + * @pf: the PF being configured + * @enable: enable or disable + * + * Configure switch rules to enable/disable LLDP handling by software + * across PF. + */ +void ice_cfg_sw_rx_lldp(struct ice_pf *pf, bool enable) +{ + struct ice_vsi *vsi; + struct ice_vf *vf; + unsigned int bkt; + + vsi = ice_get_main_vsi(pf); + ice_vsi_cfg_sw_lldp(vsi, false, enable); + + if (!test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) + return; + + ice_for_each_vf(pf, bkt, vf) { + vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + continue; + + if (ice_vf_is_lldp_ena(vf)) + ice_vsi_cfg_sw_lldp(vsi, false, enable); + } } /** @@ -2508,7 +2571,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params) if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF) { ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX, ICE_DROP_PACKET); - ice_cfg_sw_lldp(vsi, true, true); + ice_vsi_cfg_sw_lldp(vsi, true, true); } if (!vsi->agg_node) @@ -2576,7 +2639,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) return; vsi->irqs_ready = false; - ice_free_cpu_rx_rmap(vsi); ice_for_each_q_vector(vsi, i) { int irq_num; @@ -2589,12 +2651,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) vsi->q_vectors[i]->num_ring_rx)) continue; - /* clear the affinity notifier in the IRQ descriptor */ - if (!IS_ENABLED(CONFIG_RFS_ACCEL)) - irq_set_affinity_notifier(irq_num, NULL); - - /* clear the affinity_hint in the IRQ descriptor */ - irq_update_affinity_hint(irq_num, NULL); synchronize_irq(irq_num); devm_free_irq(ice_pf_to_dev(pf), irq_num, vsi->q_vectors[i]); } @@ -2749,11 +2805,18 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi) void ice_vsi_clear_napi_queues(struct ice_vsi *vsi) { struct net_device *netdev = vsi->netdev; - int q_idx; + int q_idx, v_idx; if (!netdev) return; + /* Clear the NAPI's interrupt number */ + ice_for_each_q_vector(vsi, v_idx) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; + + netif_napi_set_irq(&q_vector->napi, -1); + } + ice_for_each_txq(vsi, q_idx) netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL); @@ -2805,9 +2868,11 @@ int ice_vsi_release(struct ice_vsi *vsi) /* The Rx rule will only exist to remove if the LLDP FW * engine is currently stopped */ - if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF && - !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) - ice_cfg_sw_lldp(vsi, false, false); + if (!ice_is_safe_mode(pf) && + !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags) && + (vsi->type == ICE_VSI_PF || (vsi->type == ICE_VSI_VF && + ice_vf_is_lldp_ena(vsi->vf)))) + ice_vsi_cfg_sw_lldp(vsi, false, false); ice_vsi_decfg(vsi); @@ -3876,15 +3941,17 @@ void ice_init_feature_support(struct ice_pf *pf) ice_set_feature_support(pf, ICE_F_CGU); if (ice_is_clock_mux_in_netlist(&pf->hw)) ice_set_feature_support(pf, ICE_F_SMA_CTRL); - if (ice_gnss_is_gps_present(&pf->hw)) + if (ice_gnss_is_module_present(&pf->hw)) ice_set_feature_support(pf, ICE_F_GNSS); break; default: break; } - if (pf->hw.mac_type == ICE_MAC_E830) + if (pf->hw.mac_type == ICE_MAC_E830) { ice_set_feature_support(pf, ICE_F_MBX_LIMIT); + ice_set_feature_support(pf, ICE_F_GCS); + } } /** @@ -3931,24 +3998,6 @@ void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx) } /** - * ice_vsi_ctx_set_allow_override - allow destination override on VSI - * @ctx: pointer to VSI ctx structure - */ -void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx) -{ - ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; -} - -/** - * ice_vsi_ctx_clear_allow_override - turn off destination override on VSI - * @ctx: pointer to VSI ctx structure - */ -void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx) -{ - ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; -} - -/** * ice_vsi_update_local_lb - update sw block in VSI with local loopback bit * @vsi: pointer to VSI structure * @set: set or unset the bit diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 10d6fc479a32..654516c5fc3e 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -29,7 +29,8 @@ ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi); -void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); +void ice_vsi_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); +void ice_cfg_sw_rx_lldp(struct ice_pf *pf, bool enable); int ice_set_link(struct ice_vsi *vsi, bool ena); @@ -90,6 +91,7 @@ void ice_set_q_vector_intrl(struct ice_q_vector *q_vector); bool ice_is_safe_mode(struct ice_pf *pf); bool ice_is_rdma_ena(struct ice_pf *pf); +bool ice_is_recovery_mode(struct ice_hw *hw); bool ice_is_dflt_vsi_in_use(struct ice_port_info *pi); bool ice_is_vsi_dflt_vsi(struct ice_vsi *vsi); int ice_set_dflt_vsi(struct ice_vsi *vsi); @@ -104,10 +106,6 @@ ice_vsi_update_security(struct ice_vsi *vsi, void (*fill)(struct ice_vsi_ctx *)) void ice_vsi_ctx_set_antispoof(struct ice_vsi_ctx *ctx); void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx); - -void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx); - -void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx); int ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set); int ice_vsi_add_vlan_zero(struct ice_vsi *vsi); int ice_vsi_del_vlan_zero(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 89fa3d53d317..d97d4b25b30d 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -14,7 +14,7 @@ #include "ice_dcb_lib.h" #include "ice_dcb_nl.h" #include "devlink/devlink.h" -#include "devlink/devlink_port.h" +#include "devlink/port.h" #include "ice_sf_eth.h" #include "ice_hwmon.h" /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the @@ -1567,6 +1567,9 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) case ice_aqc_opc_lldp_set_mib_change: ice_dcb_process_lldp_set_mib_change(pf, &event); break; + case ice_aqc_opc_get_health_status: + ice_process_health_status_event(pf, &event); + break; default: dev_dbg(dev, "%s Receive Queue unknown event 0x%04x ignored\n", qtype, opcode); @@ -1714,7 +1717,7 @@ static int ice_service_task_stop(struct ice_pf *pf) ret = test_and_set_bit(ICE_SERVICE_DIS, pf->state); if (pf->serv_tmr.function) - del_timer_sync(&pf->serv_tmr); + timer_delete_sync(&pf->serv_tmr); if (pf->serv_task.func) cancel_work_sync(&pf->serv_task); @@ -1816,6 +1819,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", event, queue, pf_num, vf_num); + ice_report_mdd_event(pf, ICE_MDD_SRC_TX_PQM, pf_num, vf_num, + event, queue); wr32(hw, GL_MDET_TX_PQM, 0xffffffff); } @@ -1829,6 +1834,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", event, queue, pf_num, vf_num); + ice_report_mdd_event(pf, ICE_MDD_SRC_TX_TCLAN, pf_num, vf_num, + event, queue); wr32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw), U32_MAX); } @@ -1842,6 +1849,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_rx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n", event, queue, pf_num, vf_num); + ice_report_mdd_event(pf, ICE_MDD_SRC_RX, pf_num, vf_num, event, + queue); wr32(hw, GL_MDET_RX, 0xffffffff); } @@ -2355,6 +2364,18 @@ static void ice_check_media_subtask(struct ice_pf *pf) } } +static void ice_service_task_recovery_mode(struct work_struct *work) +{ + struct ice_pf *pf = container_of(work, struct ice_pf, serv_task); + + set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state); + ice_clean_adminq_subtask(pf); + + ice_service_task_complete(pf); + + mod_timer(&pf->serv_tmr, jiffies + msecs_to_jiffies(100)); +} + /** * ice_service_task - manage and run subtasks * @work: pointer to work_struct contained by the PF struct @@ -2364,9 +2385,11 @@ static void ice_service_task(struct work_struct *work) struct ice_pf *pf = container_of(work, struct ice_pf, serv_task); unsigned long start_time = jiffies; - /* subtasks */ + if (pf->health_reporters.tx_hang_buf.tx_ring) { + ice_report_tx_hang(pf); + pf->health_reporters.tx_hang_buf.tx_ring = NULL; + } - /* process reset requests first */ ice_reset_subtask(pf); /* bail if a reset/recovery cycle is pending or rebuild failed */ @@ -2378,11 +2401,11 @@ static void ice_service_task(struct work_struct *work) } if (test_and_clear_bit(ICE_AUX_ERR_PENDING, pf->state)) { - struct iidc_event *event; + struct iidc_rdma_event *event; event = kzalloc(sizeof(*event), GFP_KERNEL); if (event) { - set_bit(IIDC_EVENT_CRIT_ERR, event->type); + set_bit(IIDC_RDMA_EVENT_CRIT_ERR, event->type); /* report the entire OICR value to AUX driver */ swap(event->reg, pf->oicr_err_reg); ice_send_event_to_aux(pf, event); @@ -2401,11 +2424,11 @@ static void ice_service_task(struct work_struct *work) ice_plug_aux_dev(pf); if (test_and_clear_bit(ICE_FLAG_MTU_CHANGED, pf->flags)) { - struct iidc_event *event; + struct iidc_rdma_event *event; event = kzalloc(sizeof(*event), GFP_KERNEL); if (event) { - set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type); + set_bit(IIDC_RDMA_EVENT_AFTER_MTU_CHANGE, event->type); ice_send_event_to_aux(pf, event); kfree(event); } @@ -2505,34 +2528,6 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset) } /** - * ice_irq_affinity_notify - Callback for affinity changes - * @notify: context as to what irq was changed - * @mask: the new affinity mask - * - * This is a callback function used by the irq_set_affinity_notifier function - * so that we may register to receive changes to the irq affinity masks. - */ -static void -ice_irq_affinity_notify(struct irq_affinity_notify *notify, - const cpumask_t *mask) -{ - struct ice_q_vector *q_vector = - container_of(notify, struct ice_q_vector, affinity_notify); - - cpumask_copy(&q_vector->affinity_mask, mask); -} - -/** - * ice_irq_affinity_release - Callback for affinity notifier release - * @ref: internal core kernel usage - * - * This is a callback function used by the irq_set_affinity_notifier function - * to inform the current notification subscriber that they will no longer - * receive notifications. - */ -static void ice_irq_affinity_release(struct kref __always_unused *ref) {} - -/** * ice_vsi_ena_irq - Enable IRQ for the given VSI * @vsi: the VSI being configured */ @@ -2595,19 +2590,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) err); goto free_q_irqs; } - - /* register for affinity change notifications */ - if (!IS_ENABLED(CONFIG_RFS_ACCEL)) { - struct irq_affinity_notify *affinity_notify; - - affinity_notify = &q_vector->affinity_notify; - affinity_notify->notify = ice_irq_affinity_notify; - affinity_notify->release = ice_irq_affinity_release; - irq_set_affinity_notifier(irq_num, affinity_notify); - } - - /* assign the mask for this irq */ - irq_update_affinity_hint(irq_num, &q_vector->affinity_mask); } err = ice_set_cpu_rx_rmap(vsi); @@ -2623,9 +2605,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) free_q_irqs: while (vector--) { irq_num = vsi->q_vectors[vector]->irq.virq; - if (!IS_ENABLED(CONFIG_RFS_ACCEL)) - irq_set_affinity_notifier(irq_num, NULL); - irq_update_affinity_hint(irq_num, NULL); devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]); } return err; @@ -2762,6 +2741,27 @@ void ice_map_xdp_rings(struct ice_vsi *vsi) } /** + * ice_unmap_xdp_rings - Unmap XDP rings from interrupt vectors + * @vsi: the VSI with XDP rings being unmapped + */ +static void ice_unmap_xdp_rings(struct ice_vsi *vsi) +{ + int v_idx; + + ice_for_each_q_vector(vsi, v_idx) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; + struct ice_tx_ring *ring; + + ice_for_each_tx_ring(ring, q_vector->tx) + if (!ring->tx_buf || !ice_ring_is_xdp(ring)) + break; + + /* restore the value of last node prior to XDP setup */ + q_vector->tx.tx_ring = ring; + } +} + +/** * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP * @vsi: VSI to bring up Tx rings used by XDP * @prog: bpf program that will be assigned to VSI @@ -2824,7 +2824,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog, if (status) { dev_err(dev, "Failed VSI LAN queue config for XDP, error: %d\n", status); - goto clear_xdp_rings; + goto unmap_xdp_rings; } /* assign the prog only when it's not already present on VSI; @@ -2840,6 +2840,8 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog, ice_vsi_assign_bpf_prog(vsi, prog); return 0; +unmap_xdp_rings: + ice_unmap_xdp_rings(vsi); clear_xdp_rings: ice_for_each_xdp_txq(vsi, i) if (vsi->xdp_rings[i]) { @@ -2856,6 +2858,8 @@ err_map_xdp: mutex_unlock(&pf->avail_q_mutex); devm_kfree(dev, vsi->xdp_rings); + vsi->xdp_rings = NULL; + return -ENOMEM; } @@ -2871,7 +2875,7 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct ice_pf *pf = vsi->back; - int i, v_idx; + int i; /* q_vectors are freed in reset path so there's no point in detaching * rings @@ -2879,17 +2883,7 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type) if (cfg_type == ICE_XDP_CFG_PART) goto free_qmap; - ice_for_each_q_vector(vsi, v_idx) { - struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; - struct ice_tx_ring *ring; - - ice_for_each_tx_ring(ring, q_vector->tx) - if (!ring->tx_buf || !ice_ring_is_xdp(ring)) - break; - - /* restore the value of last node prior to XDP setup */ - q_vector->tx.tx_ring = ring; - } + ice_unmap_xdp_rings(vsi); free_qmap: mutex_lock(&pf->avail_q_mutex); @@ -3034,11 +3028,14 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, xdp_ring_err = ice_vsi_determine_xdp_res(vsi); if (xdp_ring_err) { NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP"); + goto resume_if; } else { xdp_ring_err = ice_prepare_xdp_rings(vsi, prog, ICE_XDP_CFG_FULL); - if (xdp_ring_err) + if (xdp_ring_err) { NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); + goto resume_if; + } } xdp_features_set_redirect_target(vsi->netdev, true); /* reallocate Rx queues that are used for zero-copy */ @@ -3056,6 +3053,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Rx resources failed"); } +resume_if: if (if_running) ret = ice_up(vsi); @@ -3281,22 +3279,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) if (oicr & PFINT_OICR_TSYN_TX_M) { ena_mask &= ~PFINT_OICR_TSYN_TX_M; - if (ice_pf_state_is_nominal(pf) && - pf->hw.dev_caps.ts_dev_info.ts_ll_int_read) { - struct ice_ptp_tx *tx = &pf->ptp.port.tx; - unsigned long flags; - u8 idx; - - spin_lock_irqsave(&tx->lock, flags); - idx = find_next_bit_wrap(tx->in_use, tx->len, - tx->last_ll_ts_idx_read + 1); - if (idx != tx->len) - ice_ptp_req_tx_single_tstamp(tx, idx); - spin_unlock_irqrestore(&tx->lock, flags); - } else if (ice_ptp_pf_handles_tx_interrupt(pf)) { - set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread); - ret = IRQ_WAKE_THREAD; - } + + ret = ice_ptp_ts_irq(pf); } if (oicr & PFINT_OICR_TSYN_EVNT_M) { @@ -3666,6 +3650,15 @@ void ice_set_netdev_features(struct net_device *netdev) */ netdev->hw_features |= NETIF_F_RXFCS; + /* Allow core to manage IRQs affinity */ + netif_set_affinity_auto(netdev); + + /* Mutual exclusivity for TSO and GCS is enforced by the set features + * ndo callback. + */ + if (ice_is_feature_supported(pf, ICE_F_GCS)) + netdev->hw_features |= NETIF_F_HW_CSUM; + netif_set_tso_max_size(netdev, ICE_MAX_TSO_SIZE); } @@ -4043,8 +4036,7 @@ static void ice_set_pf_caps(struct ice_pf *pf) } clear_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags); - if (func_caps->common_cap.ieee_1588 && - !(pf->hw.mac_type == ICE_MAC_E830)) + if (func_caps->common_cap.ieee_1588) set_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags); pf->max_pf_txqs = func_caps->common_cap.num_txq; @@ -4741,55 +4733,12 @@ static void ice_decfg_netdev(struct ice_vsi *vsi) vsi->netdev = NULL; } -/** - * ice_wait_for_fw - wait for full FW readiness - * @hw: pointer to the hardware structure - * @timeout: milliseconds that can elapse before timing out - */ -static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout) -{ - int fw_loading; - u32 elapsed = 0; - - while (elapsed <= timeout) { - fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M; - - /* firmware was not yet loaded, we have to wait more */ - if (fw_loading) { - elapsed += 100; - msleep(100); - continue; - } - return 0; - } - - return -ETIMEDOUT; -} - int ice_init_dev(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; int err; - err = ice_init_hw(hw); - if (err) { - dev_err(dev, "ice_init_hw failed: %d\n", err); - return err; - } - - /* Some cards require longer initialization times - * due to necessity of loading FW from an external source. - * This can take even half a minute. - */ - if (ice_is_pf_c827(hw)) { - err = ice_wait_for_fw(hw, 30000); - if (err) { - dev_err(dev, "ice_wait_for_fw timed out"); - return err; - } - } - ice_init_feature_support(pf); err = ice_init_ddp_config(hw, pf); @@ -4810,7 +4759,7 @@ int ice_init_dev(struct ice_pf *pf) err = ice_init_pf(pf); if (err) { dev_err(dev, "ice_init_pf failed: %d\n", err); - goto err_init_pf; + return err; } pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port; @@ -4834,7 +4783,7 @@ int ice_init_dev(struct ice_pf *pf) if (err) { dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err); err = -EIO; - goto err_init_interrupt_scheme; + goto unroll_pf_init; } /* In case of MSIX we are going to setup the misc vector right here @@ -4845,17 +4794,15 @@ int ice_init_dev(struct ice_pf *pf) err = ice_req_irq_msix_misc(pf); if (err) { dev_err(dev, "setup of misc vector failed: %d\n", err); - goto err_req_irq_msix_misc; + goto unroll_irq_scheme_init; } return 0; -err_req_irq_msix_misc: +unroll_irq_scheme_init: ice_clear_interrupt_scheme(pf); -err_init_interrupt_scheme: +unroll_pf_init: ice_deinit_pf(pf); -err_init_pf: - ice_deinit_hw(hw); return err; } @@ -5088,12 +5035,14 @@ static int ice_init_devlink(struct ice_pf *pf) ice_devlink_init_regions(pf); ice_devlink_register(pf); + ice_health_init(pf); return 0; } static void ice_deinit_devlink(struct ice_pf *pf) { + ice_health_deinit(pf); ice_devlink_unregister(pf); ice_devlink_destroy_regions(pf); ice_devlink_unregister_params(pf); @@ -5107,6 +5056,12 @@ static int ice_init(struct ice_pf *pf) if (err) return err; + if (pf->hw.mac_type == ICE_MAC_E830) { + err = pci_enable_ptm(pf->pdev, NULL); + if (err) + dev_dbg(ice_pf_to_dev(pf), "PCIe PTM not supported by PCIe bus/controller\n"); + } + err = ice_alloc_vsis(pf); if (err) goto err_alloc_vsis; @@ -5206,11 +5161,12 @@ int ice_load(struct ice_pf *pf) ice_napi_add(vsi); + ice_init_features(pf); + err = ice_init_rdma(pf); if (err) goto err_init_rdma; - ice_init_features(pf); ice_service_task_restart(pf); clear_bit(ICE_DOWN, pf->state); @@ -5218,6 +5174,7 @@ int ice_load(struct ice_pf *pf) return 0; err_init_rdma: + ice_deinit_features(pf); ice_tc_indir_block_unregister(vsi); err_tc_indir_block_register: ice_unregister_netdev(vsi); @@ -5241,14 +5198,44 @@ void ice_unload(struct ice_pf *pf) devl_assert_locked(priv_to_devlink(pf)); - ice_deinit_features(pf); ice_deinit_rdma(pf); + ice_deinit_features(pf); ice_tc_indir_block_unregister(vsi); ice_unregister_netdev(vsi); ice_devlink_destroy_pf_port(pf); ice_decfg_netdev(vsi); } +static int ice_probe_recovery_mode(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + dev_err(dev, "Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode\n"); + + INIT_HLIST_HEAD(&pf->aq_wait_list); + spin_lock_init(&pf->aq_wait_lock); + init_waitqueue_head(&pf->aq_wait_queue); + + timer_setup(&pf->serv_tmr, ice_service_timer, 0); + pf->serv_tmr_period = HZ; + INIT_WORK(&pf->serv_task, ice_service_task_recovery_mode); + clear_bit(ICE_SERVICE_SCHED, pf->state); + err = ice_create_all_ctrlq(&pf->hw); + if (err) + return err; + + scoped_guard(devl, priv_to_devlink(pf)) { + err = ice_init_devlink(pf); + if (err) + return err; + } + + ice_service_task_restart(pf); + + return 0; +} + /** * ice_probe - Device initialization routine * @pdev: PCI device information struct @@ -5312,13 +5299,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) } pci_set_master(pdev); - - adapter = ice_adapter_get(pdev); - if (IS_ERR(adapter)) - return PTR_ERR(adapter); - pf->pdev = pdev; - pf->adapter = adapter; pci_set_drvdata(pdev, pf); set_bit(ICE_DOWN, pf->state); /* Disable service task until DOWN bit is cleared */ @@ -5346,29 +5327,47 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) hw->debug_mask = debug; #endif + if (ice_is_recovery_mode(hw)) + return ice_probe_recovery_mode(pf); + + err = ice_init_hw(hw); + if (err) { + dev_err(dev, "ice_init_hw failed: %d\n", err); + return err; + } + + adapter = ice_adapter_get(pdev); + if (IS_ERR(adapter)) { + err = PTR_ERR(adapter); + goto unroll_hw_init; + } + pf->adapter = adapter; + err = ice_init(pf); if (err) - goto err_init; + goto unroll_adapter; devl_lock(priv_to_devlink(pf)); err = ice_load(pf); if (err) - goto err_load; + goto unroll_init; err = ice_init_devlink(pf); if (err) - goto err_init_devlink; + goto unroll_load; devl_unlock(priv_to_devlink(pf)); return 0; -err_init_devlink: +unroll_load: ice_unload(pf); -err_load: +unroll_init: devl_unlock(priv_to_devlink(pf)); ice_deinit(pf); -err_init: +unroll_adapter: ice_adapter_put(pdev); +unroll_hw_init: + ice_deinit_hw(hw); return err; } @@ -5448,6 +5447,14 @@ static void ice_remove(struct pci_dev *pdev) msleep(100); } + if (ice_is_recovery_mode(&pf->hw)) { + ice_service_task_stop(pf); + scoped_guard(devl, priv_to_devlink(pf)) { + ice_deinit_devlink(pf); + } + return; + } + if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) { set_bit(ICE_VF_RESETS_DISABLED, pf->state); ice_free_vfs(pf); @@ -6567,6 +6574,18 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) if (changed & NETIF_F_LOOPBACK) ret = ice_set_loopback(vsi, !!(features & NETIF_F_LOOPBACK)); + /* Due to E830 hardware limitations, TSO (NETIF_F_ALL_TSO) with GCS + * (NETIF_F_HW_CSUM) is not supported. + */ + if (ice_is_feature_supported(pf, ICE_F_GCS) && + ((features & NETIF_F_HW_CSUM) && (features & NETIF_F_ALL_TSO))) { + if (netdev->features & NETIF_F_HW_CSUM) + dev_err(ice_pf_to_dev(pf), "To enable TSO, you must first disable HW checksum.\n"); + else + dev_err(ice_pf_to_dev(pf), "To enable HW checksum, you must first disable TSO.\n"); + return -EIO; + } + return ret; } @@ -7793,6 +7812,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) /* if we get here, reset flow is successful */ clear_bit(ICE_RESET_FAILED, pf->state); + ice_health_clear(pf); + ice_plug_aux_dev(pf); if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) ice_lag_rebuild(pf); @@ -8283,16 +8304,18 @@ void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) if (tx_ring) { struct ice_hw *hw = &pf->hw; - u32 head, val = 0; + u32 head, intr = 0; head = FIELD_GET(QTX_COMM_HEAD_HEAD_M, rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue]))); /* Read interrupt register */ - val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx)); + intr = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx)); netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %u, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n", vsi->vsi_num, txqueue, tx_ring->next_to_clean, - head, tx_ring->next_to_use, val); + head, tx_ring->next_to_use, intr); + + ice_prep_tx_hang_report(pf, tx_ring, vsi->vsi_num, head, intr); } pf->tx_timeout_last_recovery = jiffies; @@ -8326,11 +8349,16 @@ void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) * @np: net device to configure * @filter_dev: device on which filter is added * @cls_flower: offload data + * @ingress: if the rule is added to an ingress block + * + * Return: 0 if the flower was successfully added or deleted, + * negative error code otherwise. */ static int ice_setup_tc_cls_flower(struct ice_netdev_priv *np, struct net_device *filter_dev, - struct flow_cls_offload *cls_flower) + struct flow_cls_offload *cls_flower, + bool ingress) { struct ice_vsi *vsi = np->vsi; @@ -8339,7 +8367,7 @@ ice_setup_tc_cls_flower(struct ice_netdev_priv *np, switch (cls_flower->command) { case FLOW_CLS_REPLACE: - return ice_add_cls_flower(filter_dev, vsi, cls_flower); + return ice_add_cls_flower(filter_dev, vsi, cls_flower, ingress); case FLOW_CLS_DESTROY: return ice_del_cls_flower(vsi, cls_flower); default: @@ -8348,20 +8376,46 @@ ice_setup_tc_cls_flower(struct ice_netdev_priv *np, } /** - * ice_setup_tc_block_cb - callback handler registered for TC block + * ice_setup_tc_block_cb_ingress - callback handler for ingress TC block * @type: TC SETUP type * @type_data: TC flower offload data that contains user input * @cb_priv: netdev private data + * + * Return: 0 if the setup was successful, negative error code otherwise. */ static int -ice_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) +ice_setup_tc_block_cb_ingress(enum tc_setup_type type, void *type_data, + void *cb_priv) { struct ice_netdev_priv *np = cb_priv; switch (type) { case TC_SETUP_CLSFLOWER: return ice_setup_tc_cls_flower(np, np->vsi->netdev, - type_data); + type_data, true); + default: + return -EOPNOTSUPP; + } +} + +/** + * ice_setup_tc_block_cb_egress - callback handler for egress TC block + * @type: TC SETUP type + * @type_data: TC flower offload data that contains user input + * @cb_priv: netdev private data + * + * Return: 0 if the setup was successful, negative error code otherwise. + */ +static int +ice_setup_tc_block_cb_egress(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct ice_netdev_priv *np = cb_priv; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return ice_setup_tc_cls_flower(np, np->vsi->netdev, + type_data, false); default: return -EOPNOTSUPP; } @@ -9306,27 +9360,45 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, void *type_data) { struct ice_netdev_priv *np = netdev_priv(netdev); + enum flow_block_binder_type binder_type; + struct iidc_rdma_core_dev_info *cdev; struct ice_pf *pf = np->vsi->back; + flow_setup_cb_t *flower_handler; bool locked = false; int err; switch (type) { case TC_SETUP_BLOCK: + binder_type = + ((struct flow_block_offload *)type_data)->binder_type; + + switch (binder_type) { + case FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS: + flower_handler = ice_setup_tc_block_cb_ingress; + break; + case FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS: + flower_handler = ice_setup_tc_block_cb_egress; + break; + default: + return -EOPNOTSUPP; + } + return flow_block_cb_setup_simple(type_data, &ice_block_cb_list, - ice_setup_tc_block_cb, - np, np, true); + flower_handler, + np, np, false); case TC_SETUP_QDISC_MQPRIO: if (ice_is_eswitch_mode_switchdev(pf)) { netdev_err(netdev, "TC MQPRIO offload not supported, switchdev is enabled\n"); return -EOPNOTSUPP; } - if (pf->adev) { + cdev = pf->cdev_info; + if (cdev && cdev->adev) { mutex_lock(&pf->adev_mutex); - device_lock(&pf->adev->dev); + device_lock(&cdev->adev->dev); locked = true; - if (pf->adev->dev.driver) { + if (cdev->adev->dev.driver) { netdev_err(netdev, "Cannot change qdisc when RDMA is active\n"); err = -EBUSY; goto adev_unlock; @@ -9340,7 +9412,7 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, adev_unlock: if (locked) { - device_unlock(&pf->adev->dev); + device_unlock(&cdev->adev->dev); mutex_unlock(&pf->adev_mutex); } return err; @@ -9376,7 +9448,7 @@ ice_indr_setup_block_cb(enum tc_setup_type type, void *type_data, case TC_SETUP_CLSFLOWER: return ice_setup_tc_cls_flower(np, priv->netdev, (struct flow_cls_offload *) - type_data); + type_data, false); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h index 6509d807627c..4f56d53d56b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.h +++ b/drivers/net/ethernet/intel/ice/ice_parser.h @@ -257,7 +257,6 @@ ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size, /*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/ #define ICE_BST_TCAM_TABLE_SIZE 256 #define ICE_BST_TCAM_KEY_SIZE 20 -#define ICE_BST_KEY_TCAM_SIZE 19 /* Boost TCAM item */ struct ice_bst_tcam_item { @@ -401,7 +400,6 @@ u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag); #define ICE_PARSER_GPR_NUM 128 #define ICE_PARSER_FLG_NUM 64 #define ICE_PARSER_ERR_NUM 16 -#define ICE_BST_KEY_SIZE 10 #define ICE_MARKER_ID_SIZE 9 #define ICE_MARKER_MAX_SIZE \ (ICE_MARKER_ID_SIZE * BITS_PER_BYTE - 1) @@ -431,13 +429,13 @@ struct ice_parser_rt { u8 pkt_buf[ICE_PARSER_MAX_PKT_LEN + ICE_PARSER_PKT_REV]; u16 pkt_len; u16 po; - u8 bst_key[ICE_BST_KEY_SIZE]; + u8 bst_key[ICE_BST_TCAM_KEY_SIZE]; struct ice_pg_cam_key pg_key; + u8 pg_prio; struct ice_alu *alu0; struct ice_alu *alu1; struct ice_alu *alu2; struct ice_pg_cam_action *action; - u8 pg_prio; struct ice_gpr_pu pu; u8 markers[ICE_MARKER_ID_SIZE]; bool protocols[ICE_PO_PAIR_SIZE]; diff --git a/drivers/net/ethernet/intel/ice/ice_parser_rt.c b/drivers/net/ethernet/intel/ice/ice_parser_rt.c index dedf5e854e4b..3995d662e050 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser_rt.c +++ b/drivers/net/ethernet/intel/ice/ice_parser_rt.c @@ -125,22 +125,20 @@ static void ice_bst_key_init(struct ice_parser_rt *rt, else key[idd] = imem->b_kb.prio; - idd = ICE_BST_KEY_TCAM_SIZE - 1; + idd = ICE_BST_TCAM_KEY_SIZE - 2; for (i = idd; i >= 0; i--) { int j; j = ho + idd - i; if (j < ICE_PARSER_MAX_PKT_LEN) - key[i] = rt->pkt_buf[ho + idd - i]; + key[i] = rt->pkt_buf[j]; else key[i] = 0; } - ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generated Boost TCAM Key:\n"); - ice_debug(rt->psr->hw, ICE_DBG_PARSER, "%02X %02X %02X %02X %02X %02X %02X %02X %02X %02X\n", - key[0], key[1], key[2], key[3], key[4], - key[5], key[6], key[7], key[8], key[9]); - ice_debug(rt->psr->hw, ICE_DBG_PARSER, "\n"); + ice_debug_array_w_prefix(rt->psr->hw, ICE_DBG_PARSER, + KBUILD_MODNAME ": Generated Boost TCAM Key", + key, ICE_BST_TCAM_KEY_SIZE); } static u16 ice_bit_rev_u16(u16 v, int len) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index efd770dfec44..b79a148ed0f2 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -16,28 +16,28 @@ static const char ice_pin_names[][64] = { }; static const struct ice_ptp_pin_desc ice_pin_desc_e82x[] = { - /* name, gpio */ - { TIME_SYNC, { 4, -1 }}, - { ONE_PPS, { -1, 5 }}, + /* name, gpio, delay */ + { TIME_SYNC, { 4, -1 }, { 0, 0 }}, + { ONE_PPS, { -1, 5 }, { 0, 11 }}, }; static const struct ice_ptp_pin_desc ice_pin_desc_e825c[] = { - /* name, gpio */ - { SDP0, { 0, 0 }}, - { SDP1, { 1, 1 }}, - { SDP2, { 2, 2 }}, - { SDP3, { 3, 3 }}, - { TIME_SYNC, { 4, -1 }}, - { ONE_PPS, { -1, 5 }}, + /* name, gpio, delay */ + { SDP0, { 0, 0 }, { 15, 14 }}, + { SDP1, { 1, 1 }, { 15, 14 }}, + { SDP2, { 2, 2 }, { 15, 14 }}, + { SDP3, { 3, 3 }, { 15, 14 }}, + { TIME_SYNC, { 4, -1 }, { 11, 0 }}, + { ONE_PPS, { -1, 5 }, { 0, 9 }}, }; static const struct ice_ptp_pin_desc ice_pin_desc_e810[] = { - /* name, gpio */ - { SDP0, { 0, 0 }}, - { SDP1, { 1, 1 }}, - { SDP2, { 2, 2 }}, - { SDP3, { 3, 3 }}, - { ONE_PPS, { -1, 5 }}, + /* name, gpio, delay */ + { SDP0, { 0, 0 }, { 0, 1 }}, + { SDP1, { 1, 1 }, { 0, 1 }}, + { SDP2, { 2, 2 }, { 0, 1 }}, + { SDP3, { 3, 3 }, { 0, 1 }}, + { ONE_PPS, { -1, 5 }, { 0, 1 }}, }; static const char ice_pin_names_nvm[][64] = { @@ -49,12 +49,12 @@ static const char ice_pin_names_nvm[][64] = { }; static const struct ice_ptp_pin_desc ice_pin_desc_e810_sma[] = { - /* name, gpio */ - { GNSS, { 1, -1 }}, - { SMA1, { 1, 0 }}, - { UFL1, { -1, 0 }}, - { SMA2, { 3, 2 }}, - { UFL2, { 3, -1 }}, + /* name, gpio, delay */ + { GNSS, { 1, -1 }, { 0, 0 }}, + { SMA1, { 1, 0 }, { 0, 1 }}, + { UFL1, { -1, 0 }, { 0, 1 }}, + { SMA2, { 3, 2 }, { 0, 1 }}, + { UFL2, { 3, -1 }, { 0, 0 }}, }; static struct ice_pf *ice_get_ctrl_pf(struct ice_pf *pf) @@ -298,18 +298,30 @@ void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) * @sts: Optional parameter for holding a pair of system timestamps from * the system clock. Will be ignored if NULL is given. */ -static u64 -ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) +u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, + struct ptp_system_timestamp *sts) { struct ice_hw *hw = &pf->hw; u32 hi, lo, lo2; u8 tmr_idx; + if (!ice_is_primary(hw)) + hw = ice_get_primary_hw(pf); + tmr_idx = ice_get_ptp_src_clock_index(hw); guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock); /* Read the system timestamp pre PHC read */ ptp_read_system_prets(sts); + if (hw->mac_type == ICE_MAC_E830) { + u64 clk_time = rd64(hw, E830_GLTSYN_TIME_L(tmr_idx)); + + /* Read the system timestamp post PHC read */ + ptp_read_system_postts(sts); + + return clk_time; + } + lo = rd32(hw, GLTSYN_TIME_L(tmr_idx)); /* Read the system timestamp post PHC read */ @@ -464,7 +476,9 @@ ice_ptp_is_tx_tracker_up(struct ice_ptp_tx *tx) */ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) { + struct ice_e810_params *params; struct ice_ptp_port *ptp_port; + unsigned long flags; struct sk_buff *skb; struct ice_pf *pf; @@ -473,6 +487,7 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); + params = &pf->hw.ptp.phy.e810; /* Drop packets which have waited for more than 2 seconds */ if (time_is_before_jiffies(tx->tstamps[idx].start + 2 * HZ)) { @@ -489,11 +504,17 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) ice_trace(tx_tstamp_fw_req, tx->tstamps[idx].skb, idx); + spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); + + params->atqbal_flags |= ATQBAL_FLAGS_INTR_IN_PROGRESS; + /* Write TS index to read to the PF register so the FW can read it */ - wr32(&pf->hw, PF_SB_ATQBAL, - TS_LL_READ_TS_INTR | FIELD_PREP(TS_LL_READ_TS_IDX, idx) | - TS_LL_READ_TS); + wr32(&pf->hw, REG_LL_PROXY_H, + REG_LL_PROXY_H_TS_INTR_ENA | FIELD_PREP(REG_LL_PROXY_H_TS_IDX, idx) | + REG_LL_PROXY_H_EXEC); tx->last_ll_ts_idx_read = idx; + + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); } /** @@ -504,35 +525,52 @@ void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx) { struct skb_shared_hwtstamps shhwtstamps = {}; u8 idx = tx->last_ll_ts_idx_read; + struct ice_e810_params *params; struct ice_ptp_port *ptp_port; u64 raw_tstamp, tstamp; bool drop_ts = false; struct sk_buff *skb; + unsigned long flags; + struct device *dev; struct ice_pf *pf; - u32 val; + u32 reg_ll_high; if (!tx->init || tx->last_ll_ts_idx_read < 0) return; ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); + dev = ice_pf_to_dev(pf); + params = &pf->hw.ptp.phy.e810; ice_trace(tx_tstamp_fw_done, tx->tstamps[idx].skb, idx); - val = rd32(&pf->hw, PF_SB_ATQBAL); + spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); + + if (!(params->atqbal_flags & ATQBAL_FLAGS_INTR_IN_PROGRESS)) + dev_dbg(dev, "%s: low latency interrupt request not in progress?\n", + __func__); + + /* Read the low 32 bit value */ + raw_tstamp = rd32(&pf->hw, REG_LL_PROXY_L); + /* Read the status together with high TS part */ + reg_ll_high = rd32(&pf->hw, REG_LL_PROXY_H); + + /* Wake up threads waiting on low latency interface */ + params->atqbal_flags &= ~ATQBAL_FLAGS_INTR_IN_PROGRESS; + + wake_up_locked(¶ms->atqbal_wq); + + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); /* When the bit is cleared, the TS is ready in the register */ - if (val & TS_LL_READ_TS) { + if (reg_ll_high & REG_LL_PROXY_H_EXEC) { dev_err(ice_pf_to_dev(pf), "Failed to get the Tx tstamp - FW not ready"); return; } /* High 8 bit value of the TS is on the bits 16:23 */ - raw_tstamp = FIELD_GET(TS_LL_READ_TS_HIGH, val); - raw_tstamp <<= 32; - - /* Read the low 32 bit value */ - raw_tstamp |= (u64)rd32(&pf->hw, PF_SB_ATQBAH); + raw_tstamp |= ((u64)FIELD_GET(REG_LL_PROXY_H_TS_HIGH, reg_ll_high)) << 32; /* Devices using this interface always verify the timestamp differs * relative to the last cached timestamp value. @@ -946,28 +984,6 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) } /** - * ice_ptp_init_tx_eth56g - Initialize tracking for Tx timestamps - * @pf: Board private structure - * @tx: the Tx tracking structure to initialize - * @port: the port this structure tracks - * - * Initialize the Tx timestamp tracker for this port. ETH56G PHYs - * have independent memory blocks for all ports. - * - * Return: 0 for success, -ENOMEM when failed to allocate Tx tracker - */ -static int ice_ptp_init_tx_eth56g(struct ice_pf *pf, struct ice_ptp_tx *tx, - u8 port) -{ - tx->block = port; - tx->offset = 0; - tx->len = INDEX_PER_PORT_ETH56G; - tx->has_ready_bitmap = 1; - - return ice_ptp_alloc_tx_tracker(tx); -} - -/** * ice_ptp_init_tx_e82x - Initialize tracking for Tx timestamps * @pf: Board private structure * @tx: the Tx tracking structure to initialize @@ -977,9 +993,11 @@ static int ice_ptp_init_tx_eth56g(struct ice_pf *pf, struct ice_ptp_tx *tx, * the timestamp block is shared for all ports in the same quad. To avoid * ports using the same timestamp index, logically break the block of * registers into chunks based on the port number. + * + * Return: 0 on success, -ENOMEM when out of memory */ -static int -ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) +static int ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, + u8 port) { tx->block = ICE_GET_QUAD_NUM(port); tx->offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT_E82X; @@ -990,24 +1008,27 @@ ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) } /** - * ice_ptp_init_tx_e810 - Initialize tracking for Tx timestamps + * ice_ptp_init_tx - Initialize tracking for Tx timestamps * @pf: Board private structure * @tx: the Tx tracking structure to initialize + * @port: the port this structure tracks + * + * Initialize the Tx timestamp tracker for this PF. For all PHYs except E82X, + * each port has its own block of timestamps, independent of the other ports. * - * Initialize the Tx timestamp tracker for this PF. For E810 devices, each - * port has its own block of timestamps, independent of the other ports. + * Return: 0 on success, -ENOMEM when out of memory */ -static int -ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx) +static int ice_ptp_init_tx(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) { - tx->block = pf->hw.port_info->lport; + tx->block = port; tx->offset = 0; - tx->len = INDEX_PER_PORT_E810; + tx->len = INDEX_PER_PORT; + /* The E810 PHY does not provide a timestamp ready bitmap. Instead, * verify new timestamps against cached copy of the last read * timestamp. */ - tx->has_ready_bitmap = 0; + tx->has_ready_bitmap = pf->hw.mac_type != ICE_MAC_E810; return ice_ptp_alloc_tx_tracker(tx); } @@ -1292,20 +1313,21 @@ ice_ptp_port_phy_stop(struct ice_ptp_port *ptp_port) struct ice_hw *hw = &pf->hw; int err; - if (ice_is_e810(hw)) - return 0; - mutex_lock(&ptp_port->ps_lock); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_stop_phy_timer_eth56g(hw, port, true); + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + err = 0; break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: kthread_cancel_delayed_work_sync(&ptp_port->ov_work); err = ice_stop_phy_timer_e82x(hw, port, true); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_stop_phy_timer_eth56g(hw, port, true); + break; default: err = -ENODEV; } @@ -1335,19 +1357,17 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port) unsigned long flags; int err; - if (ice_is_e810(hw)) - return 0; - if (!ptp_port->link_up) return ice_ptp_port_phy_stop(ptp_port); mutex_lock(&ptp_port->ps_lock); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_start_phy_timer_eth56g(hw, port); + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + err = 0; break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: /* Start the PHY timer in Vernier mode */ kthread_cancel_delayed_work_sync(&ptp_port->ov_work); @@ -1372,6 +1392,9 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port) kthread_queue_delayed_work(pf->ptp.kworker, &ptp_port->ov_work, 0); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_start_phy_timer_eth56g(hw, port); + break; default: err = -ENODEV; } @@ -1406,12 +1429,14 @@ void ice_ptp_link_change(struct ice_pf *pf, bool linkup) /* Skip HW writes if reset is in progress */ if (pf->hw.reset_ongoing) return; - switch (ice_get_phy_model(hw)) { - case ICE_PHY_E810: - /* Do not reconfigure E810 PHY */ + + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + /* Do not reconfigure E810 or E830 PHY */ return; - case ICE_PHY_ETH56G: - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: ice_ptp_port_phy_restart(ptp_port); return; default: @@ -1439,46 +1464,45 @@ static int ice_ptp_cfg_phy_interrupt(struct ice_pf *pf, bool ena, u32 threshold) ice_ptp_reset_ts_memory(hw); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: { - int port; + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + return 0; + case ICE_MAC_GENERIC: { + int quad; - for (port = 0; port < hw->ptp.num_lports; port++) { + for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); + quad++) { int err; - err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold); + err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold); if (err) { - dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n", - port, err); + dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n", + quad, err); return err; } } return 0; } - case ICE_PHY_E82X: { - int quad; + case ICE_MAC_GENERIC_3K_E825: { + int port; - for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); - quad++) { + for (port = 0; port < hw->ptp.num_lports; port++) { int err; - err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold); + err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold); if (err) { - dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n", - quad, err); + dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n", + port, err); return err; } } return 0; } - case ICE_PHY_E810: - return 0; - case ICE_PHY_UNSUP: + case ICE_MAC_UNKNOWN: default: - dev_warn(dev, "%s: Unexpected PHY model %d\n", __func__, - ice_get_phy_model(hw)); return -EOPNOTSUPP; } } @@ -1558,18 +1582,29 @@ void ice_ptp_extts_event(struct ice_pf *pf) * Event is defined in GLTSYN_EVNT_0 register */ for (chan = 0; chan < GLTSYN_EVNT_H_IDX_MAX; chan++) { + int pin_desc_idx; + /* Check if channel is enabled */ - if (pf->ptp.ext_ts_irq & (1 << chan)) { - lo = rd32(hw, GLTSYN_EVNT_L(chan, tmr_idx)); - hi = rd32(hw, GLTSYN_EVNT_H(chan, tmr_idx)); - event.timestamp = (((u64)hi) << 32) | lo; - event.type = PTP_CLOCK_EXTTS; - event.index = chan; - - /* Fire event */ - ptp_clock_event(pf->ptp.clock, &event); - pf->ptp.ext_ts_irq &= ~(1 << chan); + if (!(pf->ptp.ext_ts_irq & (1 << chan))) + continue; + + lo = rd32(hw, GLTSYN_EVNT_L(chan, tmr_idx)); + hi = rd32(hw, GLTSYN_EVNT_H(chan, tmr_idx)); + event.timestamp = (u64)hi << 32 | lo; + + /* Add delay compensation */ + pin_desc_idx = ice_ptp_find_pin_idx(pf, PTP_PF_EXTTS, chan); + if (pin_desc_idx >= 0) { + const struct ice_ptp_pin_desc *desc; + + desc = &pf->ptp.ice_pin_desc[pin_desc_idx]; + event.timestamp -= desc->delay[0]; } + + event.type = PTP_CLOCK_EXTTS; + event.index = chan; + pf->ptp.ext_ts_irq &= ~(1 << chan); + ptp_clock_event(pf->ptp.clock, &event); } } @@ -1592,14 +1627,6 @@ static int ice_ptp_cfg_extts(struct ice_pf *pf, struct ptp_extts_request *rq, int pin_desc_idx; u8 tmr_idx; - /* Reject requests with unsupported flags */ - - if (rq->flags & ~(PTP_ENABLE_FEATURE | - PTP_RISING_EDGE | - PTP_FALLING_EDGE | - PTP_STRICT_FLAGS)) - return -EOPNOTSUPP; - tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; chan = rq->index; @@ -1703,7 +1730,7 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan, /* 0. Reset mode & out_en in AUX_OUT */ wr32(hw, GLTSYN_AUX_OUT(chan, tmr_idx), 0); - if (ice_is_e825c(hw)) { + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) { int err; /* Enable/disable CGU 1PPS output for E825C */ @@ -1746,6 +1773,7 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan, 8 + chan + (tmr_idx * 4)); wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val); + ice_flush(hw); return 0; } @@ -1764,19 +1792,17 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan, static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, int on) { + unsigned int gpio_pin, prop_delay_ns; u64 clk, period, start, phase; struct ice_hw *hw = &pf->hw; - unsigned int gpio_pin; int pin_desc_idx; - if (rq->flags & ~PTP_PEROUT_PHASE) - return -EOPNOTSUPP; - pin_desc_idx = ice_ptp_find_pin_idx(pf, PTP_PF_PEROUT, rq->index); if (pin_desc_idx < 0) return -EIO; gpio_pin = pf->ptp.ice_pin_desc[pin_desc_idx].gpio[1]; + prop_delay_ns = pf->ptp.ice_pin_desc[pin_desc_idx].delay[1]; period = rq->period.sec * NSEC_PER_SEC + rq->period.nsec; /* If we're disabling the output or period is 0, clear out CLKO and TGT @@ -1786,7 +1812,7 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, return ice_ptp_write_perout(hw, rq->index, gpio_pin, 0, 0); if (strncmp(pf->ptp.pin_desc[pin_desc_idx].name, "1PPS", 64) == 0 && - period != NSEC_PER_SEC && hw->ptp.phy_model == ICE_PHY_E82X) { + period != NSEC_PER_SEC && hw->mac_type == ICE_MAC_GENERIC) { dev_err(ice_pf_to_dev(pf), "1PPS pin supports only 1 s period\n"); return -EOPNOTSUPP; } @@ -1805,14 +1831,15 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, div64_u64_rem(start, period, &phase); /* If we have only phase or start time is in the past, start the timer - * at the next multiple of period, maintaining phase. + * at the next multiple of period, maintaining phase at least 0.5 second + * from now, so we have time to write it to HW. */ - clk = ice_ptp_read_src_clk_reg(pf, NULL); - if (rq->flags & PTP_PEROUT_PHASE || start <= clk - ice_prop_delay(hw)) + clk = ice_ptp_read_src_clk_reg(pf, NULL) + NSEC_PER_MSEC * 500; + if (rq->flags & PTP_PEROUT_PHASE || start <= clk - prop_delay_ns) start = div64_u64(clk + period - 1, period) * period + phase; /* Compensate for propagation delay from the generator to the pin. */ - start -= ice_prop_delay(hw); + start -= prop_delay_ns; return ice_ptp_write_perout(hw, rq->index, gpio_pin, start, period); } @@ -2040,7 +2067,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) /* For Vernier mode on E82X, we need to recalibrate after new settime. * Start with marking timestamps as invalid. */ - if (ice_get_phy_model(hw) == ICE_PHY_E82X) { + if (hw->mac_type == ICE_MAC_GENERIC) { err = ice_ptp_clear_phy_offset_ready_e82x(hw); if (err) dev_warn(ice_pf_to_dev(pf), "Failed to mark timestamps as invalid before settime\n"); @@ -2064,7 +2091,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) ice_ptp_enable_all_perout(pf); /* Recalibrate and re-enable timestamp blocks for E822/E823 */ - if (ice_get_phy_model(hw) == ICE_PHY_E82X) + if (hw->mac_type == ICE_MAC_GENERIC) ice_ptp_restart_all_phy(pf); exit: if (err) { @@ -2142,93 +2169,157 @@ static int ice_ptp_adjtime(struct ptp_clock_info *info, s64 delta) return 0; } +/** + * struct ice_crosststamp_cfg - Device cross timestamp configuration + * @lock_reg: The hardware semaphore lock to use + * @lock_busy: Bit in the semaphore lock indicating the lock is busy + * @ctl_reg: The hardware register to request cross timestamp + * @ctl_active: Bit in the control register to request cross timestamp + * @art_time_l: Lower 32-bits of ART system time + * @art_time_h: Upper 32-bits of ART system time + * @dev_time_l: Lower 32-bits of device time (per timer index) + * @dev_time_h: Upper 32-bits of device time (per timer index) + */ +struct ice_crosststamp_cfg { + /* HW semaphore lock register */ + u32 lock_reg; + u32 lock_busy; + + /* Capture control register */ + u32 ctl_reg; + u32 ctl_active; + + /* Time storage */ + u32 art_time_l; + u32 art_time_h; + u32 dev_time_l[2]; + u32 dev_time_h[2]; +}; + +static const struct ice_crosststamp_cfg ice_crosststamp_cfg_e82x = { + .lock_reg = PFHH_SEM, + .lock_busy = PFHH_SEM_BUSY_M, + .ctl_reg = GLHH_ART_CTL, + .ctl_active = GLHH_ART_CTL_ACTIVE_M, + .art_time_l = GLHH_ART_TIME_L, + .art_time_h = GLHH_ART_TIME_H, + .dev_time_l[0] = GLTSYN_HHTIME_L(0), + .dev_time_h[0] = GLTSYN_HHTIME_H(0), + .dev_time_l[1] = GLTSYN_HHTIME_L(1), + .dev_time_h[1] = GLTSYN_HHTIME_H(1), +}; + #ifdef CONFIG_ICE_HWTS +static const struct ice_crosststamp_cfg ice_crosststamp_cfg_e830 = { + .lock_reg = E830_PFPTM_SEM, + .lock_busy = E830_PFPTM_SEM_BUSY_M, + .ctl_reg = E830_GLPTM_ART_CTL, + .ctl_active = E830_GLPTM_ART_CTL_ACTIVE_M, + .art_time_l = E830_GLPTM_ART_TIME_L, + .art_time_h = E830_GLPTM_ART_TIME_H, + .dev_time_l[0] = E830_GLTSYN_PTMTIME_L(0), + .dev_time_h[0] = E830_GLTSYN_PTMTIME_H(0), + .dev_time_l[1] = E830_GLTSYN_PTMTIME_L(1), + .dev_time_h[1] = E830_GLTSYN_PTMTIME_H(1), +}; + +#endif /* CONFIG_ICE_HWTS */ +/** + * struct ice_crosststamp_ctx - Device cross timestamp context + * @snapshot: snapshot of system clocks for historic interpolation + * @pf: pointer to the PF private structure + * @cfg: pointer to hardware configuration for cross timestamp + */ +struct ice_crosststamp_ctx { + struct system_time_snapshot snapshot; + struct ice_pf *pf; + const struct ice_crosststamp_cfg *cfg; +}; + /** - * ice_ptp_get_syncdevicetime - Get the cross time stamp info + * ice_capture_crosststamp - Capture a device/system cross timestamp * @device: Current device time * @system: System counter value read synchronously with device time - * @ctx: Context provided by timekeeping code + * @__ctx: Context passed from ice_ptp_getcrosststamp * * Read device and system (ART) clock simultaneously and return the corrected * clock values in ns. + * + * Return: zero on success, or a negative error code on failure. */ -static int -ice_ptp_get_syncdevicetime(ktime_t *device, - struct system_counterval_t *system, - void *ctx) +static int ice_capture_crosststamp(ktime_t *device, + struct system_counterval_t *system, + void *__ctx) { - struct ice_pf *pf = (struct ice_pf *)ctx; - struct ice_hw *hw = &pf->hw; - u32 hh_lock, hh_art_ctl; - int i; + struct ice_crosststamp_ctx *ctx = __ctx; + const struct ice_crosststamp_cfg *cfg; + u32 lock, ctl, ts_lo, ts_hi, tmr_idx; + struct ice_pf *pf; + struct ice_hw *hw; + int err; + u64 ts; -#define MAX_HH_HW_LOCK_TRIES 5 -#define MAX_HH_CTL_LOCK_TRIES 100 + cfg = ctx->cfg; + pf = ctx->pf; + hw = &pf->hw; - for (i = 0; i < MAX_HH_HW_LOCK_TRIES; i++) { - /* Get the HW lock */ - hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id)); - if (hh_lock & PFHH_SEM_BUSY_M) { - usleep_range(10000, 15000); - continue; - } - break; - } - if (hh_lock & PFHH_SEM_BUSY_M) { - dev_err(ice_pf_to_dev(pf), "PTP failed to get hh lock\n"); + tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; + if (tmr_idx > 1) + return -EINVAL; + + /* Poll until we obtain the cross-timestamp hardware semaphore */ + err = rd32_poll_timeout(hw, cfg->lock_reg, lock, + !(lock & cfg->lock_busy), + 10 * USEC_PER_MSEC, 50 * USEC_PER_MSEC); + if (err) { + dev_err(ice_pf_to_dev(pf), "PTP failed to get cross timestamp lock\n"); return -EBUSY; } + /* Snapshot system time for historic interpolation */ + ktime_get_snapshot(&ctx->snapshot); + /* Program cmd to master timer */ ice_ptp_src_cmd(hw, ICE_PTP_READ_TIME); /* Start the ART and device clock sync sequence */ - hh_art_ctl = rd32(hw, GLHH_ART_CTL); - hh_art_ctl = hh_art_ctl | GLHH_ART_CTL_ACTIVE_M; - wr32(hw, GLHH_ART_CTL, hh_art_ctl); - - for (i = 0; i < MAX_HH_CTL_LOCK_TRIES; i++) { - /* Wait for sync to complete */ - hh_art_ctl = rd32(hw, GLHH_ART_CTL); - if (hh_art_ctl & GLHH_ART_CTL_ACTIVE_M) { - udelay(1); - continue; - } else { - u32 hh_ts_lo, hh_ts_hi, tmr_idx; - u64 hh_ts; - - tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; - /* Read ART time */ - hh_ts_lo = rd32(hw, GLHH_ART_TIME_L); - hh_ts_hi = rd32(hw, GLHH_ART_TIME_H); - hh_ts = ((u64)hh_ts_hi << 32) | hh_ts_lo; - system->cycles = hh_ts; - system->cs_id = CSID_X86_ART; - /* Read Device source clock time */ - hh_ts_lo = rd32(hw, GLTSYN_HHTIME_L(tmr_idx)); - hh_ts_hi = rd32(hw, GLTSYN_HHTIME_H(tmr_idx)); - hh_ts = ((u64)hh_ts_hi << 32) | hh_ts_lo; - *device = ns_to_ktime(hh_ts); - break; - } - } + ctl = rd32(hw, cfg->ctl_reg); + ctl |= cfg->ctl_active; + wr32(hw, cfg->ctl_reg, ctl); + /* Poll until hardware completes the capture */ + err = rd32_poll_timeout(hw, cfg->ctl_reg, ctl, !(ctl & cfg->ctl_active), + 5, 20 * USEC_PER_MSEC); + if (err) + goto err_timeout; + + /* Read ART system time */ + ts_lo = rd32(hw, cfg->art_time_l); + ts_hi = rd32(hw, cfg->art_time_h); + ts = ((u64)ts_hi << 32) | ts_lo; + system->cycles = ts; + system->cs_id = CSID_X86_ART; + + /* Read Device source clock time */ + ts_lo = rd32(hw, cfg->dev_time_l[tmr_idx]); + ts_hi = rd32(hw, cfg->dev_time_h[tmr_idx]); + ts = ((u64)ts_hi << 32) | ts_lo; + *device = ns_to_ktime(ts); + +err_timeout: /* Clear the master timer */ ice_ptp_src_cmd(hw, ICE_PTP_NOP); /* Release HW lock */ - hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id)); - hh_lock = hh_lock & ~PFHH_SEM_BUSY_M; - wr32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id), hh_lock); + lock = rd32(hw, cfg->lock_reg); + lock &= ~cfg->lock_busy; + wr32(hw, cfg->lock_reg, lock); - if (i == MAX_HH_CTL_LOCK_TRIES) - return -ETIMEDOUT; - - return 0; + return err; } /** - * ice_ptp_getcrosststamp_e82x - Capture a device cross timestamp + * ice_ptp_getcrosststamp - Capture a device cross timestamp * @info: the driver's PTP info structure * @cts: The memory to fill the cross timestamp info * @@ -2236,22 +2327,36 @@ ice_ptp_get_syncdevicetime(ktime_t *device, * clock. Fill the cross timestamp information and report it back to the * caller. * - * This is only valid for E822 and E823 devices which have support for - * generating the cross timestamp via PCIe PTM. - * * In order to correctly correlate the ART timestamp back to the TSC time, the * CPU must have X86_FEATURE_TSC_KNOWN_FREQ. + * + * Return: zero on success, or a negative error code on failure. */ -static int -ice_ptp_getcrosststamp_e82x(struct ptp_clock_info *info, - struct system_device_crosststamp *cts) +static int ice_ptp_getcrosststamp(struct ptp_clock_info *info, + struct system_device_crosststamp *cts) { struct ice_pf *pf = ptp_info_to_pf(info); + struct ice_crosststamp_ctx ctx = { + .pf = pf, + }; + + switch (pf->hw.mac_type) { + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: + ctx.cfg = &ice_crosststamp_cfg_e82x; + break; +#ifdef CONFIG_ICE_HWTS + case ICE_MAC_E830: + ctx.cfg = &ice_crosststamp_cfg_e830; + break; +#endif /* CONFIG_ICE_HWTS */ + default: + return -EOPNOTSUPP; + } - return get_device_system_crosststamp(ice_ptp_get_syncdevicetime, - pf, NULL, cts); + return get_device_system_crosststamp(ice_capture_crosststamp, &ctx, + &ctx.snapshot, cts); } -#endif /* CONFIG_ICE_HWTS */ /** * ice_ptp_get_ts_config - ioctl interface to read the timestamping config @@ -2512,13 +2617,9 @@ static int ice_ptp_parse_sdp_entries(struct ice_pf *pf, __le16 *entries, */ static void ice_ptp_set_funcs_e82x(struct ice_pf *pf) { -#ifdef CONFIG_ICE_HWTS - if (boot_cpu_has(X86_FEATURE_ART) && - boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) - pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp_e82x; + pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp; -#endif /* CONFIG_ICE_HWTS */ - if (ice_is_e825c(&pf->hw)) { + if (pf->hw.mac_type == ICE_MAC_GENERIC_3K_E825) { pf->ptp.ice_pin_desc = ice_pin_desc_e825c; pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e825c); } else { @@ -2585,6 +2686,28 @@ err: } /** + * ice_ptp_set_funcs_e830 - Set specialized functions for E830 support + * @pf: Board private structure + * + * Assign functions to the PTP capabiltiies structure for E830 devices. + * Functions which operate across all device families should be set directly + * in ice_ptp_set_caps. Only add functions here which are distinct for E830 + * devices. + */ +static void ice_ptp_set_funcs_e830(struct ice_pf *pf) +{ +#ifdef CONFIG_ICE_HWTS + if (pcie_ptm_enabled(pf->pdev) && boot_cpu_has(X86_FEATURE_ART)) + pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp; + +#endif /* CONFIG_ICE_HWTS */ + /* Rest of the config is the same as base E810 */ + pf->ptp.ice_pin_desc = ice_pin_desc_e810; + pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e810); + ice_ptp_setup_pin_cfg(pf); +} + +/** * ice_ptp_set_caps - Set PTP capabilities * @pf: Board private structure */ @@ -2606,10 +2729,25 @@ static void ice_ptp_set_caps(struct ice_pf *pf) info->enable = ice_ptp_gpio_enable; info->verify = ice_verify_pin; - if (ice_is_e810(&pf->hw)) + info->supported_extts_flags = PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS; + info->supported_perout_flags = PTP_PEROUT_PHASE; + + switch (pf->hw.mac_type) { + case ICE_MAC_E810: ice_ptp_set_funcs_e810(pf); - else + return; + case ICE_MAC_E830: + ice_ptp_set_funcs_e830(pf); + return; + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: ice_ptp_set_funcs_e82x(pf); + return; + default: + return; + } } /** @@ -2720,6 +2858,65 @@ enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf) } /** + * ice_ptp_ts_irq - Process the PTP Tx timestamps in IRQ context + * @pf: Board private structure + * + * Return: IRQ_WAKE_THREAD if Tx timestamp read has to be handled in the bottom + * half of the interrupt and IRQ_HANDLED otherwise. + */ +irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + + switch (hw->mac_type) { + case ICE_MAC_E810: + /* E810 capable of low latency timestamping with interrupt can + * request a single timestamp in the top half and wait for + * a second LL TS interrupt from the FW when it's ready. + */ + if (hw->dev_caps.ts_dev_info.ts_ll_int_read) { + struct ice_ptp_tx *tx = &pf->ptp.port.tx; + u8 idx; + + if (!ice_pf_state_is_nominal(pf)) + return IRQ_HANDLED; + + spin_lock(&tx->lock); + idx = find_next_bit_wrap(tx->in_use, tx->len, + tx->last_ll_ts_idx_read + 1); + if (idx != tx->len) + ice_ptp_req_tx_single_tstamp(tx, idx); + spin_unlock(&tx->lock); + + return IRQ_HANDLED; + } + fallthrough; /* non-LL_TS E810 */ + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: + /* All other devices process timestamps in the bottom half due + * to sleeping or polling. + */ + if (!ice_ptp_pf_handles_tx_interrupt(pf)) + return IRQ_HANDLED; + + set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread); + return IRQ_WAKE_THREAD; + case ICE_MAC_E830: + /* E830 can read timestamps in the top half using rd32() */ + if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) { + /* Process outstanding Tx timestamps. If there + * is more work, re-arm the interrupt to trigger again. + */ + wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); + ice_flush(hw); + } + return IRQ_HANDLED; + default: + return IRQ_HANDLED; + } +} + +/** * ice_ptp_maybe_trigger_tx_interrupt - Trigger Tx timstamp interrupt * @pf: Board private structure * @@ -2739,7 +2936,7 @@ static void ice_ptp_maybe_trigger_tx_interrupt(struct ice_pf *pf) bool trigger_oicr = false; unsigned int i; - if (ice_is_e810(hw)) + if (!pf->ptp.port.tx.has_ready_bitmap) return; if (!ice_pf_src_tmr_owned(pf)) @@ -2786,6 +2983,32 @@ static void ice_ptp_periodic_work(struct kthread_work *work) } /** + * ice_ptp_prepare_rebuild_sec - Prepare second NAC for PTP reset or rebuild + * @pf: Board private structure + * @rebuild: rebuild if true, prepare if false + * @reset_type: the reset type being performed + */ +static void ice_ptp_prepare_rebuild_sec(struct ice_pf *pf, bool rebuild, + enum ice_reset_req reset_type) +{ + struct list_head *entry; + + list_for_each(entry, &pf->adapter->ports.ports) { + struct ice_ptp_port *port = list_entry(entry, + struct ice_ptp_port, + list_node); + struct ice_pf *peer_pf = ptp_port_to_pf(port); + + if (!ice_is_primary(&peer_pf->hw)) { + if (rebuild) + ice_ptp_rebuild(peer_pf, reset_type); + else + ice_ptp_prepare_for_reset(peer_pf, reset_type); + } + } +} + +/** * ice_ptp_prepare_for_reset - Prepare PTP for reset * @pf: Board private structure * @reset_type: the reset type being performed @@ -2793,6 +3016,7 @@ static void ice_ptp_periodic_work(struct kthread_work *work) void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) { struct ice_ptp *ptp = &pf->ptp; + struct ice_hw *hw = &pf->hw; u8 src_tmr; if (ptp->state != ICE_PTP_READY) @@ -2808,6 +3032,9 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) if (reset_type == ICE_RESET_PFR) return; + if (ice_pf_src_tmr_owned(pf) && hw->mac_type == ICE_MAC_GENERIC_3K_E825) + ice_ptp_prepare_rebuild_sec(pf, false, reset_type); + ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx); /* Disable periodic outputs */ @@ -2874,14 +3101,12 @@ static int ice_ptp_rebuild_owner(struct ice_pf *pf) */ ice_ptp_flush_all_tx_tracker(pf); - if (!ice_is_e810(hw)) { - /* Enable quad interrupts */ - err = ice_ptp_cfg_phy_interrupt(pf, true, 1); - if (err) - return err; + /* Enable quad interrupts */ + err = ice_ptp_cfg_phy_interrupt(pf, true, 1); + if (err) + return err; - ice_ptp_restart_all_phy(pf); - } + ice_ptp_restart_all_phy(pf); /* Re-enable all periodic outputs and external timestamp events */ ice_ptp_enable_all_perout(pf); @@ -2931,12 +3156,6 @@ err: dev_err(ice_pf_to_dev(pf), "PTP reset failed %d\n", err); } -static bool ice_is_primary(struct ice_hw *hw) -{ - return ice_is_e825c(hw) && ice_is_dual(hw) ? - !!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M) : true; -} - static int ice_ptp_setup_adapter(struct ice_pf *pf) { if (!ice_pf_src_tmr_owned(pf) || !ice_is_primary(&pf->hw)) @@ -2952,7 +3171,7 @@ static int ice_ptp_setup_pf(struct ice_pf *pf) struct ice_ptp *ctrl_ptp = ice_get_ctrl_ptp(pf); struct ice_ptp *ptp = &pf->ptp; - if (WARN_ON(!ctrl_ptp) || ice_get_phy_model(&pf->hw) == ICE_PHY_UNSUP) + if (WARN_ON(!ctrl_ptp) || pf->hw.mac_type == ICE_MAC_UNKNOWN) return -ENODEV; INIT_LIST_HEAD(&ptp->port.list_node); @@ -2969,7 +3188,7 @@ static void ice_ptp_cleanup_pf(struct ice_pf *pf) { struct ice_ptp *ptp = &pf->ptp; - if (ice_get_phy_model(&pf->hw) != ICE_PHY_UNSUP) { + if (pf->hw.mac_type != ICE_MAC_UNKNOWN) { mutex_lock(&pf->adapter->ports.lock); list_del(&ptp->port.list_node); mutex_unlock(&pf->adapter->ports.lock); @@ -3072,7 +3291,7 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp) /* Allocate a kworker for handling work required for the ports * connected to the PTP hardware clock. */ - kworker = kthread_create_worker(0, "ice-ptp-%s", + kworker = kthread_run_worker(0, "ice-ptp-%s", dev_name(ice_pf_to_dev(pf))); if (IS_ERR(kworker)) return PTR_ERR(kworker); @@ -3089,6 +3308,8 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp) * ice_ptp_init_port - Initialize PTP port structure * @pf: Board private structure * @ptp_port: PTP port structure + * + * Return: 0 on success, -ENODEV on invalid MAC type, -ENOMEM on failed alloc. */ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) { @@ -3096,16 +3317,14 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) mutex_init(&ptp_port->ps_lock); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_ptp_init_tx_eth56g(pf, &ptp_port->tx, - ptp_port->port_num); - case ICE_PHY_E810: - return ice_ptp_init_tx_e810(pf, &ptp_port->tx); - case ICE_PHY_E82X: + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + case ICE_MAC_GENERIC_3K_E825: + return ice_ptp_init_tx(pf, &ptp_port->tx, ptp_port->port_num); + case ICE_MAC_GENERIC: kthread_init_delayed_work(&ptp_port->ov_work, ice_ptp_wait_for_offsets); - return ice_ptp_init_tx_e82x(pf, &ptp_port->tx, ptp_port->port_num); default: @@ -3124,8 +3343,8 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) */ static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf) { - switch (ice_get_phy_model(&pf->hw)) { - case ICE_PHY_E82X: + switch (pf->hw.mac_type) { + case ICE_MAC_GENERIC: /* E822 based PHY has the clock owner process the interrupt * for all ports. */ @@ -3156,17 +3375,16 @@ void ice_ptp_init(struct ice_pf *pf) { struct ice_ptp *ptp = &pf->ptp; struct ice_hw *hw = &pf->hw; - int lane_num, err; + int err; ptp->state = ICE_PTP_INITIALIZING; - lane_num = ice_get_phy_lane_number(hw); - if (lane_num < 0) { - err = lane_num; + if (hw->lane_num < 0) { + err = hw->lane_num; goto err_exit; } + ptp->port.port_num = hw->lane_num; - ptp->port.port_num = (u8)lane_num; ice_ptp_init_hw(hw); ice_ptp_init_tx_interrupt_mode(pf); diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index c490d98fd9c6..3b769a0cad00 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -128,8 +128,7 @@ struct ice_ptp_tx { /* Quad and port information for initializing timestamp blocks */ #define INDEX_PER_QUAD 64 #define INDEX_PER_PORT_E82X 16 -#define INDEX_PER_PORT_E810 64 -#define INDEX_PER_PORT_ETH56G 64 +#define INDEX_PER_PORT 64 /** * struct ice_ptp_port - data used to initialize an external port for PTP @@ -211,6 +210,7 @@ enum ice_ptp_pin_nvm { * struct ice_ptp_pin_desc - hardware pin description data * @name_idx: index of the name of pin in ice_pin_names * @gpio: the associated GPIO input and output pins + * @delay: input and output signal delays in nanoseconds * * Structure describing a PTP-capable GPIO pin that extends ptp_pin_desc array * for the device. Device families have separate sets of available pins with @@ -219,6 +219,7 @@ enum ice_ptp_pin_nvm { struct ice_ptp_pin_desc { int name_idx; int gpio[2]; + unsigned int delay[2]; }; /** @@ -302,6 +303,9 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx); void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx); enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf); +irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf); +u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, + struct ptp_system_timestamp *sts); u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, const struct ice_pkt_ctx *pkt_ctx); @@ -340,6 +344,17 @@ static inline bool ice_ptp_process_ts(struct ice_pf *pf) return true; } +static inline irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) +{ + return IRQ_HANDLED; +} + +static inline u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, + struct ptp_system_timestamp *sts) +{ + return 0; +} + static inline u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, const struct ice_pkt_ctx *pkt_ctx) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h index a8e57cf05a9c..003cdfada3ca 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h @@ -10,70 +10,25 @@ /* Constants defined for the PTP 1588 clock hardware. */ const struct ice_phy_reg_info_eth56g eth56g_phy_res[NUM_ETH56G_PHY_RES] = { - /* ETH56G_PHY_REG_PTP */ - { - /* base_addr */ - { - 0x092000, - 0x126000, - 0x1BA000, - 0x24E000, - 0x2E2000, - }, - /* step */ - 0x98, + [ETH56G_PHY_REG_PTP] = { + .base_addr = 0x092000, + .step = 0x98, }, - /* ETH56G_PHY_MEM_PTP */ - { - /* base_addr */ - { - 0x093000, - 0x127000, - 0x1BB000, - 0x24F000, - 0x2E3000, - }, - /* step */ - 0x200, + [ETH56G_PHY_MEM_PTP] = { + .base_addr = 0x093000, + .step = 0x200, }, - /* ETH56G_PHY_REG_XPCS */ - { - /* base_addr */ - { - 0x000000, - 0x009400, - 0x128000, - 0x1BC000, - 0x250000, - }, - /* step */ - 0x21000, + [ETH56G_PHY_REG_XPCS] = { + .base_addr = 0x000000, + .step = 0x21000, }, - /* ETH56G_PHY_REG_MAC */ - { - /* base_addr */ - { - 0x085000, - 0x119000, - 0x1AD000, - 0x241000, - 0x2D5000, - }, - /* step */ - 0x1000, + [ETH56G_PHY_REG_MAC] = { + .base_addr = 0x085000, + .step = 0x1000, }, - /* ETH56G_PHY_REG_GPCS */ - { - /* base_addr */ - { - 0x084000, - 0x118000, - 0x1AC000, - 0x240000, - 0x2D4000, - }, - /* step */ - 0x400, + [ETH56G_PHY_REG_GPCS] = { + .base_addr = 0x084000, + .step = 0x400, }, }; @@ -341,8 +296,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 823437500, /* 823.4375 MHz PLL */ /* nominal_incval */ 0x136e44fabULL, - /* pps_delay */ - 11, }, /* ICE_TIME_REF_FREQ_122_880 -> 122.88 MHz */ @@ -351,8 +304,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 783360000, /* 783.36 MHz */ /* nominal_incval */ 0x146cc2177ULL, - /* pps_delay */ - 12, }, /* ICE_TIME_REF_FREQ_125_000 -> 125 MHz */ @@ -361,8 +312,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 796875000, /* 796.875 MHz */ /* nominal_incval */ 0x141414141ULL, - /* pps_delay */ - 12, }, /* ICE_TIME_REF_FREQ_153_600 -> 153.6 MHz */ @@ -371,8 +320,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 816000000, /* 816 MHz */ /* nominal_incval */ 0x139b9b9baULL, - /* pps_delay */ - 12, }, /* ICE_TIME_REF_FREQ_156_250 -> 156.25 MHz */ @@ -381,8 +328,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 830078125, /* 830.78125 MHz */ /* nominal_incval */ 0x134679aceULL, - /* pps_delay */ - 11, }, /* ICE_TIME_REF_FREQ_245_760 -> 245.76 MHz */ @@ -391,8 +336,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 783360000, /* 783.36 MHz */ /* nominal_incval */ 0x146cc2177ULL, - /* pps_delay */ - 12, }, }; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 02e84f5b1d45..ccac84eb34c9 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -240,7 +240,7 @@ static int ice_read_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 *val) { struct ice_sbq_msg_input cgu_msg = { .opcode = ice_sbq_msg_rd, - .dest_dev = cgu, + .dest_dev = ice_sbq_dev_cgu, .msg_addr_low = addr }; int err; @@ -272,7 +272,7 @@ static int ice_write_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 val) { struct ice_sbq_msg_input cgu_msg = { .opcode = ice_sbq_msg_wr, - .dest_dev = cgu, + .dest_dev = ice_sbq_dev_cgu, .msg_addr_low = addr, .data = val }; @@ -391,7 +391,7 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw, /* Log the current clock configuration */ ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.ts_pll_enable ? "enabled" : "disabled", + str_enabled_disabled(dw24.ts_pll_enable), ice_clk_src_str(dw24.time_ref_sel), ice_clk_freq_str(dw9.time_ref_freq_sel), bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked"); @@ -469,7 +469,7 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw, /* Log the current clock configuration */ ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.ts_pll_enable ? "enabled" : "disabled", + str_enabled_disabled(dw24.ts_pll_enable), ice_clk_src_str(dw24.time_ref_sel), ice_clk_freq_str(dw9.time_ref_freq_sel), bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked"); @@ -546,7 +546,7 @@ static int ice_cfg_cgu_pll_e825c(struct ice_hw *hw, /* Log the current clock configuration */ ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.ts_pll_enable ? "enabled" : "disabled", + str_enabled_disabled(dw24.ts_pll_enable), ice_clk_src_str(dw23.time_ref_sel), ice_clk_freq_str(dw9.time_ref_freq_sel), ro_lock.plllock_true_lock_cri ? "locked" : "unlocked"); @@ -651,7 +651,7 @@ static int ice_cfg_cgu_pll_e825c(struct ice_hw *hw, /* Log the current clock configuration */ ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.ts_pll_enable ? "enabled" : "disabled", + str_enabled_disabled(dw24.ts_pll_enable), ice_clk_src_str(dw23.time_ref_sel), ice_clk_freq_str(dw9.time_ref_freq_sel), ro_lock.plllock_true_lock_cri ? "locked" : "unlocked"); @@ -746,7 +746,7 @@ static int ice_init_cgu_e82x(struct ice_hw *hw) int err; /* Disable sticky lock detection so lock err reported is accurate */ - if (ice_is_e825c(hw)) + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) err = ice_cfg_cgu_pll_dis_sticky_bits_e825c(hw); else err = ice_cfg_cgu_pll_dis_sticky_bits_e82x(hw); @@ -756,7 +756,7 @@ static int ice_init_cgu_e82x(struct ice_hw *hw) /* Configure the CGU PLL using the parameters from the function * capabilities. */ - if (ice_is_e825c(hw)) + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) err = ice_cfg_cgu_pll_e825c(hw, ts_info->time_ref, (enum ice_clk_src)ts_info->clk_src); else @@ -827,8 +827,9 @@ static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw, /* Certain hardware families share the same register values for the * port register and source timer register. */ - switch (ice_get_phy_model(hw)) { - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: return ice_ptp_tmr_cmd_to_src_reg(hw, cmd) & TS_CMD_MASK_E810; default: break; @@ -873,8 +874,12 @@ static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw, */ void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) { + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); u32 cmd_val = ice_ptp_tmr_cmd_to_src_reg(hw, cmd); + if (!ice_is_primary(hw)) + hw = ice_get_primary_hw(pf); + wr32(hw, GLTSYN_CMD, cmd_val); } @@ -890,11 +895,25 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw) { struct ice_pf *pf = container_of(hw, struct ice_pf, hw); + if (!ice_is_primary(hw)) + hw = ice_get_primary_hw(pf); + guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock); wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD); ice_flush(hw); } +/** + * ice_ptp_cfg_sync_delay - Configure PHC to PHY synchronization delay + * @hw: pointer to HW struct + * @delay: delay between PHC and PHY SYNC command execution in nanoseconds + */ +static void ice_ptp_cfg_sync_delay(const struct ice_hw *hw, u32 delay) +{ + wr32(hw, GLTSYN_SYNC_DLAY, delay); + ice_flush(hw); +} + /* 56G PHY device functions * * The following functions operate on devices with the ETH 56G PHY. @@ -907,16 +926,24 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw) * * Return: destination sideband queue PHY device. */ -static enum ice_sbq_msg_dev ice_ptp_get_dest_dev_e825(struct ice_hw *hw, - u8 port) +static enum ice_sbq_dev_id ice_ptp_get_dest_dev_e825(struct ice_hw *hw, + u8 port) { - /* On a single complex E825, PHY 0 is always destination device phy_0 + u8 curr_phy, tgt_phy; + + tgt_phy = port >= hw->ptp.ports_per_phy; + curr_phy = hw->lane_num >= hw->ptp.ports_per_phy; + /* In the driver, lanes 4..7 are in fact 0..3 on a second PHY. + * On a single complex E825C, PHY 0 is always destination device phy_0 * and PHY 1 is phy_0_peer. + * On dual complex E825C, device phy_0 points to PHY on a current + * complex and phy_0_peer to PHY on a different complex. */ - if (port >= hw->ptp.ports_per_phy) - return eth56g_phy_1; + if ((!ice_is_dual(hw) && tgt_phy == 1) || + (ice_is_dual(hw) && tgt_phy != curr_phy)) + return ice_sbq_dev_phy_0_peer; else - return eth56g_phy_0; + return ice_sbq_dev_phy_0; } /** @@ -998,7 +1025,7 @@ static int ice_phy_res_address_eth56g(struct ice_hw *hw, u8 lane, /* Lanes 4..7 are in fact 0..3 on a second PHY */ lane %= hw->ptp.ports_per_phy; - *addr = eth56g_phy_res[res_type].base[0] + + *addr = eth56g_phy_res[res_type].base_addr + lane * eth56g_phy_res[res_type].step + offset; return 0; @@ -1228,7 +1255,7 @@ static int ice_write_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port, if (port >= hw->ptp.num_lports) return -EIO; - addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset; + addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset; return ice_write_phy_eth56g(hw, port, addr, val); } @@ -1253,7 +1280,7 @@ static int ice_read_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port, if (port >= hw->ptp.num_lports) return -EIO; - addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset; + addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset; return ice_read_phy_eth56g(hw, port, addr, val); } @@ -1576,9 +1603,8 @@ static int ice_read_ptp_tstamp_eth56g(struct ice_hw *hw, u8 port, u8 idx, * lower 8 bits in the low register, and the upper 32 bits in the high * register. */ - *tstamp = FIELD_PREP(TS_PHY_HIGH_M, hi) | - FIELD_PREP(TS_PHY_LOW_M, lo); - + *tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) | + FIELD_PREP(PHY_40B_LOW_M, lo); return 0; } @@ -2406,6 +2432,7 @@ int ice_phy_cfg_intr_eth56g(struct ice_hw *hw, u8 port, bool ena, u8 threshold) static int ice_read_phy_and_phc_time_eth56g(struct ice_hw *hw, u8 port, u64 *phy_time, u64 *phc_time) { + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); u64 tx_time, rx_time; u32 zo, lo; u8 tmr_idx; @@ -2425,8 +2452,13 @@ static int ice_read_phy_and_phc_time_eth56g(struct ice_hw *hw, u8 port, ice_ptp_exec_tmr_cmd(hw); /* Read the captured PHC time from the shadow time registers */ - zo = rd32(hw, GLTSYN_SHTIME_0(tmr_idx)); - lo = rd32(hw, GLTSYN_SHTIME_L(tmr_idx)); + if (ice_is_primary(hw)) { + zo = rd32(hw, GLTSYN_SHTIME_0(tmr_idx)); + lo = rd32(hw, GLTSYN_SHTIME_L(tmr_idx)); + } else { + zo = rd32(ice_get_primary_hw(pf), GLTSYN_SHTIME_0(tmr_idx)); + lo = rd32(ice_get_primary_hw(pf), GLTSYN_SHTIME_L(tmr_idx)); + } *phc_time = (u64)lo << 32 | zo; /* Read the captured PHY time from the PHY shadow registers */ @@ -2563,6 +2595,7 @@ int ice_stop_phy_timer_eth56g(struct ice_hw *hw, u8 port, bool soft_reset) */ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port) { + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); u32 lo, hi; u64 incval; u8 tmr_idx; @@ -2588,8 +2621,13 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port) if (err) return err; - lo = rd32(hw, GLTSYN_INCVAL_L(tmr_idx)); - hi = rd32(hw, GLTSYN_INCVAL_H(tmr_idx)); + if (ice_is_primary(hw)) { + lo = rd32(hw, GLTSYN_INCVAL_L(tmr_idx)); + hi = rd32(hw, GLTSYN_INCVAL_H(tmr_idx)); + } else { + lo = rd32(ice_get_primary_hw(pf), GLTSYN_INCVAL_L(tmr_idx)); + hi = rd32(ice_get_primary_hw(pf), GLTSYN_INCVAL_H(tmr_idx)); + } incval = (u64)hi << 32 | lo; err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_REG_TIMETUS_L, incval); @@ -2620,37 +2658,15 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port) } /** - * ice_sb_access_ena_eth56g - Enable SB devices (PHY and others) access + * ice_ptp_init_phc_e825 - Perform E825 specific PHC initialization * @hw: pointer to HW struct - * @enable: Enable or disable access * - * Enable sideband devices (PHY and others) access. - */ -static void ice_sb_access_ena_eth56g(struct ice_hw *hw, bool enable) -{ - u32 val = rd32(hw, PF_SB_REM_DEV_CTL); - - if (enable) - val |= BIT(eth56g_phy_0) | BIT(cgu) | BIT(eth56g_phy_1); - else - val &= ~(BIT(eth56g_phy_0) | BIT(cgu) | BIT(eth56g_phy_1)); - - wr32(hw, PF_SB_REM_DEV_CTL, val); -} - -/** - * ice_ptp_init_phc_eth56g - Perform E82X specific PHC initialization - * @hw: pointer to HW struct + * Perform E825-specific PTP hardware clock initialization steps. * - * Perform PHC initialization steps specific to E82X devices. - * - * Return: - * * %0 - success - * * %other - failed to initialize CGU + * Return: 0 on success, negative error code otherwise. */ -static int ice_ptp_init_phc_eth56g(struct ice_hw *hw) +static int ice_ptp_init_phc_e825(struct ice_hw *hw) { - ice_sb_access_ena_eth56g(hw, true); /* Initialize the Clock Generation Unit */ return ice_init_cgu_e82x(hw); } @@ -2729,10 +2745,7 @@ static void ice_ptp_init_phy_e825(struct ice_hw *hw) { struct ice_ptp_hw *ptp = &hw->ptp; struct ice_eth56g_params *params; - u32 phy_rev; - int err; - ptp->phy_model = ICE_PHY_ETH56G; params = &ptp->phy.eth56g; params->onestep_ena = false; params->peer_delay = 0; @@ -2740,11 +2753,6 @@ static void ice_ptp_init_phy_e825(struct ice_hw *hw) params->num_phys = 2; ptp->ports_per_phy = 4; ptp->num_lports = params->num_phys * ptp->ports_per_phy; - - ice_sb_access_ena_eth56g(hw, true); - err = ice_read_phy_eth56g(hw, hw->pf_id, PHY_REG_REVISION, &phy_rev); - if (err || phy_rev != PHY_REVISION_ETH56G) - ptp->phy_model = ICE_PHY_UNSUP; } /* E822 family functions @@ -2777,7 +2785,7 @@ static void ice_fill_phy_msg_e82x(struct ice_hw *hw, msg->msg_addr_high = P_Q1_H(P_4_BASE + offset, phy_port); } - msg->dest_dev = rmn_0; + msg->dest_dev = ice_sbq_dev_phy_0; } /** @@ -3100,7 +3108,7 @@ static int ice_fill_quad_msg_e82x(struct ice_hw *hw, if (quad >= ICE_GET_QUAD_NUM(hw->ptp.num_lports)) return -EINVAL; - msg->dest_dev = rmn_0; + msg->dest_dev = ice_sbq_dev_phy_0; if (!(quad % ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy))) addr = Q_0_BASE + offset; @@ -3219,7 +3227,8 @@ ice_read_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp) * lower 8 bits in the low register, and the upper 32 bits in the high * register. */ - *tstamp = FIELD_PREP(TS_PHY_HIGH_M, hi) | FIELD_PREP(TS_PHY_LOW_M, lo); + *tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) | + FIELD_PREP(PHY_40B_LOW_M, lo); return 0; } @@ -4792,7 +4801,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold) */ static void ice_ptp_init_phy_e82x(struct ice_ptp_hw *ptp) { - ptp->phy_model = ICE_PHY_E82X; ptp->num_lports = 8; ptp->ports_per_phy = 8; } @@ -4819,7 +4827,7 @@ static int ice_read_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 *val) msg.msg_addr_low = lower_16_bits(addr); msg.msg_addr_high = upper_16_bits(addr); msg.opcode = ice_sbq_msg_rd; - msg.dest_dev = rmn_0; + msg.dest_dev = ice_sbq_dev_phy_0; err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); if (err) { @@ -4849,7 +4857,7 @@ static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val) msg.msg_addr_low = lower_16_bits(addr); msg.msg_addr_high = upper_16_bits(addr); msg.opcode = ice_sbq_msg_wr; - msg.dest_dev = rmn_0; + msg.dest_dev = ice_sbq_dev_phy_0; msg.data = val; err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); @@ -4876,33 +4884,46 @@ static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val) static int ice_read_phy_tstamp_ll_e810(struct ice_hw *hw, u8 idx, u8 *hi, u32 *lo) { + struct ice_e810_params *params = &hw->ptp.phy.e810; + unsigned long flags; u32 val; - u8 i; + int err; + + spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); + + /* Wait for any pending in-progress low latency interrupt */ + err = wait_event_interruptible_locked_irq(params->atqbal_wq, + !(params->atqbal_flags & + ATQBAL_FLAGS_INTR_IN_PROGRESS)); + if (err) { + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + return err; + } /* Write TS index to read to the PF register so the FW can read it */ - val = FIELD_PREP(TS_LL_READ_TS_IDX, idx) | TS_LL_READ_TS; - wr32(hw, PF_SB_ATQBAL, val); + val = FIELD_PREP(REG_LL_PROXY_H_TS_IDX, idx) | REG_LL_PROXY_H_EXEC; + wr32(hw, REG_LL_PROXY_H, val); /* Read the register repeatedly until the FW provides us the TS */ - for (i = TS_LL_READ_RETRIES; i > 0; i--) { - val = rd32(hw, PF_SB_ATQBAL); + err = read_poll_timeout_atomic(rd32, val, + !FIELD_GET(REG_LL_PROXY_H_EXEC, val), 10, + REG_LL_PROXY_H_TIMEOUT_US, false, hw, + REG_LL_PROXY_H); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n"); + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + return err; + } - /* When the bit is cleared, the TS is ready in the register */ - if (!(FIELD_GET(TS_LL_READ_TS, val))) { - /* High 8 bit value of the TS is on the bits 16:23 */ - *hi = FIELD_GET(TS_LL_READ_TS_HIGH, val); + /* High 8 bit value of the TS is on the bits 16:23 */ + *hi = FIELD_GET(REG_LL_PROXY_H_TS_HIGH, val); - /* Read the low 32 bit value and set the TS valid bit */ - *lo = rd32(hw, PF_SB_ATQBAH) | TS_VALID; - return 0; - } + /* Read the low 32 bit value and set the TS valid bit */ + *lo = rd32(hw, REG_LL_PROXY_L) | TS_VALID; - udelay(10); - } + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); - /* FW failed to provide the TS in time */ - ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n"); - return -EINVAL; + return 0; } /** @@ -4973,7 +4994,8 @@ ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp) /* For E810 devices, the timestamp is reported with the lower 32 bits * in the low register, and the upper 8 bits in the high register. */ - *tstamp = ((u64)hi) << TS_HIGH_S | ((u64)lo & TS_LOW_M); + *tstamp = FIELD_PREP(PHY_EXT_40B_HIGH_M, hi) | + FIELD_PREP(PHY_EXT_40B_LOW_M, lo); return 0; } @@ -5036,8 +5058,7 @@ static int ice_ptp_init_phc_e810(struct ice_hw *hw) u8 tmr_idx; int err; - /* Ensure synchronization delay is zero */ - wr32(hw, GLTSYN_SYNC_DLAY, 0); + ice_ptp_cfg_sync_delay(hw, ICE_E810_E830_SYNC_DELAY); tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; err = ice_write_phy_reg_e810(hw, ETH_GLTSYN_ENA(tmr_idx), @@ -5085,6 +5106,55 @@ static int ice_ptp_prep_phy_time_e810(struct ice_hw *hw, u32 time) } /** + * ice_ptp_prep_phy_adj_ll_e810 - Prep PHY ports for a time adjustment + * @hw: pointer to HW struct + * @adj: adjustment value to program + * + * Use the low latency firmware interface to program PHY time adjustment to + * all PHY ports. + * + * Return: 0 on success, -EBUSY on timeout + */ +static int ice_ptp_prep_phy_adj_ll_e810(struct ice_hw *hw, s32 adj) +{ + const u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + struct ice_e810_params *params = &hw->ptp.phy.e810; + u32 val; + int err; + + spin_lock_irq(¶ms->atqbal_wq.lock); + + /* Wait for any pending in-progress low latency interrupt */ + err = wait_event_interruptible_locked_irq(params->atqbal_wq, + !(params->atqbal_flags & + ATQBAL_FLAGS_INTR_IN_PROGRESS)); + if (err) { + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + wr32(hw, REG_LL_PROXY_L, adj); + val = FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_CMD_M, REG_LL_PROXY_H_PHY_TMR_CMD_ADJ) | + FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_IDX_M, tmr_idx) | REG_LL_PROXY_H_EXEC; + wr32(hw, REG_LL_PROXY_H, val); + + /* Read the register repeatedly until the FW indicates completion */ + err = read_poll_timeout_atomic(rd32, val, + !FIELD_GET(REG_LL_PROXY_H_EXEC, val), + 10, REG_LL_PROXY_H_TIMEOUT_US, false, hw, + REG_LL_PROXY_H); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY timer adjustment using low latency interface\n"); + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + spin_unlock_irq(¶ms->atqbal_wq.lock); + + return 0; +} + +/** * ice_ptp_prep_phy_adj_e810 - Prep PHY port for a time adjustment * @hw: pointer to HW struct * @adj: adjustment value to program @@ -5102,6 +5172,9 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj) u8 tmr_idx; int err; + if (hw->dev_caps.ts_dev_info.ll_phy_tmr_update) + return ice_ptp_prep_phy_adj_ll_e810(hw, adj); + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; /* Adjustments are represented as signed 2's complement values in @@ -5125,6 +5198,56 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj) } /** + * ice_ptp_prep_phy_incval_ll_e810 - Prep PHY ports increment value change + * @hw: pointer to HW struct + * @incval: The new 40bit increment value to prepare + * + * Use the low latency firmware interface to program PHY time increment value + * for all PHY ports. + * + * Return: 0 on success, -EBUSY on timeout + */ +static int ice_ptp_prep_phy_incval_ll_e810(struct ice_hw *hw, u64 incval) +{ + const u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + struct ice_e810_params *params = &hw->ptp.phy.e810; + u32 val; + int err; + + spin_lock_irq(¶ms->atqbal_wq.lock); + + /* Wait for any pending in-progress low latency interrupt */ + err = wait_event_interruptible_locked_irq(params->atqbal_wq, + !(params->atqbal_flags & + ATQBAL_FLAGS_INTR_IN_PROGRESS)); + if (err) { + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + wr32(hw, REG_LL_PROXY_L, lower_32_bits(incval)); + val = FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_CMD_M, REG_LL_PROXY_H_PHY_TMR_CMD_FREQ) | + FIELD_PREP(REG_LL_PROXY_H_TS_HIGH, (u8)upper_32_bits(incval)) | + FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_IDX_M, tmr_idx) | REG_LL_PROXY_H_EXEC; + wr32(hw, REG_LL_PROXY_H, val); + + /* Read the register repeatedly until the FW indicates completion */ + err = read_poll_timeout_atomic(rd32, val, + !FIELD_GET(REG_LL_PROXY_H_EXEC, val), + 10, REG_LL_PROXY_H_TIMEOUT_US, false, hw, + REG_LL_PROXY_H); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY timer increment using low latency interface\n"); + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + spin_unlock_irq(¶ms->atqbal_wq.lock); + + return 0; +} + +/** * ice_ptp_prep_phy_incval_e810 - Prep PHY port increment value change * @hw: pointer to HW struct * @incval: The new 40bit increment value to prepare @@ -5139,6 +5262,9 @@ static int ice_ptp_prep_phy_incval_e810(struct ice_hw *hw, u64 incval) u8 tmr_idx; int err; + if (hw->dev_caps.ts_dev_info.ll_phy_tmr_update) + return ice_ptp_prep_phy_incval_ll_e810(hw, incval); + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; low = lower_32_bits(incval); high = upper_32_bits(incval); @@ -5198,68 +5324,6 @@ ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready) */ /** - * ice_get_pca9575_handle - * @hw: pointer to the hw struct - * @pca9575_handle: GPIO controller's handle - * - * Find and return the GPIO controller's handle in the netlist. - * When found - the value will be cached in the hw structure and following calls - * will return cached value - */ -static int -ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) -{ - struct ice_aqc_get_link_topo *cmd; - struct ice_aq_desc desc; - int status; - u8 idx; - - /* If handle was read previously return cached value */ - if (hw->io_expander_handle) { - *pca9575_handle = hw->io_expander_handle; - return 0; - } - - /* If handle was not detected read it from the netlist */ - cmd = &desc.params.get_link_topo; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); - - /* Set node type to GPIO controller */ - cmd->addr.topo_params.node_type_ctx = - (ICE_AQC_LINK_TOPO_NODE_TYPE_M & - ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL); - -#define SW_PCA9575_SFP_TOPO_IDX 2 -#define SW_PCA9575_QSFP_TOPO_IDX 1 - - /* Check if the SW IO expander controlling SMA exists in the netlist. */ - if (hw->device_id == ICE_DEV_ID_E810C_SFP) - idx = SW_PCA9575_SFP_TOPO_IDX; - else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) - idx = SW_PCA9575_QSFP_TOPO_IDX; - else - return -EOPNOTSUPP; - - cmd->addr.topo_params.index = idx; - - status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); - if (status) - return -EOPNOTSUPP; - - /* Verify if we found the right IO expander type */ - if (desc.params.get_link_topo.node_part_num != - ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) - return -EOPNOTSUPP; - - /* If present save the handle and return it */ - hw->io_expander_handle = - le16_to_cpu(desc.params.get_link_topo.addr.handle); - *pca9575_handle = hw->io_expander_handle; - - return 0; -} - -/** * ice_read_sma_ctrl * @hw: pointer to the hw struct * @data: pointer to data to be read from the GPIO controller @@ -5324,37 +5388,6 @@ int ice_write_sma_ctrl(struct ice_hw *hw, u8 data) } /** - * ice_read_pca9575_reg - * @hw: pointer to the hw struct - * @offset: GPIO controller register offset - * @data: pointer to data to be read from the GPIO controller - * - * Read the register from the GPIO controller - */ -int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data) -{ - struct ice_aqc_link_topo_addr link_topo; - __le16 addr; - u16 handle; - int err; - - memset(&link_topo, 0, sizeof(link_topo)); - - err = ice_get_pca9575_handle(hw, &handle); - if (err) - return err; - - link_topo.handle = cpu_to_le16(handle); - link_topo.topo_params.node_type_ctx = - FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, - ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED); - - addr = cpu_to_le16((u16)offset); - - return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL); -} - -/** * ice_ptp_read_sdp_ac - read SDP available connections section from NVM * @hw: pointer to the HW struct * @entries: returns the SDP available connections section from NVM @@ -5420,16 +5453,138 @@ exit: */ static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp) { - ptp->phy_model = ICE_PHY_E810; + ptp->num_lports = 8; + ptp->ports_per_phy = 4; + + init_waitqueue_head(&ptp->phy.e810.atqbal_wq); +} + +/* E830 functions + * + * The following functions operate on the E830 series devices. + * + */ + +/** + * ice_ptp_init_phc_e830 - Perform E830 specific PHC initialization + * @hw: pointer to HW struct + * + * Perform E830-specific PTP hardware clock initialization steps. + */ +static void ice_ptp_init_phc_e830(const struct ice_hw *hw) +{ + ice_ptp_cfg_sync_delay(hw, ICE_E810_E830_SYNC_DELAY); +} + +/** + * ice_ptp_write_direct_incval_e830 - Prep PHY port increment value change + * @hw: pointer to HW struct + * @incval: The new 40bit increment value to prepare + * + * Prepare the PHY port for a new increment value by programming the PHC + * GLTSYN_INCVAL_L and GLTSYN_INCVAL_H registers. The actual change is + * completed by FW automatically. + */ +static void ice_ptp_write_direct_incval_e830(const struct ice_hw *hw, + u64 incval) +{ + u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + wr32(hw, GLTSYN_INCVAL_L(tmr_idx), lower_32_bits(incval)); + wr32(hw, GLTSYN_INCVAL_H(tmr_idx), upper_32_bits(incval)); +} + +/** + * ice_ptp_write_direct_phc_time_e830 - Prepare PHY port with initial time + * @hw: Board private structure + * @time: Time to initialize the PHY port clock to + * + * Program the PHY port ETH_GLTSYN_SHTIME registers in preparation setting the + * initial clock time. The time will not actually be programmed until the + * driver issues an ICE_PTP_INIT_TIME command. + * + * The time value is the upper 32 bits of the PHY timer, usually in units of + * nominal nanoseconds. + */ +static void ice_ptp_write_direct_phc_time_e830(const struct ice_hw *hw, + u64 time) +{ + u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + wr32(hw, GLTSYN_TIME_0(tmr_idx), 0); + wr32(hw, GLTSYN_TIME_L(tmr_idx), lower_32_bits(time)); + wr32(hw, GLTSYN_TIME_H(tmr_idx), upper_32_bits(time)); +} + +/** + * ice_ptp_port_cmd_e830 - Prepare all external PHYs for a timer command + * @hw: pointer to HW struct + * @cmd: Command to be sent to the port + * + * Prepare the external PHYs connected to this device for a timer sync + * command. + * + * Return: 0 on success, negative error code when PHY write failed + */ +static int ice_ptp_port_cmd_e830(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +{ + u32 val = ice_ptp_tmr_cmd_to_port_reg(hw, cmd); + + return ice_write_phy_reg_e810(hw, E830_ETH_GLTSYN_CMD, val); +} + +/** + * ice_read_phy_tstamp_e830 - Read a PHY timestamp out of the external PHY + * @hw: pointer to the HW struct + * @idx: the timestamp index to read + * @tstamp: on return, the 40bit timestamp value + * + * Read a 40bit timestamp value out of the timestamp block of the external PHY + * on the E830 device. + */ +static void ice_read_phy_tstamp_e830(const struct ice_hw *hw, u8 idx, + u64 *tstamp) +{ + u32 hi, lo; + + hi = rd32(hw, E830_PRTTSYN_TXTIME_H(idx)); + lo = rd32(hw, E830_PRTTSYN_TXTIME_L(idx)); + + /* For E830 devices, the timestamp is reported with the lower 32 bits + * in the low register, and the upper 8 bits in the high register. + */ + *tstamp = FIELD_PREP(PHY_EXT_40B_HIGH_M, hi) | + FIELD_PREP(PHY_EXT_40B_LOW_M, lo); +} + +/** + * ice_get_phy_tx_tstamp_ready_e830 - Read Tx memory status register + * @hw: pointer to the HW struct + * @port: the PHY port to read + * @tstamp_ready: contents of the Tx memory status register + */ +static void ice_get_phy_tx_tstamp_ready_e830(const struct ice_hw *hw, u8 port, + u64 *tstamp_ready) +{ + *tstamp_ready = rd32(hw, E830_PRTMAC_TS_TX_MEM_VALID_H); + *tstamp_ready <<= 32; + *tstamp_ready |= rd32(hw, E830_PRTMAC_TS_TX_MEM_VALID_L); +} + +/** + * ice_ptp_init_phy_e830 - initialize PHY parameters + * @ptp: pointer to the PTP HW struct + */ +static void ice_ptp_init_phy_e830(struct ice_ptp_hw *ptp) +{ ptp->num_lports = 8; ptp->ports_per_phy = 4; } /* Device agnostic functions * - * The following functions implement shared behavior common to both E822 and - * E810 devices, possibly calling a device specific implementation where - * necessary. + * The following functions implement shared behavior common to all devices, + * possibly calling a device specific implementation where necessary. */ /** @@ -5492,14 +5647,22 @@ void ice_ptp_init_hw(struct ice_hw *hw) { struct ice_ptp_hw *ptp = &hw->ptp; - if (ice_is_e822(hw) || ice_is_e823(hw)) - ice_ptp_init_phy_e82x(ptp); - else if (ice_is_e810(hw)) + switch (hw->mac_type) { + case ICE_MAC_E810: ice_ptp_init_phy_e810(ptp); - else if (ice_is_e825c(hw)) + break; + case ICE_MAC_E830: + ice_ptp_init_phy_e830(ptp); + break; + case ICE_MAC_GENERIC: + ice_ptp_init_phy_e82x(ptp); + break; + case ICE_MAC_GENERIC_3K_E825: ice_ptp_init_phy_e825(hw); - else - ptp->phy_model = ICE_PHY_UNSUP; + break; + default: + return; + } } /** @@ -5520,11 +5683,11 @@ void ice_ptp_init_hw(struct ice_hw *hw) static int ice_ptp_write_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_ptp_write_port_cmd_eth56g(hw, port, cmd); - case ICE_PHY_E82X: + switch (hw->mac_type) { + case ICE_MAC_GENERIC: return ice_ptp_write_port_cmd_e82x(hw, port, cmd); + case ICE_MAC_GENERIC_3K_E825: + return ice_ptp_write_port_cmd_eth56g(hw, port, cmd); default: return -EOPNOTSUPP; } @@ -5585,9 +5748,11 @@ static int ice_ptp_port_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) u32 port; /* PHY models which can program all ports simultaneously */ - switch (ice_get_phy_model(hw)) { - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_ptp_port_cmd_e810(hw, cmd); + case ICE_MAC_E830: + return ice_ptp_port_cmd_e830(hw, cmd); default: break; } @@ -5658,23 +5823,29 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time) tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; /* Source timers */ + /* For E830 we don't need to use shadow registers, its automatic */ + if (hw->mac_type == ICE_MAC_E830) { + ice_ptp_write_direct_phc_time_e830(hw, time); + return 0; + } + wr32(hw, GLTSYN_SHTIME_L(tmr_idx), lower_32_bits(time)); wr32(hw, GLTSYN_SHTIME_H(tmr_idx), upper_32_bits(time)); wr32(hw, GLTSYN_SHTIME_0(tmr_idx), 0); /* PHY timers */ /* Fill Rx and Tx ports and send msg to PHY */ - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_ptp_prep_phy_time_eth56g(hw, - (u32)(time & 0xFFFFFFFF)); - break; - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: err = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF); break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: err = ice_ptp_prep_phy_time_e82x(hw, time & 0xFFFFFFFF); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_ptp_prep_phy_time_eth56g(hw, + (u32)(time & 0xFFFFFFFF)); + break; default: err = -EOPNOTSUPP; } @@ -5706,20 +5877,26 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval) tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + /* For E830 we don't need to use shadow registers, its automatic */ + if (hw->mac_type == ICE_MAC_E830) { + ice_ptp_write_direct_incval_e830(hw, incval); + return 0; + } + /* Shadow Adjust */ wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval)); wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval)); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_ptp_prep_phy_incval_eth56g(hw, incval); - break; - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: err = ice_ptp_prep_phy_incval_e810(hw, incval); break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: err = ice_ptp_prep_phy_incval_e82x(hw, incval); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_ptp_prep_phy_incval_eth56g(hw, incval); + break; default: err = -EOPNOTSUPP; } @@ -5779,16 +5956,19 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) wr32(hw, GLTSYN_SHADJ_L(tmr_idx), 0); wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_ptp_prep_phy_adj_eth56g(hw, adj); - break; - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: err = ice_ptp_prep_phy_adj_e810(hw, adj); break; - case ICE_PHY_E82X: + case ICE_MAC_E830: + /* E830 sync PHYs automatically after setting GLTSYN_SHADJ */ + return 0; + case ICE_MAC_GENERIC: err = ice_ptp_prep_phy_adj_e82x(hw, adj); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_ptp_prep_phy_adj_eth56g(hw, adj); + break; default: err = -EOPNOTSUPP; } @@ -5812,13 +5992,16 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) */ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp); - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_read_phy_tstamp_e810(hw, block, idx, tstamp); - case ICE_PHY_E82X: + case ICE_MAC_E830: + ice_read_phy_tstamp_e830(hw, idx, tstamp); + return 0; + case ICE_MAC_GENERIC: return ice_read_phy_tstamp_e82x(hw, block, idx, tstamp); + case ICE_MAC_GENERIC_3K_E825: + return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp); default: return -EOPNOTSUPP; } @@ -5842,13 +6025,13 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) */ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_clear_ptp_tstamp_eth56g(hw, block, idx); - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_clear_phy_tstamp_e810(hw, block, idx); - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: return ice_clear_phy_tstamp_e82x(hw, block, idx); + case ICE_MAC_GENERIC_3K_E825: + return ice_clear_ptp_tstamp_eth56g(hw, block, idx); default: return -EOPNOTSUPP; } @@ -5905,14 +6088,14 @@ static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx) */ void ice_ptp_reset_ts_memory(struct ice_hw *hw) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - ice_ptp_reset_ts_memory_eth56g(hw); - break; - case ICE_PHY_E82X: + switch (hw->mac_type) { + case ICE_MAC_GENERIC: ice_ptp_reset_ts_memory_e82x(hw); break; - case ICE_PHY_E810: + case ICE_MAC_GENERIC_3K_E825: + ice_ptp_reset_ts_memory_eth56g(hw); + break; + case ICE_MAC_E810: default: return; } @@ -5934,13 +6117,16 @@ int ice_ptp_init_phc(struct ice_hw *hw) /* Clear event err indications for auxiliary pins */ (void)rd32(hw, GLTSYN_STAT(src_idx)); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_ptp_init_phc_eth56g(hw); - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_ptp_init_phc_e810(hw); - case ICE_PHY_E82X: + case ICE_MAC_E830: + ice_ptp_init_phc_e830(hw); + return 0; + case ICE_MAC_GENERIC: return ice_ptp_init_phc_e82x(hw); + case ICE_MAC_GENERIC_3K_E825: + return ice_ptp_init_phc_e825(hw); default: return -EOPNOTSUPP; } @@ -5959,17 +6145,19 @@ int ice_ptp_init_phc(struct ice_hw *hw) */ int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_get_phy_tx_tstamp_ready_eth56g(hw, block, - tstamp_ready); - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_get_phy_tx_tstamp_ready_e810(hw, block, tstamp_ready); - case ICE_PHY_E82X: + case ICE_MAC_E830: + ice_get_phy_tx_tstamp_ready_e830(hw, block, tstamp_ready); + return 0; + case ICE_MAC_GENERIC: return ice_get_phy_tx_tstamp_ready_e82x(hw, block, tstamp_ready); - break; + case ICE_MAC_GENERIC_3K_E825: + return ice_get_phy_tx_tstamp_ready_eth56g(hw, block, + tstamp_ready); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 1cee0f1bba2d..83f20fa7ace7 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -65,14 +65,14 @@ enum ice_eth56g_link_spd { /** * struct ice_phy_reg_info_eth56g - ETH56G PHY register parameters - * @base: base address for each PHY block + * @base_addr: base address for each PHY block * @step: step between PHY lanes * * Characteristic information for the various PHY register parameters in the * ETH56G devices */ struct ice_phy_reg_info_eth56g { - u32 base[NUM_ETH56G_PHY_RES]; + u32 base_addr; u32 step; }; @@ -80,7 +80,6 @@ struct ice_phy_reg_info_eth56g { * struct ice_time_ref_info_e82x * @pll_freq: Frequency of PLL that drives timer ticks in Hz * @nominal_incval: increment to generate nanoseconds in GLTSYN_TIME_L - * @pps_delay: propagation delay of the PPS output signal * * Characteristic information for the various TIME_REF sources possible in the * E822 devices @@ -88,7 +87,6 @@ struct ice_phy_reg_info_eth56g { struct ice_time_ref_info_e82x { u64 pll_freq; u64 nominal_incval; - u8 pps_delay; }; /** @@ -326,8 +324,7 @@ extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD]; */ #define ICE_E810_PLL_FREQ 812500000 #define ICE_PTP_NOMINAL_INCVAL_E810 0x13b13b13bULL -#define ICE_E810_OUT_PROP_DELAY_NS 1 -#define ICE_E825C_OUT_PROP_DELAY_NS 11 +#define ICE_E810_E830_SYNC_DELAY 0 /* Device agnostic functions */ u8 ice_get_ptp_src_clock_index(struct ice_hw *hw); @@ -389,11 +386,6 @@ static inline u64 ice_e82x_nominal_incval(enum ice_time_ref_freq time_ref) return e82x_time_ref[time_ref].nominal_incval; } -static inline u64 ice_e82x_pps_delay(enum ice_time_ref_freq time_ref) -{ - return e82x_time_ref[time_ref].pps_delay; -} - /* E822 Vernier calibration functions */ int ice_stop_phy_timer_e82x(struct ice_hw *hw, u8 port, bool soft_reset); int ice_start_phy_timer_e82x(struct ice_hw *hw, u8 port); @@ -404,7 +396,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold); /* E810 family functions */ int ice_read_sma_ctrl(struct ice_hw *hw, u8 *data); int ice_write_sma_ctrl(struct ice_hw *hw, u8 data); -int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data); int ice_ptp_read_sdp_ac(struct ice_hw *hw, __le16 *entries, uint *num_entries); int ice_cgu_get_num_pins(struct ice_hw *hw, bool input); enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input); @@ -432,20 +423,6 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port); #define ICE_ETH56G_NOMINAL_THRESH4 0x7777 #define ICE_ETH56G_NOMINAL_TX_THRESH 0x6 -static inline u64 ice_prop_delay(const struct ice_hw *hw) -{ - switch (hw->ptp.phy_model) { - case ICE_PHY_ETH56G: - return ICE_E825C_OUT_PROP_DELAY_NS; - case ICE_PHY_E810: - return ICE_E810_OUT_PROP_DELAY_NS; - case ICE_PHY_E82X: - return ice_e82x_pps_delay(ice_e82x_time_ref(hw)); - default: - return 0; - } -} - /** * ice_get_base_incval - Get base clock increment value * @hw: pointer to the HW struct @@ -454,23 +431,19 @@ static inline u64 ice_prop_delay(const struct ice_hw *hw) */ static inline u64 ice_get_base_incval(struct ice_hw *hw) { - switch (hw->ptp.phy_model) { - case ICE_PHY_ETH56G: - return ICE_ETH56G_NOMINAL_INCVAL; - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: return ICE_PTP_NOMINAL_INCVAL_E810; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: return ice_e82x_nominal_incval(ice_e82x_time_ref(hw)); + case ICE_MAC_GENERIC_3K_E825: + return ICE_ETH56G_NOMINAL_INCVAL; default: return 0; } } -static inline bool ice_is_dual(struct ice_hw *hw) -{ - return !!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_DUAL_M); -} - #define PFTSYN_SEM_BYTES 4 #define ICE_PTP_CLOCK_INDEX_0 0x00 @@ -673,27 +646,41 @@ static inline bool ice_is_dual(struct ice_hw *hw) /* E810 timer command register */ #define E810_ETH_GLTSYN_CMD 0x03000344 +/* E830 timer command register */ +#define E830_ETH_GLTSYN_CMD 0x00088814 + +/* E810 PHC time register */ +#define E830_GLTSYN_TIME_L(_tmr_idx) (0x0008A000 + 0x1000 * (_tmr_idx)) + /* Source timer incval macros */ #define INCVAL_HIGH_M 0xFF -/* Timestamp block macros */ +/* PHY 40b registers macros */ +#define PHY_EXT_40B_LOW_M GENMASK(31, 0) +#define PHY_EXT_40B_HIGH_M GENMASK_ULL(39, 32) +#define PHY_40B_LOW_M GENMASK(7, 0) +#define PHY_40B_HIGH_M GENMASK_ULL(39, 8) #define TS_VALID BIT(0) #define TS_LOW_M 0xFFFFFFFF #define TS_HIGH_M 0xFF #define TS_HIGH_S 32 -#define TS_PHY_LOW_M GENMASK(7, 0) -#define TS_PHY_HIGH_M GENMASK_ULL(39, 8) - #define BYTES_PER_IDX_ADDR_L_U 8 #define BYTES_PER_IDX_ADDR_L 4 /* Tx timestamp low latency read definitions */ -#define TS_LL_READ_RETRIES 200 -#define TS_LL_READ_TS_HIGH GENMASK(23, 16) -#define TS_LL_READ_TS_IDX GENMASK(29, 24) -#define TS_LL_READ_TS_INTR BIT(30) -#define TS_LL_READ_TS BIT(31) +#define REG_LL_PROXY_H_TIMEOUT_US 2000 +#define REG_LL_PROXY_H_PHY_TMR_CMD_M GENMASK(7, 6) +#define REG_LL_PROXY_H_PHY_TMR_CMD_ADJ 0x1 +#define REG_LL_PROXY_H_PHY_TMR_CMD_FREQ 0x2 +#define REG_LL_PROXY_H_TS_HIGH GENMASK(23, 16) +#define REG_LL_PROXY_H_PHY_TMR_IDX_M BIT(24) +#define REG_LL_PROXY_H_TS_IDX GENMASK(29, 24) +#define REG_LL_PROXY_H_TS_INTR_ENA BIT(30) +#define REG_LL_PROXY_H_EXEC BIT(31) + +#define REG_LL_PROXY_L PF_SB_ATQBAH +#define REG_LL_PROXY_H PF_SB_ATQBAL /* Internal PHY timestamp address */ #define TS_L(a, idx) ((a) + ((idx) * BYTES_PER_IDX_ADDR_L_U)) @@ -788,36 +775,19 @@ static inline bool ice_is_dual(struct ice_hw *hw) #define PHY_MAC_XIF_TS_SFD_ENA_M ICE_M(0x1, 20) #define PHY_MAC_XIF_GMII_TS_SEL_M ICE_M(0x1, 21) -/* GPCS config register */ -#define PHY_GPCS_CONFIG_REG0 0x268 -#define PHY_GPCS_CONFIG_REG0_TX_THR_M ICE_M(0xF, 24) -#define PHY_GPCS_BITSLIP 0x5C - #define PHY_TS_INT_CONFIG_THRESHOLD_M ICE_M(0x3F, 0) #define PHY_TS_INT_CONFIG_ENA_M BIT(6) -/* 1-step PTP config */ -#define PHY_PTP_1STEP_CONFIG 0x270 -#define PHY_PTP_1STEP_T1S_UP64_M ICE_M(0xF, 4) -#define PHY_PTP_1STEP_T1S_DELTA_M ICE_M(0xF, 8) -#define PHY_PTP_1STEP_PEER_DELAY(_port) (0x274 + 4 * (_port)) -#define PHY_PTP_1STEP_PD_ADD_PD_M ICE_M(0x1, 0) -#define PHY_PTP_1STEP_PD_DELAY_M ICE_M(0x3fffffff, 1) -#define PHY_PTP_1STEP_PD_DLY_V_M ICE_M(0x1, 31) - /* Macros to derive offsets for TimeStampLow and TimeStampHigh */ #define PHY_TSTAMP_L(x) (((x) * 8) + 0) #define PHY_TSTAMP_U(x) (((x) * 8) + 4) -#define PHY_REG_REVISION 0x85000 - #define PHY_REG_DESKEW_0 0x94 #define PHY_REG_DESKEW_0_RLEVEL GENMASK(6, 0) #define PHY_REG_DESKEW_0_RLEVEL_FRAC GENMASK(9, 7) #define PHY_REG_DESKEW_0_RLEVEL_FRAC_W 3 #define PHY_REG_DESKEW_0_VALID GENMASK(10, 10) -#define PHY_REG_GPCS_BITSLIP 0x5C #define PHY_REG_SD_BIT_SLIP(_port_offset) (0x29C + 4 * (_port_offset)) #define PHY_REVISION_ETH56G 0x10200 #define PHY_VENDOR_TXLANE_THRESH 0x2000C @@ -837,7 +807,21 @@ static inline bool ice_is_dual(struct ice_hw *hw) #define PHY_MAC_BLOCKTIME 0x50 #define PHY_MAC_MARKERTIME 0x54 #define PHY_MAC_TX_OFFSET 0x58 +#define PHY_GPCS_BITSLIP 0x5C #define PHY_PTP_INT_STATUS 0x7FD140 +/* ETH56G registers shared per quad */ +/* GPCS config register */ +#define PHY_GPCS_CONFIG_REG0 0x268 +#define PHY_GPCS_CONFIG_REG0_TX_THR_M GENMASK(27, 24) +/* 1-step PTP config */ +#define PHY_PTP_1STEP_CONFIG 0x270 +#define PHY_PTP_1STEP_T1S_UP64_M GENMASK(7, 4) +#define PHY_PTP_1STEP_T1S_DELTA_M GENMASK(11, 8) +#define PHY_PTP_1STEP_PEER_DELAY(_quad_lane) (0x274 + 4 * (_quad_lane)) +#define PHY_PTP_1STEP_PD_ADD_PD_M BIT(0) +#define PHY_PTP_1STEP_PD_DELAY_M GENMASK(30, 1) +#define PHY_PTP_1STEP_PD_DLY_V_M BIT(31) + #endif /* _ICE_PTP_HW_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index 970a99a52bf1..cb08746556a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -4,7 +4,7 @@ #include "ice.h" #include "ice_eswitch.h" #include "devlink/devlink.h" -#include "devlink/devlink_port.h" +#include "devlink/port.h" #include "ice_sriov.h" #include "ice_tc_lib.h" #include "ice_dcb_lib.h" @@ -219,7 +219,8 @@ ice_repr_setup_tc_cls_flower(struct ice_repr *repr, { switch (flower->command) { case FLOW_CLS_REPLACE: - return ice_add_cls_flower(repr->netdev, repr->src_vsi, flower); + return ice_add_cls_flower(repr->netdev, repr->src_vsi, flower, + true); case FLOW_CLS_DESTROY: return ice_del_cls_flower(repr->src_vsi, flower); default: @@ -336,6 +337,7 @@ void ice_repr_destroy(struct ice_repr *repr) static void ice_repr_rem_vf(struct ice_repr *repr) { ice_eswitch_decfg_vsi(repr->src_vsi, repr->parent_mac); + ice_pass_vf_tx_lldp(repr->src_vsi, true); unregister_netdev(repr->netdev); ice_devlink_destroy_vf_port(repr->vf); ice_virtchnl_set_dflt_ops(repr->vf); @@ -417,6 +419,10 @@ static int ice_repr_add_vf(struct ice_repr *repr) if (err) goto err_netdev; + err = ice_drop_vf_tx_lldp(repr->src_vsi, true); + if (err) + goto err_drop_lldp; + err = ice_eswitch_cfg_vsi(repr->src_vsi, repr->parent_mac); if (err) goto err_cfg_vsi; @@ -429,6 +435,8 @@ static int ice_repr_add_vf(struct ice_repr *repr) return 0; err_cfg_vsi: + ice_pass_vf_tx_lldp(repr->src_vsi, true); +err_drop_lldp: unregister_netdev(repr->netdev); err_netdev: ice_devlink_destroy_vf_port(vf); diff --git a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h index 3b0054faf70c..183dd5457d6a 100644 --- a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h @@ -46,13 +46,10 @@ struct ice_sbq_evt_desc { u8 data[24]; }; -enum ice_sbq_msg_dev { - eth56g_phy_0 = 0x02, - rmn_0 = 0x02, - rmn_1 = 0x03, - rmn_2 = 0x04, - cgu = 0x06, - eth56g_phy_1 = 0x0D, +enum ice_sbq_dev_id { + ice_sbq_dev_phy_0 = 0x02, + ice_sbq_dev_cgu = 0x06, + ice_sbq_dev_phy_0_peer = 0x0D, }; enum ice_sbq_msg_opcode { diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 6ca13c5dcb14..d9d09296d1d4 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -85,6 +85,27 @@ ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid) } /** + * ice_sched_find_next_vsi_node - find the next node for a given VSI + * @vsi_node: VSI support node to start search with + * + * Return: Next VSI support node, or NULL. + * + * The function returns a pointer to the next node from the VSI layer + * assigned to the given VSI, or NULL if there is no such a node. + */ +static struct ice_sched_node * +ice_sched_find_next_vsi_node(struct ice_sched_node *vsi_node) +{ + unsigned int vsi_handle = vsi_node->vsi_handle; + + while ((vsi_node = vsi_node->sibling) != NULL) + if (vsi_node->vsi_handle == vsi_handle) + break; + + return vsi_node; +} + +/** * ice_aqc_send_sched_elem_cmd - send scheduling elements cmd * @hw: pointer to the HW struct * @cmd_opc: cmd opcode @@ -1084,8 +1105,10 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi, if (parent->num_children < max_child_nodes) { new_num_nodes = max_child_nodes - parent->num_children; } else { - /* This parent is full, try the next sibling */ - parent = parent->sibling; + /* This parent is full, + * try the next available sibling. + */ + parent = ice_sched_find_next_vsi_node(parent); /* Don't modify the first node TEID memory if the * first node was added already in the above call. * Instead send some temp memory for all other @@ -1528,12 +1551,23 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, /* get the first queue group node from VSI sub-tree */ qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer); while (qgrp_node) { + struct ice_sched_node *next_vsi_node; + /* make sure the qgroup node is part of the VSI subtree */ if (ice_sched_find_node_in_subtree(pi->hw, vsi_node, qgrp_node)) if (qgrp_node->num_children < max_children && qgrp_node->owner == owner) break; qgrp_node = qgrp_node->sibling; + if (qgrp_node) + continue; + + next_vsi_node = ice_sched_find_next_vsi_node(vsi_node); + if (!next_vsi_node) + break; + + vsi_node = next_vsi_node; + qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer); } /* Select the best queue group */ @@ -1604,16 +1638,16 @@ ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node, /** * ice_sched_calc_vsi_child_nodes - calculate number of VSI child nodes * @hw: pointer to the HW struct - * @num_qs: number of queues + * @num_new_qs: number of new queues that will be added to the tree * @num_nodes: num nodes array * * This function calculates the number of VSI child nodes based on the * number of queues. */ static void -ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes) +ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_new_qs, u16 *num_nodes) { - u16 num = num_qs; + u16 num = num_new_qs; u8 i, qgl, vsil; qgl = ice_sched_get_qgrp_layer(hw); @@ -1779,7 +1813,11 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle, if (!parent) return -EIO; - if (i == vsil) + /* Do not modify the VSI handle for already existing VSI nodes, + * (if no new VSI node was added to the tree). + * Assign the VSI handle only to newly added VSI nodes. + */ + if (i == vsil && num_added) parent->vsi_handle = vsi_handle; } @@ -1813,6 +1851,41 @@ ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_handle, u8 tc) } /** + * ice_sched_recalc_vsi_support_nodes - recalculate VSI support nodes count + * @hw: pointer to the HW struct + * @vsi_node: pointer to the leftmost VSI node that needs to be extended + * @new_numqs: new number of queues that has to be handled by the VSI + * @new_num_nodes: pointer to nodes count table to modify the VSI layer entry + * + * This function recalculates the number of supported nodes that need to + * be added after adding more Tx queues for a given VSI. + * The number of new VSI support nodes that shall be added will be saved + * to the @new_num_nodes table for the VSI layer. + */ +static void +ice_sched_recalc_vsi_support_nodes(struct ice_hw *hw, + struct ice_sched_node *vsi_node, + unsigned int new_numqs, u16 *new_num_nodes) +{ + u32 vsi_nodes_cnt = 1; + u32 max_queue_cnt = 1; + u32 qgl, vsil; + + qgl = ice_sched_get_qgrp_layer(hw); + vsil = ice_sched_get_vsi_layer(hw); + + for (u32 i = vsil; i <= qgl; i++) + max_queue_cnt *= hw->max_children[i]; + + while ((vsi_node = ice_sched_find_next_vsi_node(vsi_node)) != NULL) + vsi_nodes_cnt++; + + if (new_numqs > (max_queue_cnt * vsi_nodes_cnt)) + new_num_nodes[vsil] = DIV_ROUND_UP(new_numqs, max_queue_cnt) - + vsi_nodes_cnt; +} + +/** * ice_sched_update_vsi_child_nodes - update VSI child nodes * @pi: port information structure * @vsi_handle: software VSI handle @@ -1863,15 +1936,25 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, return status; } - if (new_numqs) - ice_sched_calc_vsi_child_nodes(hw, new_numqs, new_num_nodes); - /* Keep the max number of queue configuration all the time. Update the - * tree only if number of queues > previous number of queues. This may + ice_sched_recalc_vsi_support_nodes(hw, vsi_node, + new_numqs, new_num_nodes); + ice_sched_calc_vsi_child_nodes(hw, new_numqs - prev_numqs, + new_num_nodes); + + /* Never decrease the number of queues in the tree. Update the tree + * only if number of queues > previous number of queues. This may * leave some extra nodes in the tree if number of queues < previous * number but that wouldn't harm anything. Removing those extra nodes * may complicate the code if those nodes are part of SRL or * individually rate limited. + * Also, add the required VSI support nodes if the existing ones cannot + * handle the requested new number of queues. */ + status = ice_sched_add_vsi_support_nodes(pi, vsi_handle, tc_node, + new_num_nodes); + if (status) + return status; + status = ice_sched_add_vsi_child_nodes(pi, vsi_handle, tc_node, new_num_nodes, owner); if (status) @@ -2013,6 +2096,58 @@ static bool ice_sched_is_leaf_node_present(struct ice_sched_node *node) } /** + * ice_sched_rm_vsi_subtree - remove all nodes assigned to a given VSI + * @pi: port information structure + * @vsi_node: pointer to the leftmost node of the VSI to be removed + * @owner: LAN or RDMA + * @tc: TC number + * + * Return: Zero in case of success, or -EBUSY if the VSI has leaf nodes in TC. + * + * This function removes all the VSI support nodes associated with a given VSI + * and its LAN or RDMA children nodes from the scheduler tree. + */ +static int +ice_sched_rm_vsi_subtree(struct ice_port_info *pi, + struct ice_sched_node *vsi_node, u8 owner, u8 tc) +{ + u16 vsi_handle = vsi_node->vsi_handle; + bool all_vsi_nodes_removed = true; + int j = 0; + + while (vsi_node) { + struct ice_sched_node *next_vsi_node; + + if (ice_sched_is_leaf_node_present(vsi_node)) { + ice_debug(pi->hw, ICE_DBG_SCHED, "VSI has leaf nodes in TC %d\n", tc); + return -EBUSY; + } + while (j < vsi_node->num_children) { + if (vsi_node->children[j]->owner == owner) + ice_free_sched_node(pi, vsi_node->children[j]); + else + j++; + } + + next_vsi_node = ice_sched_find_next_vsi_node(vsi_node); + + /* remove the VSI if it has no children */ + if (!vsi_node->num_children) + ice_free_sched_node(pi, vsi_node); + else + all_vsi_nodes_removed = false; + + vsi_node = next_vsi_node; + } + + /* clean up aggregator related VSI info if any */ + if (all_vsi_nodes_removed) + ice_sched_rm_agg_vsi_info(pi, vsi_handle); + + return 0; +} + +/** * ice_sched_rm_vsi_cfg - remove the VSI and its children nodes * @pi: port information structure * @vsi_handle: software VSI handle @@ -2038,7 +2173,6 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner) ice_for_each_traffic_class(i) { struct ice_sched_node *vsi_node, *tc_node; - u8 j = 0; tc_node = ice_sched_get_tc_node(pi, i); if (!tc_node) @@ -2048,31 +2182,12 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner) if (!vsi_node) continue; - if (ice_sched_is_leaf_node_present(vsi_node)) { - ice_debug(pi->hw, ICE_DBG_SCHED, "VSI has leaf nodes in TC %d\n", i); - status = -EBUSY; + status = ice_sched_rm_vsi_subtree(pi, vsi_node, owner, i); + if (status) goto exit_sched_rm_vsi_cfg; - } - while (j < vsi_node->num_children) { - if (vsi_node->children[j]->owner == owner) { - ice_free_sched_node(pi, vsi_node->children[j]); - /* reset the counter again since the num - * children will be updated after node removal - */ - j = 0; - } else { - j++; - } - } - /* remove the VSI if it has no children */ - if (!vsi_node->num_children) { - ice_free_sched_node(pi, vsi_node); - vsi_ctx->sched.vsi_node[i] = NULL; + vsi_ctx->sched.vsi_node[i] = NULL; - /* clean up aggregator related VSI info if any */ - ice_sched_rm_agg_vsi_info(pi, vsi_handle); - } if (owner == ICE_SCHED_NODE_OWNER_LAN) vsi_ctx->sched.max_lanq[i] = 0; else diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.c b/drivers/net/ethernet/intel/ice/ice_sf_eth.c index 75d7147e1c01..1a2c94375ca7 100644 --- a/drivers/net/ethernet/intel/ice/ice_sf_eth.c +++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.c @@ -5,8 +5,8 @@ #include "ice_txrx.h" #include "ice_fltr.h" #include "ice_sf_eth.h" -#include "devlink/devlink_port.h" #include "devlink/devlink.h" +#include "devlink/port.h" static const struct net_device_ops ice_sf_netdev_ops = { .ndo_open = ice_open, diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index b83f99c01d91..0e4dc1a5cff0 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -36,6 +36,7 @@ static void ice_free_vf_entries(struct ice_pf *pf) hash_for_each_safe(vfs->table, bkt, tmp, vf, entry) { hash_del_rcu(&vf->entry); + ice_deinitialize_vf_entry(vf); ice_put_vf(vf); } } @@ -62,6 +63,7 @@ static void ice_free_vf_res(struct ice_vf *vf) if (vf->lan_vsi_idx != ICE_NO_VSI) { ice_vf_vsi_release(vf); vf->num_mac = 0; + vf->num_mac_lldp = 0; } last_vector_idx = vf->first_vector_idx + vf->num_msix - 1; @@ -123,27 +125,6 @@ static void ice_dis_vf_mappings(struct ice_vf *vf) } /** - * ice_sriov_free_msix_res - Reset/free any used MSIX resources - * @pf: pointer to the PF structure - * - * Since no MSIX entries are taken from the pf->irq_tracker then just clear - * the pf->sriov_base_vector. - * - * Returns 0 on success, and -EINVAL on error. - */ -static int ice_sriov_free_msix_res(struct ice_pf *pf) -{ - if (!pf) - return -EINVAL; - - bitmap_free(pf->sriov_irq_bm); - pf->sriov_irq_size = 0; - pf->sriov_base_vector = 0; - - return 0; -} - -/** * ice_free_vfs - Free all VFs * @pf: pointer to the PF structure */ @@ -177,6 +158,7 @@ void ice_free_vfs(struct ice_pf *pf) ice_eswitch_detach_vf(pf, vf); ice_dis_vf_qs(vf); + ice_virt_free_irqs(pf, vf->first_vector_idx, vf->num_msix); if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { /* disable VF qp mappings and set VF disable state */ @@ -193,16 +175,9 @@ void ice_free_vfs(struct ice_pf *pf) wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); } - /* clear malicious info since the VF is getting released */ - if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) - list_del(&vf->mbx_info.list_entry); - mutex_unlock(&vf->cfg_lock); } - if (ice_sriov_free_msix_res(pf)) - dev_err(dev, "Failed to free MSIX resources used by SR-IOV\n"); - vfs->num_qps_per = 0; ice_free_vf_entries(pf); @@ -372,40 +347,6 @@ void ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector) } /** - * ice_sriov_set_msix_res - Set any used MSIX resources - * @pf: pointer to PF structure - * @num_msix_needed: number of MSIX vectors needed for all SR-IOV VFs - * - * This function allows SR-IOV resources to be taken from the end of the PF's - * allowed HW MSIX vectors so that the irq_tracker will not be affected. We - * just set the pf->sriov_base_vector and return success. - * - * If there are not enough resources available, return an error. This should - * always be caught by ice_set_per_vf_res(). - * - * Return 0 on success, and -EINVAL when there are not enough MSIX vectors - * in the PF's space available for SR-IOV. - */ -static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed) -{ - u16 total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; - int vectors_used = ice_get_max_used_msix_vector(pf); - int sriov_base_vector; - - sriov_base_vector = total_vectors - num_msix_needed; - - /* make sure we only grab irq_tracker entries from the list end and - * that we have enough available MSIX vectors - */ - if (sriov_base_vector < vectors_used) - return -EINVAL; - - pf->sriov_base_vector = sriov_base_vector; - - return 0; -} - -/** * ice_set_per_vf_res - check if vectors and queues are available * @pf: pointer to the PF structure * @num_vfs: the number of SR-IOV VFs being configured @@ -429,11 +370,9 @@ static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed) */ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) { - int vectors_used = ice_get_max_used_msix_vector(pf); u16 num_msix_per_vf, num_txq, num_rxq, avail_qs; int msix_avail_per_vf, msix_avail_for_sriov; struct device *dev = ice_pf_to_dev(pf); - int err; lockdep_assert_held(&pf->vfs.table_lock); @@ -441,8 +380,7 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) return -EINVAL; /* determine MSI-X resources per VF */ - msix_avail_for_sriov = pf->hw.func_caps.common_cap.num_msix_vectors - - vectors_used; + msix_avail_for_sriov = pf->virt_irq_tracker.num_entries; msix_avail_per_vf = msix_avail_for_sriov / num_vfs; if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MED) { num_msix_per_vf = ICE_NUM_VF_MSIX_MED; @@ -481,13 +419,6 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) return -ENOSPC; } - err = ice_sriov_set_msix_res(pf, num_msix_per_vf * num_vfs); - if (err) { - dev_err(dev, "Unable to set MSI-X resources for %d VFs, err %d\n", - num_vfs, err); - return err; - } - /* only allow equal Tx/Rx queue count (i.e. queue pairs) */ pf->vfs.num_qps_per = min_t(int, num_txq, num_rxq); pf->vfs.num_msix_per = num_msix_per_vf; @@ -498,52 +429,6 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) } /** - * ice_sriov_get_irqs - get irqs for SR-IOV usacase - * @pf: pointer to PF structure - * @needed: number of irqs to get - * - * This returns the first MSI-X vector index in PF space that is used by this - * VF. This index is used when accessing PF relative registers such as - * GLINT_VECT2FUNC and GLINT_DYN_CTL. - * This will always be the OICR index in the AVF driver so any functionality - * using vf->first_vector_idx for queue configuration_id: id of VF which will - * use this irqs - * - * Only SRIOV specific vectors are tracked in sriov_irq_bm. SRIOV vectors are - * allocated from the end of global irq index. First bit in sriov_irq_bm means - * last irq index etc. It simplifies extension of SRIOV vectors. - * They will be always located from sriov_base_vector to the last irq - * index. While increasing/decreasing sriov_base_vector can be moved. - */ -static int ice_sriov_get_irqs(struct ice_pf *pf, u16 needed) -{ - int res = bitmap_find_next_zero_area(pf->sriov_irq_bm, - pf->sriov_irq_size, 0, needed, 0); - /* conversion from number in bitmap to global irq index */ - int index = pf->sriov_irq_size - res - needed; - - if (res >= pf->sriov_irq_size || index < pf->sriov_base_vector) - return -ENOENT; - - bitmap_set(pf->sriov_irq_bm, res, needed); - return index; -} - -/** - * ice_sriov_free_irqs - free irqs used by the VF - * @pf: pointer to PF structure - * @vf: pointer to VF structure - */ -static void ice_sriov_free_irqs(struct ice_pf *pf, struct ice_vf *vf) -{ - /* Move back from first vector index to first index in bitmap */ - int bm_i = pf->sriov_irq_size - vf->first_vector_idx - vf->num_msix; - - bitmap_clear(pf->sriov_irq_bm, bm_i, vf->num_msix); - vf->first_vector_idx = 0; -} - -/** * ice_init_vf_vsi_res - initialize/setup VF VSI resources * @vf: VF to initialize/setup the VSI for * @@ -556,7 +441,7 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf) struct ice_vsi *vsi; int err; - vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix); if (vf->first_vector_idx < 0) return -ENOMEM; @@ -856,16 +741,10 @@ err_free_entries: */ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) { - int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; int ret; - pf->sriov_irq_bm = bitmap_zalloc(total_vectors, GFP_KERNEL); - if (!pf->sriov_irq_bm) - return -ENOMEM; - pf->sriov_irq_size = total_vectors; - /* Disable global interrupt 0 so we don't try to handle the VFLR. */ wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index), ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); @@ -918,7 +797,6 @@ err_unroll_intr: /* rearm interrupts here */ ice_irq_dynamic_ena(hw, NULL, NULL); clear_bit(ICE_OICR_INTR_DIS, pf->state); - bitmap_free(pf->sriov_irq_bm); return ret; } @@ -992,16 +870,7 @@ u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev) { struct ice_pf *pf = pci_get_drvdata(pdev); - return pf->sriov_irq_size - ice_get_max_used_msix_vector(pf); -} - -static int ice_sriov_move_base_vector(struct ice_pf *pf, int move) -{ - if (pf->sriov_base_vector - move < ice_get_max_used_msix_vector(pf)) - return -ENOMEM; - - pf->sriov_base_vector -= move; - return 0; + return pf->virt_irq_tracker.num_entries; } static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id) @@ -1020,7 +889,8 @@ static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id) continue; ice_dis_vf_mappings(tmp_vf); - ice_sriov_free_irqs(pf, tmp_vf); + ice_virt_free_irqs(pf, tmp_vf->first_vector_idx, + tmp_vf->num_msix); vf_ids[to_remap] = tmp_vf->vf_id; to_remap += 1; @@ -1032,7 +902,7 @@ static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id) continue; tmp_vf->first_vector_idx = - ice_sriov_get_irqs(pf, tmp_vf->num_msix); + ice_virt_get_irqs(pf, tmp_vf->num_msix); /* there is no need to rebuild VSI as we are only changing the * vector indexes not amount of MSI-X or queues */ @@ -1105,20 +975,15 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) prev_msix = vf->num_msix; prev_queues = vf->num_vf_qs; - if (ice_sriov_move_base_vector(pf, msix_vec_count - prev_msix)) { - ice_put_vf(vf); - return -ENOSPC; - } - ice_dis_vf_mappings(vf); - ice_sriov_free_irqs(pf, vf); + ice_virt_free_irqs(pf, vf->first_vector_idx, vf->num_msix); /* Remap all VFs beside the one is now configured */ ice_sriov_remap_vectors(pf, vf->vf_id); vf->num_msix = msix_vec_count; vf->num_vf_qs = queues; - vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix); if (vf->first_vector_idx < 0) goto unroll; @@ -1147,7 +1012,8 @@ unroll: vf->num_msix = prev_msix; vf->num_vf_qs = prev_queues; - vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + + vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix); if (vf->first_vector_idx < 0) { ice_put_vf(vf); return -EINVAL; @@ -1537,6 +1403,9 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) mutex_lock(&vf->cfg_lock); + while (!trusted && vf->num_mac_lldp) + ice_vf_update_mac_lldp_num(vf, ice_get_vf_vsi(vf), false); + vf->trusted = trusted; ice_reset_vf(vf, ICE_VF_RESET_NOTIFY); dev_info(ice_pf_to_dev(pf), "VF %u is now %strusted\n", diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 0e740342e294..9d9a7edd3618 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -3146,7 +3146,7 @@ ice_add_update_vsi_list(struct ice_hw *hw, u16 vsi_handle_arr[2]; /* A rule already exists with the new VSI being added */ - if (cur_fltr->fwd_id.hw_vsi_id == new_fltr->fwd_id.hw_vsi_id) + if (cur_fltr->vsi_handle == new_fltr->vsi_handle) return -EEXIST; vsi_handle_arr[0] = cur_fltr->vsi_handle; @@ -4784,7 +4784,8 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, */ if (found && recp[i].tun_type == rinfo->tun_type && recp[i].need_pass_l2 == rinfo->need_pass_l2 && - recp[i].allow_pass_l2 == rinfo->allow_pass_l2) + recp[i].allow_pass_l2 == rinfo->allow_pass_l2 && + recp[i].priority == rinfo->priority) return i; /* Return the recipe ID */ } } @@ -5977,7 +5978,7 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw, /* A rule already exists with the new VSI being added */ if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map)) - return 0; + return -EEXIST; /* Update the previously created VSI list set with * the new VSI ID passed in diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index ea39b999a0d0..fb9ea7f8ef44 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -12,14 +12,11 @@ /** * ice_tc_count_lkups - determine lookup count for switch filter * @flags: TC-flower flags - * @headers: Pointer to TC flower filter header structure * @fltr: Pointer to outer TC filter structure * - * Determine lookup count based on TC flower input for switch filter. + * Return: lookup count based on TC flower input for a switch filter. */ -static int -ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, - struct ice_tc_flower_fltr *fltr) +static int ice_tc_count_lkups(u32 flags, struct ice_tc_flower_fltr *fltr) { int lkups_cnt = 1; /* 0th lookup is metadata */ @@ -684,26 +681,26 @@ static int ice_tc_setup_action(struct net_device *filter_dev, fltr->action.fltr_act = action; if (ice_is_port_repr_netdev(filter_dev) && - ice_is_port_repr_netdev(target_dev)) { + ice_is_port_repr_netdev(target_dev) && + fltr->direction == ICE_ESWITCH_FLTR_EGRESS) { repr = ice_netdev_to_repr(target_dev); fltr->dest_vsi = repr->src_vsi; - fltr->direction = ICE_ESWITCH_FLTR_EGRESS; } else if (ice_is_port_repr_netdev(filter_dev) && - ice_tc_is_dev_uplink(target_dev)) { + ice_tc_is_dev_uplink(target_dev) && + fltr->direction == ICE_ESWITCH_FLTR_EGRESS) { repr = ice_netdev_to_repr(filter_dev); fltr->dest_vsi = repr->src_vsi->back->eswitch.uplink_vsi; - fltr->direction = ICE_ESWITCH_FLTR_EGRESS; } else if (ice_tc_is_dev_uplink(filter_dev) && - ice_is_port_repr_netdev(target_dev)) { + ice_is_port_repr_netdev(target_dev) && + fltr->direction == ICE_ESWITCH_FLTR_INGRESS) { repr = ice_netdev_to_repr(target_dev); fltr->dest_vsi = repr->src_vsi; - fltr->direction = ICE_ESWITCH_FLTR_INGRESS; } else { NL_SET_ERR_MSG_MOD(fltr->extack, - "Unsupported netdevice in switchdev mode"); + "The action is not supported for this netdevice"); return -EINVAL; } @@ -716,13 +713,11 @@ ice_tc_setup_drop_action(struct net_device *filter_dev, { fltr->action.fltr_act = ICE_DROP_PACKET; - if (ice_is_port_repr_netdev(filter_dev)) { - fltr->direction = ICE_ESWITCH_FLTR_EGRESS; - } else if (ice_tc_is_dev_uplink(filter_dev)) { - fltr->direction = ICE_ESWITCH_FLTR_INGRESS; - } else { + if (!ice_tc_is_dev_uplink(filter_dev) && + !(ice_is_port_repr_netdev(filter_dev) && + fltr->direction == ICE_ESWITCH_FLTR_INGRESS)) { NL_SET_ERR_MSG_MOD(fltr->extack, - "Unsupported netdevice in switchdev mode"); + "The action is not supported for this netdevice"); return -EINVAL; } @@ -767,10 +762,157 @@ static int ice_eswitch_tc_parse_action(struct net_device *filter_dev, return 0; } +static bool ice_is_fltr_lldp(struct ice_tc_flower_fltr *fltr) +{ + return fltr->outer_headers.l2_key.n_proto == htons(ETH_P_LLDP); +} + +static bool ice_is_fltr_pf_tx_lldp(struct ice_tc_flower_fltr *fltr) +{ + struct ice_vsi *vsi = fltr->src_vsi, *uplink; + + if (!ice_is_switchdev_running(vsi->back)) + return false; + + uplink = vsi->back->eswitch.uplink_vsi; + return vsi == uplink && fltr->action.fltr_act == ICE_DROP_PACKET && + ice_is_fltr_lldp(fltr) && + fltr->direction == ICE_ESWITCH_FLTR_EGRESS && + fltr->flags == ICE_TC_FLWR_FIELD_ETH_TYPE_ID; +} + +static bool ice_is_fltr_vf_tx_lldp(struct ice_tc_flower_fltr *fltr) +{ + struct ice_vsi *vsi = fltr->src_vsi, *uplink; + + uplink = vsi->back->eswitch.uplink_vsi; + return fltr->src_vsi->type == ICE_VSI_VF && ice_is_fltr_lldp(fltr) && + fltr->direction == ICE_ESWITCH_FLTR_EGRESS && + fltr->dest_vsi == uplink; +} + +static struct ice_tc_flower_fltr * +ice_find_pf_tx_lldp_fltr(struct ice_pf *pf) +{ + struct ice_tc_flower_fltr *fltr; + + hlist_for_each_entry(fltr, &pf->tc_flower_fltr_list, tc_flower_node) + if (ice_is_fltr_pf_tx_lldp(fltr)) + return fltr; + + return NULL; +} + +static bool ice_any_vf_lldp_tx_ena(struct ice_pf *pf) +{ + struct ice_vf *vf; + unsigned int bkt; + + ice_for_each_vf(pf, bkt, vf) + if (vf->lldp_tx_ena) + return true; + + return false; +} + +int ice_pass_vf_tx_lldp(struct ice_vsi *vsi, bool deinit) +{ + struct ice_rule_query_data remove_entry = { + .rid = vsi->vf->lldp_recipe_id, + .rule_id = vsi->vf->lldp_rule_id, + .vsi_handle = vsi->idx, + }; + struct ice_pf *pf = vsi->back; + int err; + + if (vsi->vf->lldp_tx_ena) + return 0; + + if (!deinit && !ice_find_pf_tx_lldp_fltr(vsi->back)) + return -EINVAL; + + if (!deinit && ice_any_vf_lldp_tx_ena(pf)) + return -EINVAL; + + err = ice_rem_adv_rule_by_id(&pf->hw, &remove_entry); + if (!err) + vsi->vf->lldp_tx_ena = true; + + return err; +} + +int ice_drop_vf_tx_lldp(struct ice_vsi *vsi, bool init) +{ + struct ice_rule_query_data rule_added; + struct ice_adv_rule_info rinfo = { + .priority = 7, + .src_vsi = vsi->idx, + .sw_act = { + .src = vsi->idx, + .flag = ICE_FLTR_TX, + .fltr_act = ICE_DROP_PACKET, + .vsi_handle = vsi->idx, + }, + .flags_info.act_valid = true, + }; + struct ice_adv_lkup_elem list[3]; + struct ice_pf *pf = vsi->back; + int err; + + if (!init && !vsi->vf->lldp_tx_ena) + return 0; + + memset(list, 0, sizeof(list)); + ice_rule_add_direction_metadata(&list[0]); + ice_rule_add_src_vsi_metadata(&list[1]); + list[2].type = ICE_ETYPE_OL; + list[2].h_u.ethertype.ethtype_id = htons(ETH_P_LLDP); + list[2].m_u.ethertype.ethtype_id = htons(0xFFFF); + + err = ice_add_adv_rule(&pf->hw, list, ARRAY_SIZE(list), &rinfo, + &rule_added); + if (err) { + dev_err(&pf->pdev->dev, + "Failed to add an LLDP rule to VSI 0x%X: %d\n", + vsi->idx, err); + } else { + vsi->vf->lldp_recipe_id = rule_added.rid; + vsi->vf->lldp_rule_id = rule_added.rule_id; + vsi->vf->lldp_tx_ena = false; + } + + return err; +} + +static void ice_handle_add_pf_lldp_drop_rule(struct ice_vsi *vsi) +{ + struct ice_tc_flower_fltr *fltr; + struct ice_pf *pf = vsi->back; + + hlist_for_each_entry(fltr, &pf->tc_flower_fltr_list, tc_flower_node) { + if (!ice_is_fltr_vf_tx_lldp(fltr)) + continue; + ice_pass_vf_tx_lldp(fltr->src_vsi, true); + break; + } +} + +static void ice_handle_del_pf_lldp_drop_rule(struct ice_pf *pf) +{ + int i; + + /* Make the VF LLDP fwd to uplink rule dormant */ + ice_for_each_vsi(pf, i) { + struct ice_vsi *vf_vsi = pf->vsi[i]; + + if (vf_vsi && vf_vsi->type == ICE_VSI_VF) + ice_drop_vf_tx_lldp(vf_vsi, false); + } +} + static int ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) { - struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers; struct ice_adv_rule_info rule_info = { 0 }; struct ice_rule_query_data rule_added; struct ice_hw *hw = &vsi->back->hw; @@ -785,7 +927,10 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) return -EOPNOTSUPP; } - lkups_cnt = ice_tc_count_lkups(flags, headers, fltr); + if (ice_is_fltr_vf_tx_lldp(fltr)) + return ice_pass_vf_tx_lldp(vsi, false); + + lkups_cnt = ice_tc_count_lkups(flags, fltr); list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); if (!list) return -ENOMEM; @@ -814,6 +959,11 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) rule_info.sw_act.src = hw->pf_id; rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE; } else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS && + !fltr->dest_vsi && vsi == vsi->back->eswitch.uplink_vsi) { + /* PF to Uplink */ + rule_info.sw_act.flag |= ICE_FLTR_TX; + rule_info.sw_act.src = vsi->idx; + } else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS && fltr->dest_vsi == vsi->back->eswitch.uplink_vsi) { /* VF to Uplink */ rule_info.sw_act.flag |= ICE_FLTR_TX; @@ -846,11 +996,17 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because it already exist"); ret = -EINVAL; goto exit; + } else if (ret == -ENOSPC) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter: insufficient space available."); + goto exit; } else if (ret) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter due to error"); goto exit; } + if (ice_is_fltr_pf_tx_lldp(fltr)) + ice_handle_add_pf_lldp_drop_rule(vsi); + /* store the output params, which are needed later for removing * advanced switch filter */ @@ -985,7 +1141,6 @@ static int ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr) { - struct ice_tc_flower_lyr_2_4_hdrs *headers = &tc_fltr->outer_headers; struct ice_adv_rule_info rule_info = {0}; struct ice_rule_query_data rule_added; struct ice_adv_lkup_elem *list; @@ -1021,7 +1176,7 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, return PTR_ERR(dest_vsi); } - lkups_cnt = ice_tc_count_lkups(flags, headers, tc_fltr); + lkups_cnt = ice_tc_count_lkups(flags, tc_fltr); list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); if (!list) return -ENOMEM; @@ -1056,8 +1211,13 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, tc_fltr->action.fwd.q.hw_queue, lkups_cnt); break; case ICE_DROP_PACKET: - rule_info.sw_act.flag |= ICE_FLTR_RX; - rule_info.sw_act.src = hw->pf_id; + if (tc_fltr->direction == ICE_ESWITCH_FLTR_EGRESS) { + rule_info.sw_act.flag |= ICE_FLTR_TX; + rule_info.sw_act.src = vsi->idx; + } else { + rule_info.sw_act.flag |= ICE_FLTR_RX; + rule_info.sw_act.src = hw->pf_id; + } rule_info.priority = ICE_SWITCH_FLTR_PRIO_VSI; break; default: @@ -1071,6 +1231,10 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, "Unable to add filter because it already exist"); ret = -EINVAL; goto exit; + } else if (ret == -ENOSPC) { + NL_SET_ERR_MSG_MOD(tc_fltr->extack, + "Unable to add filter: insufficient space available."); + goto exit; } else if (ret) { NL_SET_ERR_MSG_MOD(tc_fltr->extack, "Unable to add filter due to error"); @@ -1463,11 +1627,16 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, * @filter_dev: Pointer to device on which filter is being added * @f: Pointer to struct flow_cls_offload * @fltr: Pointer to filter structure + * @ingress: if the rule is added to an ingress block + * + * Return: 0 if the flower was parsed successfully, -EINVAL if the flower + * cannot be parsed, -EOPNOTSUPP if such filter cannot be configured + * for the given VSI. */ static int ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, struct flow_cls_offload *f, - struct ice_tc_flower_fltr *fltr) + struct ice_tc_flower_fltr *fltr, bool ingress) { struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers; struct flow_rule *rule = flow_cls_offload_flow_rule(f); @@ -1551,6 +1720,20 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, fltr->flags |= ICE_TC_FLWR_FIELD_ETH_TYPE_ID; } + if (!ingress) { + bool switchdev = + ice_is_eswitch_mode_switchdev(vsi->back); + + if (switchdev != (n_proto_key == ETH_P_LLDP)) { + NL_SET_ERR_MSG_FMT_MOD(fltr->extack, + "%sLLDP filtering is not supported on egress in %s mode", + switchdev ? "Non-" : "", + switchdev ? "switchdev" : + "legacy"); + return -EOPNOTSUPP; + } + } + headers->l2_key.n_proto = cpu_to_be16(n_proto_key); headers->l2_mask.n_proto = cpu_to_be16(n_proto_mask); headers->l3_key.ip_proto = match.key->ip_proto; @@ -1726,6 +1909,14 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, return -EINVAL; } } + + /* Ingress filter on representor results in an egress filter in HW + * and vice versa + */ + ingress = ice_is_port_repr_netdev(filter_dev) ? !ingress : ingress; + fltr->direction = ingress ? ICE_ESWITCH_FLTR_INGRESS : + ICE_ESWITCH_FLTR_EGRESS; + return 0; } @@ -1939,6 +2130,12 @@ static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) struct ice_pf *pf = vsi->back; int err; + if (ice_is_fltr_pf_tx_lldp(fltr)) + ice_handle_del_pf_lldp_drop_rule(pf); + + if (ice_is_fltr_vf_tx_lldp(fltr)) + return ice_drop_vf_tx_lldp(vsi, false); + rule_rem.rid = fltr->rid; rule_rem.rule_id = fltr->rule_id; rule_rem.vsi_handle = fltr->dest_vsi_handle; @@ -1975,14 +2172,18 @@ static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) * @vsi: Pointer to VSI * @f: Pointer to flower offload structure * @__fltr: Pointer to struct ice_tc_flower_fltr + * @ingress: if the rule is added to an ingress block * * This function parses TC-flower input fields, parses action, * and adds a filter. + * + * Return: 0 if the filter was successfully added, + * negative error code otherwise. */ static int ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi, struct flow_cls_offload *f, - struct ice_tc_flower_fltr **__fltr) + struct ice_tc_flower_fltr **__fltr, bool ingress) { struct ice_tc_flower_fltr *fltr; int err; @@ -1999,7 +2200,7 @@ ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi, fltr->src_vsi = vsi; INIT_HLIST_NODE(&fltr->tc_flower_node); - err = ice_parse_cls_flower(netdev, vsi, f, fltr); + err = ice_parse_cls_flower(netdev, vsi, f, fltr, ingress); if (err < 0) goto err; @@ -2042,10 +2243,13 @@ ice_find_tc_flower_fltr(struct ice_pf *pf, unsigned long cookie) * @netdev: Pointer to filter device * @vsi: Pointer to VSI * @cls_flower: Pointer to flower offload structure + * @ingress: if the rule is added to an ingress block + * + * Return: 0 if the flower was successfully added, + * negative error code otherwise. */ -int -ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, - struct flow_cls_offload *cls_flower) +int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower, bool ingress) { struct netlink_ext_ack *extack = cls_flower->common.extack; struct net_device *vsi_netdev = vsi->netdev; @@ -2080,7 +2284,7 @@ ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, } /* prep and add TC-flower filter in HW */ - err = ice_add_tc_fltr(netdev, vsi, cls_flower, &fltr); + err = ice_add_tc_fltr(netdev, vsi, cls_flower, &fltr, ingress); if (err) return err; diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h index d84f153517ec..8a3ab2f22af9 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h @@ -211,13 +211,14 @@ static inline int ice_chnl_dmac_fltr_cnt(struct ice_pf *pf) } struct ice_vsi *ice_locate_vsi_using_queue(struct ice_vsi *vsi, int queue); -int -ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, - struct flow_cls_offload *cls_flower); -int -ice_del_cls_flower(struct ice_vsi *vsi, struct flow_cls_offload *cls_flower); +int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower, bool ingress); +int ice_del_cls_flower(struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower); void ice_replay_tc_fltrs(struct ice_pf *pf); bool ice_is_tunnel_supported(struct net_device *dev); +int ice_drop_vf_tx_lldp(struct ice_vsi *vsi, bool init); +int ice_pass_vf_tx_lldp(struct ice_vsi *vsi, bool deinit); static inline bool ice_is_forward_action(enum ice_sw_fwd_act_type fltr_act) { diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 5d2d7736fd5f..0e5107fe62ad 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -527,15 +527,14 @@ err: * @xdp: xdp_buff used as input to the XDP program * @xdp_prog: XDP program to run * @xdp_ring: ring to be used for XDP_TX action - * @rx_buf: Rx buffer to store the XDP action * @eop_desc: Last descriptor in packet to read metadata from * * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ -static void +static u32 ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring, - struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc) + union ice_32b_rx_flex_desc *eop_desc) { unsigned int ret = ICE_XDP_PASS; u32 act; @@ -574,7 +573,7 @@ out_failure: ret = ICE_XDP_CONSUMED; } exit: - ice_set_rx_bufs_act(xdp, rx_ring, ret); + return ret; } /** @@ -860,10 +859,8 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, xdp_buff_set_frags_flag(xdp); } - if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { - ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED); + if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) return -ENOMEM; - } __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page, rx_buf->page_offset, size); @@ -924,7 +921,6 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, struct ice_rx_buf *rx_buf; rx_buf = &rx_ring->rx_buf[ntc]; - rx_buf->pgcnt = page_count(rx_buf->page); prefetchw(rx_buf->page); if (!size) @@ -941,6 +937,31 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, } /** + * ice_get_pgcnts - grab page_count() for gathered fragments + * @rx_ring: Rx descriptor ring to store the page counts on + * + * This function is intended to be called right before running XDP + * program so that the page recycling mechanism will be able to take + * a correct decision regarding underlying pages; this is done in such + * way as XDP program can change the refcount of page + */ +static void ice_get_pgcnts(struct ice_rx_ring *rx_ring) +{ + u32 nr_frags = rx_ring->nr_frags + 1; + u32 idx = rx_ring->first_desc; + struct ice_rx_buf *rx_buf; + u32 cnt = rx_ring->count; + + for (int i = 0; i < nr_frags; i++) { + rx_buf = &rx_ring->rx_buf[idx]; + rx_buf->pgcnt = page_count(rx_buf->page); + + if (++idx == cnt) + idx = 0; + } +} + +/** * ice_build_skb - Build skb around an existing buffer * @rx_ring: Rx descriptor ring to transact packets on * @xdp: xdp_buff pointing to the data @@ -1051,12 +1072,12 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) rx_buf->page_offset + headlen, size, xdp->frame_sz); } else { - /* buffer is unused, change the act that should be taken later - * on; data was copied onto skb's linear part so there's no + /* buffer is unused, restore biased page count in Rx buffer; + * data was copied onto skb's linear part so there's no * need for adjusting page offset and we can reuse this buffer * as-is */ - rx_buf->act = ICE_SKB_CONSUMED; + rx_buf->pagecnt_bias++; } if (unlikely(xdp_buff_has_frags(xdp))) { @@ -1104,6 +1125,65 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf) } /** + * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all frame frags + * @rx_ring: Rx ring with all the auxiliary data + * @xdp: XDP buffer carrying linear + frags part + * @xdp_xmit: XDP_TX/XDP_REDIRECT verdict storage + * @ntc: a current next_to_clean value to be stored at rx_ring + * @verdict: return code from XDP program execution + * + * Walk through gathered fragments and satisfy internal page + * recycle mechanism; we take here an action related to verdict + * returned by XDP program; + */ +static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, + u32 *xdp_xmit, u32 ntc, u32 verdict) +{ + u32 nr_frags = rx_ring->nr_frags + 1; + u32 idx = rx_ring->first_desc; + u32 cnt = rx_ring->count; + u32 post_xdp_frags = 1; + struct ice_rx_buf *buf; + int i; + + if (unlikely(xdp_buff_has_frags(xdp))) + post_xdp_frags += xdp_get_shared_info_from_buff(xdp)->nr_frags; + + for (i = 0; i < post_xdp_frags; i++) { + buf = &rx_ring->rx_buf[idx]; + + if (verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) { + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); + *xdp_xmit |= verdict; + } else if (verdict & ICE_XDP_CONSUMED) { + buf->pagecnt_bias++; + } else if (verdict == ICE_XDP_PASS) { + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); + } + + ice_put_rx_buf(rx_ring, buf); + + if (++idx == cnt) + idx = 0; + } + /* handle buffers that represented frags released by XDP prog; + * for these we keep pagecnt_bias as-is; refcount from struct page + * has been decremented within XDP prog and we do not have to increase + * the biased refcnt + */ + for (; i < nr_frags; i++) { + buf = &rx_ring->rx_buf[idx]; + ice_put_rx_buf(rx_ring, buf); + if (++idx == cnt) + idx = 0; + } + + xdp->data = NULL; + rx_ring->first_desc = ntc; + rx_ring->nr_frags = 0; +} + +/** * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: Rx descriptor ring to transact packets on * @budget: Total limit on number of packets to process @@ -1120,15 +1200,13 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_pkts = 0; unsigned int offset = rx_ring->rx_offset; struct xdp_buff *xdp = &rx_ring->xdp; - u32 cached_ntc = rx_ring->first_desc; struct ice_tx_ring *xdp_ring = NULL; struct bpf_prog *xdp_prog = NULL; u32 ntc = rx_ring->next_to_clean; + u32 cached_ntu, xdp_verdict; u32 cnt = rx_ring->count; u32 xdp_xmit = 0; - u32 cached_ntu; bool failure; - u32 first; xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (xdp_prog) { @@ -1190,6 +1268,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); xdp_buff_clear_frags_flag(xdp); } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { + ice_put_rx_mbuf(rx_ring, xdp, NULL, ntc, ICE_XDP_CONSUMED); break; } if (++ntc == cnt) @@ -1199,15 +1278,15 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) if (ice_is_non_eop(rx_ring, rx_desc)) continue; - ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc); - if (rx_buf->act == ICE_XDP_PASS) + ice_get_pgcnts(rx_ring); + xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc); + if (xdp_verdict == ICE_XDP_PASS) goto construct_skb; total_rx_bytes += xdp_get_buff_len(xdp); total_rx_pkts++; - xdp->data = NULL; - rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; + ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict); + continue; construct_skb: if (likely(ice_ring_uses_build_skb(rx_ring))) @@ -1217,18 +1296,12 @@ construct_skb: /* exit if we failed to retrieve a buffer */ if (!skb) { rx_ring->ring_stats->rx_stats.alloc_page_failed++; - rx_buf->act = ICE_XDP_CONSUMED; - if (unlikely(xdp_buff_has_frags(xdp))) - ice_set_rx_bufs_act(xdp, rx_ring, - ICE_XDP_CONSUMED); - xdp->data = NULL; - rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; - break; + xdp_verdict = ICE_XDP_CONSUMED; } - xdp->data = NULL; - rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; + ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict); + + if (!skb) + break; stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); if (unlikely(ice_test_staterr(rx_desc->wb.status_error0, @@ -1257,23 +1330,6 @@ construct_skb: total_rx_pkts++; } - first = rx_ring->first_desc; - while (cached_ntc != first) { - struct ice_rx_buf *buf = &rx_ring->rx_buf[cached_ntc]; - - if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) { - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - xdp_xmit |= buf->act; - } else if (buf->act & ICE_XDP_CONSUMED) { - buf->pagecnt_bias++; - } else if (buf->act == ICE_XDP_PASS) { - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - } - - ice_put_rx_buf(rx_ring, buf); - if (++cached_ntc >= cnt) - cached_ntc = 0; - } rx_ring->next_to_clean = ntc; /* return up to cleaned_count buffers to hardware */ failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring)); @@ -1753,6 +1809,7 @@ dma_error: static int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) { + const struct ice_tx_ring *tx_ring = off->tx_ring; u32 l4_len = 0, l3_len = 0, l2_len = 0; struct sk_buff *skb = first->skb; union { @@ -1902,6 +1959,30 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) l3_len = l4.hdr - ip.hdr; offset |= (l3_len / 4) << ICE_TX_DESC_LEN_IPLEN_S; + if ((tx_ring->netdev->features & NETIF_F_HW_CSUM) && + !(first->tx_flags & ICE_TX_FLAGS_TSO) && + !skb_csum_is_sctp(skb)) { + /* Set GCS */ + u16 csum_start = (skb->csum_start - skb->mac_header) / 2; + u16 csum_offset = skb->csum_offset / 2; + u16 gcs_params; + + gcs_params = FIELD_PREP(ICE_TX_GCS_DESC_START_M, csum_start) | + FIELD_PREP(ICE_TX_GCS_DESC_OFFSET_M, csum_offset) | + FIELD_PREP(ICE_TX_GCS_DESC_TYPE_M, + ICE_TX_GCS_DESC_CSUM_PSH); + + /* Unlike legacy HW checksums, GCS requires a context + * descriptor. + */ + off->cd_qw1 |= ICE_TX_DESC_DTYPE_CTX; + off->cd_gcs_params = gcs_params; + /* Fill out CSO info in data descriptors */ + off->td_offset |= offset; + off->td_cmd |= cmd; + return 1; + } + /* Enable L4 checksum offloads */ switch (l4_proto) { case IPPROTO_TCP: @@ -2359,17 +2440,20 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) /* allow CONTROL frames egress from main VSI if FW LLDP disabled */ eth = (struct ethhdr *)skb_mac_header(skb); - if (unlikely((skb->priority == TC_PRIO_CONTROL || - eth->h_proto == htons(ETH_P_LLDP)) && - vsi->type == ICE_VSI_PF && - vsi->port_info->qos_cfg.is_sw_lldp)) + + if ((ice_is_switchdev_running(vsi->back) || + ice_lag_is_switchdev_running(vsi->back)) && + vsi->type != ICE_VSI_SF) + ice_eswitch_set_target_vsi(skb, &offload); + else if (unlikely((skb->priority == TC_PRIO_CONTROL || + eth->h_proto == htons(ETH_P_LLDP)) && + vsi->type == ICE_VSI_PF && + vsi->port_info->qos_cfg.is_sw_lldp)) offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX | ICE_TX_CTX_DESC_SWTCH_UPLINK << ICE_TXD_CTX_QW1_CMD_S); ice_tstamp(tx_ring, skb, first, &offload); - if (ice_is_switchdev_running(vsi->back) && vsi->type != ICE_VSI_SF) - ice_eswitch_set_target_vsi(skb, &offload); if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) { struct ice_tx_ctx_desc *cdesc; @@ -2383,7 +2467,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) /* setup context descriptor */ cdesc->tunneling_params = cpu_to_le32(offload.cd_tunnel_params); cdesc->l2tag2 = cpu_to_le16(offload.cd_l2tag2); - cdesc->rsvd = cpu_to_le16(0); + cdesc->gcs = cpu_to_le16(offload.cd_gcs_params); cdesc->qw1 = cpu_to_le64(offload.cd_qw1); } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index cb347c852ba9..a4b1e9514632 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -193,6 +193,7 @@ struct ice_tx_offload_params { u32 td_l2tag1; u32 cd_tunnel_params; u16 cd_l2tag2; + u16 cd_gcs_params; u8 header_len; }; @@ -201,7 +202,6 @@ struct ice_rx_buf { struct page *page; unsigned int page_offset; unsigned int pgcnt; - unsigned int act; unsigned int pagecnt_bias; }; @@ -367,6 +367,7 @@ struct ice_rx_ring { #define ICE_RX_FLAGS_RING_BUILD_SKB BIT(1) #define ICE_RX_FLAGS_CRC_STRIP_DIS BIT(2) #define ICE_RX_FLAGS_MULTIDEV BIT(3) +#define ICE_RX_FLAGS_RING_GCS BIT(4) u8 flags; /* CL5 - 5th cacheline starts here */ struct xdp_rxq_info xdp_rxq; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 2719f0e20933..45cfaabc41cb 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -81,6 +81,23 @@ ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring, } /** + * ice_rx_gcs - Set generic checksum in skb + * @skb: skb currently being received and modified + * @rx_desc: receive descriptor + */ +static void ice_rx_gcs(struct sk_buff *skb, + const union ice_32b_rx_flex_desc *rx_desc) +{ + const struct ice_32b_rx_flex_desc_nic *desc; + u16 csum; + + desc = (struct ice_32b_rx_flex_desc_nic *)rx_desc; + skb->ip_summed = CHECKSUM_COMPLETE; + csum = (__force u16)desc->raw_csum; + skb->csum = csum_unfold((__force __sum16)swab16(csum)); +} + +/** * ice_rx_csum - Indicate in skb if checksum is good * @ring: the ring we care about * @skb: skb currently being received and modified @@ -107,6 +124,15 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb, rx_status0 = le16_to_cpu(rx_desc->wb.status_error0); rx_status1 = le16_to_cpu(rx_desc->wb.status_error1); + if ((ring->flags & ICE_RX_FLAGS_RING_GCS) && + rx_desc->wb.rxdid == ICE_RXDID_FLEX_NIC && + (decoded.inner_prot == LIBETH_RX_PT_INNER_TCP || + decoded.inner_prot == LIBETH_RX_PT_INNER_UDP || + decoded.inner_prot == LIBETH_RX_PT_INNER_ICMP)) { + ice_rx_gcs(skb, rx_desc); + return; + } + /* check if HW has decoded the packet and checksum */ if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S))) return; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index 79f960c6680d..6cf32b404127 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -6,49 +6,6 @@ #include "ice.h" /** - * ice_set_rx_bufs_act - propagate Rx buffer action to frags - * @xdp: XDP buffer representing frame (linear and frags part) - * @rx_ring: Rx ring struct - * act: action to store onto Rx buffers related to XDP buffer parts - * - * Set action that should be taken before putting Rx buffer from first frag - * to the last. - */ -static inline void -ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring, - const unsigned int act) -{ - u32 sinfo_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags; - u32 nr_frags = rx_ring->nr_frags + 1; - u32 idx = rx_ring->first_desc; - u32 cnt = rx_ring->count; - struct ice_rx_buf *buf; - - for (int i = 0; i < nr_frags; i++) { - buf = &rx_ring->rx_buf[idx]; - buf->act = act; - - if (++idx == cnt) - idx = 0; - } - - /* adjust pagecnt_bias on frags freed by XDP prog */ - if (sinfo_frags < rx_ring->nr_frags && act == ICE_XDP_CONSUMED) { - u32 delta = rx_ring->nr_frags - sinfo_frags; - - while (delta) { - if (idx == 0) - idx = cnt - 1; - else - idx--; - buf = &rx_ring->rx_buf[idx]; - buf->pagecnt_bias--; - delta--; - } - } -} - -/** * ice_test_staterr - tests bits in Rx descriptor status and error fields * @status_err_n: Rx descriptor status_error0 or status_error1 bits * @stat_err_bits: value to mask diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 4a9ef722635f..3d68f465952d 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -18,6 +18,8 @@ #include "ice_sbq_cmd.h" #include "ice_vlan_mode.h" #include "ice_fwlog.h" +#include <linux/wait.h> +#include <net/dscp.h> static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc) { @@ -368,6 +370,7 @@ struct ice_ts_func_info { #define ICE_TS_TMR1_ENA_M BIT(26) #define ICE_TS_LL_TX_TS_READ_M BIT(28) #define ICE_TS_LL_TX_TS_INT_READ_M BIT(29) +#define ICE_TS_LL_PHY_TMR_UPDATE_M BIT(30) struct ice_ts_dev_info { /* Device specific info */ @@ -382,6 +385,7 @@ struct ice_ts_dev_info { u8 tmr1_ena; u8 ts_ll_read; u8 ts_ll_int_read; + u8 ll_phy_tmr_update; }; #define ICE_NAC_TOPO_PRIMARY_M BIT(0) @@ -692,7 +696,6 @@ struct ice_dcb_app_priority_table { #define ICE_MAX_USER_PRIORITY 8 #define ICE_DCBX_MAX_APPS 64 -#define ICE_DSCP_NUM_VAL 64 #define ICE_LLDPDU_SIZE 1500 #define ICE_TLV_STATUS_OPER 0x1 #define ICE_TLV_STATUS_SYNC 0x2 @@ -715,9 +718,9 @@ struct ice_dcbx_cfg { u8 pfc_mode; struct ice_dcb_app_priority_table app[ICE_DCBX_MAX_APPS]; /* when DSCP mapping defined by user set its bit to 1 */ - DECLARE_BITMAP(dscp_mapped, ICE_DSCP_NUM_VAL); + DECLARE_BITMAP(dscp_mapped, DSCP_MAX); /* array holding DSCP -> UP/TC values for DSCP L3 QoS mode */ - u8 dscp_map[ICE_DSCP_NUM_VAL]; + u8 dscp_map[DSCP_MAX]; u8 dcbx_mode; #define ICE_DCBX_MODE_CEE 0x1 #define ICE_DCBX_MODE_IEEE 0x2 @@ -848,6 +851,14 @@ struct ice_mbx_data { #define ICE_PORTS_PER_QUAD 4 #define ICE_GET_QUAD_NUM(port) ((port) / ICE_PORTS_PER_QUAD) +#define ATQBAL_FLAGS_INTR_IN_PROGRESS BIT(0) + +struct ice_e810_params { + /* The wait queue lock also protects the low latency interface */ + wait_queue_head_t atqbal_wq; + unsigned int atqbal_flags; +}; + struct ice_eth56g_params { u8 num_phys; bool onestep_ena; @@ -856,17 +867,10 @@ struct ice_eth56g_params { }; union ice_phy_params { + struct ice_e810_params e810; struct ice_eth56g_params eth56g; }; -/* PHY model */ -enum ice_phy_model { - ICE_PHY_UNSUP = -1, - ICE_PHY_E810 = 1, - ICE_PHY_E82X, - ICE_PHY_ETH56G, -}; - /* Global Link Topology */ enum ice_global_link_topo { ICE_LINK_TOPO_UP_TO_2_LINKS, @@ -876,7 +880,6 @@ enum ice_global_link_topo { }; struct ice_ptp_hw { - enum ice_phy_model phy_model; union ice_phy_params phy; u8 num_lports; u8 ports_per_phy; @@ -967,6 +970,7 @@ struct ice_hw { u8 intrl_gran; struct ice_ptp_hw ptp; + s8 lane_num; /* Active package version (currently active) */ struct ice_pkg_ver active_pkg_ver; @@ -1214,4 +1218,9 @@ struct ice_aq_get_set_rss_lut_params { #define ICE_FW_API_REPORT_DFLT_CFG_MIN 7 #define ICE_FW_API_REPORT_DFLT_CFG_PATCH 3 +/* AQ API version for Health Status support */ +#define ICE_FW_API_HEALTH_REPORT_MAJ 1 +#define ICE_FW_API_HEALTH_REPORT_MIN 7 +#define ICE_FW_API_HEALTH_REPORT_PATCH 6 + #endif /* _ICE_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index c7c0c2f50c26..48cd533e93b7 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -226,6 +226,7 @@ static void ice_vf_clear_counters(struct ice_vf *vf) vsi->num_vlan = 0; vf->num_mac = 0; + vf->num_mac_lldp = 0; memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events)); memset(&vf->mdd_rx_events, 0, sizeof(vf->mdd_rx_events)); } @@ -1036,6 +1037,14 @@ void ice_initialize_vf_entry(struct ice_vf *vf) mutex_init(&vf->cfg_lock); } +void ice_deinitialize_vf_entry(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + + if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) + list_del(&vf->mbx_info.list_entry); +} + /** * ice_dis_vf_qs - Disable the VF queues * @vf: pointer to the VF structure @@ -1393,3 +1402,28 @@ struct ice_vsi *ice_get_vf_ctrl_vsi(struct ice_pf *pf, struct ice_vsi *vsi) rcu_read_unlock(); return ctrl_vsi; } + +/** + * ice_vf_update_mac_lldp_num - update the VF's number of LLDP addresses + * @vf: a VF to add the address to + * @vsi: the corresponding VSI + * @incr: is the rule added or removed + */ +void ice_vf_update_mac_lldp_num(struct ice_vf *vf, struct ice_vsi *vsi, + bool incr) +{ + bool lldp_by_fw = test_bit(ICE_FLAG_FW_LLDP_AGENT, vsi->back->flags); + bool was_ena = ice_vf_is_lldp_ena(vf) && !lldp_by_fw; + bool is_ena; + + if (WARN_ON(!vsi)) { + vf->num_mac_lldp = 0; + return; + } + + vf->num_mac_lldp += incr ? 1 : -1; + is_ena = ice_vf_is_lldp_ena(vf) && !lldp_by_fw; + + if (was_ena != is_ena) + ice_vsi_cfg_sw_lldp(vsi, false, is_ena); +} diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index 4261fe1c2bcd..482f4285fd35 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -124,6 +124,10 @@ struct ice_vf { u8 spoofchk:1; u8 link_forced:1; u8 link_up:1; /* only valid if VF link is forced */ + u8 lldp_tx_ena:1; + + u32 ptp_caps; + unsigned int min_tx_rate; /* Minimum Tx bandwidth limit in Mbps */ unsigned int max_tx_rate; /* Maximum Tx bandwidth limit in Mbps */ DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ @@ -131,6 +135,7 @@ struct ice_vf { unsigned long vf_caps; /* VF's adv. capabilities */ u8 num_req_qs; /* num of queue pairs requested by VF */ u16 num_mac; + u16 num_mac_lldp; u16 num_vf_qs; /* num of queue configured per VF */ u8 vlan_strip_ena; /* Outer and Inner VLAN strip enable */ #define ICE_INNER_VLAN_STRIP_ENA BIT(0) @@ -146,6 +151,9 @@ struct ice_vf { /* devlink port data */ struct devlink_port devlink_port; + u16 lldp_recipe_id; + u16 lldp_rule_id; + u16 num_msix; /* num of MSI-X configured on this VF */ struct ice_vf_qs_bw qs_bw[ICE_MAX_RSS_QS_PER_VF]; }; @@ -177,6 +185,11 @@ static inline u16 ice_vf_get_port_vlan_tpid(struct ice_vf *vf) return vf->port_vlan_info.tpid; } +static inline bool ice_vf_is_lldp_ena(struct ice_vf *vf) +{ + return vf->num_mac_lldp && vf->trusted; +} + /* VF Hash Table access functions * * These functions provide abstraction for interacting with the VF hash table. @@ -242,6 +255,8 @@ ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m); int ice_reset_vf(struct ice_vf *vf, u32 flags); void ice_reset_all_vfs(struct ice_pf *pf); struct ice_vsi *ice_get_vf_ctrl_vsi(struct ice_pf *pf, struct ice_vsi *vsi); +void ice_vf_update_mac_lldp_num(struct ice_vf *vf, struct ice_vsi *vsi, + bool incr); #else /* CONFIG_PCI_IOV */ static inline struct ice_vf *ice_get_vf_by_id(struct ice_pf *pf, u16 vf_id) { diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h index 0c7e77c0a09f..5392b0404986 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -24,6 +24,7 @@ #endif void ice_initialize_vf_entry(struct ice_vf *vf); +void ice_deinitialize_vf_entry(struct ice_vf *vf); void ice_dis_vf_qs(struct ice_vf *vf); int ice_check_vf_init(struct ice_vf *vf); enum virtchnl_status_code ice_err_to_virt_err(int err); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index ff4ad788d96a..eeeb9968e477 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -498,6 +498,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_QOS) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_QOS; + if (vf->driver_caps & VIRTCHNL_VF_CAP_PTP) + vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_PTP; + vfres->num_vsis = 1; /* Tx and Rx queue are equal for VF */ vfres->num_queue_pairs = vsi->num_txq; @@ -562,7 +565,7 @@ bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) * * check for the valid queue ID */ -static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u8 qid) +static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u16 qid) { /* allocated Tx and Rx queues should be always equal for VF VSI */ return qid < vsi->alloc_txq; @@ -1862,15 +1865,33 @@ static int ice_vc_cfg_q_bw(struct ice_vf *vf, u8 *msg) for (i = 0; i < qbw->num_queues; i++) { if (qbw->cfg[i].shaper.peak != 0 && vf->max_tx_rate != 0 && - qbw->cfg[i].shaper.peak > vf->max_tx_rate) + qbw->cfg[i].shaper.peak > vf->max_tx_rate) { dev_warn(ice_pf_to_dev(vf->pf), "The maximum queue %d rate limit configuration may not take effect because the maximum TX rate for VF-%d is %d\n", qbw->cfg[i].queue_id, vf->vf_id, vf->max_tx_rate); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } if (qbw->cfg[i].shaper.committed != 0 && vf->min_tx_rate != 0 && - qbw->cfg[i].shaper.committed < vf->min_tx_rate) + qbw->cfg[i].shaper.committed < vf->min_tx_rate) { dev_warn(ice_pf_to_dev(vf->pf), "The minimum queue %d rate limit configuration may not take effect because the minimum TX rate for VF-%d is %d\n", qbw->cfg[i].queue_id, vf->vf_id, - vf->max_tx_rate); + vf->min_tx_rate); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + if (qbw->cfg[i].queue_id > vf->num_vf_qs) { + dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure invalid queue_id\n", + vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + if (qbw->cfg[i].tc >= ICE_MAX_TRAFFIC_CLASS) { + dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure a traffic class higher than allowed\n", + vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } } for (i = 0; i < qbw->num_queues; i++) { @@ -1900,13 +1921,21 @@ err: */ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg) { + u16 quanta_prof_id, quanta_size, start_qid, num_queues, end_qid, i; enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - u16 quanta_prof_id, quanta_size, start_qid, end_qid, i; struct virtchnl_quanta_cfg *qquanta = (struct virtchnl_quanta_cfg *)msg; struct ice_vsi *vsi; int ret; + start_qid = qquanta->queue_select.start_queue_id; + num_queues = qquanta->queue_select.num_queues; + + if (check_add_overflow(start_qid, num_queues, &end_qid)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto err; @@ -1918,8 +1947,6 @@ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg) goto err; } - end_qid = qquanta->queue_select.start_queue_id + - qquanta->queue_select.num_queues; if (end_qid > ICE_MAX_RSS_QS_PER_VF || end_qid > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) { dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n", @@ -1948,7 +1975,6 @@ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg) goto err; } - start_qid = qquanta->queue_select.start_queue_id; for (i = start_qid; i < end_qid; i++) vsi->tx_rings[i]->quanta_prof_id = quanta_prof_id; @@ -1975,6 +2001,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) struct ice_vsi *vsi; u8 act_prt, pri_prt; int i = -1, q_idx; + bool ena_ts; lag = pf->lag; mutex_lock(&pf->lag_mutex); @@ -2104,9 +2131,14 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) rxdid = ICE_RXDID_LEGACY_1; } + ena_ts = ((vf->driver_caps & + VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) && + (vf->driver_caps & VIRTCHNL_VF_CAP_PTP) && + (qpi->rxq.flags & VIRTCHNL_PTP_RX_TSTAMP)); + ice_write_qrxflxp_cntxt(&vsi->back->hw, - vsi->rxq_map[q_idx], - rxdid, 0x03, false); + vsi->rxq_map[q_idx], rxdid, + ICE_RXDID_PRIO, ena_ts); } } @@ -2234,6 +2266,51 @@ ice_vfhw_mac_add(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr) } /** + * ice_is_mc_lldp_eth_addr - check if the given MAC is a multicast LLDP address + * @mac: address to check + * + * Return: true if the address is one of the three possible LLDP multicast + * addresses, false otherwise. + */ +static bool ice_is_mc_lldp_eth_addr(const u8 *mac) +{ + const u8 lldp_mac_base[] = {0x01, 0x80, 0xc2, 0x00, 0x00}; + + if (memcmp(mac, lldp_mac_base, sizeof(lldp_mac_base))) + return false; + + return (mac[5] == 0x0e || mac[5] == 0x03 || mac[5] == 0x00); +} + +/** + * ice_vc_can_add_mac - check if the VF is allowed to add a given MAC + * @vf: a VF to add the address to + * @mac: address to check + * + * Return: true if the VF is allowed to add such MAC address, false otherwise. + */ +static bool ice_vc_can_add_mac(const struct ice_vf *vf, const u8 *mac) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + + if (is_unicast_ether_addr(mac) && + !ice_can_vf_change_mac((struct ice_vf *)vf)) { + dev_err(dev, + "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); + return false; + } + + if (!vf->trusted && ice_is_mc_lldp_eth_addr(mac)) { + dev_warn(dev, + "An untrusted VF %u is attempting to configure an LLDP multicast address\n", + vf->vf_id); + return false; + } + + return true; +} + +/** * ice_vc_add_mac_addr - attempt to add the MAC address passed in * @vf: pointer to the VF info * @vsi: pointer to the VF's VSI @@ -2251,10 +2328,8 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, if (ether_addr_equal(mac_addr, vf->dev_lan_addr)) return 0; - if (is_unicast_ether_addr(mac_addr) && !ice_can_vf_change_mac(vf)) { - dev_err(dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); + if (!ice_vc_can_add_mac(vf, mac_addr)) return -EPERM; - } ret = ice_fltr_add_mac(vsi, mac_addr, ICE_FWD_TO_VSI); if (ret == -EEXIST) { @@ -2269,6 +2344,8 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, return ret; } else { vf->num_mac++; + if (ice_is_mc_lldp_eth_addr(mac_addr)) + ice_vf_update_mac_lldp_num(vf, vsi, true); } ice_vfhw_mac_add(vf, vc_ether_addr); @@ -2363,6 +2440,8 @@ ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, ice_vfhw_mac_del(vf, vc_ether_addr); vf->num_mac--; + if (ice_is_mc_lldp_eth_addr(mac_addr)) + ice_vf_update_mac_lldp_num(vf, vsi, false); return 0; } @@ -3031,8 +3110,8 @@ err: static int ice_vc_query_rxdid(struct ice_vf *vf) { enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_supported_rxdids rxdid = {}; struct ice_pf *pf = vf->pf; + u64 rxdid; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -3044,7 +3123,7 @@ static int ice_vc_query_rxdid(struct ice_vf *vf) goto err; } - rxdid.supported_rxdids = pf->supported_rxdids; + rxdid = pf->supported_rxdids; err: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, @@ -4092,6 +4171,59 @@ out: v_ret, NULL, 0); } +static int ice_vc_get_ptp_cap(struct ice_vf *vf, + const struct virtchnl_ptp_caps *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM; + u32 caps = VIRTCHNL_1588_PTP_CAP_RX_TSTAMP | + VIRTCHNL_1588_PTP_CAP_READ_PHC; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + goto err; + + v_ret = VIRTCHNL_STATUS_SUCCESS; + + if (msg->caps & caps) + vf->ptp_caps = caps; + +err: + /* send the response back to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_CAPS, v_ret, + (u8 *)&vf->ptp_caps, + sizeof(struct virtchnl_ptp_caps)); +} + +static int ice_vc_get_phc_time(struct ice_vf *vf) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM; + struct virtchnl_phc_time *phc_time = NULL; + struct ice_pf *pf = vf->pf; + u32 len = 0; + int ret; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + goto err; + + v_ret = VIRTCHNL_STATUS_SUCCESS; + + phc_time = kzalloc(sizeof(*phc_time), GFP_KERNEL); + if (!phc_time) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + goto err; + } + + len = sizeof(*phc_time); + + phc_time->time = ice_ptp_read_src_clk_reg(pf, NULL); + +err: + /* send the response back to the VF */ + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_TIME, v_ret, + (u8 *)phc_time, len); + kfree(phc_time); + return ret; +} + static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = { .get_ver_msg = ice_vc_get_ver_msg, .get_vf_res_msg = ice_vc_get_vf_res_msg, @@ -4128,6 +4260,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = { .get_qos_caps = ice_vc_get_qos_caps, .cfg_q_bw = ice_vc_cfg_q_bw, .cfg_q_quanta = ice_vc_cfg_q_quanta, + .get_ptp_cap = ice_vc_get_ptp_cap, + .get_phc_time = ice_vc_get_phc_time, /* If you add a new op here please make sure to add it to * ice_virtchnl_repr_ops as well. */ @@ -4188,7 +4322,6 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg) } ice_vfhw_mac_add(vf, &al->list[i]); - vf->num_mac++; break; } @@ -4264,6 +4397,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = { .get_qos_caps = ice_vc_get_qos_caps, .cfg_q_bw = ice_vc_cfg_q_bw, .cfg_q_quanta = ice_vc_cfg_q_quanta, + .get_ptp_cap = ice_vc_get_ptp_cap, + .get_phc_time = ice_vc_get_phc_time, }; /** @@ -4501,6 +4636,12 @@ error_handler: case VIRTCHNL_OP_CONFIG_QUANTA: err = ops->cfg_q_quanta(vf, msg); break; + case VIRTCHNL_OP_1588_PTP_GET_CAPS: + err = ops->get_ptp_cap(vf, (const void *)msg); + break; + case VIRTCHNL_OP_1588_PTP_GET_TIME: + err = ops->get_phc_time(vf); + break; case VIRTCHNL_OP_UNKNOWN: default: dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode, diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h index 0c629aef9baf..222990f229d5 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h @@ -26,6 +26,9 @@ #define ICE_MAX_MACADDR_PER_VF 18 #define ICE_FLEX_DESC_RXDID_MAX_NUM 64 +/* Priority to be compared against previous priority from the pipe */ +#define ICE_RXDID_PRIO 0x03 + /* VFs only get a single VSI. For ice hardware, the VF does not need to know * its VSI index. However, the virtchnl interface requires a VSI number, * mainly due to legacy hardware. @@ -72,6 +75,9 @@ struct ice_virtchnl_ops { int (*cfg_q_tc_map)(struct ice_vf *vf, u8 *msg); int (*cfg_q_bw)(struct ice_vf *vf, u8 *msg); int (*cfg_q_quanta)(struct ice_vf *vf, u8 *msg); + int (*get_ptp_cap)(struct ice_vf *vf, + const struct virtchnl_ptp_caps *msg); + int (*get_phc_time)(struct ice_vf *vf); }; #ifdef CONFIG_PCI_IOV diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c index c105a82ee136..a3d1579a619a 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -84,6 +84,12 @@ static const u32 fdir_pf_allowlist_opcodes[] = { VIRTCHNL_OP_ADD_FDIR_FILTER, VIRTCHNL_OP_DEL_FDIR_FILTER, }; +/* VIRTCHNL_VF_CAP_PTP */ +static const u32 ptp_allowlist_opcodes[] = { + VIRTCHNL_OP_1588_PTP_GET_CAPS, + VIRTCHNL_OP_1588_PTP_GET_TIME, +}; + static const u32 tc_allowlist_opcodes[] = { VIRTCHNL_OP_GET_QOS_CAPS, VIRTCHNL_OP_CONFIG_QUEUE_BW, VIRTCHNL_OP_CONFIG_QUANTA, @@ -110,6 +116,7 @@ static const struct allowlist_opcode_info allowlist_opcodes[] = { ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN_V2, vlan_v2_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_QOS, tc_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_CAP_PTP, ptp_allowlist_opcodes), }; /** diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index 14e3f0f89c78..1cca9b2262e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -832,21 +832,27 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto, struct virtchnl_fdir_fltr_conf *conf) { - u8 *pkt_buf, *msk_buf __free(kfree); + u8 *pkt_buf, *msk_buf __free(kfree) = NULL; struct ice_parser_result rslt; struct ice_pf *pf = vf->pf; + u16 pkt_len, udp_port = 0; struct ice_parser *psr; int status = -ENOMEM; struct ice_hw *hw; - u16 udp_port = 0; - pkt_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL); - msk_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL); + pkt_len = proto->raw.pkt_len; + + if (!pkt_len || pkt_len > VIRTCHNL_MAX_SIZE_RAW_PACKET) + return -EINVAL; + + pkt_buf = kzalloc(pkt_len, GFP_KERNEL); + msk_buf = kzalloc(pkt_len, GFP_KERNEL); + if (!pkt_buf || !msk_buf) goto err_mem_alloc; - memcpy(pkt_buf, proto->raw.spec, proto->raw.pkt_len); - memcpy(msk_buf, proto->raw.mask, proto->raw.pkt_len); + memcpy(pkt_buf, proto->raw.spec, pkt_len); + memcpy(msk_buf, proto->raw.mask, pkt_len); hw = &pf->hw; @@ -862,7 +868,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf, if (ice_get_open_tunnel_port(hw, &udp_port, TNL_VXLAN)) ice_parser_vxlan_tunnel_set(psr, udp_port, true); - status = ice_parser_run(psr, pkt_buf, proto->raw.pkt_len, &rslt); + status = ice_parser_run(psr, pkt_buf, pkt_len, &rslt); if (status) goto err_parser_destroy; @@ -876,7 +882,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf, } status = ice_parser_profile_init(&rslt, pkt_buf, msk_buf, - proto->raw.pkt_len, ICE_BLK_FD, + pkt_len, ICE_BLK_FD, conf->prof); if (status) goto err_parser_profile_init; @@ -885,7 +891,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf, ice_parser_profile_dump(hw, conf->prof); /* Store raw flow info into @conf */ - conf->pkt_len = proto->raw.pkt_len; + conf->pkt_len = pkt_len; conf->pkt_buf = pkt_buf; conf->parser_ena = true; @@ -1515,7 +1521,7 @@ ice_vc_fdir_irq_handler(struct ice_vsi *ctrl_vsi, memcpy(&ctx_done->rx_desc, rx_desc, sizeof(*rx_desc)); spin_unlock_irqrestore(&fdir->ctx_lock, flags); - ret = del_timer(&ctx_irq->rx_tmr); + ret = timer_delete(&ctx_irq->rx_tmr); if (!ret) dev_err(dev, "VF %d: Unexpected inactive timer!\n", vf->vf_id); @@ -1910,7 +1916,7 @@ static void ice_vc_fdir_clear_irq_ctx(struct ice_vf *vf) struct ice_vf_fdir_ctx *ctx = &vf->fdir.ctx_irq; unsigned long flags; - del_timer(&ctx->rx_tmr); + timer_delete(&ctx->rx_tmr); spin_lock_irqsave(&vf->fdir.ctx_lock, flags); ctx->flags &= ~ICE_VF_FDIR_CTX_VALID; spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags); @@ -2091,6 +2097,11 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) pf = vf->pf; dev = ice_pf_to_dev(pf); vf_vsi = ice_get_vf_vsi(vf); + if (!vf_vsi) { + dev_err(dev, "Can not get FDIR vf_vsi for VF %u\n", vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err_exit; + } #define ICE_VF_MAX_FDIR_FILTERS 128 if (!ice_fdir_num_avail_fltr(&pf->hw, vf_vsi) || diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 334ae945d640..a3a4eaa17739 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019, Intel Corporation. */ #include <linux/bpf_trace.h> +#include <linux/unroll.h> #include <net/xdp_sock_drv.h> #include <net/xdp.h> #include "ice.h" @@ -801,35 +802,6 @@ out_failure: return result; } -static int -ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first, - struct xdp_buff *xdp, const unsigned int size) -{ - struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first); - - if (!size) - return 0; - - if (!xdp_buff_has_frags(first)) { - sinfo->nr_frags = 0; - sinfo->xdp_frags_size = 0; - xdp_buff_set_frags_flag(first); - } - - if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { - xsk_buff_free(first); - return -ENOMEM; - } - - __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, - virt_to_page(xdp->data_hard_start), - XDP_PACKET_HEADROOM, size); - sinfo->xdp_frags_size += size; - xsk_buff_add_frag(xdp); - - return 0; -} - /** * ice_clean_rx_irq_zc - consumes packets from the hardware ring * @rx_ring: AF_XDP Rx ring @@ -895,7 +867,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, if (!first) { first = xdp; - } else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) { + } else if (likely(size) && !xsk_buff_add_frag(first, xdp)) { + xsk_buff_free(first); break; } @@ -1017,7 +990,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct ice_tx_desc *tx_desc; u32 i; - loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) { + unrolled_count(PKTS_PER_BATCH) + for (i = 0; i < PKTS_PER_BATCH; i++) { dma_addr_t dma; dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index 45adeb513253..8dc5d55e26c5 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -7,14 +7,6 @@ #define PKTS_PER_BATCH 8 -#ifdef __clang__ -#define loop_unrolled_for _Pragma("clang loop unroll_count(8)") for -#elif __GNUC__ >= 8 -#define loop_unrolled_for _Pragma("GCC unroll 8") for -#else -#define loop_unrolled_for for -#endif - struct ice_vsi; #ifdef CONFIG_XDP_SOCKETS |