diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ice/ice_devlink.c')
| -rw-r--r-- | drivers/net/ethernet/intel/ice/ice_devlink.c | 758 |
1 files changed, 684 insertions, 74 deletions
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index b9bd9f9472f6..e6ec20079ced 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -1,12 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020, Intel Corporation. */ +#include <linux/vmalloc.h> + #include "ice.h" #include "ice_lib.h" #include "ice_devlink.h" #include "ice_eswitch.h" #include "ice_fw_update.h" +static int ice_active_port_option = -1; + /* context for devlink info version reporting */ struct ice_info_ctx { char buf[128]; @@ -39,13 +43,13 @@ static void ice_info_get_dsn(struct ice_pf *pf, struct ice_info_ctx *ctx) static void ice_info_pba(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_hw *hw = &pf->hw; - enum ice_status status; + int status; status = ice_read_pba_string(hw, (u8 *)ctx->buf, sizeof(ctx->buf)); if (status) /* We failed to locate the PBA, so just skip this entry */ - dev_dbg(ice_pf_to_dev(pf), "Failed to read Product Board Assembly string, status %s\n", - ice_stat_str(status)); + dev_dbg(ice_pf_to_dev(pf), "Failed to read Product Board Assembly string, status %d\n", + status); } static void ice_info_fw_mgmt(struct ice_pf *pf, struct ice_info_ctx *ctx) @@ -251,7 +255,6 @@ static int ice_devlink_info_get(struct devlink *devlink, struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; struct ice_info_ctx *ctx; - enum ice_status status; size_t i; int err; @@ -266,20 +269,19 @@ static int ice_devlink_info_get(struct devlink *devlink, return -ENOMEM; /* discover capabilities first */ - status = ice_discover_dev_caps(hw, &ctx->dev_caps); - if (status) { - dev_dbg(dev, "Failed to discover device capabilities, status %s aq_err %s\n", - ice_stat_str(status), ice_aq_str(hw->adminq.sq_last_status)); + err = ice_discover_dev_caps(hw, &ctx->dev_caps); + if (err) { + dev_dbg(dev, "Failed to discover device capabilities, status %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); NL_SET_ERR_MSG_MOD(extack, "Unable to discover device capabilities"); - err = -EIO; goto out_free_ctx; } if (ctx->dev_caps.common_cap.nvm_update_pending_orom) { - status = ice_get_inactive_orom_ver(hw, &ctx->pending_orom); - if (status) { - dev_dbg(dev, "Unable to read inactive Option ROM version data, status %s aq_err %s\n", - ice_stat_str(status), ice_aq_str(hw->adminq.sq_last_status)); + err = ice_get_inactive_orom_ver(hw, &ctx->pending_orom); + if (err) { + dev_dbg(dev, "Unable to read inactive Option ROM version data, status %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); /* disable display of pending Option ROM */ ctx->dev_caps.common_cap.nvm_update_pending_orom = false; @@ -287,10 +289,10 @@ static int ice_devlink_info_get(struct devlink *devlink, } if (ctx->dev_caps.common_cap.nvm_update_pending_nvm) { - status = ice_get_inactive_nvm_ver(hw, &ctx->pending_nvm); - if (status) { - dev_dbg(dev, "Unable to read inactive NVM version data, status %s aq_err %s\n", - ice_stat_str(status), ice_aq_str(hw->adminq.sq_last_status)); + err = ice_get_inactive_nvm_ver(hw, &ctx->pending_nvm); + if (err) { + dev_dbg(dev, "Unable to read inactive NVM version data, status %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); /* disable display of pending Option ROM */ ctx->dev_caps.common_cap.nvm_update_pending_nvm = false; @@ -298,10 +300,10 @@ static int ice_devlink_info_get(struct devlink *devlink, } if (ctx->dev_caps.common_cap.nvm_update_pending_netlist) { - status = ice_get_inactive_netlist_ver(hw, &ctx->pending_netlist); - if (status) { - dev_dbg(dev, "Unable to read inactive Netlist version data, status %s aq_err %s\n", - ice_stat_str(status), ice_aq_str(hw->adminq.sq_last_status)); + err = ice_get_inactive_netlist_ver(hw, &ctx->pending_netlist); + if (err) { + dev_dbg(dev, "Unable to read inactive Netlist version data, status %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); /* disable display of pending Option ROM */ ctx->dev_caps.common_cap.nvm_update_pending_netlist = false; @@ -373,63 +375,472 @@ out_free_ctx: } /** - * ice_devlink_flash_update - Update firmware stored in flash on the device - * @devlink: pointer to devlink associated with device to update - * @params: flash update parameters + * ice_devlink_reload_empr_start - Start EMP reset to activate new firmware + * @devlink: pointer to the devlink instance to reload + * @netns_change: if true, the network namespace is changing + * @action: the action to perform. Must be DEVLINK_RELOAD_ACTION_FW_ACTIVATE + * @limit: limits on what reload should do, such as not resetting * @extack: netlink extended ACK structure * - * Perform a device flash update. The bulk of the update logic is contained - * within the ice_flash_pldm_image function. + * Allow user to activate new Embedded Management Processor firmware by + * issuing device specific EMP reset. Called in response to + * a DEVLINK_CMD_RELOAD with the DEVLINK_RELOAD_ACTION_FW_ACTIVATE. * - * Returns: zero on success, or an error code on failure. + * Note that teardown and rebuild of the driver state happens automatically as + * part of an interrupt and watchdog task. This is because all physical + * functions on the device must be able to reset when an EMP reset occurs from + * any source. */ static int -ice_devlink_flash_update(struct devlink *devlink, - struct devlink_flash_update_params *params, - struct netlink_ext_ack *extack) +ice_devlink_reload_empr_start(struct devlink *devlink, bool netns_change, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); + struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - u8 preservation; + u8 pending; int err; - if (!params->overwrite_mask) { - /* preserve all settings and identifiers */ - preservation = ICE_AQC_NVM_PRESERVE_ALL; - } else if (params->overwrite_mask == DEVLINK_FLASH_OVERWRITE_SETTINGS) { - /* overwrite settings, but preserve the vital device identifiers */ - preservation = ICE_AQC_NVM_PRESERVE_SELECTED; - } else if (params->overwrite_mask == (DEVLINK_FLASH_OVERWRITE_SETTINGS | - DEVLINK_FLASH_OVERWRITE_IDENTIFIERS)) { - /* overwrite both settings and identifiers, preserve nothing */ - preservation = ICE_AQC_NVM_NO_PRESERVATION; - } else { - NL_SET_ERR_MSG_MOD(extack, "Requested overwrite mask is not supported"); - return -EOPNOTSUPP; + err = ice_get_pending_updates(pf, &pending, extack); + if (err) + return err; + + /* pending is a bitmask of which flash banks have a pending update, + * including the main NVM bank, the Option ROM bank, and the netlist + * bank. If any of these bits are set, then there is a pending update + * waiting to be activated. + */ + if (!pending) { + NL_SET_ERR_MSG_MOD(extack, "No pending firmware update"); + return -ECANCELED; } - if (!hw->dev_caps.common_cap.nvm_unified_update) { - NL_SET_ERR_MSG_MOD(extack, "Current firmware does not support unified update"); - return -EOPNOTSUPP; + if (pf->fw_emp_reset_disabled) { + NL_SET_ERR_MSG_MOD(extack, "EMP reset is not available. To activate firmware, a reboot or power cycle is needed"); + return -ECANCELED; } - err = ice_check_for_pending_update(pf, NULL, extack); - if (err) + dev_dbg(dev, "Issuing device EMP reset to activate firmware\n"); + + err = ice_aq_nvm_update_empr(hw); + if (err) { + dev_err(dev, "Failed to trigger EMP device reset to reload firmware, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + NL_SET_ERR_MSG_MOD(extack, "Failed to trigger EMP device reset to reload firmware"); + return err; + } + + return 0; +} + +/** + * ice_devlink_reload_empr_finish - Wait for EMP reset to finish + * @devlink: pointer to the devlink instance reloading + * @action: the action requested + * @limit: limits imposed by userspace, such as not resetting + * @actions_performed: on return, indicate what actions actually performed + * @extack: netlink extended ACK structure + * + * Wait for driver to finish rebuilding after EMP reset is completed. This + * includes time to wait for both the actual device reset as well as the time + * for the driver's rebuild to complete. + */ +static int +ice_devlink_reload_empr_finish(struct devlink *devlink, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + u32 *actions_performed, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + int err; + + *actions_performed = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE); + + err = ice_wait_for_reset(pf, 60 * HZ); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Device still resetting after 1 minute"); return err; + } + + return 0; +} + +/** + * ice_devlink_port_opt_speed_str - convert speed to a string + * @speed: speed value + */ +static const char *ice_devlink_port_opt_speed_str(u8 speed) +{ + switch (speed & ICE_AQC_PORT_OPT_MAX_LANE_M) { + case ICE_AQC_PORT_OPT_MAX_LANE_100M: + return "0.1"; + case ICE_AQC_PORT_OPT_MAX_LANE_1G: + return "1"; + case ICE_AQC_PORT_OPT_MAX_LANE_2500M: + return "2.5"; + case ICE_AQC_PORT_OPT_MAX_LANE_5G: + return "5"; + case ICE_AQC_PORT_OPT_MAX_LANE_10G: + return "10"; + case ICE_AQC_PORT_OPT_MAX_LANE_25G: + return "25"; + case ICE_AQC_PORT_OPT_MAX_LANE_50G: + return "50"; + case ICE_AQC_PORT_OPT_MAX_LANE_100G: + return "100"; + } + + return "-"; +} + +#define ICE_PORT_OPT_DESC_LEN 50 +/** + * ice_devlink_port_options_print - Print available port split options + * @pf: the PF to print split port options + * + * Prints a table with available port split options and max port speeds + */ +static void ice_devlink_port_options_print(struct ice_pf *pf) +{ + u8 i, j, options_count, cnt, speed, pending_idx, active_idx; + struct ice_aqc_get_port_options_elem *options, *opt; + struct device *dev = ice_pf_to_dev(pf); + bool active_valid, pending_valid; + char desc[ICE_PORT_OPT_DESC_LEN]; + const char *str; + int status; + + options = kcalloc(ICE_AQC_PORT_OPT_MAX * ICE_MAX_PORT_PER_PCI_DEV, + sizeof(*options), GFP_KERNEL); + if (!options) + return; + + for (i = 0; i < ICE_MAX_PORT_PER_PCI_DEV; i++) { + opt = options + i * ICE_AQC_PORT_OPT_MAX; + options_count = ICE_AQC_PORT_OPT_MAX; + active_valid = 0; + + status = ice_aq_get_port_options(&pf->hw, opt, &options_count, + i, true, &active_idx, + &active_valid, &pending_idx, + &pending_valid); + if (status) { + dev_dbg(dev, "Couldn't read port option for port %d, err %d\n", + i, status); + goto err; + } + } + + dev_dbg(dev, "Available port split options and max port speeds (Gbps):\n"); + dev_dbg(dev, "Status Split Quad 0 Quad 1\n"); + dev_dbg(dev, " count L0 L1 L2 L3 L4 L5 L6 L7\n"); + + for (i = 0; i < options_count; i++) { + cnt = 0; + + if (i == ice_active_port_option) + str = "Active"; + else if ((i == pending_idx) && pending_valid) + str = "Pending"; + else + str = ""; + + cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, + "%-8s", str); + + cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, + "%-6u", options[i].pmd); + + for (j = 0; j < ICE_MAX_PORT_PER_PCI_DEV; ++j) { + speed = options[i + j * ICE_AQC_PORT_OPT_MAX].max_lane_speed; + str = ice_devlink_port_opt_speed_str(speed); + cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, + "%3s ", str); + } + + dev_dbg(dev, "%s\n", desc); + } + +err: + kfree(options); +} + +/** + * ice_devlink_aq_set_port_option - Send set port option admin queue command + * @pf: the PF to print split port options + * @option_idx: selected port option + * @extack: extended netdev ack structure + * + * Sends set port option admin queue command with selected port option and + * calls NVM write activate. + */ +static int +ice_devlink_aq_set_port_option(struct ice_pf *pf, u8 option_idx, + struct netlink_ext_ack *extack) +{ + struct device *dev = ice_pf_to_dev(pf); + int status; + + status = ice_aq_set_port_option(&pf->hw, 0, true, option_idx); + if (status) { + dev_dbg(dev, "ice_aq_set_port_option, err %d aq_err %d\n", + status, pf->hw.adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Port split request failed"); + return -EIO; + } - devlink_flash_update_status_notify(devlink, "Preparing to flash", NULL, 0, 0); + status = ice_acquire_nvm(&pf->hw, ICE_RES_WRITE); + if (status) { + dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n", + status, pf->hw.adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); + return -EIO; + } - return ice_flash_pldm_image(pf, params->fw, preservation, extack); + status = ice_nvm_write_activate(&pf->hw, ICE_AQC_NVM_ACTIV_REQ_EMPR, NULL); + if (status) { + dev_dbg(dev, "ice_nvm_write_activate failed, err %d aq_err %d\n", + status, pf->hw.adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Port split request failed to save data"); + ice_release_nvm(&pf->hw); + return -EIO; + } + + ice_release_nvm(&pf->hw); + + NL_SET_ERR_MSG_MOD(extack, "Reboot required to finish port split"); + return 0; +} + +/** + * ice_devlink_port_split - .port_split devlink handler + * @devlink: devlink instance structure + * @port: devlink port structure + * @count: number of ports to split to + * @extack: extended netdev ack structure + * + * Callback for the devlink .port_split operation. + * + * Unfortunately, the devlink expression of available options is limited + * to just a number, so search for an FW port option which supports + * the specified number. As there could be multiple FW port options with + * the same port split count, allow switching between them. When the same + * port split count request is issued again, switch to the next FW port + * option with the same port split count. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_devlink_port_split(struct devlink *devlink, struct devlink_port *port, + unsigned int count, struct netlink_ext_ack *extack) +{ + struct ice_aqc_get_port_options_elem options[ICE_AQC_PORT_OPT_MAX]; + u8 i, j, active_idx, pending_idx, new_option; + struct ice_pf *pf = devlink_priv(devlink); + u8 option_count = ICE_AQC_PORT_OPT_MAX; + struct device *dev = ice_pf_to_dev(pf); + bool active_valid, pending_valid; + int status; + + status = ice_aq_get_port_options(&pf->hw, options, &option_count, + 0, true, &active_idx, &active_valid, + &pending_idx, &pending_valid); + if (status) { + dev_dbg(dev, "Couldn't read port split options, err = %d\n", + status); + NL_SET_ERR_MSG_MOD(extack, "Failed to get available port split options"); + return -EIO; + } + + new_option = ICE_AQC_PORT_OPT_MAX; + active_idx = pending_valid ? pending_idx : active_idx; + for (i = 1; i <= option_count; i++) { + /* In order to allow switching between FW port options with + * the same port split count, search for a new option starting + * from the active/pending option (with array wrap around). + */ + j = (active_idx + i) % option_count; + + if (count == options[j].pmd) { + new_option = j; + break; + } + } + + if (new_option == active_idx) { + dev_dbg(dev, "request to split: count: %u is already set and there are no other options\n", + count); + NL_SET_ERR_MSG_MOD(extack, "Requested split count is already set"); + ice_devlink_port_options_print(pf); + return -EINVAL; + } + + if (new_option == ICE_AQC_PORT_OPT_MAX) { + dev_dbg(dev, "request to split: count: %u not found\n", count); + NL_SET_ERR_MSG_MOD(extack, "Port split requested unsupported port config"); + ice_devlink_port_options_print(pf); + return -EINVAL; + } + + status = ice_devlink_aq_set_port_option(pf, new_option, extack); + if (status) + return status; + + ice_devlink_port_options_print(pf); + + return 0; +} + +/** + * ice_devlink_port_unsplit - .port_unsplit devlink handler + * @devlink: devlink instance structure + * @port: devlink port structure + * @extack: extended netdev ack structure + * + * Callback for the devlink .port_unsplit operation. + * Calls ice_devlink_port_split with split count set to 1. + * There could be no FW option available with split count 1. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_devlink_port_unsplit(struct devlink *devlink, struct devlink_port *port, + struct netlink_ext_ack *extack) +{ + return ice_devlink_port_split(devlink, port, 1, extack); } static const struct devlink_ops ice_devlink_ops = { .supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK, + .reload_actions = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), + /* The ice driver currently does not support driver reinit */ + .reload_down = ice_devlink_reload_empr_start, + .reload_up = ice_devlink_reload_empr_finish, + .port_split = ice_devlink_port_split, + .port_unsplit = ice_devlink_port_unsplit, .eswitch_mode_get = ice_eswitch_mode_get, .eswitch_mode_set = ice_eswitch_mode_set, .info_get = ice_devlink_info_get, .flash_update = ice_devlink_flash_update, }; +static int +ice_devlink_enable_roce_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct ice_pf *pf = devlink_priv(devlink); + + ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ? true : false; + + return 0; +} + +static int +ice_devlink_enable_roce_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct ice_pf *pf = devlink_priv(devlink); + bool roce_ena = ctx->val.vbool; + int ret; + + if (!roce_ena) { + ice_unplug_aux_dev(pf); + pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2; + return 0; + } + + pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2; + ret = ice_plug_aux_dev(pf); + if (ret) + pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2; + + return ret; +} + +static int +ice_devlink_enable_roce_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + + if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + return -EOPNOTSUPP; + + if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP) { + NL_SET_ERR_MSG_MOD(extack, "iWARP is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously"); + return -EOPNOTSUPP; + } + + return 0; +} + +static int +ice_devlink_enable_iw_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct ice_pf *pf = devlink_priv(devlink); + + ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP; + + return 0; +} + +static int +ice_devlink_enable_iw_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct ice_pf *pf = devlink_priv(devlink); + bool iw_ena = ctx->val.vbool; + int ret; + + if (!iw_ena) { + ice_unplug_aux_dev(pf); + pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP; + return 0; + } + + pf->rdma_mode |= IIDC_RDMA_PROTOCOL_IWARP; + ret = ice_plug_aux_dev(pf); + if (ret) + pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP; + + return ret; +} + +static int +ice_devlink_enable_iw_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + + if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + return -EOPNOTSUPP; + + if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2) { + NL_SET_ERR_MSG_MOD(extack, "RoCEv2 is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously"); + return -EOPNOTSUPP; + } + + return 0; +} + +static const struct devlink_param ice_devlink_params[] = { + DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_RUNTIME), + ice_devlink_enable_roce_get, + ice_devlink_enable_roce_set, + ice_devlink_enable_roce_validate), + DEVLINK_PARAM_GENERIC(ENABLE_IWARP, BIT(DEVLINK_PARAM_CMODE_RUNTIME), + ice_devlink_enable_iw_get, + ice_devlink_enable_iw_set, + ice_devlink_enable_iw_validate), + +}; + static void ice_devlink_free(void *devlink_ptr) { devlink_free((struct devlink *)devlink_ptr); @@ -470,6 +881,7 @@ void ice_devlink_register(struct ice_pf *pf) { struct devlink *devlink = priv_to_devlink(pf); + devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); } @@ -485,6 +897,86 @@ void ice_devlink_unregister(struct ice_pf *pf) } /** + * ice_devlink_set_switch_id - Set unique switch id based on pci dsn + * @pf: the PF to create a devlink port for + * @ppid: struct with switch id information + */ +static void +ice_devlink_set_switch_id(struct ice_pf *pf, struct netdev_phys_item_id *ppid) +{ + struct pci_dev *pdev = pf->pdev; + u64 id; + + id = pci_get_dsn(pdev); + + ppid->id_len = sizeof(id); + put_unaligned_be64(id, &ppid->id); +} + +int ice_devlink_register_params(struct ice_pf *pf) +{ + struct devlink *devlink = priv_to_devlink(pf); + union devlink_param_value value; + int err; + + err = devlink_params_register(devlink, ice_devlink_params, + ARRAY_SIZE(ice_devlink_params)); + if (err) + return err; + + value.vbool = false; + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_IWARP, + value); + + value.vbool = test_bit(ICE_FLAG_RDMA_ENA, pf->flags) ? true : false; + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + value); + + return 0; +} + +void ice_devlink_unregister_params(struct ice_pf *pf) +{ + devlink_params_unregister(priv_to_devlink(pf), ice_devlink_params, + ARRAY_SIZE(ice_devlink_params)); +} + +/** + * ice_devlink_set_port_split_options - Set port split options + * @pf: the PF to set port split options + * @attrs: devlink attributes + * + * Sets devlink port split options based on available FW port options + */ +static void +ice_devlink_set_port_split_options(struct ice_pf *pf, + struct devlink_port_attrs *attrs) +{ + struct ice_aqc_get_port_options_elem options[ICE_AQC_PORT_OPT_MAX]; + u8 i, active_idx, pending_idx, option_count = ICE_AQC_PORT_OPT_MAX; + bool active_valid, pending_valid; + int status; + + status = ice_aq_get_port_options(&pf->hw, options, &option_count, + 0, true, &active_idx, &active_valid, + &pending_idx, &pending_valid); + if (status) { + dev_dbg(ice_pf_to_dev(pf), "Couldn't read port split options, err = %d\n", + status); + return; + } + + /* find the biggest available port split count */ + for (i = 0; i < option_count; i++) + attrs->lanes = max_t(int, attrs->lanes, options[i].pmd); + + attrs->splittable = attrs->lanes ? 1 : 0; + ice_active_port_option = active_idx; +} + +/** * ice_devlink_create_pf_port - Create a devlink port for this PF * @pf: the PF to create a devlink port for * @@ -511,6 +1003,15 @@ int ice_devlink_create_pf_port(struct ice_pf *pf) attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; attrs.phys.port_number = pf->hw.bus.func; + + /* As FW supports only port split options for whole device, + * set port split options only for first PF. + */ + if (pf->hw.pf_id == 0) + ice_devlink_set_port_split_options(pf, &attrs); + + ice_devlink_set_switch_id(pf, &attrs.switch_id); + devlink_port_attrs_set(devlink_port, &attrs); devlink = priv_to_devlink(pf); @@ -560,13 +1061,18 @@ int ice_devlink_create_vf_port(struct ice_vf *vf) pf = vf->pf; dev = ice_pf_to_dev(pf); - vsi = ice_get_vf_vsi(vf); devlink_port = &vf->devlink_port; + vsi = ice_get_vf_vsi(vf); + if (!vsi) + return -EINVAL; + attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF; attrs.pci_vf.pf = pf->hw.bus.func; attrs.pci_vf.vf = vf->vf_id; + ice_devlink_set_switch_id(pf, &attrs.switch_id); + devlink_port_attrs_set(devlink_port, &attrs); devlink = priv_to_devlink(pf); @@ -596,17 +1102,23 @@ void ice_devlink_destroy_vf_port(struct ice_vf *vf) devlink_port_unregister(devlink_port); } +#define ICE_DEVLINK_READ_BLK_SIZE (1024 * 1024) + /** - * ice_devlink_nvm_snapshot - Capture a snapshot of the Shadow RAM contents + * ice_devlink_nvm_snapshot - Capture a snapshot of the NVM flash contents * @devlink: the devlink instance * @ops: the devlink region being snapshotted * @extack: extended ACK response structure * @data: on exit points to snapshot data buffer * * This function is called in response to the DEVLINK_CMD_REGION_TRIGGER for - * the shadow-ram devlink region. It captures a snapshot of the shadow ram - * contents. This snapshot can later be viewed via the devlink-region - * interface. + * the nvm-flash devlink region. It captures a snapshot of the full NVM flash + * contents, including both banks of flash. This snapshot can later be viewed + * via the devlink-region interface. + * + * It captures the flash using the FLASH_ONLY bit set when reading via + * firmware, so it does not read the current Shadow RAM contents. For that, + * use the shadow-ram region. * * @returns zero on success, and updates the data pointer. Returns a non-zero * error code on failure. @@ -618,37 +1130,116 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink, struct ice_pf *pf = devlink_priv(devlink); struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - enum ice_status status; - void *nvm_data; - u32 nvm_size; + u8 *nvm_data, *tmp, i; + u32 nvm_size, left; + s8 num_blks; + int status; nvm_size = hw->flash.flash_size; nvm_data = vzalloc(nvm_size); if (!nvm_data) return -ENOMEM; - status = ice_acquire_nvm(hw, ICE_RES_READ); - if (status) { + + num_blks = DIV_ROUND_UP(nvm_size, ICE_DEVLINK_READ_BLK_SIZE); + tmp = nvm_data; + left = nvm_size; + + /* Some systems take longer to read the NVM than others which causes the + * FW to reclaim the NVM lock before the entire NVM has been read. Fix + * this by breaking the reads of the NVM into smaller chunks that will + * probably not take as long. This has some overhead since we are + * increasing the number of AQ commands, but it should always work + */ + for (i = 0; i < num_blks; i++) { + u32 read_sz = min_t(u32, ICE_DEVLINK_READ_BLK_SIZE, left); + + status = ice_acquire_nvm(hw, ICE_RES_READ); + if (status) { + dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n", + status, hw->adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); + vfree(nvm_data); + return -EIO; + } + + status = ice_read_flat_nvm(hw, i * ICE_DEVLINK_READ_BLK_SIZE, + &read_sz, tmp, false); + if (status) { + dev_dbg(dev, "ice_read_flat_nvm failed after reading %u bytes, err %d aq_err %d\n", + read_sz, status, hw->adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents"); + ice_release_nvm(hw); + vfree(nvm_data); + return -EIO; + } + ice_release_nvm(hw); + + tmp += read_sz; + left -= read_sz; + } + + *data = nvm_data; + + return 0; +} + +/** + * ice_devlink_sram_snapshot - Capture a snapshot of the Shadow RAM contents + * @devlink: the devlink instance + * @ops: the devlink region being snapshotted + * @extack: extended ACK response structure + * @data: on exit points to snapshot data buffer + * + * This function is called in response to the DEVLINK_CMD_REGION_TRIGGER for + * the shadow-ram devlink region. It captures a snapshot of the shadow ram + * contents. This snapshot can later be viewed via the devlink-region + * interface. + * + * @returns zero on success, and updates the data pointer. Returns a non-zero + * error code on failure. + */ +static int +ice_devlink_sram_snapshot(struct devlink *devlink, + const struct devlink_region_ops __always_unused *ops, + struct netlink_ext_ack *extack, u8 **data) +{ + struct ice_pf *pf = devlink_priv(devlink); + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + u8 *sram_data; + u32 sram_size; + int err; + + sram_size = hw->flash.sr_words * 2u; + sram_data = vzalloc(sram_size); + if (!sram_data) + return -ENOMEM; + + err = ice_acquire_nvm(hw, ICE_RES_READ); + if (err) { dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n", - status, hw->adminq.sq_last_status); + err, hw->adminq.sq_last_status); NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); - vfree(nvm_data); - return -EIO; + vfree(sram_data); + return err; } - status = ice_read_flat_nvm(hw, 0, &nvm_size, nvm_data, false); - if (status) { + /* Read from the Shadow RAM, rather than directly from NVM */ + err = ice_read_flat_nvm(hw, 0, &sram_size, sram_data, true); + if (err) { dev_dbg(dev, "ice_read_flat_nvm failed after reading %u bytes, err %d aq_err %d\n", - nvm_size, status, hw->adminq.sq_last_status); - NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents"); + sram_size, err, hw->adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, + "Failed to read Shadow RAM contents"); ice_release_nvm(hw); - vfree(nvm_data); - return -EIO; + vfree(sram_data); + return err; } ice_release_nvm(hw); - *data = nvm_data; + *data = sram_data; return 0; } @@ -675,8 +1266,8 @@ ice_devlink_devcaps_snapshot(struct devlink *devlink, struct ice_pf *pf = devlink_priv(devlink); struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - enum ice_status status; void *devcaps; + int status; devcaps = vzalloc(ICE_AQ_MAX_BUF_LEN); if (!devcaps) @@ -689,7 +1280,7 @@ ice_devlink_devcaps_snapshot(struct devlink *devlink, status, hw->adminq.sq_last_status); NL_SET_ERR_MSG_MOD(extack, "Failed to read device capabilities"); vfree(devcaps); - return -EIO; + return status; } *data = (u8 *)devcaps; @@ -703,6 +1294,12 @@ static const struct devlink_region_ops ice_nvm_region_ops = { .snapshot = ice_devlink_nvm_snapshot, }; +static const struct devlink_region_ops ice_sram_region_ops = { + .name = "shadow-ram", + .destructor = vfree, + .snapshot = ice_devlink_sram_snapshot, +}; + static const struct devlink_region_ops ice_devcaps_region_ops = { .name = "device-caps", .destructor = vfree, @@ -720,7 +1317,7 @@ void ice_devlink_init_regions(struct ice_pf *pf) { struct devlink *devlink = priv_to_devlink(pf); struct device *dev = ice_pf_to_dev(pf); - u64 nvm_size; + u64 nvm_size, sram_size; nvm_size = pf->hw.flash.flash_size; pf->nvm_region = devlink_region_create(devlink, &ice_nvm_region_ops, 1, @@ -731,6 +1328,15 @@ void ice_devlink_init_regions(struct ice_pf *pf) pf->nvm_region = NULL; } + sram_size = pf->hw.flash.sr_words * 2u; + pf->sram_region = devlink_region_create(devlink, &ice_sram_region_ops, + 1, sram_size); + if (IS_ERR(pf->sram_region)) { + dev_err(dev, "failed to create shadow-ram devlink region, err %ld\n", + PTR_ERR(pf->sram_region)); + pf->sram_region = NULL; + } + pf->devcaps_region = devlink_region_create(devlink, &ice_devcaps_region_ops, 10, ICE_AQ_MAX_BUF_LEN); @@ -751,6 +1357,10 @@ void ice_devlink_destroy_regions(struct ice_pf *pf) { if (pf->nvm_region) devlink_region_destroy(pf->nvm_region); + + if (pf->sram_region) + devlink_region_destroy(pf->sram_region); + if (pf->devcaps_region) devlink_region_destroy(pf->devcaps_region); } |