diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ice')
84 files changed, 7655 insertions, 4199 deletions
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 0679907980f7..03500e28ac99 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -5,6 +5,7 @@ # Makefile for the Intel(R) Ethernet Connection E800 Series Linux Driver # +subdir-ccflags-y += -I$(src) obj-$(CONFIG_ICE) += ice.o ice-y := ice_main.o \ @@ -28,13 +29,17 @@ ice-y := ice_main.o \ ice_flex_pipe.o \ ice_flow.o \ ice_idc.o \ - ice_devlink.o \ + devlink/devlink.o \ + devlink/devlink_port.o \ ice_ddp.o \ ice_fw_update.o \ ice_lag.o \ ice_ethtool.o \ ice_repr.o \ - ice_tc_lib.o + ice_tc_lib.o \ + ice_fwlog.o \ + ice_debugfs.o \ + ice_adapter.o ice-$(CONFIG_PCI_IOV) += \ ice_sriov.o \ ice_virtchnl.o \ @@ -49,3 +54,4 @@ ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o ice_eswitch_br.o ice-$(CONFIG_GNSS) += ice_gnss.o +ice-$(CONFIG_ICE_HWMON) += ice_hwmon.o diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index 80dc5445b50d..c4b69655cdf5 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -5,13 +5,11 @@ #include "ice.h" #include "ice_lib.h" -#include "ice_devlink.h" +#include "devlink.h" #include "ice_eswitch.h" #include "ice_fw_update.h" #include "ice_dcb_lib.h" -static int ice_active_port_option = -1; - /* context for devlink info version reporting */ struct ice_info_ctx { char buf[128]; @@ -193,6 +191,24 @@ ice_info_pending_netlist_build(struct ice_pf __always_unused *pf, snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", netlist->hash); } +static void ice_info_cgu_fw_build(struct ice_pf *pf, struct ice_info_ctx *ctx) +{ + u32 id, cfg_ver, fw_ver; + + if (!ice_is_feature_supported(pf, ICE_F_CGU)) + return; + if (ice_aq_get_cgu_info(&pf->hw, &id, &cfg_ver, &fw_ver)) + return; + snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u", id, cfg_ver, fw_ver); +} + +static void ice_info_cgu_id(struct ice_pf *pf, struct ice_info_ctx *ctx) +{ + if (!ice_is_feature_supported(pf, ICE_F_CGU)) + return; + snprintf(ctx->buf, sizeof(ctx->buf), "%u", pf->hw.cgu_part_number); +} + #define fixed(key, getter) { ICE_VERSION_FIXED, key, getter, NULL } #define running(key, getter) { ICE_VERSION_RUNNING, key, getter, NULL } #define stored(key, getter, fallback) { ICE_VERSION_STORED, key, getter, fallback } @@ -235,6 +251,8 @@ static const struct ice_devlink_version { running("fw.app.bundle_id", ice_info_ddp_pkg_bundle_id), combined("fw.netlist", ice_info_netlist_ver, ice_info_pending_netlist_ver), combined("fw.netlist.build", ice_info_netlist_build, ice_info_pending_netlist_build), + fixed("cgu.id", ice_info_cgu_id), + running("fw.cgu", ice_info_cgu_fw_build), }; /** @@ -425,6 +443,20 @@ ice_devlink_reload_empr_start(struct ice_pf *pf, } /** + * ice_devlink_reinit_down - unload given PF + * @pf: pointer to the PF struct + */ +static void ice_devlink_reinit_down(struct ice_pf *pf) +{ + /* No need to take devl_lock, it's already taken by devlink API */ + ice_unload(pf); + rtnl_lock(); + ice_vsi_decfg(ice_get_main_vsi(pf)); + rtnl_unlock(); + ice_deinit_dev(pf); +} + +/** * ice_devlink_reload_down - prepare for reload * @devlink: pointer to the devlink instance to reload * @netns_change: if true, the network namespace is changing @@ -444,20 +476,20 @@ ice_devlink_reload_down(struct devlink *devlink, bool netns_change, case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: if (ice_is_eswitch_mode_switchdev(pf)) { NL_SET_ERR_MSG_MOD(extack, - "Go to legacy mode before doing reinit\n"); + "Go to legacy mode before doing reinit"); return -EOPNOTSUPP; } if (ice_is_adq_active(pf)) { NL_SET_ERR_MSG_MOD(extack, - "Turn off ADQ before doing reinit\n"); + "Turn off ADQ before doing reinit"); return -EOPNOTSUPP; } if (ice_has_vfs(pf)) { NL_SET_ERR_MSG_MOD(extack, - "Remove all VFs before doing reinit\n"); + "Remove all VFs before doing reinit"); return -EOPNOTSUPP; } - ice_unload(pf); + ice_devlink_reinit_down(pf); return 0; case DEVLINK_RELOAD_ACTION_FW_ACTIVATE: return ice_devlink_reload_empr_start(pf, extack); @@ -492,248 +524,153 @@ ice_devlink_reload_empr_finish(struct ice_pf *pf, } /** - * 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 + * ice_get_tx_topo_user_sel - Read user's choice from flash + * @pf: pointer to pf structure + * @layers: value read from flash will be saved here * - * Prints a table with available port split options and max port speeds + * Reads user's preference for Tx Scheduler Topology Tree from PFA TLV. + * + * Return: zero when read was successful, negative values otherwise. */ -static void ice_devlink_port_options_print(struct ice_pf *pf) +static int ice_get_tx_topo_user_sel(struct ice_pf *pf, uint8_t *layers) { - 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; + struct ice_aqc_nvm_tx_topo_user_sel usr_sel = {}; + struct ice_hw *hw = &pf->hw; + int err; - options = kcalloc(ICE_AQC_PORT_OPT_MAX * ICE_MAX_PORT_PER_PCI_DEV, - sizeof(*options), GFP_KERNEL); - if (!options) - return; + err = ice_acquire_nvm(hw, ICE_RES_READ); + if (err) + return err; - 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; + err = ice_aq_read_nvm(hw, ICE_AQC_NVM_TX_TOPO_MOD_ID, 0, + sizeof(usr_sel), &usr_sel, true, true, NULL); + if (err) + goto exit_release_res; - 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; - } - } + if (usr_sel.data & ICE_AQC_NVM_TX_TOPO_USER_SEL) + *layers = ICE_SCHED_5_LAYERS; + else + *layers = ICE_SCHED_9_LAYERS; - 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"); +exit_release_res: + ice_release_nvm(hw); - for (i = 0; i < options_count; i++) { - cnt = 0; + return err; +} - if (i == ice_active_port_option) - str = "Active"; - else if ((i == pending_idx) && pending_valid) - str = "Pending"; - else - str = ""; +/** + * ice_update_tx_topo_user_sel - Save user's preference in flash + * @pf: pointer to pf structure + * @layers: value to be saved in flash + * + * Variable "layers" defines user's preference about number of layers in Tx + * Scheduler Topology Tree. This choice should be stored in PFA TLV field + * and be picked up by driver, next time during init. + * + * Return: zero when save was successful, negative values otherwise. + */ +static int ice_update_tx_topo_user_sel(struct ice_pf *pf, int layers) +{ + struct ice_aqc_nvm_tx_topo_user_sel usr_sel = {}; + struct ice_hw *hw = &pf->hw; + int err; - cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, - "%-8s", str); + err = ice_acquire_nvm(hw, ICE_RES_WRITE); + if (err) + return err; - cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, - "%-6u", options[i].pmd); + err = ice_aq_read_nvm(hw, ICE_AQC_NVM_TX_TOPO_MOD_ID, 0, + sizeof(usr_sel), &usr_sel, true, true, NULL); + if (err) + goto exit_release_res; - 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); - } + if (layers == ICE_SCHED_5_LAYERS) + usr_sel.data |= ICE_AQC_NVM_TX_TOPO_USER_SEL; + else + usr_sel.data &= ~ICE_AQC_NVM_TX_TOPO_USER_SEL; - dev_dbg(dev, "%s\n", desc); - } + err = ice_write_one_nvm_block(pf, ICE_AQC_NVM_TX_TOPO_MOD_ID, 2, + sizeof(usr_sel.data), &usr_sel.data, + true, NULL, NULL); +exit_release_res: + ice_release_nvm(hw); -err: - kfree(options); + return err; } /** - * 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 + * ice_devlink_tx_sched_layers_get - Get tx_scheduling_layers parameter + * @devlink: pointer to the devlink instance + * @id: the parameter ID to set + * @ctx: context to store the parameter value * - * Sends set port option admin queue command with selected port option and - * calls NVM write activate. + * Return: zero on success and negative value on failure. */ -static int -ice_devlink_aq_set_port_option(struct ice_pf *pf, u8 option_idx, - struct netlink_ext_ack *extack) +static int ice_devlink_tx_sched_layers_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) { - 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; - } - - 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; - } - - 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; - } + struct ice_pf *pf = devlink_priv(devlink); + int err; - ice_release_nvm(&pf->hw); + err = ice_get_tx_topo_user_sel(pf, &ctx->val.vu8); + if (err) + return err; - 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. + * ice_devlink_tx_sched_layers_set - Set tx_scheduling_layers parameter + * @devlink: pointer to the devlink instance + * @id: the parameter ID to set + * @ctx: context to get the parameter value + * @extack: netlink extended ACK structure * - * Return: zero on success or an error code on failure. + * Return: zero on success and negative value on failure. */ -static int -ice_devlink_port_split(struct devlink *devlink, struct devlink_port *port, - unsigned int count, struct netlink_ext_ack *extack) +static int ice_devlink_tx_sched_layers_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + 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; - } + int err; - status = ice_devlink_aq_set_port_option(pf, new_option, extack); - if (status) - return status; + err = ice_update_tx_topo_user_sel(pf, ctx->val.vu8); + if (err) + return err; - ice_devlink_port_options_print(pf); + NL_SET_ERR_MSG_MOD(extack, + "Tx scheduling layers have been changed on this device. You must do the PCI slot powercycle for the change to take effect."); return 0; } /** - * ice_devlink_port_unsplit - .port_unsplit devlink handler - * @devlink: devlink instance structure - * @port: devlink port structure - * @extack: extended netdev ack structure + * ice_devlink_tx_sched_layers_validate - Validate passed tx_scheduling_layers + * parameter value + * @devlink: unused pointer to devlink instance + * @id: the parameter ID to validate + * @val: value to validate + * @extack: netlink extended 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. + * Supported values are: + * - 5 - five layers Tx Scheduler Topology Tree + * - 9 - nine layers Tx Scheduler Topology Tree * - * Return: zero on success or an error code on failure. + * Return: zero when passed parameter value is supported. Negative value on + * error. */ -static int -ice_devlink_port_unsplit(struct devlink *devlink, struct devlink_port *port, - struct netlink_ext_ack *extack) +static int ice_devlink_tx_sched_layers_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) { - return ice_devlink_port_split(devlink, port, 1, extack); + if (val.vu8 != ICE_SCHED_5_LAYERS && val.vu8 != ICE_SCHED_9_LAYERS) { + NL_SET_ERR_MSG_MOD(extack, + "Wrong number of tx scheduler layers provided."); + return -EINVAL; + } + + return 0; } /** @@ -810,6 +747,10 @@ static void ice_traverse_tx_tree(struct devlink *devlink, struct ice_sched_node struct ice_vf *vf; int i; + if (node->rate_node) + /* already added, skip to the next */ + goto traverse_children; + if (node->parent == tc_node) { /* create root node */ rate_node = devl_rate_node_create(devlink, node, node->name, NULL); @@ -831,6 +772,7 @@ static void ice_traverse_tx_tree(struct devlink *devlink, struct ice_sched_node if (rate_node && !IS_ERR(rate_node)) node->rate_node = rate_node; +traverse_children: for (i = 0; i < node->num_children; i++) ice_traverse_tx_tree(devlink, node->children[i], tc_node, pf); } @@ -861,6 +803,30 @@ int ice_devlink_rate_init_tx_topology(struct devlink *devlink, struct ice_vsi *v return 0; } +static void ice_clear_rate_nodes(struct ice_sched_node *node) +{ + node->rate_node = NULL; + + for (int i = 0; i < node->num_children; i++) + ice_clear_rate_nodes(node->children[i]); +} + +/** + * ice_devlink_rate_clear_tx_topology - clear node->rate_node + * @vsi: main vsi struct + * + * Clear rate_node to cleanup creation of Tx topology. + * + */ +void ice_devlink_rate_clear_tx_topology(struct ice_vsi *vsi) +{ + struct ice_port_info *pi = vsi->port_info; + + mutex_lock(&pi->sched_lock); + ice_clear_rate_nodes(pi->root->children[0]); + mutex_unlock(&pi->sched_lock); +} + /** * ice_set_object_tx_share - sets node scheduling parameter * @pi: devlink struct instance @@ -1221,6 +1187,43 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate, } /** + * ice_devlink_reinit_up - do reinit of the given PF + * @pf: pointer to the PF struct + */ +static int ice_devlink_reinit_up(struct ice_pf *pf) +{ + struct ice_vsi *vsi = ice_get_main_vsi(pf); + int err; + + err = ice_init_dev(pf); + if (err) + return err; + + vsi->flags = ICE_VSI_FLAG_INIT; + + rtnl_lock(); + err = ice_vsi_cfg(vsi); + rtnl_unlock(); + if (err) + goto err_vsi_cfg; + + /* No need to take devl_lock, it's already taken by devlink API */ + err = ice_load(pf); + if (err) + goto err_load; + + return 0; + +err_load: + rtnl_lock(); + ice_vsi_decfg(vsi); + rtnl_unlock(); +err_vsi_cfg: + ice_deinit_dev(pf); + return err; +} + +/** * ice_devlink_reload_up - do reload up after reinit * @devlink: pointer to the devlink instance reloading * @action: the action requested @@ -1240,7 +1243,7 @@ ice_devlink_reload_up(struct devlink *devlink, switch (action) { case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: *actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT); - return ice_load(pf); + return ice_devlink_reinit_up(pf); case DEVLINK_RELOAD_ACTION_FW_ACTIVATE: *actions_performed = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE); return ice_devlink_reload_empr_finish(pf, extack); @@ -1289,9 +1292,9 @@ ice_devlink_enable_roce_get(struct devlink *devlink, u32 id, return 0; } -static int -ice_devlink_enable_roce_set(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) +static int ice_devlink_enable_roce_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); bool roce_ena = ctx->val.vbool; @@ -1340,9 +1343,9 @@ ice_devlink_enable_iw_get(struct devlink *devlink, u32 id, return 0; } -static int -ice_devlink_enable_iw_set(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) +static int ice_devlink_enable_iw_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); bool iw_ena = ctx->val.vbool; @@ -1380,6 +1383,11 @@ ice_devlink_enable_iw_validate(struct devlink *devlink, u32 id, return 0; } +enum ice_param_id { + ICE_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS, +}; + static const struct devlink_param ice_devlink_params[] = { DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_RUNTIME), ice_devlink_enable_roce_get, @@ -1389,7 +1397,13 @@ static const struct devlink_param ice_devlink_params[] = { ice_devlink_enable_iw_get, ice_devlink_enable_iw_set, ice_devlink_enable_iw_validate), - + DEVLINK_PARAM_DRIVER(ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS, + "tx_scheduling_layers", + DEVLINK_PARAM_TYPE_U8, + BIT(DEVLINK_PARAM_CMODE_PERMANENT), + ice_devlink_tx_sched_layers_get, + ice_devlink_tx_sched_layers_set, + ice_devlink_tx_sched_layers_validate), }; static void ice_devlink_free(void *devlink_ptr) @@ -1432,7 +1446,7 @@ void ice_devlink_register(struct ice_pf *pf) { struct devlink *devlink = priv_to_devlink(pf); - devlink_register(devlink); + devl_register(devlink); } /** @@ -1443,194 +1457,28 @@ void ice_devlink_register(struct ice_pf *pf) */ void ice_devlink_unregister(struct ice_pf *pf) { - devlink_unregister(priv_to_devlink(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); + devl_unregister(priv_to_devlink(pf)); } int ice_devlink_register_params(struct ice_pf *pf) { struct devlink *devlink = priv_to_devlink(pf); + struct ice_hw *hw = &pf->hw; + size_t params_size; - return devlink_params_register(devlink, ice_devlink_params, - ARRAY_SIZE(ice_devlink_params)); -} - -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; -} - -static const struct devlink_port_ops ice_devlink_port_ops = { - .port_split = ice_devlink_port_split, - .port_unsplit = ice_devlink_port_unsplit, -}; - -/** - * ice_devlink_create_pf_port - Create a devlink port for this PF - * @pf: the PF to create a devlink port for - * - * Create and register a devlink_port for this PF. - * - * Return: zero on success or an error code on failure. - */ -int ice_devlink_create_pf_port(struct ice_pf *pf) -{ - struct devlink_port_attrs attrs = {}; - struct devlink_port *devlink_port; - struct devlink *devlink; - struct ice_vsi *vsi; - struct device *dev; - int err; - - dev = ice_pf_to_dev(pf); - - devlink_port = &pf->devlink_port; - - vsi = ice_get_main_vsi(pf); - if (!vsi) - return -EIO; - - 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); - - err = devlink_port_register_with_ops(devlink, devlink_port, vsi->idx, - &ice_devlink_port_ops); - if (err) { - dev_err(dev, "Failed to create devlink port for PF %d, error %d\n", - pf->hw.pf_id, err); - return err; - } - - return 0; -} - -/** - * ice_devlink_destroy_pf_port - Destroy the devlink_port for this PF - * @pf: the PF to cleanup - * - * Unregisters the devlink_port structure associated with this PF. - */ -void ice_devlink_destroy_pf_port(struct ice_pf *pf) -{ - devlink_port_unregister(&pf->devlink_port); -} - -/** - * ice_devlink_create_vf_port - Create a devlink port for this VF - * @vf: the VF to create a port for - * - * Create and register a devlink_port for this VF. - * - * Return: zero on success or an error code on failure. - */ -int ice_devlink_create_vf_port(struct ice_vf *vf) -{ - struct devlink_port_attrs attrs = {}; - struct devlink_port *devlink_port; - struct devlink *devlink; - struct ice_vsi *vsi; - struct device *dev; - struct ice_pf *pf; - int err; - - pf = vf->pf; - dev = ice_pf_to_dev(pf); - 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); + params_size = ARRAY_SIZE(ice_devlink_params); - devlink_port_attrs_set(devlink_port, &attrs); - devlink = priv_to_devlink(pf); + if (!hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) + params_size--; - err = devlink_port_register(devlink, devlink_port, vsi->idx); - if (err) { - dev_err(dev, "Failed to create devlink port for VF %d, error %d\n", - vf->vf_id, err); - return err; - } - - return 0; + return devl_params_register(devlink, ice_devlink_params, + params_size); } -/** - * ice_devlink_destroy_vf_port - Destroy the devlink_port for this VF - * @vf: the VF to cleanup - * - * Unregisters the devlink_port structure associated with this VF. - */ -void ice_devlink_destroy_vf_port(struct ice_vf *vf) +void ice_devlink_unregister_params(struct ice_pf *pf) { - devl_rate_leaf_destroy(&vf->devlink_port); - devlink_port_unregister(&vf->devlink_port); + devl_params_unregister(priv_to_devlink(pf), ice_devlink_params, + ARRAY_SIZE(ice_devlink_params)); } #define ICE_DEVLINK_READ_BLK_SIZE (1024 * 1024) @@ -1871,8 +1719,8 @@ void ice_devlink_init_regions(struct ice_pf *pf) u64 nvm_size, sram_size; nvm_size = pf->hw.flash.flash_size; - pf->nvm_region = devlink_region_create(devlink, &ice_nvm_region_ops, 1, - nvm_size); + pf->nvm_region = devl_region_create(devlink, &ice_nvm_region_ops, 1, + nvm_size); if (IS_ERR(pf->nvm_region)) { dev_err(dev, "failed to create NVM devlink region, err %ld\n", PTR_ERR(pf->nvm_region)); @@ -1880,17 +1728,17 @@ void ice_devlink_init_regions(struct ice_pf *pf) } sram_size = pf->hw.flash.sr_words * 2u; - pf->sram_region = devlink_region_create(devlink, &ice_sram_region_ops, - 1, sram_size); + pf->sram_region = devl_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); + pf->devcaps_region = devl_region_create(devlink, + &ice_devcaps_region_ops, 10, + ICE_AQ_MAX_BUF_LEN); if (IS_ERR(pf->devcaps_region)) { dev_err(dev, "failed to create device-caps devlink region, err %ld\n", PTR_ERR(pf->devcaps_region)); @@ -1907,11 +1755,11 @@ void ice_devlink_init_regions(struct ice_pf *pf) void ice_devlink_destroy_regions(struct ice_pf *pf) { if (pf->nvm_region) - devlink_region_destroy(pf->nvm_region); + devl_region_destroy(pf->nvm_region); if (pf->sram_region) - devlink_region_destroy(pf->sram_region); + devl_region_destroy(pf->sram_region); if (pf->devcaps_region) - devlink_region_destroy(pf->devcaps_region); + devl_region_destroy(pf->devcaps_region); } diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.h b/drivers/net/ethernet/intel/ice/devlink/devlink.h index 6ec96779f52e..d291c0e2e17b 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.h +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.h @@ -20,5 +20,6 @@ void ice_devlink_destroy_regions(struct ice_pf *pf); int ice_devlink_rate_init_tx_topology(struct devlink *devlink, struct ice_vsi *vsi); void ice_tear_down_devlink_rate_tree(struct ice_pf *pf); +void ice_devlink_rate_clear_tx_topology(struct ice_vsi *vsi); #endif /* _ICE_DEVLINK_H_ */ diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c new file mode 100644 index 000000000000..13e6790d3cae --- /dev/null +++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c @@ -0,0 +1,430 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024, Intel Corporation. */ + +#include <linux/vmalloc.h> + +#include "ice.h" +#include "devlink.h" + +static int ice_active_port_option = -1; + +/** + * 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; + } + + 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; + } + + 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); +} + +/** + * 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; +} + +static const struct devlink_port_ops ice_devlink_port_ops = { + .port_split = ice_devlink_port_split, + .port_unsplit = ice_devlink_port_unsplit, +}; + +/** + * 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); +} + +/** + * ice_devlink_create_pf_port - Create a devlink port for this PF + * @pf: the PF to create a devlink port for + * + * Create and register a devlink_port for this PF. + * This function has to be called under devl_lock. + * + * Return: zero on success or an error code on failure. + */ +int ice_devlink_create_pf_port(struct ice_pf *pf) +{ + struct devlink_port_attrs attrs = {}; + struct devlink_port *devlink_port; + struct devlink *devlink; + struct ice_vsi *vsi; + struct device *dev; + int err; + + devlink = priv_to_devlink(pf); + + dev = ice_pf_to_dev(pf); + + devlink_port = &pf->devlink_port; + + vsi = ice_get_main_vsi(pf); + if (!vsi) + return -EIO; + + 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); + + err = devl_port_register_with_ops(devlink, devlink_port, vsi->idx, + &ice_devlink_port_ops); + if (err) { + dev_err(dev, "Failed to create devlink port for PF %d, error %d\n", + pf->hw.pf_id, err); + return err; + } + + return 0; +} + +/** + * ice_devlink_destroy_pf_port - Destroy the devlink_port for this PF + * @pf: the PF to cleanup + * + * Unregisters the devlink_port structure associated with this PF. + * This function has to be called under devl_lock. + */ +void ice_devlink_destroy_pf_port(struct ice_pf *pf) +{ + devl_port_unregister(&pf->devlink_port); +} + +/** + * ice_devlink_create_vf_port - Create a devlink port for this VF + * @vf: the VF to create a port for + * + * Create and register a devlink_port for this VF. + * + * Return: zero on success or an error code on failure. + */ +int ice_devlink_create_vf_port(struct ice_vf *vf) +{ + struct devlink_port_attrs attrs = {}; + struct devlink_port *devlink_port; + struct devlink *devlink; + struct ice_vsi *vsi; + struct device *dev; + struct ice_pf *pf; + int err; + + pf = vf->pf; + dev = ice_pf_to_dev(pf); + 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); + + err = devlink_port_register(devlink, devlink_port, vsi->idx); + if (err) { + dev_err(dev, "Failed to create devlink port for VF %d, error %d\n", + vf->vf_id, err); + return err; + } + + return 0; +} + +/** + * ice_devlink_destroy_vf_port - Destroy the devlink_port for this VF + * @vf: the VF to cleanup + * + * Unregisters the devlink_port structure associated with this VF. + */ +void ice_devlink_destroy_vf_port(struct ice_vf *vf) +{ + devl_rate_leaf_destroy(&vf->devlink_port); + devlink_port_unregister(&vf->devlink_port); +} diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h b/drivers/net/ethernet/intel/ice/devlink/devlink_port.h new file mode 100644 index 000000000000..9223bcdb6444 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024, Intel Corporation. */ + +#ifndef _DEVLINK_PORT_H_ +#define _DEVLINK_PORT_H_ + +int ice_devlink_create_pf_port(struct ice_pf *pf); +void ice_devlink_destroy_pf_port(struct ice_pf *pf); +int ice_devlink_create_vf_port(struct ice_vf *vf); +void ice_devlink_destroy_vf_port(struct ice_vf *vf); + +#endif /* _DEVLINK_PORT_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 351e0d36df44..6ad8002b22e1 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -77,6 +77,7 @@ #include "ice_gnss.h" #include "ice_irq.h" #include "ice_dpll.h" +#include "ice_adapter.h" #define ICE_BAR0 0 #define ICE_REQ_DESC_MULTIPLE 32 @@ -330,7 +331,6 @@ struct ice_vsi { struct net_device *netdev; struct ice_sw *vsw; /* switch this VSI is on */ struct ice_pf *back; /* back pointer to PF */ - struct ice_port_info *port_info; /* back pointer to port_info */ struct ice_rx_ring **rx_rings; /* Rx ring array */ struct ice_tx_ring **tx_rings; /* Tx ring array */ struct ice_q_vector **q_vectors; /* q_vector array */ @@ -348,18 +348,16 @@ struct ice_vsi { /* tell if only dynamic irq allocation is allowed */ bool irq_dyn_alloc; - enum ice_vsi_type type; u16 vsi_num; /* HW (absolute) index of this VSI */ u16 idx; /* software index in pf->vsi[] */ - struct ice_vf *vf; /* VF associated with this VSI */ - u16 num_gfltr; u16 num_bfltr; /* RSS config */ u16 rss_table_size; /* HW RSS table size */ u16 rss_size; /* Allocated RSS queues */ + u8 rss_hfunc; /* User configured hash type */ u8 *rss_hkey_user; /* User configured hash keys */ u8 *rss_lut_user; /* User configured lookup table entries */ u8 rss_lut_type; /* used to configure Get/Set RSS LUT AQ call */ @@ -444,12 +442,18 @@ struct ice_vsi { u8 old_numtc; u16 old_ena_tc; - struct ice_channel *ch; - /* setup back reference, to which aggregator node this VSI * corresponds to */ struct ice_agg_node *agg_node; + + struct_group_tagged(ice_vsi_cfg_params, params, + struct ice_port_info *port_info; /* back pointer to port_info */ + struct ice_channel *ch; /* VSI's channel structure, may be NULL */ + struct ice_vf *vf; /* VF associated with this VSI, may be NULL */ + u32 flags; /* VSI flags used for rebuild and configuration */ + enum ice_vsi_type type; /* the type of the VSI */ + ); } ____cacheline_internodealigned_in_smp; /* struct that defines an interrupt vector */ @@ -457,7 +461,7 @@ struct ice_q_vector { struct ice_vsi *vsi; u16 v_idx; /* index in the vsi->q_vector array. */ - u16 reg_idx; + u16 reg_idx; /* PF relative register index */ u8 num_ring_rx; /* total number of Rx rings in vector */ u8 num_ring_tx; /* total number of Tx rings in vector */ u8 wb_on_itr:1; /* if true, WB on ITR is enabled */ @@ -479,6 +483,7 @@ struct ice_q_vector { char name[ICE_INT_NAME_STR_LEN]; u16 total_events; /* net_dim(): number of interrupts processed */ + u16 vf_reg_idx; /* VF relative register index */ struct msi_map irq; } ____cacheline_internodealigned_in_smp; @@ -492,7 +497,6 @@ enum ice_pf_flags { ICE_FLAG_DCB_ENA, ICE_FLAG_FD_ENA, ICE_FLAG_PTP_SUPPORTED, /* PTP is supported by NVM */ - ICE_FLAG_PTP, /* PTP is enabled by software */ ICE_FLAG_ADV_FEATURES, ICE_FLAG_TC_MQPRIO, /* support for Multi queue TC */ ICE_FLAG_CLS_FLOWER, @@ -517,15 +521,14 @@ enum ice_pf_flags { }; enum ice_misc_thread_tasks { - ICE_MISC_THREAD_EXTTS_EVENT, ICE_MISC_THREAD_TX_TSTAMP, ICE_MISC_THREAD_NBITS /* must be last */ }; -struct ice_switchdev_info { - struct ice_vsi *control_vsi; +struct ice_eswitch { struct ice_vsi *uplink_vsi; struct ice_esw_br_offloads *br_offloads; + struct xarray reprs; bool is_running; }; @@ -538,6 +541,7 @@ struct ice_agg_node { struct ice_pf { struct pci_dev *pdev; + struct ice_adapter *adapter; struct devlink_region *nvm_region; struct devlink_region *sram_region; @@ -563,6 +567,10 @@ struct ice_pf { struct ice_vsi_stats **vsi_stats; struct ice_sw *first_sw; /* first switch created by firmware */ u16 eswitch_mode; /* current mode of eswitch */ + struct dentry *ice_debugfs_pf; + struct dentry *ice_debugfs_pf_fwlog; + /* keep track of all the dentrys for FW log modules */ + struct dentry **ice_debugfs_pf_fwlog_modules; struct ice_vfs vfs; DECLARE_BITMAP(features, ICE_F_MAX); DECLARE_BITMAP(state, ICE_STATE_NBITS); @@ -595,8 +603,10 @@ struct ice_pf { wait_queue_head_t reset_wait_queue; u32 hw_csum_rx_error; + u32 hw_rx_eipe_error; u32 oicr_err_reg; struct msi_map oicr_irq; /* Other interrupt cause MSIX vector */ + 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 */ @@ -621,6 +631,7 @@ struct ice_pf { 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; @@ -637,7 +648,7 @@ struct ice_pf { struct ice_link_default_override_tlv link_dflt_override; struct ice_lag *lag; /* Link Aggregation information */ - struct ice_switchdev_info switchdev; + struct ice_eswitch eswitch; struct ice_esw_br_port *br_port; #define ICE_INVALID_AGG_NODE_ID 0 @@ -648,6 +659,7 @@ struct ice_pf { #define ICE_MAX_VF_AGG_NODES 32 struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES]; struct ice_dplls dplls; + struct device *hwmon_dev; }; extern struct workqueue_struct *ice_lag_wq; @@ -846,7 +858,7 @@ static inline struct ice_vsi *ice_find_vsi(struct ice_pf *pf, u16 vsi_num) */ static inline bool ice_is_switchdev_running(struct ice_pf *pf) { - return pf->switchdev.is_running; + return pf->eswitch.is_running; } #define ICE_FD_STAT_CTR_BLOCK_COUNT 256 @@ -881,6 +893,12 @@ static inline bool ice_is_adq_active(struct ice_pf *pf) return false; } +void ice_debugfs_fwlog_init(struct ice_pf *pf); +void ice_debugfs_pf_deinit(struct ice_pf *pf); +void ice_debugfs_init(void); +void ice_debugfs_exit(void); +void ice_pf_fwlog_update_module(struct ice_pf *pf, int log_level, int module); + bool netif_is_ice(const struct net_device *dev); int ice_vsi_setup_tx_rings(struct ice_vsi *vsi); int ice_vsi_setup_rx_rings(struct ice_vsi *vsi); @@ -912,6 +930,7 @@ int ice_set_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size); int ice_get_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size); int ice_set_rss_key(struct ice_vsi *vsi, u8 *seed); int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed); +int ice_set_rss_hfunc(struct ice_vsi *vsi, u8 hfunc); void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size); int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset); void ice_print_link_msg(struct ice_vsi *vsi, bool isup); @@ -963,6 +982,8 @@ void ice_service_task_schedule(struct ice_pf *pf); int ice_load(struct ice_pf *pf); void ice_unload(struct ice_pf *pf); void ice_adv_lnk_speed_maps_init(void); +int ice_init_dev(struct ice_pf *pf); +void ice_deinit_dev(struct ice_pf *pf); /** * ice_set_rdma_cap - enable RDMA support @@ -989,4 +1010,6 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf) set_bit(ICE_FLAG_UNPLUG_AUX_DEV, pf->flags); clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); } + +extern const struct xdp_metadata_ops ice_xdp_md_ops; #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c new file mode 100644 index 000000000000..52d15ef7f4b1 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_adapter.c @@ -0,0 +1,116 @@ +// 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> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/xarray.h> +#include "ice_adapter.h" + +static DEFINE_XARRAY(ice_adapters); + +/* 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_BUS GENMASK(12, 5) +#define INDEX_FIELD_SLOT GENMASK(4, 0) + +static unsigned long ice_adapter_index(const struct pci_dev *pdev) +{ + unsigned int domain = pci_domain_nr(pdev->bus); + + WARN_ON(domain > FIELD_MAX(INDEX_FIELD_DOMAIN)); + + return FIELD_PREP(INDEX_FIELD_DOMAIN, domain) | + FIELD_PREP(INDEX_FIELD_BUS, pdev->bus->number) | + FIELD_PREP(INDEX_FIELD_SLOT, PCI_SLOT(pdev->devfn)); +} + +static struct ice_adapter *ice_adapter_new(void) +{ + struct ice_adapter *adapter; + + adapter = kzalloc(sizeof(*adapter), GFP_KERNEL); + if (!adapter) + return NULL; + + spin_lock_init(&adapter->ptp_gltsyn_time_lock); + refcount_set(&adapter->refcount, 1); + + return adapter; +} + +static void ice_adapter_free(struct ice_adapter *adapter) +{ + kfree(adapter); +} + +DEFINE_FREE(ice_adapter_free, struct ice_adapter*, if (_T) ice_adapter_free(_T)) + +/** + * ice_adapter_get - Get a shared ice_adapter structure. + * @pdev: Pointer to the pci_dev whose driver is getting the ice_adapter. + * + * Gets a pointer to a shared ice_adapter structure. Physical functions (PFs) + * of the same multi-function PCI device share one ice_adapter structure. + * The ice_adapter is reference-counted. The PF driver must use ice_adapter_put + * to release its reference. + * + * Context: Process, may sleep. + * 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 *ret, __free(ice_adapter_free) *adapter = NULL; + unsigned long index = ice_adapter_index(pdev); + + adapter = ice_adapter_new(); + if (!adapter) + return ERR_PTR(-ENOMEM); + + xa_lock(&ice_adapters); + ret = __xa_cmpxchg(&ice_adapters, index, NULL, adapter, GFP_KERNEL); + if (xa_is_err(ret)) { + ret = ERR_PTR(xa_err(ret)); + goto unlock; + } + if (ret) { + refcount_inc(&ret->refcount); + goto unlock; + } + ret = no_free_ptr(adapter); +unlock: + xa_unlock(&ice_adapters); + return ret; +} + +/** + * ice_adapter_put - Release a reference to the shared ice_adapter structure. + * @pdev: Pointer to the pci_dev whose driver is releasing the ice_adapter. + * + * Releases the reference to ice_adapter previously obtained with + * ice_adapter_get. + * + * Context: Any. + */ +void ice_adapter_put(const struct pci_dev *pdev) +{ + unsigned long index = ice_adapter_index(pdev); + struct ice_adapter *adapter; + + xa_lock(&ice_adapters); + adapter = xa_load(&ice_adapters, index); + if (WARN_ON(!adapter)) + goto unlock; + + if (!refcount_dec_and_test(&adapter->refcount)) + goto unlock; + + WARN_ON(__xa_erase(&ice_adapters, index) != adapter); + ice_adapter_free(adapter); +unlock: + xa_unlock(&ice_adapters); +} diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h new file mode 100644 index 000000000000..9d11014ec02f --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_adapter.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-FileCopyrightText: Copyright Red Hat */ + +#ifndef _ICE_ADAPTER_H_ +#define _ICE_ADAPTER_H_ + +#include <linux/spinlock_types.h> +#include <linux/refcount_types.h> + +struct pci_dev; + +/** + * struct ice_adapter - PCI adapter resources shared across PFs + * @ptp_gltsyn_time_lock: Spinlock protecting access to the GLTSYN_TIME + * register of the PTP clock. + * @refcount: Reference count. struct ice_pf objects hold the references. + */ +struct ice_adapter { + /* For access to the GLTSYN_TIME register */ + spinlock_t ptp_gltsyn_time_lock; + + refcount_t refcount; +}; + +struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev); +void ice_adapter_put(const 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 d7fdb7ba7268..e76c388b9905 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -117,9 +117,11 @@ struct ice_aqc_list_caps_elem { #define ICE_AQC_CAPS_NET_VER 0x004C #define ICE_AQC_CAPS_PENDING_NET_VER 0x004D #define ICE_AQC_CAPS_RDMA 0x0051 +#define ICE_AQC_CAPS_SENSOR_READING 0x0067 #define ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE 0x0076 #define ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT 0x0077 #define ICE_AQC_CAPS_NVM_MGMT 0x0080 +#define ICE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE 0x0085 #define ICE_AQC_CAPS_FW_LAG_SUPPORT 0x0092 #define ICE_AQC_BIT_ROCEV2_LAG 0x01 #define ICE_AQC_BIT_SRIOV_LAG 0x02 @@ -263,6 +265,8 @@ struct ice_aqc_set_port_params { #define ICE_AQC_RES_TYPE_FLAG_SHARED BIT(7) #define ICE_AQC_RES_TYPE_FLAG_SCAN_BOTTOM BIT(12) #define ICE_AQC_RES_TYPE_FLAG_IGNORE_INDEX BIT(13) +#define ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_SHARED BIT(14) +#define ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_CTL BIT(15) #define ICE_AQC_RES_TYPE_FLAG_DEDICATED 0x00 @@ -421,10 +425,10 @@ struct ice_aqc_vsi_props { #define ICE_AQ_VSI_INNER_VLAN_INSERT_PVID BIT(2) #define ICE_AQ_VSI_INNER_VLAN_EMODE_S 3 #define ICE_AQ_VSI_INNER_VLAN_EMODE_M (0x3 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) -#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH (0x0 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) -#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_UP (0x1 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) -#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR (0x2 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) -#define ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING (0x3 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH 0x0U +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_UP 0x1U +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR 0x2U +#define ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING 0x3U u8 inner_vlan_reserved2[3]; /* ingress egress up sections */ __le32 ingress_table; /* bitmap, 3 bits per up */ @@ -490,11 +494,11 @@ struct ice_aqc_vsi_props { #define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S 2 #define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_M (0xF << ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S) #define ICE_AQ_VSI_Q_OPT_RSS_HASH_S 6 -#define ICE_AQ_VSI_Q_OPT_RSS_HASH_M (0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_TPLZ (0x0 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_SYM_TPLZ (0x1 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_XOR (0x2 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_JHASH (0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_M GENMASK(7, 6) +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ 0x0U +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ 0x1U +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_XOR 0x2U +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_JHASH 0x3U u8 q_opt_tc; #define ICE_AQ_VSI_Q_OPT_TC_OVR_S 0 #define ICE_AQ_VSI_Q_OPT_TC_OVR_M (0x1F << ICE_AQ_VSI_Q_OPT_TC_OVR_S) @@ -592,8 +596,9 @@ struct ice_aqc_recipe_data_elem { struct ice_aqc_recipe_to_profile { __le16 profile_id; u8 rsvd[6]; - DECLARE_BITMAP(recipe_assoc, ICE_MAX_NUM_RECIPES); + __le64 recipe_assoc; }; +static_assert(sizeof(struct ice_aqc_recipe_to_profile) == 16); /* Add/Update/Remove/Get switch rules (indirect 0x02A0, 0x02A1, 0x02A2, 0x02A3) */ @@ -806,6 +811,23 @@ struct ice_aqc_get_topo { __le32 addr_low; }; +/* Get/Set Tx Topology (indirect 0x0418/0x0417) */ +struct ice_aqc_get_set_tx_topo { + u8 set_flags; +#define ICE_AQC_TX_TOPO_FLAGS_CORRER BIT(0) +#define ICE_AQC_TX_TOPO_FLAGS_SRC_RAM BIT(1) +#define ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW BIT(4) +#define ICE_AQC_TX_TOPO_FLAGS_ISSUED BIT(5) + + u8 get_flags; +#define ICE_AQC_TX_TOPO_GET_RAM 2 + + __le16 reserved1; + __le32 reserved2; + __le32 addr_high; + __le32 addr_low; +}; + /* Update TSE (indirect 0x0403) * Get TSE (indirect 0x0404) * Add TSE (indirect 0x0401) @@ -1359,8 +1381,9 @@ struct ice_aqc_get_link_status_data { u8 lp_flowcontrol; #define ICE_AQ_LINK_LP_PAUSE_ADV BIT(0) #define ICE_AQ_LINK_LP_ASM_DIR_ADV BIT(1) + u8 reserved5[5]; #define ICE_AQC_LS_DATA_SIZE_V2 \ - offsetofend(struct ice_aqc_get_link_status_data, lp_flowcontrol) + offsetofend(struct ice_aqc_get_link_status_data, reserved5) } __packed; /* Set event mask command (direct 0x0613) */ @@ -1413,6 +1436,30 @@ struct ice_aqc_get_phy_rec_clk_out { __le16 node_handle; }; +/* Get sensor reading (direct 0x0632) */ +struct ice_aqc_get_sensor_reading { + u8 sensor; + u8 format; + u8 reserved[6]; + __le32 addr_high; + __le32 addr_low; +}; + +/* Get sensor reading response (direct 0x0632) */ +struct ice_aqc_get_sensor_reading_resp { + union { + u8 raw[8]; + /* Output data for sensor 0x00, format 0x00 */ + struct _packed { + s8 temp; + u8 temp_warning_threshold; + u8 temp_critical_threshold; + u8 temp_fatal_threshold; + u8 reserved[4]; + } s0f0; + } data; +}; + struct ice_aqc_link_topo_params { u8 lport_num; u8 lport_num_valid; @@ -1637,6 +1684,15 @@ struct ice_aqc_nvm { #define ICE_AQC_NVM_START_POINT 0 +#define ICE_AQC_NVM_TX_TOPO_MOD_ID 0x14B + +struct ice_aqc_nvm_tx_topo_user_sel { + __le16 length; + u8 data; +#define ICE_AQC_NVM_TX_TOPO_USER_SEL BIT(4) + u8 reserved; +}; + /* NVM Checksum Command (direct, 0x0706) */ struct ice_aqc_nvm_checksum { u8 flags; @@ -2069,78 +2125,6 @@ struct ice_aqc_add_rdma_qset_data { struct ice_aqc_add_tx_rdma_qset_entry rdma_qsets[]; }; -/* Configure Firmware Logging Command (indirect 0xFF09) - * Logging Information Read Response (indirect 0xFF10) - * Note: The 0xFF10 command has no input parameters. - */ -struct ice_aqc_fw_logging { - u8 log_ctrl; -#define ICE_AQC_FW_LOG_AQ_EN BIT(0) -#define ICE_AQC_FW_LOG_UART_EN BIT(1) - u8 rsvd0; - u8 log_ctrl_valid; /* Not used by 0xFF10 Response */ -#define ICE_AQC_FW_LOG_AQ_VALID BIT(0) -#define ICE_AQC_FW_LOG_UART_VALID BIT(1) - u8 rsvd1[5]; - __le32 addr_high; - __le32 addr_low; -}; - -enum ice_aqc_fw_logging_mod { - ICE_AQC_FW_LOG_ID_GENERAL = 0, - ICE_AQC_FW_LOG_ID_CTRL, - ICE_AQC_FW_LOG_ID_LINK, - ICE_AQC_FW_LOG_ID_LINK_TOPO, - ICE_AQC_FW_LOG_ID_DNL, - ICE_AQC_FW_LOG_ID_I2C, - ICE_AQC_FW_LOG_ID_SDP, - ICE_AQC_FW_LOG_ID_MDIO, - ICE_AQC_FW_LOG_ID_ADMINQ, - ICE_AQC_FW_LOG_ID_HDMA, - ICE_AQC_FW_LOG_ID_LLDP, - ICE_AQC_FW_LOG_ID_DCBX, - ICE_AQC_FW_LOG_ID_DCB, - ICE_AQC_FW_LOG_ID_NETPROXY, - ICE_AQC_FW_LOG_ID_NVM, - ICE_AQC_FW_LOG_ID_AUTH, - ICE_AQC_FW_LOG_ID_VPD, - ICE_AQC_FW_LOG_ID_IOSF, - ICE_AQC_FW_LOG_ID_PARSER, - ICE_AQC_FW_LOG_ID_SW, - ICE_AQC_FW_LOG_ID_SCHEDULER, - ICE_AQC_FW_LOG_ID_TXQ, - ICE_AQC_FW_LOG_ID_RSVD, - ICE_AQC_FW_LOG_ID_POST, - ICE_AQC_FW_LOG_ID_WATCHDOG, - ICE_AQC_FW_LOG_ID_TASK_DISPATCH, - ICE_AQC_FW_LOG_ID_MNG, - ICE_AQC_FW_LOG_ID_MAX, -}; - -/* Defines for both above FW logging command/response buffers */ -#define ICE_AQC_FW_LOG_ID_S 0 -#define ICE_AQC_FW_LOG_ID_M (0xFFF << ICE_AQC_FW_LOG_ID_S) - -#define ICE_AQC_FW_LOG_CONF_SUCCESS 0 /* Used by response */ -#define ICE_AQC_FW_LOG_CONF_BAD_INDX BIT(12) /* Used by response */ - -#define ICE_AQC_FW_LOG_EN_S 12 -#define ICE_AQC_FW_LOG_EN_M (0xF << ICE_AQC_FW_LOG_EN_S) -#define ICE_AQC_FW_LOG_INFO_EN BIT(12) /* Used by command */ -#define ICE_AQC_FW_LOG_INIT_EN BIT(13) /* Used by command */ -#define ICE_AQC_FW_LOG_FLOW_EN BIT(14) /* Used by command */ -#define ICE_AQC_FW_LOG_ERR_EN BIT(15) /* Used by command */ - -/* Get/Clear FW Log (indirect 0xFF11) */ -struct ice_aqc_get_clear_fw_log { - u8 flags; -#define ICE_AQC_FW_LOG_CLEAR BIT(0) -#define ICE_AQC_FW_LOG_MORE_DATA_AVAIL BIT(1) - u8 rsvd1[7]; - __le32 addr_high; - __le32 addr_low; -}; - /* Download Package (indirect 0x0C40) */ /* Also used for Update Package (indirect 0x0C41 and 0x0C42) */ struct ice_aqc_download_pkg { @@ -2403,6 +2387,84 @@ struct ice_aqc_event_lan_overflow { u8 reserved[8]; }; +enum ice_aqc_fw_logging_mod { + ICE_AQC_FW_LOG_ID_GENERAL = 0, + ICE_AQC_FW_LOG_ID_CTRL, + ICE_AQC_FW_LOG_ID_LINK, + ICE_AQC_FW_LOG_ID_LINK_TOPO, + ICE_AQC_FW_LOG_ID_DNL, + ICE_AQC_FW_LOG_ID_I2C, + ICE_AQC_FW_LOG_ID_SDP, + ICE_AQC_FW_LOG_ID_MDIO, + ICE_AQC_FW_LOG_ID_ADMINQ, + ICE_AQC_FW_LOG_ID_HDMA, + ICE_AQC_FW_LOG_ID_LLDP, + ICE_AQC_FW_LOG_ID_DCBX, + ICE_AQC_FW_LOG_ID_DCB, + ICE_AQC_FW_LOG_ID_XLR, + ICE_AQC_FW_LOG_ID_NVM, + ICE_AQC_FW_LOG_ID_AUTH, + ICE_AQC_FW_LOG_ID_VPD, + ICE_AQC_FW_LOG_ID_IOSF, + ICE_AQC_FW_LOG_ID_PARSER, + ICE_AQC_FW_LOG_ID_SW, + ICE_AQC_FW_LOG_ID_SCHEDULER, + ICE_AQC_FW_LOG_ID_TXQ, + ICE_AQC_FW_LOG_ID_RSVD, + ICE_AQC_FW_LOG_ID_POST, + ICE_AQC_FW_LOG_ID_WATCHDOG, + ICE_AQC_FW_LOG_ID_TASK_DISPATCH, + ICE_AQC_FW_LOG_ID_MNG, + ICE_AQC_FW_LOG_ID_SYNCE, + ICE_AQC_FW_LOG_ID_HEALTH, + ICE_AQC_FW_LOG_ID_TSDRV, + ICE_AQC_FW_LOG_ID_PFREG, + ICE_AQC_FW_LOG_ID_MDLVER, + ICE_AQC_FW_LOG_ID_MAX, +}; + +/* Set FW Logging configuration (indirect 0xFF30) + * Register for FW Logging (indirect 0xFF31) + * Query FW Logging (indirect 0xFF32) + * FW Log Event (indirect 0xFF33) + */ +struct ice_aqc_fw_log { + u8 cmd_flags; +#define ICE_AQC_FW_LOG_CONF_UART_EN BIT(0) +#define ICE_AQC_FW_LOG_CONF_AQ_EN BIT(1) +#define ICE_AQC_FW_LOG_QUERY_REGISTERED BIT(2) +#define ICE_AQC_FW_LOG_CONF_SET_VALID BIT(3) +#define ICE_AQC_FW_LOG_AQ_REGISTER BIT(0) +#define ICE_AQC_FW_LOG_AQ_QUERY BIT(2) + + u8 rsp_flag; + __le16 fw_rt_msb; + union { + struct { + __le32 fw_rt_lsb; + } sync; + struct { + __le16 log_resolution; +#define ICE_AQC_FW_LOG_MIN_RESOLUTION (1) +#define ICE_AQC_FW_LOG_MAX_RESOLUTION (128) + + __le16 mdl_cnt; + } cfg; + } ops; + __le32 addr_high; + __le32 addr_low; +}; + +/* Response Buffer for: + * Set Firmware Logging Configuration (0xFF30) + * Query FW Logging (0xFF32) + */ +struct ice_aqc_fw_log_cfg_resp { + __le16 module_identifier; + u8 log_level; + u8 rsvd0; +}; + /** * struct ice_aq_desc - Admin Queue (AQ) descriptor * @flags: ICE_AQ_FLAG_* flags @@ -2443,6 +2505,8 @@ struct ice_aq_desc { struct ice_aqc_restart_an restart_an; struct ice_aqc_set_phy_rec_clk_out set_phy_rec_clk_out; struct ice_aqc_get_phy_rec_clk_out get_phy_rec_clk_out; + struct ice_aqc_get_sensor_reading get_sensor_reading; + struct ice_aqc_get_sensor_reading_resp get_sensor_reading_resp; struct ice_aqc_gpio read_write_gpio; struct ice_aqc_sff_eeprom read_write_sff_param; struct ice_aqc_set_port_id_led set_port_id_led; @@ -2480,8 +2544,6 @@ struct ice_aq_desc { struct ice_aqc_add_rdma_qset add_rdma_qset; struct ice_aqc_add_get_update_free_vsi vsi_cmd; struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res; - struct ice_aqc_fw_logging fw_logging; - struct ice_aqc_get_clear_fw_log get_clear_fw_log; struct ice_aqc_download_pkg download_pkg; struct ice_aqc_set_cgu_input_config set_cgu_input_config; struct ice_aqc_get_cgu_input_config get_cgu_input_config; @@ -2493,6 +2555,7 @@ struct ice_aq_desc { struct ice_aqc_get_cgu_ref_prio get_cgu_ref_prio; struct ice_aqc_get_cgu_info get_cgu_info; struct ice_aqc_driver_shared_params drv_shared_params; + struct ice_aqc_fw_log fw_log; struct ice_aqc_set_mac_lb set_mac_lb; struct ice_aqc_alloc_free_res_cmd sw_res_ctrl; struct ice_aqc_set_mac_cfg set_mac_cfg; @@ -2502,6 +2565,7 @@ struct ice_aq_desc { struct ice_aqc_get_link_topo get_link_topo; struct ice_aqc_i2c read_write_i2c; struct ice_aqc_read_i2c_resp read_i2c_resp; + struct ice_aqc_get_set_tx_topo get_set_tx_topo; } params; }; @@ -2608,6 +2672,10 @@ enum ice_adminq_opc { ice_aqc_opc_query_sched_res = 0x0412, ice_aqc_opc_remove_rl_profiles = 0x0415, + /* tx topology commands */ + ice_aqc_opc_set_tx_topo = 0x0417, + ice_aqc_opc_get_tx_topo = 0x0418, + /* PHY commands */ ice_aqc_opc_get_phy_caps = 0x0600, ice_aqc_opc_set_phy_cfg = 0x0601, @@ -2618,6 +2686,7 @@ enum ice_adminq_opc { ice_aqc_opc_set_mac_lb = 0x0620, ice_aqc_opc_set_phy_rec_clk_out = 0x0630, ice_aqc_opc_get_phy_rec_clk_out = 0x0631, + ice_aqc_opc_get_sensor_reading = 0x0632, ice_aqc_opc_get_link_topo = 0x06E0, ice_aqc_opc_read_i2c = 0x06E2, ice_aqc_opc_write_i2c = 0x06E3, @@ -2690,9 +2759,11 @@ enum ice_adminq_opc { /* Standalone Commands/Events */ ice_aqc_opc_event_lan_overflow = 0x1001, - /* debug commands */ - ice_aqc_opc_fw_logging = 0xFF09, - ice_aqc_opc_fw_logging_info = 0xFF10, + /* FW Logging Commands */ + ice_aqc_opc_fw_logs_config = 0xFF30, + ice_aqc_opc_fw_logs_register = 0xFF31, + ice_aqc_opc_fw_logs_query = 0xFF32, + ice_aqc_opc_fw_logs_event = 0xFF33, }; #endif /* _ICE_ADMINQ_CMD_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index cca0e753f38f..7cee365cc7d1 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -2,6 +2,7 @@ /* Copyright (C) 2018-2020, Intel Corporation. */ #include "ice.h" +#include <net/rps.h> /** * ice_is_arfs_active - helper to check is aRFS is active diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 7fa43827a3f0..687f6cb2b917 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -121,7 +121,7 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx) q_vector->irq.index = -ENOENT; if (vsi->type == ICE_VSI_VF) { - q_vector->reg_idx = ice_calc_vf_reg_idx(vsi->vf, q_vector); + ice_calc_vf_reg_idx(vsi->vf, q_vector); goto out; } else if (vsi->type == ICE_VSI_CTRL && vsi->vf) { struct ice_vsi *ctrl_vsi = ice_get_vf_ctrl_vsi(pf, vsi); @@ -145,6 +145,7 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx) 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)) @@ -189,10 +190,16 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx) } q_vector = vsi->q_vectors[v_idx]; - ice_for_each_tx_ring(tx_ring, q_vector->tx) + ice_for_each_tx_ring(tx_ring, q_vector->tx) { + ice_queue_set_napi(vsi, tx_ring->q_index, NETDEV_QUEUE_TYPE_TX, + NULL); tx_ring->q_vector = NULL; - ice_for_each_rx_ring(rx_ring, q_vector->rx) + } + ice_for_each_rx_ring(rx_ring, q_vector->rx) { + ice_queue_set_napi(vsi, rx_ring->q_index, NETDEV_QUEUE_TYPE_RX, + NULL); rx_ring->q_vector = NULL; + } /* only VSI with an associated netdev is set up with NAPI */ if (vsi->netdev) @@ -224,24 +231,16 @@ static void ice_cfg_itr_gran(struct ice_hw *hw) /* no need to update global register if ITR gran is already set */ if (!(regval & GLINT_CTL_DIS_AUTOMASK_M) && - (((regval & GLINT_CTL_ITR_GRAN_200_M) >> - GLINT_CTL_ITR_GRAN_200_S) == ICE_ITR_GRAN_US) && - (((regval & GLINT_CTL_ITR_GRAN_100_M) >> - GLINT_CTL_ITR_GRAN_100_S) == ICE_ITR_GRAN_US) && - (((regval & GLINT_CTL_ITR_GRAN_50_M) >> - GLINT_CTL_ITR_GRAN_50_S) == ICE_ITR_GRAN_US) && - (((regval & GLINT_CTL_ITR_GRAN_25_M) >> - GLINT_CTL_ITR_GRAN_25_S) == ICE_ITR_GRAN_US)) + (FIELD_GET(GLINT_CTL_ITR_GRAN_200_M, regval) == ICE_ITR_GRAN_US) && + (FIELD_GET(GLINT_CTL_ITR_GRAN_100_M, regval) == ICE_ITR_GRAN_US) && + (FIELD_GET(GLINT_CTL_ITR_GRAN_50_M, regval) == ICE_ITR_GRAN_US) && + (FIELD_GET(GLINT_CTL_ITR_GRAN_25_M, regval) == ICE_ITR_GRAN_US)) return; - regval = ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_200_S) & - GLINT_CTL_ITR_GRAN_200_M) | - ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_100_S) & - GLINT_CTL_ITR_GRAN_100_M) | - ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_50_S) & - GLINT_CTL_ITR_GRAN_50_M) | - ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_25_S) & - GLINT_CTL_ITR_GRAN_25_M); + regval = FIELD_PREP(GLINT_CTL_ITR_GRAN_200_M, ICE_ITR_GRAN_US) | + FIELD_PREP(GLINT_CTL_ITR_GRAN_100_M, ICE_ITR_GRAN_US) | + FIELD_PREP(GLINT_CTL_ITR_GRAN_50_M, ICE_ITR_GRAN_US) | + FIELD_PREP(GLINT_CTL_ITR_GRAN_25_M, ICE_ITR_GRAN_US); wr32(hw, GLINT_CTL, regval); } @@ -266,30 +265,6 @@ static u16 ice_calc_txq_handle(struct ice_vsi *vsi, struct ice_tx_ring *ring, u8 } /** - * ice_eswitch_calc_txq_handle - * @ring: pointer to ring which unique index is needed - * - * To correctly work with many netdevs ring->q_index of Tx rings on switchdev - * VSI can repeat. Hardware ring setup requires unique q_index. Calculate it - * here by finding index in vsi->tx_rings of this ring. - * - * Return ICE_INVAL_Q_INDEX when index wasn't found. Should never happen, - * because VSI is get from ring->vsi, so it has to be present in this VSI. - */ -static u16 ice_eswitch_calc_txq_handle(struct ice_tx_ring *ring) -{ - struct ice_vsi *vsi = ring->vsi; - int i; - - ice_for_each_txq(vsi, i) { - if (vsi->tx_rings[i] == ring) - return i; - } - - return ICE_INVAL_Q_INDEX; -} - -/** * ice_cfg_xps_tx_ring - Configure XPS for a Tx ring * @ring: The Tx ring to configure * @@ -355,9 +330,6 @@ ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf->vf_id; tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VF; break; - case ICE_VSI_SWITCHDEV_CTRL: - tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VMQ; - break; default: return; } @@ -481,6 +453,14 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) /* Rx queue threshold in units of 64 */ rlan_ctx.lrxqthresh = 1; + /* PF acts as uplink for switchdev; set flex descriptor with src_vsi + * metadata and flags to allow redirecting to PR netdev + */ + if (ice_is_eswitch_mode_switchdev(vsi->back)) { + ring->flags |= ICE_RX_FLAGS_MULTIDEV; + rxdid = ICE_RXDID_FLEX_NIC_2; + } + /* Enable Flexible Descriptors in the queue context which * allows this driver to select a specific receive descriptor format * increasing context priority to pick up profile ID; default is 0x01; @@ -519,13 +499,26 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) return 0; } +static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring) +{ + void *ctx_ptr = &ring->pkt_ctx; + struct xsk_cb_desc desc = {}; + + XSK_CHECK_PRIV_TYPE(struct ice_xdp_buff); + desc.src = &ctx_ptr; + desc.off = offsetof(struct ice_xdp_buff, pkt_ctx) - + sizeof(struct xdp_buff); + desc.bytes = sizeof(ctx_ptr); + xsk_pool_fill_cb(ring->xsk_pool, &desc); +} + /** * ice_vsi_cfg_rxq - Configure an Rx queue * @ring: the ring being configured * * Return 0 on success and a negative value on error. */ -int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) +static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) { struct device *dev = ice_pf_to_dev(ring->vsi->back); u32 num_bufs = ICE_RX_DESC_UNUSED(ring); @@ -534,36 +527,46 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) ring->rx_buf_len = ring->vsi->rx_buf_len; if (ring->vsi->type == ICE_VSI_PF) { - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) - /* coverity[check_return] */ - __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->q_index, - ring->q_vector->napi.napi_id, - ring->vsi->rx_buf_len); + if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->q_index, + ring->q_vector->napi.napi_id, + ring->rx_buf_len); + if (err) + return err; + } ring->xsk_pool = ice_xsk_pool(ring); if (ring->xsk_pool) { - xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + xdp_rxq_info_unreg(&ring->xdp_rxq); ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->q_index, + ring->q_vector->napi.napi_id, + ring->rx_buf_len); + if (err) + return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); if (err) return err; xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); + ice_xsk_pool_fill_cb(ring); dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->q_index); } else { - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) - /* coverity[check_return] */ - __xdp_rxq_info_reg(&ring->xdp_rxq, - ring->netdev, - ring->q_index, - ring->q_vector->napi.napi_id, - ring->vsi->rx_buf_len); + if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->q_index, + ring->q_vector->napi.napi_id, + ring->rx_buf_len); + if (err) + return err; + } err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, @@ -575,6 +578,7 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq); ring->xdp.data = NULL; + ring->xdp_ext.pkt_ctx = &ring->pkt_ctx; err = ice_setup_rx_ctx(ring); if (err) { dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n", @@ -609,6 +613,62 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) return 0; } +int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) +{ + if (q_idx >= vsi->num_rxq) + return -EINVAL; + + return ice_vsi_cfg_rxq(vsi->rx_rings[q_idx]); +} + +/** + * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length + * @vsi: VSI + */ +static void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) +{ + if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { + vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX; + vsi->rx_buf_len = ICE_RXBUF_1664; +#if (PAGE_SIZE < 8192) + } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && + (vsi->netdev->mtu <= ETH_DATA_LEN)) { + vsi->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; + vsi->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN; +#endif + } else { + vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; + vsi->rx_buf_len = ICE_RXBUF_3072; + } +} + +/** + * ice_vsi_cfg_rxqs - Configure the VSI for Rx + * @vsi: the VSI being configured + * + * Return 0 on success and a negative value on error + * Configure the Rx VSI for operation. + */ +int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) +{ + u16 i; + + if (vsi->type == ICE_VSI_VF) + goto setup_rings; + + ice_vsi_cfg_frame_size(vsi); +setup_rings: + /* set up individual rings */ + ice_for_each_rxq(vsi, i) { + int err = ice_vsi_cfg_rxq(vsi->rx_rings[i]); + + if (err) + return err; + } + + return 0; +} + /** * __ice_vsi_get_qs - helper function for assigning queues from PF to VSI * @qs_cfg: gathered variables needed for pf->vsi queues assignment @@ -804,7 +864,7 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi) * @ring: Tx ring to be configured * @qg_buf: queue group buffer */ -int +static int ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, struct ice_aqc_add_tx_qgrp *qg_buf) { @@ -841,14 +901,7 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, /* Add unique software queue handle of the Tx queue per * TC into the VSI Tx ring */ - if (vsi->type == ICE_VSI_SWITCHDEV_CTRL) { - ring->q_handle = ice_eswitch_calc_txq_handle(ring); - - if (ring->q_handle == ICE_INVAL_Q_INDEX) - return -ENODEV; - } else { - ring->q_handle = ice_calc_txq_handle(vsi, ring, tc); - } + ring->q_handle = ice_calc_txq_handle(vsi, ring, tc); if (ch) status = ice_ena_vsi_txq(vsi->port_info, ch->ch_vsi->idx, 0, @@ -875,6 +928,80 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, return 0; } +int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, + u16 q_idx) +{ + DEFINE_RAW_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); + + if (q_idx >= vsi->alloc_txq || !tx_rings || !tx_rings[q_idx]) + return -EINVAL; + + qg_buf->num_txqs = 1; + + return ice_vsi_cfg_txq(vsi, tx_rings[q_idx], qg_buf); +} + +/** + * ice_vsi_cfg_txqs - Configure the VSI for Tx + * @vsi: the VSI being configured + * @rings: Tx ring array to be configured + * @count: number of Tx ring array elements + * + * Return 0 on success and a negative value on error + * Configure the Tx VSI for operation. + */ +static int +ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_tx_ring **rings, u16 count) +{ + DEFINE_RAW_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); + int err = 0; + u16 q_idx; + + qg_buf->num_txqs = 1; + + for (q_idx = 0; q_idx < count; q_idx++) { + err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf); + if (err) + break; + } + + return err; +} + +/** + * ice_vsi_cfg_lan_txqs - Configure the VSI for Tx + * @vsi: the VSI being configured + * + * Return 0 on success and a negative value on error + * Configure the Tx VSI for operation. + */ +int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi) +{ + return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, vsi->num_txq); +} + +/** + * ice_vsi_cfg_xdp_txqs - Configure Tx queues dedicated for XDP in given VSI + * @vsi: the VSI being configured + * + * Return 0 on success and a negative value on error + * Configure the Tx queues dedicated for XDP in given VSI for operation. + */ +int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) +{ + int ret; + int i; + + ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings, vsi->num_xdp_txq); + if (ret) + return ret; + + ice_for_each_rxq(vsi, i) + ice_tx_xsk_pool(vsi, i); + + return 0; +} + /** * ice_cfg_itr - configure the initial interrupt throttle values * @hw: pointer to the HW structure @@ -913,10 +1040,10 @@ ice_cfg_txq_interrupt(struct ice_vsi *vsi, u16 txq, u16 msix_idx, u16 itr_idx) struct ice_hw *hw = &pf->hw; u32 val; - itr_idx = (itr_idx << QINT_TQCTL_ITR_INDX_S) & QINT_TQCTL_ITR_INDX_M; + itr_idx = FIELD_PREP(QINT_TQCTL_ITR_INDX_M, itr_idx); val = QINT_TQCTL_CAUSE_ENA_M | itr_idx | - ((msix_idx << QINT_TQCTL_MSIX_INDX_S) & QINT_TQCTL_MSIX_INDX_M); + FIELD_PREP(QINT_TQCTL_MSIX_INDX_M, msix_idx); wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), val); if (ice_is_xdp_ena_vsi(vsi)) { @@ -945,10 +1072,10 @@ ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx) struct ice_hw *hw = &pf->hw; u32 val; - itr_idx = (itr_idx << QINT_RQCTL_ITR_INDX_S) & QINT_RQCTL_ITR_INDX_M; + itr_idx = FIELD_PREP(QINT_RQCTL_ITR_INDX_M, itr_idx); val = QINT_RQCTL_CAUSE_ENA_M | itr_idx | - ((msix_idx << QINT_RQCTL_MSIX_INDX_S) & QINT_RQCTL_MSIX_INDX_M); + FIELD_PREP(QINT_RQCTL_MSIX_INDX_M, msix_idx); wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), val); @@ -960,7 +1087,7 @@ ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx) * @hw: pointer to the HW structure * @q_vector: interrupt vector to trigger the software interrupt for */ -void ice_trigger_sw_intr(struct ice_hw *hw, struct ice_q_vector *q_vector) +void ice_trigger_sw_intr(struct ice_hw *hw, const struct ice_q_vector *q_vector) { wr32(hw, GLINT_DYN_CTL(q_vector->reg_idx), (ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S) | @@ -1035,7 +1162,7 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, * are needed for stopping Tx queue */ void -ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_tx_ring *ring, +ice_fill_txq_meta(const struct ice_vsi *vsi, struct ice_tx_ring *ring, struct ice_txq_meta *txq_meta) { struct ice_channel *ch = ring->ch; diff --git a/drivers/net/ethernet/intel/ice/ice_base.h b/drivers/net/ethernet/intel/ice/ice_base.h index b67dca417acb..b711bc921928 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.h +++ b/drivers/net/ethernet/intel/ice/ice_base.h @@ -6,7 +6,8 @@ #include "ice.h" -int ice_vsi_cfg_rxq(struct ice_rx_ring *ring); +int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx); +int ice_vsi_cfg_rxqs(struct ice_vsi *vsi); int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg); int ice_vsi_ctrl_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx, bool wait); @@ -14,20 +15,21 @@ int ice_vsi_wait_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx); int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi); void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi); void ice_vsi_free_q_vectors(struct ice_vsi *vsi); -int -ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, - struct ice_aqc_add_tx_qgrp *qg_buf); +int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, + u16 q_idx); +int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi); +int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi); void ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector); void ice_cfg_txq_interrupt(struct ice_vsi *vsi, u16 txq, u16 msix_idx, u16 itr_idx); void ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx); -void ice_trigger_sw_intr(struct ice_hw *hw, struct ice_q_vector *q_vector); +void ice_trigger_sw_intr(struct ice_hw *hw, const struct ice_q_vector *q_vector); int ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, u16 rel_vmvf_num, struct ice_tx_ring *ring, struct ice_txq_meta *txq_meta); void -ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_tx_ring *ring, +ice_fill_txq_meta(const struct ice_vsi *vsi, struct ice_tx_ring *ring, struct ice_txq_meta *txq_meta); #endif /* _ICE_BASE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 9a6c25f98632..5649b257e631 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -154,10 +154,22 @@ static int ice_set_mac_type(struct ice_hw *hw) case ICE_DEV_ID_E823L_SFP: hw->mac_type = ICE_MAC_GENERIC; break; - case ICE_DEV_ID_E830_BACKPLANE: - case ICE_DEV_ID_E830_QSFP56: - case ICE_DEV_ID_E830_SFP: - case ICE_DEV_ID_E830_SFP_DD: + case ICE_DEV_ID_E825C_BACKPLANE: + case ICE_DEV_ID_E825C_QSFP: + case ICE_DEV_ID_E825C_SFP: + case ICE_DEV_ID_E825C_SGMII: + hw->mac_type = ICE_MAC_GENERIC_3K_E825; + break; + case ICE_DEV_ID_E830CC_BACKPLANE: + case ICE_DEV_ID_E830CC_QSFP56: + case ICE_DEV_ID_E830CC_SFP: + case ICE_DEV_ID_E830CC_SFP_DD: + case ICE_DEV_ID_E830C_BACKPLANE: + case ICE_DEV_ID_E830_XXV_BACKPLANE: + case ICE_DEV_ID_E830C_QSFP: + case ICE_DEV_ID_E830_XXV_QSFP: + case ICE_DEV_ID_E830C_SFP: + case ICE_DEV_ID_E830_XXV_SFP: hw->mac_type = ICE_MAC_E830; break; default: @@ -170,6 +182,18 @@ 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 + */ +bool ice_is_generic_mac(struct ice_hw *hw) +{ + return (hw->mac_type == ICE_MAC_GENERIC || + hw->mac_type == ICE_MAC_GENERIC_3K_E825); +} + +/** * ice_is_e810 * @hw: pointer to the hardware structure * @@ -241,6 +265,25 @@ bool ice_is_e823(struct ice_hw *hw) } /** + * 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: + return true; + default: + return false; + } +} + +/** * ice_clear_pf_cfg - Clear PF configuration * @hw: pointer to the hardware structure * @@ -934,216 +977,6 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw) } /** - * ice_get_fw_log_cfg - get FW logging configuration - * @hw: pointer to the HW struct - */ -static int ice_get_fw_log_cfg(struct ice_hw *hw) -{ - struct ice_aq_desc desc; - __le16 *config; - int status; - u16 size; - - size = sizeof(*config) * ICE_AQC_FW_LOG_ID_MAX; - config = kzalloc(size, GFP_KERNEL); - if (!config) - return -ENOMEM; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logging_info); - - status = ice_aq_send_cmd(hw, &desc, config, size, NULL); - if (!status) { - u16 i; - - /* Save FW logging information into the HW structure */ - for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) { - u16 v, m, flgs; - - v = le16_to_cpu(config[i]); - m = (v & ICE_AQC_FW_LOG_ID_M) >> ICE_AQC_FW_LOG_ID_S; - flgs = (v & ICE_AQC_FW_LOG_EN_M) >> ICE_AQC_FW_LOG_EN_S; - - if (m < ICE_AQC_FW_LOG_ID_MAX) - hw->fw_log.evnts[m].cur = flgs; - } - } - - kfree(config); - - return status; -} - -/** - * ice_cfg_fw_log - configure FW logging - * @hw: pointer to the HW struct - * @enable: enable certain FW logging events if true, disable all if false - * - * This function enables/disables the FW logging via Rx CQ events and a UART - * port based on predetermined configurations. FW logging via the Rx CQ can be - * enabled/disabled for individual PF's. However, FW logging via the UART can - * only be enabled/disabled for all PFs on the same device. - * - * To enable overall FW logging, the "cq_en" and "uart_en" enable bits in - * hw->fw_log need to be set accordingly, e.g. based on user-provided input, - * before initializing the device. - * - * When re/configuring FW logging, callers need to update the "cfg" elements of - * the hw->fw_log.evnts array with the desired logging event configurations for - * modules of interest. When disabling FW logging completely, the callers can - * just pass false in the "enable" parameter. On completion, the function will - * update the "cur" element of the hw->fw_log.evnts array with the resulting - * logging event configurations of the modules that are being re/configured. FW - * logging modules that are not part of a reconfiguration operation retain their - * previous states. - * - * Before resetting the device, it is recommended that the driver disables FW - * logging before shutting down the control queue. When disabling FW logging - * ("enable" = false), the latest configurations of FW logging events stored in - * hw->fw_log.evnts[] are not overridden to allow them to be reconfigured after - * a device reset. - * - * When enabling FW logging to emit log messages via the Rx CQ during the - * device's initialization phase, a mechanism alternative to interrupt handlers - * needs to be used to extract FW log messages from the Rx CQ periodically and - * to prevent the Rx CQ from being full and stalling other types of control - * messages from FW to SW. Interrupts are typically disabled during the device's - * initialization phase. - */ -static int ice_cfg_fw_log(struct ice_hw *hw, bool enable) -{ - struct ice_aqc_fw_logging *cmd; - u16 i, chgs = 0, len = 0; - struct ice_aq_desc desc; - __le16 *data = NULL; - u8 actv_evnts = 0; - void *buf = NULL; - int status = 0; - - if (!hw->fw_log.cq_en && !hw->fw_log.uart_en) - return 0; - - /* Disable FW logging only when the control queue is still responsive */ - if (!enable && - (!hw->fw_log.actv_evnts || !ice_check_sq_alive(hw, &hw->adminq))) - return 0; - - /* Get current FW log settings */ - status = ice_get_fw_log_cfg(hw); - if (status) - return status; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logging); - cmd = &desc.params.fw_logging; - - /* Indicate which controls are valid */ - if (hw->fw_log.cq_en) - cmd->log_ctrl_valid |= ICE_AQC_FW_LOG_AQ_VALID; - - if (hw->fw_log.uart_en) - cmd->log_ctrl_valid |= ICE_AQC_FW_LOG_UART_VALID; - - if (enable) { - /* Fill in an array of entries with FW logging modules and - * logging events being reconfigured. - */ - for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) { - u16 val; - - /* Keep track of enabled event types */ - actv_evnts |= hw->fw_log.evnts[i].cfg; - - if (hw->fw_log.evnts[i].cfg == hw->fw_log.evnts[i].cur) - continue; - - if (!data) { - data = devm_kcalloc(ice_hw_to_dev(hw), - ICE_AQC_FW_LOG_ID_MAX, - sizeof(*data), - GFP_KERNEL); - if (!data) - return -ENOMEM; - } - - val = i << ICE_AQC_FW_LOG_ID_S; - val |= hw->fw_log.evnts[i].cfg << ICE_AQC_FW_LOG_EN_S; - data[chgs++] = cpu_to_le16(val); - } - - /* Only enable FW logging if at least one module is specified. - * If FW logging is currently enabled but all modules are not - * enabled to emit log messages, disable FW logging altogether. - */ - if (actv_evnts) { - /* Leave if there is effectively no change */ - if (!chgs) - goto out; - - if (hw->fw_log.cq_en) - cmd->log_ctrl |= ICE_AQC_FW_LOG_AQ_EN; - - if (hw->fw_log.uart_en) - cmd->log_ctrl |= ICE_AQC_FW_LOG_UART_EN; - - buf = data; - len = sizeof(*data) * chgs; - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - } - } - - status = ice_aq_send_cmd(hw, &desc, buf, len, NULL); - if (!status) { - /* Update the current configuration to reflect events enabled. - * hw->fw_log.cq_en and hw->fw_log.uart_en indicate if the FW - * logging mode is enabled for the device. They do not reflect - * actual modules being enabled to emit log messages. So, their - * values remain unchanged even when all modules are disabled. - */ - u16 cnt = enable ? chgs : (u16)ICE_AQC_FW_LOG_ID_MAX; - - hw->fw_log.actv_evnts = actv_evnts; - for (i = 0; i < cnt; i++) { - u16 v, m; - - if (!enable) { - /* When disabling all FW logging events as part - * of device's de-initialization, the original - * configurations are retained, and can be used - * to reconfigure FW logging later if the device - * is re-initialized. - */ - hw->fw_log.evnts[i].cur = 0; - continue; - } - - v = le16_to_cpu(data[i]); - m = (v & ICE_AQC_FW_LOG_ID_M) >> ICE_AQC_FW_LOG_ID_S; - hw->fw_log.evnts[m].cur = hw->fw_log.evnts[m].cfg; - } - } - -out: - devm_kfree(ice_hw_to_dev(hw), data); - - return status; -} - -/** - * ice_output_fw_log - * @hw: pointer to the HW struct - * @desc: pointer to the AQ message descriptor - * @buf: pointer to the buffer accompanying the AQ message - * - * Formats a FW Log message and outputs it via the standard driver logs. - */ -void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf) -{ - ice_debug(hw, ICE_DBG_FW_LOG, "[ FW Log Msg Start ]\n"); - ice_debug_array(hw, ICE_DBG_FW_LOG, 16, 1, (u8 *)buf, - le16_to_cpu(desc->datalen)); - ice_debug(hw, ICE_DBG_FW_LOG, "[ FW Log Msg End ]\n"); -} - -/** * ice_get_itr_intrl_gran * @hw: pointer to the HW struct * @@ -1152,9 +985,8 @@ void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf) */ static void ice_get_itr_intrl_gran(struct ice_hw *hw) { - u8 max_agg_bw = (rd32(hw, GL_PWR_MODE_CTL) & - GL_PWR_MODE_CTL_CAR_MAX_BW_M) >> - GL_PWR_MODE_CTL_CAR_MAX_BW_S; + u8 max_agg_bw = FIELD_GET(GL_PWR_MODE_CTL_CAR_MAX_BW_M, + rd32(hw, GL_PWR_MODE_CTL)); switch (max_agg_bw) { case ICE_MAX_AGG_BW_200G: @@ -1176,9 +1008,9 @@ static void ice_get_itr_intrl_gran(struct ice_hw *hw) */ int ice_init_hw(struct ice_hw *hw) { - struct ice_aqc_get_phy_caps_data *pcaps; + struct ice_aqc_get_phy_caps_data *pcaps __free(kfree) = NULL; + void *mac_buf __free(kfree) = NULL; u16 mac_buf_len; - void *mac_buf; int status; /* Set MAC type based on DeviceID */ @@ -1186,9 +1018,7 @@ int ice_init_hw(struct ice_hw *hw) if (status) return status; - hw->pf_id = (u8)(rd32(hw, PF_FUNC_RID) & - PF_FUNC_RID_FUNC_NUM_M) >> - PF_FUNC_RID_FUNC_NUM_S; + hw->pf_id = FIELD_GET(PF_FUNC_RID_FUNC_NUM_M, rd32(hw, PF_FUNC_RID)); status = ice_reset(hw, ICE_RESET_PFR); if (status) @@ -1200,10 +1030,10 @@ int ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_cqinit; - /* Enable FW logging. Not fatal if this fails. */ - status = ice_cfg_fw_log(hw, true); + status = ice_fwlog_init(hw); if (status) - ice_debug(hw, ICE_DBG_INIT, "Failed to enable FW logging.\n"); + ice_debug(hw, ICE_DBG_FW_LOG, "Error initializing FW logging: %d\n", + status); status = ice_clear_pf_cfg(hw); if (status) @@ -1258,7 +1088,7 @@ int ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_sched; - pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps), GFP_KERNEL); + pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); if (!pcaps) { status = -ENOMEM; goto err_unroll_sched; @@ -1268,7 +1098,6 @@ int ice_init_hw(struct ice_hw *hw) status = ice_aq_get_phy_caps(hw->port_info, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, pcaps, NULL); - devm_kfree(ice_hw_to_dev(hw), pcaps); if (status) dev_warn(ice_hw_to_dev(hw), "Get PHY capabilities failed status = %d, continuing anyway\n", status); @@ -1295,18 +1124,15 @@ int ice_init_hw(struct ice_hw *hw) /* Get MAC information */ /* A single port can report up to two (LAN and WoL) addresses */ - mac_buf = devm_kcalloc(ice_hw_to_dev(hw), 2, - sizeof(struct ice_aqc_manage_mac_read_resp), - GFP_KERNEL); - mac_buf_len = 2 * sizeof(struct ice_aqc_manage_mac_read_resp); - + mac_buf = kcalloc(2, sizeof(struct ice_aqc_manage_mac_read_resp), + GFP_KERNEL); if (!mac_buf) { status = -ENOMEM; goto err_unroll_fltr_mgmt_struct; } + mac_buf_len = 2 * sizeof(struct ice_aqc_manage_mac_read_resp); status = ice_aq_manage_mac_read(hw, mac_buf, mac_buf_len, NULL); - devm_kfree(ice_hw_to_dev(hw), mac_buf); if (status) goto err_unroll_fltr_mgmt_struct; @@ -1322,6 +1148,8 @@ int ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_fltr_mgmt_struct; mutex_init(&hw->tnl_lock); + ice_init_chk_recipe_reuse_support(hw); + return 0; err_unroll_fltr_mgmt_struct: @@ -1354,8 +1182,7 @@ void ice_deinit_hw(struct ice_hw *hw) ice_free_hw_tbls(hw); mutex_destroy(&hw->tnl_lock); - /* Attempt to disable FW logging before shutting down control queues */ - ice_cfg_fw_log(hw, false); + ice_fwlog_deinit(hw); ice_destroy_all_ctrlq(hw); /* Clear VSI contexts if not already cleared */ @@ -1374,8 +1201,8 @@ int ice_check_reset(struct ice_hw *hw) * or EMPR has occurred. The grst delay value is in 100ms units. * Add 1sec for outstanding AQ commands that can take a long time. */ - grst_timeout = ((rd32(hw, GLGEN_RSTCTL) & GLGEN_RSTCTL_GRSTDEL_M) >> - GLGEN_RSTCTL_GRSTDEL_S) + 10; + grst_timeout = FIELD_GET(GLGEN_RSTCTL_GRSTDEL_M, + rd32(hw, GLGEN_RSTCTL)) + 10; for (cnt = 0; cnt < grst_timeout; cnt++) { mdelay(100); @@ -1576,9 +1403,8 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = { * it to HW register space and enables the hardware to prefetch descriptors * instead of only fetching them on demand */ -int -ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, - u32 rxq_index) +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 }; @@ -1797,6 +1623,8 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, case ice_aqc_opc_set_port_params: case ice_aqc_opc_get_vlan_mode_parameters: case ice_aqc_opc_set_vlan_mode_parameters: + case ice_aqc_opc_set_tx_topo: + case ice_aqc_opc_get_tx_topo: case ice_aqc_opc_add_recipe: case ice_aqc_opc_recipe_to_profile: case ice_aqc_opc_get_recipe: @@ -2353,6 +2181,9 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, ice_debug(hw, ICE_DBG_INIT, "%s: sriov_lag = %u\n", prefix, caps->sriov_lag); break; + case ICE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE: + caps->tx_sched_topo_comp_mode_en = (number == 1); + break; default: /* Not one of the recognized common capabilities */ found = false; @@ -2459,7 +2290,7 @@ 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); - info->clk_freq = (number & ICE_TS_CLK_FREQ_M) >> ICE_TS_CLK_FREQ_S; + info->clk_freq = FIELD_GET(ICE_TS_CLK_FREQ_M, number); info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0); if (info->clk_freq < NUM_ICE_TIME_REF_FREQ) { @@ -2660,11 +2491,12 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, info->tmr0_owned = ((number & ICE_TS_TMR0_OWND_M) != 0); info->tmr0_ena = ((number & ICE_TS_TMR0_ENA_M) != 0); - info->tmr1_owner = (number & ICE_TS_TMR1_OWNR_M) >> ICE_TS_TMR1_OWNR_S; + info->tmr1_owner = FIELD_GET(ICE_TS_TMR1_OWNR_M, number); info->tmr1_owned = ((number & ICE_TS_TMR1_OWND_M) != 0); info->tmr1_ena = ((number & ICE_TS_TMR1_ENA_M) != 0); 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->ena_ports = logical_id; info->tmr_own_map = phys_id; @@ -2685,6 +2517,8 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, info->tmr1_ena); ice_debug(hw, ICE_DBG_INIT, "dev caps: ts_ll_read = %u\n", 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: ieee_1588 ena_ports = %u\n", info->ena_ports); ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr_own_map = %u\n", @@ -2711,6 +2545,26 @@ ice_parse_fdir_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, } /** + * ice_parse_sensor_reading_cap - Parse ICE_AQC_CAPS_SENSOR_READING cap + * @hw: pointer to the HW struct + * @dev_p: pointer to device capabilities structure + * @cap: capability element to parse + * + * Parse ICE_AQC_CAPS_SENSOR_READING for device capability for reading + * enabled sensors. + */ +static void +ice_parse_sensor_reading_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, + struct ice_aqc_list_caps_elem *cap) +{ + dev_p->supported_sensors = le32_to_cpu(cap->number); + + ice_debug(hw, ICE_DBG_INIT, + "dev caps: supported sensors (bitmap) = 0x%x\n", + dev_p->supported_sensors); +} + +/** * ice_parse_dev_caps - Parse device capabilities * @hw: pointer to the HW struct * @dev_p: pointer to device capabilities structure @@ -2755,9 +2609,12 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, case ICE_AQC_CAPS_1588: ice_parse_1588_dev_caps(hw, dev_p, &cap_resp[i]); break; - case ICE_AQC_CAPS_FD: + case ICE_AQC_CAPS_FD: ice_parse_fdir_dev_caps(hw, dev_p, &cap_resp[i]); break; + case ICE_AQC_CAPS_SENSOR_READING: + ice_parse_sensor_reading_cap(hw, dev_p, &cap_resp[i]); + break; default: /* Don't list common capabilities as unknown */ if (!found) @@ -3428,19 +3285,14 @@ int ice_update_link_info(struct ice_port_info *pi) return status; if (li->link_info & ICE_AQ_MEDIA_AVAILABLE) { - struct ice_aqc_get_phy_caps_data *pcaps; - struct ice_hw *hw; + struct ice_aqc_get_phy_caps_data *pcaps __free(kfree) = NULL; - hw = pi->hw; - pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps), - GFP_KERNEL); + pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); if (!pcaps) return -ENOMEM; status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, pcaps, NULL); - - devm_kfree(ice_hw_to_dev(hw), pcaps); } return status; @@ -3581,8 +3433,8 @@ ice_cfg_phy_fc(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, int ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update) { + struct ice_aqc_get_phy_caps_data *pcaps __free(kfree) = NULL; struct ice_aqc_set_phy_cfg_data cfg = { 0 }; - struct ice_aqc_get_phy_caps_data *pcaps; struct ice_hw *hw; int status; @@ -3592,7 +3444,7 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update) *aq_failures = 0; hw = pi->hw; - pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps), GFP_KERNEL); + pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); if (!pcaps) return -ENOMEM; @@ -3644,7 +3496,6 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update) } out: - devm_kfree(ice_hw_to_dev(hw), pcaps); return status; } @@ -3723,7 +3574,7 @@ int ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, enum ice_fec_mode fec) { - struct ice_aqc_get_phy_caps_data *pcaps; + struct ice_aqc_get_phy_caps_data *pcaps __free(kfree) = NULL; struct ice_hw *hw; int status; @@ -3792,8 +3643,6 @@ ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, } out: - kfree(pcaps); - return status; } @@ -4072,6 +3921,7 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, { struct ice_aqc_sff_eeprom *cmd; struct ice_aq_desc desc; + u16 i2c_bus_addr; int status; if (!data || (mem_addr & 0xff00)) @@ -4082,15 +3932,13 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, desc.flags = cpu_to_le16(ICE_AQ_FLAG_RD); cmd->lport_num = (u8)(lport & 0xff); cmd->lport_num_valid = (u8)((lport >> 8) & 0x01); - cmd->i2c_bus_addr = cpu_to_le16(((bus_addr >> 1) & - ICE_AQC_SFF_I2CBUS_7BIT_M) | - ((set_page << - ICE_AQC_SFF_SET_EEPROM_PAGE_S) & - ICE_AQC_SFF_SET_EEPROM_PAGE_M)); - cmd->i2c_mem_addr = cpu_to_le16(mem_addr & 0xff); - cmd->eeprom_page = cpu_to_le16((u16)page << ICE_AQC_SFF_EEPROM_PAGE_S); + i2c_bus_addr = FIELD_PREP(ICE_AQC_SFF_I2CBUS_7BIT_M, bus_addr >> 1) | + FIELD_PREP(ICE_AQC_SFF_SET_EEPROM_PAGE_M, set_page); if (write) - cmd->i2c_bus_addr |= cpu_to_le16(ICE_AQC_SFF_IS_WRITE); + i2c_bus_addr |= ICE_AQC_SFF_IS_WRITE; + cmd->i2c_bus_addr = cpu_to_le16(i2c_bus_addr); + cmd->i2c_mem_addr = cpu_to_le16(mem_addr & 0xff); + cmd->eeprom_page = le16_encode_bits(page, ICE_AQC_SFF_EEPROM_PAGE_M); status = ice_aq_send_cmd(hw, &desc, data, length, cd); return status; @@ -4345,6 +4193,7 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, struct ice_aqc_dis_txq_item *item; struct ice_aqc_dis_txqs *cmd; struct ice_aq_desc desc; + u16 vmvf_and_timeout; u16 i, sz = 0; int status; @@ -4360,27 +4209,26 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, cmd->num_entries = num_qgrps; - cmd->vmvf_and_timeout = cpu_to_le16((5 << ICE_AQC_Q_DIS_TIMEOUT_S) & - ICE_AQC_Q_DIS_TIMEOUT_M); + vmvf_and_timeout = FIELD_PREP(ICE_AQC_Q_DIS_TIMEOUT_M, 5); switch (rst_src) { case ICE_VM_RESET: cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VM_RESET; - cmd->vmvf_and_timeout |= - cpu_to_le16(vmvf_num & ICE_AQC_Q_DIS_VMVF_NUM_M); + vmvf_and_timeout |= vmvf_num & ICE_AQC_Q_DIS_VMVF_NUM_M; break; case ICE_VF_RESET: cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VF_RESET; /* In this case, FW expects vmvf_num to be absolute VF ID */ - cmd->vmvf_and_timeout |= - cpu_to_le16((vmvf_num + hw->func_caps.vf_base_id) & - ICE_AQC_Q_DIS_VMVF_NUM_M); + vmvf_and_timeout |= (vmvf_num + hw->func_caps.vf_base_id) & + ICE_AQC_Q_DIS_VMVF_NUM_M; break; case ICE_NO_RESET: default: break; } + cmd->vmvf_and_timeout = cpu_to_le16(vmvf_and_timeout); + /* flush pipe on time out */ cmd->cmd_type |= ICE_AQC_Q_DIS_CMD_FLUSH_PIPE; /* If no queue group info, we are in a reset flow. Issue the AQ */ @@ -4455,10 +4303,8 @@ ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf, cmd->cmd_type = ICE_AQC_Q_CFG_TC_CHNG; cmd->num_qs = num_qs; cmd->port_num_chng = (oldport & ICE_AQC_Q_CFG_SRC_PRT_M); - cmd->port_num_chng |= (newport << ICE_AQC_Q_CFG_DST_PRT_S) & - ICE_AQC_Q_CFG_DST_PRT_M; - cmd->time_out = (5 << ICE_AQC_Q_CFG_TIMEOUT_S) & - ICE_AQC_Q_CFG_TIMEOUT_M; + cmd->port_num_chng |= FIELD_PREP(ICE_AQC_Q_CFG_DST_PRT_M, newport); + cmd->time_out = FIELD_PREP(ICE_AQC_Q_CFG_TIMEOUT_M, 5); cmd->blocked_cgds = 0; status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); @@ -4516,13 +4362,13 @@ ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps, /* End of FW Admin Queue command wrappers */ /** - * ice_write_byte - write a byte to a packed context structure - * @src_ctx: the context structure to read from - * @dest_ctx: the context to be written to - * @ce_info: a description of the struct to be filled + * 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_write_byte(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) +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; @@ -4533,14 +4379,11 @@ ice_write_byte(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) /* prepare the bits and mask */ shift_width = ce_info->lsb % 8; - mask = (u8)(BIT(ce_info->width) - 1); + mask = GENMASK(ce_info->width - 1 + shift_width, shift_width); src_byte = *from; - src_byte &= mask; - - /* shift to correct alignment */ - mask <<= shift_width; src_byte <<= shift_width; + src_byte &= mask; /* get the current bits from the target bit string */ dest = dest_ctx + (ce_info->lsb / 8); @@ -4555,13 +4398,13 @@ ice_write_byte(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) } /** - * ice_write_word - write a word to a packed context structure - * @src_ctx: the context structure to read from - * @dest_ctx: the context to be written to - * @ce_info: a description of the struct to be filled + * 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_write_word(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) +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; @@ -4573,17 +4416,14 @@ ice_write_word(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) /* prepare the bits and mask */ shift_width = ce_info->lsb % 8; - mask = BIT(ce_info->width) - 1; + 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 &= mask; - - /* shift to correct alignment */ - mask <<= shift_width; src_word <<= shift_width; + src_word &= mask; /* get the current bits from the target bit string */ dest = dest_ctx + (ce_info->lsb / 8); @@ -4598,13 +4438,13 @@ ice_write_word(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) } /** - * ice_write_dword - write a dword to a packed context structure - * @src_ctx: the context structure to read from - * @dest_ctx: the context to be written to - * @ce_info: a description of the struct to be filled + * 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_write_dword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) +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; @@ -4616,25 +4456,14 @@ ice_write_dword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) /* prepare the bits and mask */ shift_width = ce_info->lsb % 8; - - /* if the field width is exactly 32 on an x86 machine, then the shift - * operation will not work because the SHL instructions count is masked - * to 5 bits so the shift will do nothing - */ - if (ce_info->width < 32) - mask = BIT(ce_info->width) - 1; - else - mask = (u32)~0; + 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 &= mask; - - /* shift to correct alignment */ - mask <<= shift_width; src_dword <<= shift_width; + src_dword &= mask; /* get the current bits from the target bit string */ dest = dest_ctx + (ce_info->lsb / 8); @@ -4649,13 +4478,13 @@ ice_write_dword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) } /** - * ice_write_qword - write a qword to a packed context structure - * @src_ctx: the context structure to read from - * @dest_ctx: the context to be written to - * @ce_info: a description of the struct to be filled + * 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_write_qword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) +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; @@ -4667,25 +4496,14 @@ ice_write_qword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) /* prepare the bits and mask */ shift_width = ce_info->lsb % 8; - - /* if the field width is exactly 64 on an x86 machine, then the shift - * operation will not work because the SHL instructions count is masked - * to 6 bits so the shift will do nothing - */ - if (ce_info->width < 64) - mask = BIT_ULL(ce_info->width) - 1; - else - mask = (u64)~0; + 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 &= mask; - - /* shift to correct alignment */ - mask <<= shift_width; src_qword <<= shift_width; + src_qword &= mask; /* get the current bits from the target bit string */ dest = dest_ctx + (ce_info->lsb / 8); @@ -4704,11 +4522,10 @@ ice_write_qword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) * @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: a description of the structure to be transformed + * @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 ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, + const struct ice_ctx_ele *ce_info) { int f; @@ -4724,16 +4541,16 @@ ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, } switch (ce_info[f].size_of) { case sizeof(u8): - ice_write_byte(src_ctx, dest_ctx, &ce_info[f]); + ice_pack_ctx_byte(src_ctx, dest_ctx, &ce_info[f]); break; case sizeof(u16): - ice_write_word(src_ctx, dest_ctx, &ce_info[f]); + ice_pack_ctx_word(src_ctx, dest_ctx, &ce_info[f]); break; case sizeof(u32): - ice_write_dword(src_ctx, dest_ctx, &ce_info[f]); + ice_pack_ctx_dword(src_ctx, dest_ctx, &ce_info[f]); break; case sizeof(u64): - ice_write_qword(src_ctx, dest_ctx, &ce_info[f]); + ice_pack_ctx_qword(src_ctx, dest_ctx, &ce_info[f]); break; default: return -EINVAL; @@ -4891,7 +4708,7 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, enum ice_disq_rst_src rst_src, u16 vmvf_num, struct ice_sq_cd *cd) { - DEFINE_FLEX(struct ice_aqc_dis_txq_item, qg_list, q_id, 1); + DEFINE_RAW_FLEX(struct ice_aqc_dis_txq_item, qg_list, q_id, 1); u16 i, buf_size = __struct_size(qg_list); struct ice_q_ctx *q_ctx; int status = -ENOENT; @@ -5113,7 +4930,7 @@ int ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, u16 *q_id) { - DEFINE_FLEX(struct ice_aqc_dis_txq_item, qg_list, q_id, 1); + DEFINE_RAW_FLEX(struct ice_aqc_dis_txq_item, qg_list, q_id, 1); u16 qg_size = __struct_size(qg_list); struct ice_hw *hw; int status = 0; @@ -5332,7 +5149,6 @@ ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state, u8 *eec_mode) { struct ice_aqc_get_cgu_dpll_status *cmd; - const s64 nsec_per_psec = 1000LL; struct ice_aq_desc desc; int status; @@ -5348,8 +5164,7 @@ ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state, *phase_offset = le32_to_cpu(cmd->phase_offset_h); *phase_offset <<= 32; *phase_offset += le32_to_cpu(cmd->phase_offset_l); - *phase_offset = div64_s64(sign_extend64(*phase_offset, 47), - nsec_per_psec); + *phase_offset = sign_extend64(*phase_offset, 47); *eec_mode = cmd->eec_mode; } @@ -5541,6 +5356,35 @@ ice_aq_get_phy_rec_clk_out(struct ice_hw *hw, u8 *phy_output, u8 *port_num, } /** + * ice_aq_get_sensor_reading + * @hw: pointer to the HW struct + * @data: pointer to data to be read from the sensor + * + * Get sensor reading (0x0632) + */ +int ice_aq_get_sensor_reading(struct ice_hw *hw, + struct ice_aqc_get_sensor_reading_resp *data) +{ + struct ice_aqc_get_sensor_reading *cmd; + struct ice_aq_desc desc; + int status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_sensor_reading); + cmd = &desc.params.get_sensor_reading; +#define ICE_INTERNAL_TEMP_SENSOR_FORMAT 0 +#define ICE_INTERNAL_TEMP_SENSOR 0 + cmd->sensor = ICE_INTERNAL_TEMP_SENSOR; + cmd->format = ICE_INTERNAL_TEMP_SENSOR_FORMAT; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!status) + memcpy(data, &desc.params.get_sensor_reading_resp, + sizeof(*data)); + + return status; +} + +/** * ice_replay_pre_init - replay pre initialization * @hw: pointer to the HW struct * @@ -5935,7 +5779,7 @@ ice_get_link_default_override(struct ice_link_default_override_tlv *ldo, ice_debug(hw, ICE_DBG_INIT, "Failed to read override link options.\n"); return status; } - ldo->options = buf & ICE_LINK_OVERRIDE_OPT_M; + ldo->options = FIELD_GET(ICE_LINK_OVERRIDE_OPT_M, buf); ldo->phy_config = (buf & ICE_LINK_OVERRIDE_PHY_CFG_M) >> ICE_LINK_OVERRIDE_PHY_CFG_S; diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 31fdcac33986..ffb22c7ce28b 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -6,6 +6,7 @@ #include <linux/bitfield.h> +#include "ice.h" #include "ice_type.h" #include "ice_nvm.h" #include "ice_flex_pipe.h" @@ -52,9 +53,8 @@ int ice_get_caps(struct ice_hw *hw); void ice_set_safe_mode_caps(struct ice_hw *hw); -int -ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, - u32 rxq_index); +int ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, + u32 rxq_index); int ice_aq_get_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *get_params); @@ -71,9 +71,8 @@ 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); +int ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, + const struct ice_ctx_ele *ce_info); extern struct mutex ice_global_cfg_lock_sw; @@ -111,6 +110,7 @@ ice_update_phy_type(u64 *phy_type_low, u64 *phy_type_high, 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 @@ -199,7 +199,6 @@ ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf, struct ice_sq_cd *cd); int ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle); void ice_replay_post(struct ice_hw *hw); -void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf); struct ice_q_ctx * ice_get_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 q_handle); int ice_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in); @@ -241,6 +240,8 @@ ice_aq_set_phy_rec_clk_out(struct ice_hw *hw, u8 phy_output, bool enable, int ice_aq_get_phy_rec_clk_out(struct ice_hw *hw, u8 *phy_output, u8 *port_num, u8 *flags, u16 *node_handle); +int ice_aq_get_sensor_reading(struct ice_hw *hw, + struct ice_aqc_get_sensor_reading_resp *data); void ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); @@ -249,6 +250,7 @@ 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_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); diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index e7d2474c431c..ffe660f34992 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -666,7 +666,7 @@ bool ice_is_sbq_supported(struct ice_hw *hw) /* The device sideband queue is only supported on devices with the * generic MAC type. */ - return hw->mac_type == ICE_MAC_GENERIC; + return ice_is_generic_mac(hw); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index 396e555023aa..74418c445cc4 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -35,8 +35,7 @@ ice_aq_get_lldp_mib(struct ice_hw *hw, u8 bridge_type, u8 mib_type, void *buf, ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_get_mib); cmd->type = mib_type & ICE_AQ_LLDP_MIB_TYPE_M; - cmd->type |= (bridge_type << ICE_AQ_LLDP_BRID_TYPE_S) & - ICE_AQ_LLDP_BRID_TYPE_M; + cmd->type |= FIELD_PREP(ICE_AQ_LLDP_BRID_TYPE_M, bridge_type); desc.datalen = cpu_to_le16(buf_size); @@ -147,8 +146,7 @@ static u8 ice_get_dcbx_status(struct ice_hw *hw) u32 reg; reg = rd32(hw, PRTDCB_GENS); - return (u8)((reg & PRTDCB_GENS_DCBX_STATUS_M) >> - PRTDCB_GENS_DCBX_STATUS_S); + return FIELD_GET(PRTDCB_GENS_DCBX_STATUS_M, reg); } /** @@ -174,11 +172,9 @@ ice_parse_ieee_ets_common_tlv(u8 *buf, struct ice_dcb_ets_cfg *ets_cfg) */ for (i = 0; i < 4; i++) { ets_cfg->prio_table[i * 2] = - ((buf[offset] & ICE_IEEE_ETS_PRIO_1_M) >> - ICE_IEEE_ETS_PRIO_1_S); + FIELD_GET(ICE_IEEE_ETS_PRIO_1_M, buf[offset]); ets_cfg->prio_table[i * 2 + 1] = - ((buf[offset] & ICE_IEEE_ETS_PRIO_0_M) >> - ICE_IEEE_ETS_PRIO_0_S); + FIELD_GET(ICE_IEEE_ETS_PRIO_0_M, buf[offset]); offset++; } @@ -222,11 +218,9 @@ ice_parse_ieee_etscfg_tlv(struct ice_lldp_org_tlv *tlv, * |1bit | 1bit|3 bits|3bits| */ etscfg = &dcbcfg->etscfg; - etscfg->willing = ((buf[0] & ICE_IEEE_ETS_WILLING_M) >> - ICE_IEEE_ETS_WILLING_S); - etscfg->cbs = ((buf[0] & ICE_IEEE_ETS_CBS_M) >> ICE_IEEE_ETS_CBS_S); - etscfg->maxtcs = ((buf[0] & ICE_IEEE_ETS_MAXTC_M) >> - ICE_IEEE_ETS_MAXTC_S); + etscfg->willing = FIELD_GET(ICE_IEEE_ETS_WILLING_M, buf[0]); + etscfg->cbs = FIELD_GET(ICE_IEEE_ETS_CBS_M, buf[0]); + etscfg->maxtcs = FIELD_GET(ICE_IEEE_ETS_MAXTC_M, buf[0]); /* Begin parsing at Priority Assignment Table (offset 1 in buf) */ ice_parse_ieee_ets_common_tlv(&buf[1], etscfg); @@ -268,11 +262,9 @@ ice_parse_ieee_pfccfg_tlv(struct ice_lldp_org_tlv *tlv, * ----------------------------------------- * |1bit | 1bit|2 bits|4bits| 1 octet | */ - dcbcfg->pfc.willing = ((buf[0] & ICE_IEEE_PFC_WILLING_M) >> - ICE_IEEE_PFC_WILLING_S); - dcbcfg->pfc.mbc = ((buf[0] & ICE_IEEE_PFC_MBC_M) >> ICE_IEEE_PFC_MBC_S); - dcbcfg->pfc.pfccap = ((buf[0] & ICE_IEEE_PFC_CAP_M) >> - ICE_IEEE_PFC_CAP_S); + dcbcfg->pfc.willing = FIELD_GET(ICE_IEEE_PFC_WILLING_M, buf[0]); + dcbcfg->pfc.mbc = FIELD_GET(ICE_IEEE_PFC_MBC_M, buf[0]); + dcbcfg->pfc.pfccap = FIELD_GET(ICE_IEEE_PFC_CAP_M, buf[0]); dcbcfg->pfc.pfcena = buf[1]; } @@ -294,7 +286,7 @@ ice_parse_ieee_app_tlv(struct ice_lldp_org_tlv *tlv, u8 *buf; typelen = ntohs(tlv->typelen); - len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S); + len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); buf = tlv->tlvinfo; /* Removing sizeof(ouisubtype) and reserved byte from len. @@ -314,12 +306,10 @@ ice_parse_ieee_app_tlv(struct ice_lldp_org_tlv *tlv, * ----------------------------------------- */ while (offset < len) { - dcbcfg->app[i].priority = ((buf[offset] & - ICE_IEEE_APP_PRIO_M) >> - ICE_IEEE_APP_PRIO_S); - dcbcfg->app[i].selector = ((buf[offset] & - ICE_IEEE_APP_SEL_M) >> - ICE_IEEE_APP_SEL_S); + dcbcfg->app[i].priority = FIELD_GET(ICE_IEEE_APP_PRIO_M, + buf[offset]); + dcbcfg->app[i].selector = FIELD_GET(ICE_IEEE_APP_SEL_M, + buf[offset]); dcbcfg->app[i].prot_id = (buf[offset + 1] << 0x8) | buf[offset + 2]; /* Move to next app */ @@ -347,8 +337,7 @@ ice_parse_ieee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) u8 subtype; ouisubtype = ntohl(tlv->ouisubtype); - subtype = (u8)((ouisubtype & ICE_LLDP_TLV_SUBTYPE_M) >> - ICE_LLDP_TLV_SUBTYPE_S); + subtype = FIELD_GET(ICE_LLDP_TLV_SUBTYPE_M, ouisubtype); switch (subtype) { case ICE_IEEE_SUBTYPE_ETS_CFG: ice_parse_ieee_etscfg_tlv(tlv, dcbcfg); @@ -399,11 +388,9 @@ ice_parse_cee_pgcfg_tlv(struct ice_cee_feat_tlv *tlv, */ for (i = 0; i < 4; i++) { etscfg->prio_table[i * 2] = - ((buf[offset] & ICE_CEE_PGID_PRIO_1_M) >> - ICE_CEE_PGID_PRIO_1_S); + FIELD_GET(ICE_CEE_PGID_PRIO_1_M, buf[offset]); etscfg->prio_table[i * 2 + 1] = - ((buf[offset] & ICE_CEE_PGID_PRIO_0_M) >> - ICE_CEE_PGID_PRIO_0_S); + FIELD_GET(ICE_CEE_PGID_PRIO_0_M, buf[offset]); offset++; } @@ -466,7 +453,7 @@ ice_parse_cee_app_tlv(struct ice_cee_feat_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) u8 i; typelen = ntohs(tlv->hdr.typelen); - len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S); + len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); dcbcfg->numapps = len / sizeof(*app); if (!dcbcfg->numapps) @@ -521,14 +508,13 @@ ice_parse_cee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) u32 ouisubtype; ouisubtype = ntohl(tlv->ouisubtype); - subtype = (u8)((ouisubtype & ICE_LLDP_TLV_SUBTYPE_M) >> - ICE_LLDP_TLV_SUBTYPE_S); + subtype = FIELD_GET(ICE_LLDP_TLV_SUBTYPE_M, ouisubtype); /* Return if not CEE DCBX */ if (subtype != ICE_CEE_DCBX_TYPE) return; typelen = ntohs(tlv->typelen); - tlvlen = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S); + tlvlen = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); len = sizeof(tlv->typelen) + sizeof(ouisubtype) + sizeof(struct ice_cee_ctrl_tlv); /* Return if no CEE DCBX Feature TLVs */ @@ -540,9 +526,8 @@ ice_parse_cee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) u16 sublen; typelen = ntohs(sub_tlv->hdr.typelen); - sublen = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S); - subtype = (u8)((typelen & ICE_LLDP_TLV_TYPE_M) >> - ICE_LLDP_TLV_TYPE_S); + sublen = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); + subtype = FIELD_GET(ICE_LLDP_TLV_TYPE_M, typelen); switch (subtype) { case ICE_CEE_SUBTYPE_PG_CFG: ice_parse_cee_pgcfg_tlv(sub_tlv, dcbcfg); @@ -579,7 +564,7 @@ ice_parse_org_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) u32 oui; ouisubtype = ntohl(tlv->ouisubtype); - oui = ((ouisubtype & ICE_LLDP_TLV_OUI_M) >> ICE_LLDP_TLV_OUI_S); + oui = FIELD_GET(ICE_LLDP_TLV_OUI_M, ouisubtype); switch (oui) { case ICE_IEEE_8021QAZ_OUI: ice_parse_ieee_tlv(tlv, dcbcfg); @@ -616,8 +601,8 @@ static int ice_lldp_to_dcb_cfg(u8 *lldpmib, struct ice_dcbx_cfg *dcbcfg) tlv = (struct ice_lldp_org_tlv *)lldpmib; while (1) { typelen = ntohs(tlv->typelen); - type = ((typelen & ICE_LLDP_TLV_TYPE_M) >> ICE_LLDP_TLV_TYPE_S); - len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S); + type = FIELD_GET(ICE_LLDP_TLV_TYPE_M, typelen); + len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); offset += sizeof(typelen) + len; /* END TLV or beyond LLDPDU size */ @@ -806,11 +791,11 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg, */ for (i = 0; i < ICE_MAX_TRAFFIC_CLASS / 2; i++) { dcbcfg->etscfg.prio_table[i * 2] = - ((cee_cfg->oper_prio_tc[i] & ICE_CEE_PGID_PRIO_0_M) >> - ICE_CEE_PGID_PRIO_0_S); + FIELD_GET(ICE_CEE_PGID_PRIO_0_M, + cee_cfg->oper_prio_tc[i]); dcbcfg->etscfg.prio_table[i * 2 + 1] = - ((cee_cfg->oper_prio_tc[i] & ICE_CEE_PGID_PRIO_1_M) >> - ICE_CEE_PGID_PRIO_1_S); + FIELD_GET(ICE_CEE_PGID_PRIO_1_M, + cee_cfg->oper_prio_tc[i]); } ice_for_each_traffic_class(i) { @@ -982,7 +967,7 @@ void ice_get_dcb_cfg_from_mib_change(struct ice_port_info *pi, mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw; - change_type = FIELD_GET(ICE_AQ_LLDP_MIB_TYPE_M, mib->type); + change_type = FIELD_GET(ICE_AQ_LLDP_MIB_TYPE_M, mib->type); if (change_type == ICE_AQ_LLDP_MIB_REMOTE) dcbx_cfg = &pi->qos_cfg.remote_dcbx_cfg; @@ -1483,7 +1468,7 @@ ice_dcb_cfg_to_lldp(u8 *lldpmib, u16 *miblen, struct ice_dcbx_cfg *dcbcfg) while (1) { ice_add_dcb_tlv(tlv, dcbcfg, tlvid++); typelen = ntohs(tlv->typelen); - len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S; + len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); if (len) offset += len + 2; /* END TLV or beyond LLDPDU size */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 850db8e0e6b0..a94e7072b570 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -3,7 +3,7 @@ #include "ice_dcb_lib.h" #include "ice_dcb_nl.h" -#include "ice_devlink.h" +#include "devlink/devlink.h" /** * ice_dcb_get_ena_tc - return bitmap of enabled TCs @@ -291,7 +291,6 @@ static void ice_dcb_ena_dis_vsi(struct ice_pf *pf, bool ena, bool locked) switch (vsi->type) { case ICE_VSI_CHNL: - case ICE_VSI_SWITCHDEV_CTRL: case ICE_VSI_PF: if (ena) ice_ena_vsi(vsi, locked); @@ -776,8 +775,7 @@ void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked) /* no need to proceed with remaining cfg if it is CHNL * or switchdev VSI */ - if (vsi->type == ICE_VSI_CHNL || - vsi->type == ICE_VSI_SWITCHDEV_CTRL) + if (vsi->type == ICE_VSI_CHNL) continue; ice_vsi_map_rings_to_vectors(vsi); @@ -934,7 +932,7 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, skb->priority != TC_PRIO_CONTROL) { first->vid &= ~VLAN_PRIO_MASK; /* Mask the lower 3 bits to set the 802.1p priority */ - first->vid |= (skb->priority << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK; + first->vid |= FIELD_PREP(VLAN_PRIO_MASK, skb->priority); /* if this is not already set it means a VLAN 0 + priority needs * to be offloaded */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index e1fbc6de452d..6d50b90a7359 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -227,7 +227,7 @@ static void ice_get_pfc_delay(struct ice_hw *hw, u16 *delay) u32 val; val = rd32(hw, PRTDCB_GENC); - *delay = (u16)((val & PRTDCB_GENC_PFCLDA_M) >> PRTDCB_GENC_PFCLDA_S); + *delay = FIELD_GET(PRTDCB_GENC_PFCLDA_M, val); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index cfb1580f5850..ce5034ed2b24 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -4,6 +4,7 @@ #include "ice_common.h" #include "ice.h" #include "ice_ddp.h" +#include "ice_sched.h" /* For supporting double VLAN mode, it is necessary to enable or disable certain * boost tcam entries. The metadata labels names that match the following @@ -721,6 +722,12 @@ static bool ice_is_gtp_c_profile(u16 prof_idx) } } +static bool ice_is_pfcp_profile(u16 prof_idx) +{ + return prof_idx >= ICE_PROFID_IPV4_PFCP_NODE && + prof_idx <= ICE_PROFID_IPV6_PFCP_SESSION; +} + /** * ice_get_sw_prof_type - determine switch profile type * @hw: pointer to the HW structure @@ -738,6 +745,9 @@ static enum ice_prof_type ice_get_sw_prof_type(struct ice_hw *hw, if (ice_is_gtp_u_profile(prof_idx)) return ICE_PROF_TUN_GTPU; + if (ice_is_pfcp_profile(prof_idx)) + return ICE_PROF_TUN_PFCP; + for (i = 0; i < hw->blk[ICE_BLK_SW].es.fvw; i++) { /* UDP tunnel will have UDP_OF protocol ID and VNI offset */ if (fv->ew[i].prot_id == (u8)ICE_PROT_UDP_OF && @@ -1424,14 +1434,14 @@ ice_dwnld_sign_and_cfg_segs(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr, goto exit; } - conf_idx = le32_to_cpu(seg->signed_seg_idx); - start = le32_to_cpu(seg->signed_buf_start); count = le32_to_cpu(seg->signed_buf_count); - state = ice_download_pkg_sig_seg(hw, seg); - if (state) + if (state || !count) goto exit; + conf_idx = le32_to_cpu(seg->signed_seg_idx); + start = le32_to_cpu(seg->signed_buf_start); + state = ice_download_pkg_config_seg(hw, pkg_hdr, conf_idx, start, count); @@ -1479,14 +1489,14 @@ ice_post_dwnld_pkg_actions(struct ice_hw *hw) } /** - * ice_download_pkg + * ice_download_pkg_with_sig_seg * @hw: pointer to the hardware structure * @pkg_hdr: pointer to package header * * Handles the download of a complete package. */ static enum ice_ddp_state -ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) +ice_download_pkg_with_sig_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) { enum ice_aq_err aq_err = hw->adminq.sq_last_status; enum ice_ddp_state state = ICE_DDP_PKG_ERR; @@ -1519,6 +1529,103 @@ ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) state = ice_post_dwnld_pkg_actions(hw); ice_release_global_cfg_lock(hw); + + return state; +} + +/** + * ice_dwnld_cfg_bufs + * @hw: pointer to the hardware structure + * @bufs: pointer to an array of buffers + * @count: the number of buffers in the array + * + * Obtains global config lock and downloads the package configuration buffers + * to the firmware. + */ +static enum ice_ddp_state +ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) +{ + enum ice_ddp_state state; + struct ice_buf_hdr *bh; + int status; + + if (!bufs || !count) + return ICE_DDP_PKG_ERR; + + /* If the first buffer's first section has its metadata bit set + * then there are no buffers to be downloaded, and the operation is + * considered a success. + */ + bh = (struct ice_buf_hdr *)bufs; + if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF) + return ICE_DDP_PKG_SUCCESS; + + status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE); + if (status) { + if (status == -EALREADY) + return ICE_DDP_PKG_ALREADY_LOADED; + return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status); + } + + state = ice_dwnld_cfg_bufs_no_lock(hw, bufs, 0, count, true); + if (!state) + state = ice_post_dwnld_pkg_actions(hw); + + ice_release_global_cfg_lock(hw); + + return state; +} + +/** + * ice_download_pkg_without_sig_seg + * @hw: pointer to the hardware structure + * @ice_seg: pointer to the segment of the package to be downloaded + * + * Handles the download of a complete package without signature segment. + */ +static enum ice_ddp_state +ice_download_pkg_without_sig_seg(struct ice_hw *hw, struct ice_seg *ice_seg) +{ + struct ice_buf_table *ice_buf_tbl; + + ice_debug(hw, ICE_DBG_PKG, "Segment format version: %d.%d.%d.%d\n", + ice_seg->hdr.seg_format_ver.major, + ice_seg->hdr.seg_format_ver.minor, + ice_seg->hdr.seg_format_ver.update, + ice_seg->hdr.seg_format_ver.draft); + + ice_debug(hw, ICE_DBG_PKG, "Seg: type 0x%X, size %d, name %s\n", + le32_to_cpu(ice_seg->hdr.seg_type), + le32_to_cpu(ice_seg->hdr.seg_size), ice_seg->hdr.seg_id); + + ice_buf_tbl = ice_find_buf_table(ice_seg); + + ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n", + le32_to_cpu(ice_buf_tbl->buf_count)); + + return ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array, + le32_to_cpu(ice_buf_tbl->buf_count)); +} + +/** + * ice_download_pkg + * @hw: pointer to the hardware structure + * @pkg_hdr: pointer to package header + * @ice_seg: pointer to the segment of the package to be downloaded + * + * Handles the download of a complete package. + */ +static enum ice_ddp_state +ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr, + struct ice_seg *ice_seg) +{ + enum ice_ddp_state state; + + if (hw->pkg_has_signing_seg) + state = ice_download_pkg_with_sig_seg(hw, pkg_hdr); + else + state = ice_download_pkg_without_sig_seg(hw, ice_seg); + ice_post_pkg_dwnld_vlan_mode_cfg(hw); return state; @@ -1728,6 +1835,7 @@ static u32 ice_get_pkg_segment_id(enum ice_mac_type mac_type) seg_id = SEGMENT_TYPE_ICE_E830; break; case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: default: seg_id = SEGMENT_TYPE_ICE_E810; break; @@ -1748,6 +1856,9 @@ static u32 ice_get_pkg_sign_type(enum ice_mac_type mac_type) case ICE_MAC_E830: sign_type = SEGMENT_SIGN_TYPE_RSA3K_SBB; break; + case ICE_MAC_GENERIC_3K_E825: + sign_type = SEGMENT_SIGN_TYPE_RSA3K_E825; + break; case ICE_MAC_GENERIC: default: sign_type = SEGMENT_SIGN_TYPE_RSA2K; @@ -1837,8 +1948,8 @@ static enum ice_ddp_state ice_init_pkg_info(struct ice_hw *hw, */ static enum ice_ddp_state ice_get_pkg_info(struct ice_hw *hw) { - DEFINE_FLEX(struct ice_aqc_get_pkg_info_resp, pkg_info, pkg_info, - ICE_PKG_CNT); + DEFINE_RAW_FLEX(struct ice_aqc_get_pkg_info_resp, pkg_info, pkg_info, + ICE_PKG_CNT); u16 size = __struct_size(pkg_info); u32 i; @@ -1889,8 +2000,8 @@ static enum ice_ddp_state ice_chk_pkg_compat(struct ice_hw *hw, struct ice_pkg_hdr *ospkg, struct ice_seg **seg) { - DEFINE_FLEX(struct ice_aqc_get_pkg_info_resp, pkg, pkg_info, - ICE_PKG_CNT); + DEFINE_RAW_FLEX(struct ice_aqc_get_pkg_info_resp, pkg, pkg_info, + ICE_PKG_CNT); u16 size = __struct_size(pkg); enum ice_ddp_state state; u32 i; @@ -2083,7 +2194,7 @@ enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) /* initialize package hints and then download package */ ice_init_pkg_hints(hw, seg); - state = ice_download_pkg(hw, pkg); + state = ice_download_pkg(hw, pkg, seg); if (state == ICE_DDP_PKG_ALREADY_LOADED) { ice_debug(hw, ICE_DBG_INIT, "package previously loaded - no work.\n"); @@ -2162,3 +2273,211 @@ enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, return state; } + +/** + * ice_get_set_tx_topo - get or set Tx topology + * @hw: pointer to the HW struct + * @buf: pointer to Tx topology buffer + * @buf_size: buffer size + * @cd: pointer to command details structure or NULL + * @flags: pointer to descriptor flags + * @set: 0-get, 1-set topology + * + * The function will get or set Tx topology + * + * Return: zero when set was successful, negative values otherwise. + */ +static int +ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size, + struct ice_sq_cd *cd, u8 *flags, bool set) +{ + struct ice_aqc_get_set_tx_topo *cmd; + struct ice_aq_desc desc; + int status; + + cmd = &desc.params.get_set_tx_topo; + if (set) { + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_tx_topo); + cmd->set_flags = ICE_AQC_TX_TOPO_FLAGS_ISSUED; + /* requested to update a new topology, not a default topology */ + if (buf) + 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); + } 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); + + status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); + if (status) + return status; + /* read the return flag values (first byte) for get operation */ + if (!set && flags) + *flags = desc.params.get_set_tx_topo.set_flags; + + return 0; +} + +/** + * ice_cfg_tx_topo - Initialize new Tx topology if available + * @hw: pointer to the HW struct + * @buf: pointer to Tx topology buffer + * @len: buffer size + * + * The function will apply the new Tx topology from the package buffer + * if available. + * + * Return: zero when update was successful, negative values otherwise. + */ +int ice_cfg_tx_topo(struct ice_hw *hw, u8 *buf, u32 len) +{ + u8 *current_topo, *new_topo = NULL; + struct ice_run_time_cfg_seg *seg; + struct ice_buf_hdr *section; + struct ice_pkg_hdr *pkg_hdr; + enum ice_ddp_state state; + u16 offset, size = 0; + u32 reg = 0; + int status; + u8 flags; + + if (!buf || !len) + return -EINVAL; + + /* Does FW support new Tx topology mode ? */ + if (!hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) { + ice_debug(hw, ICE_DBG_INIT, "FW doesn't support compatibility mode\n"); + return -EOPNOTSUPP; + } + + current_topo = kzalloc(ICE_AQ_MAX_BUF_LEN, GFP_KERNEL); + if (!current_topo) + return -ENOMEM; + + /* Get the current Tx topology */ + status = ice_get_set_tx_topo(hw, current_topo, ICE_AQ_MAX_BUF_LEN, NULL, + &flags, false); + + kfree(current_topo); + + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Get current topology is failed\n"); + return status; + } + + /* Is default topology already applied ? */ + if (!(flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) && + hw->num_tx_sched_layers == ICE_SCHED_9_LAYERS) { + ice_debug(hw, ICE_DBG_INIT, "Default topology already applied\n"); + return -EEXIST; + } + + /* Is new topology already applied ? */ + if ((flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) && + hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS) { + ice_debug(hw, ICE_DBG_INIT, "New topology already applied\n"); + return -EEXIST; + } + + /* Setting topology already issued? */ + if (flags & ICE_AQC_TX_TOPO_FLAGS_ISSUED) { + ice_debug(hw, ICE_DBG_INIT, "Update Tx topology was done by another PF\n"); + /* Add a small delay before exiting */ + msleep(2000); + return -EEXIST; + } + + /* Change the topology from new to default (5 to 9) */ + if (!(flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) && + hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS) { + ice_debug(hw, ICE_DBG_INIT, "Change topology from 5 to 9 layers\n"); + goto update_topo; + } + + pkg_hdr = (struct ice_pkg_hdr *)buf; + state = ice_verify_pkg(pkg_hdr, len); + if (state) { + ice_debug(hw, ICE_DBG_INIT, "Failed to verify pkg (err: %d)\n", + state); + return -EIO; + } + + /* Find runtime configuration segment */ + seg = (struct ice_run_time_cfg_seg *) + ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE_RUN_TIME_CFG, pkg_hdr); + if (!seg) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology segment is missing\n"); + return -EIO; + } + + if (le32_to_cpu(seg->buf_table.buf_count) < ICE_MIN_S_COUNT) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology segment count(%d) is wrong\n", + seg->buf_table.buf_count); + return -EIO; + } + + section = ice_pkg_val_buf(seg->buf_table.buf_array); + if (!section || le32_to_cpu(section->section_entry[0].type) != + ICE_SID_TX_5_LAYER_TOPO) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology section type is wrong\n"); + return -EIO; + } + + size = le16_to_cpu(section->section_entry[0].size); + offset = le16_to_cpu(section->section_entry[0].offset); + if (size < ICE_MIN_S_SZ || size > ICE_MAX_S_SZ) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology section size is wrong\n"); + return -EIO; + } + + /* Make sure the section fits in the buffer */ + if (offset + size > ICE_PKG_BUF_SIZE) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology buffer > 4K\n"); + return -EIO; + } + + /* Get the new topology buffer */ + new_topo = ((u8 *)section) + offset; + +update_topo: + /* Acquire global lock to make sure that set topology issued + * by one PF. + */ + status = ice_acquire_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID, ICE_RES_WRITE, + ICE_GLOBAL_CFG_LOCK_TIMEOUT); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to acquire global lock\n"); + return status; + } + + /* Check if reset was triggered already. */ + reg = rd32(hw, GLGEN_RSTAT); + if (reg & GLGEN_RSTAT_DEVSTATE_M) { + /* Reset is in progress, re-init the HW again */ + ice_debug(hw, ICE_DBG_INIT, "Reset is in progress. Layer topology might be applied already\n"); + ice_check_reset(hw); + return 0; + } + + /* Set new topology */ + status = ice_get_set_tx_topo(hw, new_topo, size, NULL, NULL, true); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed setting Tx topology\n"); + return status; + } + + /* New topology is updated, delay 1 second before issuing the CORER */ + msleep(1000); + ice_reset(hw, ICE_RESET_CORER); + /* CORER will clear the global lock, so no explicit call + * required for release. + */ + + return 0; +} diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.h b/drivers/net/ethernet/intel/ice/ice_ddp.h index ff66c2ffb1a2..622543f08b43 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.h +++ b/drivers/net/ethernet/intel/ice/ice_ddp.h @@ -454,4 +454,6 @@ u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld); void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, u32 sect_type); +int ice_cfg_tx_topo(struct ice_hw *hw, u8 *buf, u32 len); + #endif diff --git a/drivers/net/ethernet/intel/ice/ice_debugfs.c b/drivers/net/ethernet/intel/ice/ice_debugfs.c new file mode 100644 index 000000000000..9fc0fd95a13d --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_debugfs.c @@ -0,0 +1,674 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022, Intel Corporation. */ + +#include <linux/fs.h> +#include <linux/debugfs.h> +#include <linux/random.h> +#include <linux/vmalloc.h> +#include "ice.h" + +static struct dentry *ice_debugfs_root; + +/* create a define that has an extra module that doesn't really exist. this + * is so we can add a module 'all' to easily enable/disable all the modules + */ +#define ICE_NR_FW_LOG_MODULES (ICE_AQC_FW_LOG_ID_MAX + 1) + +/* the ordering in this array is important. it matches the ordering of the + * values in the FW so the index is the same value as in ice_aqc_fw_logging_mod + */ +static const char * const ice_fwlog_module_string[] = { + "general", + "ctrl", + "link", + "link_topo", + "dnl", + "i2c", + "sdp", + "mdio", + "adminq", + "hdma", + "lldp", + "dcbx", + "dcb", + "xlr", + "nvm", + "auth", + "vpd", + "iosf", + "parser", + "sw", + "scheduler", + "txq", + "rsvd", + "post", + "watchdog", + "task_dispatch", + "mng", + "synce", + "health", + "tsdrv", + "pfreg", + "mdlver", + "all", +}; + +/* the ordering in this array is important. it matches the ordering of the + * values in the FW so the index is the same value as in ice_fwlog_level + */ +static const char * const ice_fwlog_level_string[] = { + "none", + "error", + "warning", + "normal", + "verbose", +}; + +static const char * const ice_fwlog_log_size[] = { + "128K", + "256K", + "512K", + "1M", + "2M", +}; + +/** + * ice_fwlog_print_module_cfg - print current FW logging module configuration + * @hw: pointer to the HW structure + * @module: module to print + * @s: the seq file to put data into + */ +static void +ice_fwlog_print_module_cfg(struct ice_hw *hw, int module, struct seq_file *s) +{ + struct ice_fwlog_cfg *cfg = &hw->fwlog_cfg; + struct ice_fwlog_module_entry *entry; + + if (module != ICE_AQC_FW_LOG_ID_MAX) { + entry = &cfg->module_entries[module]; + + seq_printf(s, "\tModule: %s, Log Level: %s\n", + ice_fwlog_module_string[entry->module_id], + ice_fwlog_level_string[entry->log_level]); + } else { + int i; + + for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) { + entry = &cfg->module_entries[i]; + + seq_printf(s, "\tModule: %s, Log Level: %s\n", + ice_fwlog_module_string[entry->module_id], + ice_fwlog_level_string[entry->log_level]); + } + } +} + +static int ice_find_module_by_dentry(struct ice_pf *pf, struct dentry *d) +{ + int i, module; + + module = -1; + /* find the module based on the dentry */ + for (i = 0; i < ICE_NR_FW_LOG_MODULES; i++) { + if (d == pf->ice_debugfs_pf_fwlog_modules[i]) { + module = i; + break; + } + } + + return module; +} + +/** + * ice_debugfs_module_show - read from 'module' file + * @s: the opened file + * @v: pointer to the offset + */ +static int ice_debugfs_module_show(struct seq_file *s, void *v) +{ + const struct file *filp = s->file; + struct dentry *dentry; + struct ice_pf *pf; + int module; + + dentry = file_dentry(filp); + pf = s->private; + + module = ice_find_module_by_dentry(pf, dentry); + if (module < 0) { + dev_info(ice_pf_to_dev(pf), "unknown module\n"); + return -EINVAL; + } + + ice_fwlog_print_module_cfg(&pf->hw, module, s); + + return 0; +} + +static int ice_debugfs_module_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, ice_debugfs_module_show, inode->i_private); +} + +/** + * ice_debugfs_module_write - write into 'module' file + * @filp: the opened file + * @buf: where to find the user's data + * @count: the length of the user's data + * @ppos: file position offset + */ +static ssize_t +ice_debugfs_module_write(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct ice_pf *pf = file_inode(filp)->i_private; + struct dentry *dentry = file_dentry(filp); + struct device *dev = ice_pf_to_dev(pf); + char user_val[16], *cmd_buf; + int module, log_level, cnt; + + /* don't allow partial writes or invalid input */ + if (*ppos != 0 || count > 8) + return -EINVAL; + + cmd_buf = memdup_user_nul(buf, count); + if (IS_ERR(cmd_buf)) + return PTR_ERR(cmd_buf); + + module = ice_find_module_by_dentry(pf, dentry); + if (module < 0) { + dev_info(dev, "unknown module\n"); + return -EINVAL; + } + + cnt = sscanf(cmd_buf, "%s", user_val); + if (cnt != 1) + return -EINVAL; + + log_level = sysfs_match_string(ice_fwlog_level_string, user_val); + if (log_level < 0) { + dev_info(dev, "unknown log level '%s'\n", user_val); + return -EINVAL; + } + + if (module != ICE_AQC_FW_LOG_ID_MAX) { + ice_pf_fwlog_update_module(pf, log_level, module); + } else { + /* the module 'all' is a shortcut so that we can set + * all of the modules to the same level quickly + */ + int i; + + for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) + ice_pf_fwlog_update_module(pf, log_level, i); + } + + return count; +} + +static const struct file_operations ice_debugfs_module_fops = { + .owner = THIS_MODULE, + .open = ice_debugfs_module_open, + .read = seq_read, + .release = single_release, + .write = ice_debugfs_module_write, +}; + +/** + * ice_debugfs_nr_messages_read - read from 'nr_messages' file + * @filp: the opened file + * @buffer: where to write the data for the user to read + * @count: the size of the user's buffer + * @ppos: file position offset + */ +static ssize_t ice_debugfs_nr_messages_read(struct file *filp, + char __user *buffer, size_t count, + loff_t *ppos) +{ + struct ice_pf *pf = filp->private_data; + struct ice_hw *hw = &pf->hw; + char buff[32] = {}; + + snprintf(buff, sizeof(buff), "%d\n", + hw->fwlog_cfg.log_resolution); + + return simple_read_from_buffer(buffer, count, ppos, buff, strlen(buff)); +} + +/** + * ice_debugfs_nr_messages_write - write into 'nr_messages' file + * @filp: the opened file + * @buf: where to find the user's data + * @count: the length of the user's data + * @ppos: file position offset + */ +static ssize_t +ice_debugfs_nr_messages_write(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct ice_pf *pf = filp->private_data; + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + char user_val[8], *cmd_buf; + s16 nr_messages; + ssize_t ret; + + /* don't allow partial writes or invalid input */ + if (*ppos != 0 || count > 4) + return -EINVAL; + + cmd_buf = memdup_user_nul(buf, count); + if (IS_ERR(cmd_buf)) + return PTR_ERR(cmd_buf); + + ret = sscanf(cmd_buf, "%s", user_val); + if (ret != 1) + return -EINVAL; + + ret = kstrtos16(user_val, 0, &nr_messages); + if (ret) + return ret; + + if (nr_messages < ICE_AQC_FW_LOG_MIN_RESOLUTION || + nr_messages > ICE_AQC_FW_LOG_MAX_RESOLUTION) { + dev_err(dev, "Invalid FW log number of messages %d, value must be between %d - %d\n", + nr_messages, ICE_AQC_FW_LOG_MIN_RESOLUTION, + ICE_AQC_FW_LOG_MAX_RESOLUTION); + return -EINVAL; + } + + hw->fwlog_cfg.log_resolution = nr_messages; + + return count; +} + +static const struct file_operations ice_debugfs_nr_messages_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = ice_debugfs_nr_messages_read, + .write = ice_debugfs_nr_messages_write, +}; + +/** + * ice_debugfs_enable_read - read from 'enable' file + * @filp: the opened file + * @buffer: where to write the data for the user to read + * @count: the size of the user's buffer + * @ppos: file position offset + */ +static ssize_t ice_debugfs_enable_read(struct file *filp, + char __user *buffer, size_t count, + loff_t *ppos) +{ + struct ice_pf *pf = filp->private_data; + struct ice_hw *hw = &pf->hw; + char buff[32] = {}; + + snprintf(buff, sizeof(buff), "%u\n", + (u16)(hw->fwlog_cfg.options & + ICE_FWLOG_OPTION_IS_REGISTERED) >> 3); + + return simple_read_from_buffer(buffer, count, ppos, buff, strlen(buff)); +} + +/** + * ice_debugfs_enable_write - write into 'enable' file + * @filp: the opened file + * @buf: where to find the user's data + * @count: the length of the user's data + * @ppos: file position offset + */ +static ssize_t +ice_debugfs_enable_write(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct ice_pf *pf = filp->private_data; + struct ice_hw *hw = &pf->hw; + char user_val[8], *cmd_buf; + bool enable; + ssize_t ret; + + /* don't allow partial writes or invalid input */ + if (*ppos != 0 || count > 2) + return -EINVAL; + + cmd_buf = memdup_user_nul(buf, count); + if (IS_ERR(cmd_buf)) + return PTR_ERR(cmd_buf); + + ret = sscanf(cmd_buf, "%s", user_val); + if (ret != 1) + return -EINVAL; + + ret = kstrtobool(user_val, &enable); + if (ret) + goto enable_write_error; + + if (enable) + hw->fwlog_cfg.options |= ICE_FWLOG_OPTION_ARQ_ENA; + else + hw->fwlog_cfg.options &= ~ICE_FWLOG_OPTION_ARQ_ENA; + + ret = ice_fwlog_set(hw, &hw->fwlog_cfg); + if (ret) + goto enable_write_error; + + if (enable) + ret = ice_fwlog_register(hw); + else + ret = ice_fwlog_unregister(hw); + + if (ret) + goto enable_write_error; + + /* if we get here, nothing went wrong; return count since we didn't + * really write anything + */ + ret = (ssize_t)count; + +enable_write_error: + /* This function always consumes all of the written input, or produces + * an error. Check and enforce this. Otherwise, the write operation + * won't complete properly. + */ + if (WARN_ON(ret != (ssize_t)count && ret >= 0)) + ret = -EIO; + + return ret; +} + +static const struct file_operations ice_debugfs_enable_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = ice_debugfs_enable_read, + .write = ice_debugfs_enable_write, +}; + +/** + * ice_debugfs_log_size_read - read from 'log_size' file + * @filp: the opened file + * @buffer: where to write the data for the user to read + * @count: the size of the user's buffer + * @ppos: file position offset + */ +static ssize_t ice_debugfs_log_size_read(struct file *filp, + char __user *buffer, size_t count, + loff_t *ppos) +{ + struct ice_pf *pf = filp->private_data; + struct ice_hw *hw = &pf->hw; + char buff[32] = {}; + int index; + + index = hw->fwlog_ring.index; + snprintf(buff, sizeof(buff), "%s\n", ice_fwlog_log_size[index]); + + return simple_read_from_buffer(buffer, count, ppos, buff, strlen(buff)); +} + +/** + * ice_debugfs_log_size_write - write into 'log_size' file + * @filp: the opened file + * @buf: where to find the user's data + * @count: the length of the user's data + * @ppos: file position offset + */ +static ssize_t +ice_debugfs_log_size_write(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct ice_pf *pf = filp->private_data; + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + char user_val[8], *cmd_buf; + ssize_t ret; + int index; + + /* don't allow partial writes or invalid input */ + if (*ppos != 0 || count > 5) + return -EINVAL; + + cmd_buf = memdup_user_nul(buf, count); + if (IS_ERR(cmd_buf)) + return PTR_ERR(cmd_buf); + + ret = sscanf(cmd_buf, "%s", user_val); + if (ret != 1) + return -EINVAL; + + index = sysfs_match_string(ice_fwlog_log_size, user_val); + if (index < 0) { + dev_info(dev, "Invalid log size '%s'. The value must be one of 128K, 256K, 512K, 1M, 2M\n", + user_val); + ret = -EINVAL; + goto log_size_write_error; + } else if (hw->fwlog_cfg.options & ICE_FWLOG_OPTION_IS_REGISTERED) { + dev_info(dev, "FW logging is currently running. Please disable FW logging to change log_size\n"); + ret = -EINVAL; + goto log_size_write_error; + } + + /* free all the buffers and the tracking info and resize */ + ice_fwlog_realloc_rings(hw, index); + + /* if we get here, nothing went wrong; return count since we didn't + * really write anything + */ + ret = (ssize_t)count; + +log_size_write_error: + /* This function always consumes all of the written input, or produces + * an error. Check and enforce this. Otherwise, the write operation + * won't complete properly. + */ + if (WARN_ON(ret != (ssize_t)count && ret >= 0)) + ret = -EIO; + + return ret; +} + +static const struct file_operations ice_debugfs_log_size_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = ice_debugfs_log_size_read, + .write = ice_debugfs_log_size_write, +}; + +/** + * ice_debugfs_data_read - read from 'data' file + * @filp: the opened file + * @buffer: where to write the data for the user to read + * @count: the size of the user's buffer + * @ppos: file position offset + */ +static ssize_t ice_debugfs_data_read(struct file *filp, char __user *buffer, + size_t count, loff_t *ppos) +{ + struct ice_pf *pf = filp->private_data; + struct ice_hw *hw = &pf->hw; + int data_copied = 0; + bool done = false; + + if (ice_fwlog_ring_empty(&hw->fwlog_ring)) + return 0; + + while (!ice_fwlog_ring_empty(&hw->fwlog_ring) && !done) { + struct ice_fwlog_data *log; + u16 cur_buf_len; + + log = &hw->fwlog_ring.rings[hw->fwlog_ring.head]; + cur_buf_len = log->data_size; + if (cur_buf_len >= count) { + done = true; + continue; + } + + if (copy_to_user(buffer, log->data, cur_buf_len)) { + /* if there is an error then bail and return whatever + * the driver has copied so far + */ + done = true; + continue; + } + + data_copied += cur_buf_len; + buffer += cur_buf_len; + count -= cur_buf_len; + *ppos += cur_buf_len; + ice_fwlog_ring_increment(&hw->fwlog_ring.head, + hw->fwlog_ring.size); + } + + return data_copied; +} + +/** + * ice_debugfs_data_write - write into 'data' file + * @filp: the opened file + * @buf: where to find the user's data + * @count: the length of the user's data + * @ppos: file position offset + */ +static ssize_t +ice_debugfs_data_write(struct file *filp, const char __user *buf, size_t count, + loff_t *ppos) +{ + struct ice_pf *pf = filp->private_data; + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + ssize_t ret; + + /* don't allow partial writes */ + if (*ppos != 0) + return 0; + + /* any value is allowed to clear the buffer so no need to even look at + * what the value is + */ + if (!(hw->fwlog_cfg.options & ICE_FWLOG_OPTION_IS_REGISTERED)) { + hw->fwlog_ring.head = 0; + hw->fwlog_ring.tail = 0; + } else { + dev_info(dev, "Can't clear FW log data while FW log running\n"); + ret = -EINVAL; + goto nr_buffs_write_error; + } + + /* if we get here, nothing went wrong; return count since we didn't + * really write anything + */ + ret = (ssize_t)count; + +nr_buffs_write_error: + /* This function always consumes all of the written input, or produces + * an error. Check and enforce this. Otherwise, the write operation + * won't complete properly. + */ + if (WARN_ON(ret != (ssize_t)count && ret >= 0)) + ret = -EIO; + + return ret; +} + +static const struct file_operations ice_debugfs_data_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = ice_debugfs_data_read, + .write = ice_debugfs_data_write, +}; + +/** + * ice_debugfs_fwlog_init - setup the debugfs directory + * @pf: the ice that is starting up + */ +void ice_debugfs_fwlog_init(struct ice_pf *pf) +{ + const char *name = pci_name(pf->pdev); + struct dentry *fw_modules_dir; + struct dentry **fw_modules; + int i; + + /* only support fw log commands on PF 0 */ + if (pf->hw.bus.func) + return; + + /* allocate space for this first because if it fails then we don't + * need to unwind + */ + fw_modules = kcalloc(ICE_NR_FW_LOG_MODULES, sizeof(*fw_modules), + GFP_KERNEL); + if (!fw_modules) + return; + + pf->ice_debugfs_pf = debugfs_create_dir(name, ice_debugfs_root); + if (IS_ERR(pf->ice_debugfs_pf)) + goto err_create_module_files; + + pf->ice_debugfs_pf_fwlog = debugfs_create_dir("fwlog", + pf->ice_debugfs_pf); + if (IS_ERR(pf->ice_debugfs_pf)) + goto err_create_module_files; + + fw_modules_dir = debugfs_create_dir("modules", + pf->ice_debugfs_pf_fwlog); + if (IS_ERR(fw_modules_dir)) + goto err_create_module_files; + + for (i = 0; i < ICE_NR_FW_LOG_MODULES; i++) { + fw_modules[i] = debugfs_create_file(ice_fwlog_module_string[i], + 0600, fw_modules_dir, pf, + &ice_debugfs_module_fops); + if (IS_ERR(fw_modules[i])) + goto err_create_module_files; + } + + debugfs_create_file("nr_messages", 0600, + pf->ice_debugfs_pf_fwlog, pf, + &ice_debugfs_nr_messages_fops); + + pf->ice_debugfs_pf_fwlog_modules = fw_modules; + + debugfs_create_file("enable", 0600, pf->ice_debugfs_pf_fwlog, + pf, &ice_debugfs_enable_fops); + + debugfs_create_file("log_size", 0600, pf->ice_debugfs_pf_fwlog, + pf, &ice_debugfs_log_size_fops); + + debugfs_create_file("data", 0600, pf->ice_debugfs_pf_fwlog, + pf, &ice_debugfs_data_fops); + + return; + +err_create_module_files: + debugfs_remove_recursive(pf->ice_debugfs_pf_fwlog); + kfree(fw_modules); +} + +/** + * ice_debugfs_pf_deinit - cleanup PF's debugfs + * @pf: pointer to the PF struct + */ +void ice_debugfs_pf_deinit(struct ice_pf *pf) +{ + debugfs_remove_recursive(pf->ice_debugfs_pf); + pf->ice_debugfs_pf = NULL; +} + +/** + * ice_debugfs_init - create root directory for debugfs entries + */ +void ice_debugfs_init(void) +{ + ice_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL); + if (IS_ERR(ice_debugfs_root)) + pr_info("init of debugfs failed\n"); +} + +/** + * ice_debugfs_exit - remove debugfs entries + */ +void ice_debugfs_exit(void) +{ + debugfs_remove_recursive(ice_debugfs_root); + ice_debugfs_root = NULL; +} diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index a2d384dbfc76..34fd604132f5 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -16,14 +16,26 @@ #define ICE_DEV_ID_E823L_1GBE 0x124F /* Intel(R) Ethernet Connection E823-L for QSFP */ #define ICE_DEV_ID_E823L_QSFP 0x151D +/* Intel(R) Ethernet Controller E830-CC for backplane */ +#define ICE_DEV_ID_E830CC_BACKPLANE 0x12D1 +/* Intel(R) Ethernet Controller E830-CC for QSFP */ +#define ICE_DEV_ID_E830CC_QSFP56 0x12D2 +/* Intel(R) Ethernet Controller E830-CC for SFP */ +#define ICE_DEV_ID_E830CC_SFP 0x12D3 +/* Intel(R) Ethernet Controller E830-CC for SFP-DD */ +#define ICE_DEV_ID_E830CC_SFP_DD 0x12D4 /* Intel(R) Ethernet Controller E830-C for backplane */ -#define ICE_DEV_ID_E830_BACKPLANE 0x12D1 +#define ICE_DEV_ID_E830C_BACKPLANE 0x12D5 /* Intel(R) Ethernet Controller E830-C for QSFP */ -#define ICE_DEV_ID_E830_QSFP56 0x12D2 +#define ICE_DEV_ID_E830C_QSFP 0x12D8 /* Intel(R) Ethernet Controller E830-C for SFP */ -#define ICE_DEV_ID_E830_SFP 0x12D3 -/* Intel(R) Ethernet Controller E830-C for SFP-DD */ -#define ICE_DEV_ID_E830_SFP_DD 0x12D4 +#define ICE_DEV_ID_E830C_SFP 0x12DA +/* Intel(R) Ethernet Controller E830-XXV for backplane */ +#define ICE_DEV_ID_E830_XXV_BACKPLANE 0x12DC +/* Intel(R) Ethernet Controller E830-XXV for QSFP */ +#define ICE_DEV_ID_E830_XXV_QSFP 0x12DD +/* Intel(R) Ethernet Controller E830-XXV for SFP */ +#define ICE_DEV_ID_E830_XXV_SFP 0x12DE /* Intel(R) Ethernet Controller E810-C for backplane */ #define ICE_DEV_ID_E810C_BACKPLANE 0x1591 /* Intel(R) Ethernet Controller E810-C for QSFP */ @@ -71,5 +83,13 @@ #define ICE_DEV_ID_E822L_10G_BASE_T 0x1899 /* Intel(R) Ethernet Connection E822-L 1GbE */ #define ICE_DEV_ID_E822L_SGMII 0x189A +/* Intel(R) Ethernet Connection E825-C for backplane */ +#define ICE_DEV_ID_E825C_BACKPLANE 0x579c +/* Intel(R) Ethernet Connection E825-C for QSFP */ +#define ICE_DEV_ID_E825C_QSFP 0x579d +/* Intel(R) Ethernet Connection E825-C for SFP */ +#define ICE_DEV_ID_E825C_SFP 0x579e +/* Intel(R) Ethernet Connection E825-C 1GbE */ +#define ICE_DEV_ID_E825C_SGMII 0x579f #endif /* _ICE_DEVIDS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 835c419ccc74..e92be6f130a3 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -31,6 +31,26 @@ static const char * const pin_type_name[] = { }; /** + * ice_dpll_is_reset - check if reset is in progress + * @pf: private board structure + * @extack: error reporting + * + * If reset is in progress, fill extack with error. + * + * Return: + * * false - no reset in progress + * * true - reset in progress + */ +static bool ice_dpll_is_reset(struct ice_pf *pf, struct netlink_ext_ack *extack) +{ + if (ice_is_reset_in_progress(pf->state)) { + NL_SET_ERR_MSG(extack, "PF reset in progress"); + return true; + } + return false; +} + +/** * ice_dpll_pin_freq_set - set pin's frequency * @pf: private board structure * @pin: pointer to a pin @@ -109,6 +129,9 @@ ice_dpll_frequency_set(const struct dpll_pin *pin, void *pin_priv, struct ice_pf *pf = d->pf; int ret; + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); ret = ice_dpll_pin_freq_set(pf, p, pin_type, frequency, extack); mutex_unlock(&pf->dplls.lock); @@ -254,6 +277,7 @@ ice_dpll_output_frequency_get(const struct dpll_pin *pin, void *pin_priv, * ice_dpll_pin_enable - enable a pin on dplls * @hw: board private hw structure * @pin: pointer to a pin + * @dpll_idx: dpll index to connect to output pin * @pin_type: type of pin being enabled * @extack: error reporting * @@ -266,7 +290,7 @@ ice_dpll_output_frequency_get(const struct dpll_pin *pin, void *pin_priv, */ static int ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin, - enum ice_dpll_pin_type pin_type, + u8 dpll_idx, enum ice_dpll_pin_type pin_type, struct netlink_ext_ack *extack) { u8 flags = 0; @@ -280,10 +304,12 @@ ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin, ret = ice_aq_set_input_pin_cfg(hw, pin->idx, 0, flags, 0, 0); break; case ICE_DPLL_PIN_TYPE_OUTPUT: + flags = ICE_AQC_SET_CGU_OUT_CFG_UPDATE_SRC_SEL; if (pin->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) flags |= ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN; flags |= ICE_AQC_SET_CGU_OUT_CFG_OUT_EN; - ret = ice_aq_set_output_pin_cfg(hw, pin->idx, flags, 0, 0, 0); + ret = ice_aq_set_output_pin_cfg(hw, pin->idx, flags, dpll_idx, + 0, 0); break; default: return -EINVAL; @@ -370,7 +396,7 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, case ICE_DPLL_PIN_TYPE_INPUT: ret = ice_aq_get_input_pin_cfg(&pf->hw, pin->idx, NULL, NULL, NULL, &pin->flags[0], - &pin->freq, NULL); + &pin->freq, &pin->phase_adjust); if (ret) goto err; if (ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN & pin->flags[0]) { @@ -398,14 +424,27 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, break; case ICE_DPLL_PIN_TYPE_OUTPUT: ret = ice_aq_get_output_pin_cfg(&pf->hw, pin->idx, - &pin->flags[0], NULL, + &pin->flags[0], &parent, &pin->freq, NULL); if (ret) goto err; - if (ICE_AQC_SET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) - pin->state[0] = DPLL_PIN_STATE_CONNECTED; - else - pin->state[0] = DPLL_PIN_STATE_DISCONNECTED; + + parent &= ICE_AQC_GET_CGU_OUT_CFG_DPLL_SRC_SEL; + if (ICE_AQC_SET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) { + pin->state[pf->dplls.eec.dpll_idx] = + parent == pf->dplls.eec.dpll_idx ? + DPLL_PIN_STATE_CONNECTED : + DPLL_PIN_STATE_DISCONNECTED; + pin->state[pf->dplls.pps.dpll_idx] = + parent == pf->dplls.pps.dpll_idx ? + DPLL_PIN_STATE_CONNECTED : + DPLL_PIN_STATE_DISCONNECTED; + } else { + pin->state[pf->dplls.eec.dpll_idx] = + DPLL_PIN_STATE_DISCONNECTED; + pin->state[pf->dplls.pps.dpll_idx] = + DPLL_PIN_STATE_DISCONNECTED; + } break; case ICE_DPLL_PIN_TYPE_RCLK_INPUT: for (parent = 0; parent < pf->dplls.rclk.num_parents; @@ -488,6 +527,7 @@ ice_dpll_hw_input_prio_set(struct ice_pf *pf, struct ice_dpll *dpll, * @dpll: registered dpll pointer * @dpll_priv: private data pointer passed on dpll registration * @status: on success holds dpll's lock status + * @status_error: status error value * @extack: error reporting * * Dpll subsystem callback, provides dpll's lock status. @@ -500,6 +540,7 @@ ice_dpll_hw_input_prio_set(struct ice_pf *pf, struct ice_dpll *dpll, static int ice_dpll_lock_status_get(const struct dpll_device *dpll, void *dpll_priv, enum dpll_lock_status *status, + enum dpll_lock_status_error *status_error, struct netlink_ext_ack *extack) { struct ice_dpll *d = dpll_priv; @@ -513,31 +554,6 @@ ice_dpll_lock_status_get(const struct dpll_device *dpll, void *dpll_priv, } /** - * ice_dpll_mode_supported - check if dpll's working mode is supported - * @dpll: registered dpll pointer - * @dpll_priv: private data pointer passed on dpll registration - * @mode: mode to be checked for support - * @extack: error reporting - * - * Dpll subsystem callback. Provides information if working mode is supported - * by dpll. - * - * Return: - * * true - mode is supported - * * false - mode is not supported - */ -static bool ice_dpll_mode_supported(const struct dpll_device *dpll, - void *dpll_priv, - enum dpll_mode mode, - struct netlink_ext_ack *extack) -{ - if (mode == DPLL_MODE_AUTOMATIC) - return true; - - return false; -} - -/** * ice_dpll_mode_get - get dpll's working mode * @dpll: registered dpll pointer * @dpll_priv: private data pointer passed on dpll registration @@ -593,9 +609,13 @@ ice_dpll_pin_state_set(const struct dpll_pin *pin, void *pin_priv, struct ice_pf *pf = d->pf; int ret; + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); if (enable) - ret = ice_dpll_pin_enable(&pf->hw, p, pin_type, extack); + ret = ice_dpll_pin_enable(&pf->hw, p, d->dpll_idx, pin_type, + extack); else ret = ice_dpll_pin_disable(&pf->hw, p, pin_type, extack); if (!ret) @@ -628,6 +648,11 @@ ice_dpll_output_state_set(const struct dpll_pin *pin, void *pin_priv, struct netlink_ext_ack *extack) { bool enable = state == DPLL_PIN_STATE_CONNECTED; + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + + if (!enable && p->state[d->dpll_idx] == DPLL_PIN_STATE_DISCONNECTED) + return 0; return ice_dpll_pin_state_set(pin, pin_priv, dpll, dpll_priv, enable, extack, ICE_DPLL_PIN_TYPE_OUTPUT); @@ -690,14 +715,16 @@ ice_dpll_pin_state_get(const struct dpll_pin *pin, void *pin_priv, struct ice_pf *pf = d->pf; int ret; + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); ret = ice_dpll_pin_state_update(pf, p, pin_type, extack); if (ret) goto unlock; - if (pin_type == ICE_DPLL_PIN_TYPE_INPUT) + if (pin_type == ICE_DPLL_PIN_TYPE_INPUT || + pin_type == ICE_DPLL_PIN_TYPE_OUTPUT) *state = p->state[d->dpll_idx]; - else if (pin_type == ICE_DPLL_PIN_TYPE_OUTPUT) - *state = p->state[0]; ret = 0; unlock: mutex_unlock(&pf->dplls.lock); @@ -815,11 +842,8 @@ ice_dpll_input_prio_set(const struct dpll_pin *pin, void *pin_priv, struct ice_pf *pf = d->pf; int ret; - if (prio > ICE_DPLL_PRIO_MAX) { - NL_SET_ERR_MSG_FMT(extack, "prio out of supported range 0-%d", - ICE_DPLL_PRIO_MAX); - return -EINVAL; - } + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; mutex_lock(&pf->dplls.lock); ret = ice_dpll_hw_input_prio_set(pf, d, p, prio, extack); @@ -941,6 +965,9 @@ ice_dpll_pin_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv, u8 flag, flags_en = 0; int ret; + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); switch (type) { case ICE_DPLL_PIN_TYPE_INPUT: @@ -1100,6 +1127,9 @@ ice_dpll_rclk_state_on_pin_set(const struct dpll_pin *pin, void *pin_priv, int ret = -EINVAL; u32 hw_idx; + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); hw_idx = parent->idx - pf->dplls.base_rclk_idx; if (hw_idx >= pf->dplls.num_inputs) @@ -1154,6 +1184,9 @@ ice_dpll_rclk_state_on_pin_get(const struct dpll_pin *pin, void *pin_priv, int ret = -EINVAL; u32 hw_idx; + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); hw_idx = parent->idx - pf->dplls.base_rclk_idx; if (hw_idx >= pf->dplls.num_inputs) @@ -1203,7 +1236,6 @@ static const struct dpll_pin_ops ice_dpll_output_ops = { static const struct dpll_device_ops ice_dpll_ops = { .lock_status_get = ice_dpll_lock_status_get, - .mode_supported = ice_dpll_mode_supported, .mode_get = ice_dpll_mode_get, }; @@ -1337,8 +1369,10 @@ static void ice_dpll_periodic_work(struct kthread_work *work) struct ice_pf *pf = container_of(d, struct ice_pf, dplls); struct ice_dpll *de = &pf->dplls.eec; struct ice_dpll *dp = &pf->dplls.pps; - int ret; + int ret = 0; + if (ice_is_reset_in_progress(pf->state)) + goto resched; mutex_lock(&pf->dplls.lock); ret = ice_dpll_update_state(pf, de, false); if (!ret) @@ -1358,6 +1392,7 @@ static void ice_dpll_periodic_work(struct kthread_work *work) ice_dpll_notify_changes(de); ice_dpll_notify_changes(dp); +resched: /* Run twice a second or reschedule if update failed */ kthread_queue_delayed_work(d->kworker, &d->work, ret ? msecs_to_jiffies(10) : @@ -1564,7 +1599,7 @@ static void ice_dpll_deinit_rclk_pin(struct ice_pf *pf) } if (WARN_ON_ONCE(!vsi || !vsi->netdev)) return; - netdev_dpll_pin_clear(vsi->netdev); + dpll_netdev_pin_clear(vsi->netdev); dpll_pin_put(rclk->pin); } @@ -1608,7 +1643,7 @@ ice_dpll_init_rclk_pins(struct ice_pf *pf, struct ice_dpll_pin *pin, } if (WARN_ON((!vsi || !vsi->netdev))) return -EINVAL; - netdev_dpll_pin_set(vsi->netdev, pf->dplls.rclk.pin); + dpll_netdev_pin_set(vsi->netdev, pf->dplls.rclk.pin); return 0; @@ -1756,6 +1791,7 @@ ice_dpll_init_dpll(struct ice_pf *pf, struct ice_dpll *d, bool cgu, } d->pf = pf; if (cgu) { + ice_dpll_update_state(pf, d, true); ret = dpll_device_register(d->dpll, type, &ice_dpll_ops, d); if (ret) { dpll_device_put(d->dpll); @@ -1796,8 +1832,6 @@ static int ice_dpll_init_worker(struct ice_pf *pf) struct ice_dplls *d = &pf->dplls; struct kthread_worker *kworker; - ice_dpll_update_state(pf, &d->eec, true); - ice_dpll_update_state(pf, &d->pps, true); kthread_init_delayed_work(&d->work, ice_dpll_periodic_work); kworker = kthread_create_worker(0, "ice-dplls-%s", dev_name(ice_pf_to_dev(pf))); @@ -1830,6 +1864,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, int num_pins, i, ret = -EINVAL; struct ice_hw *hw = &pf->hw; struct ice_dpll_pin *pins; + unsigned long caps; u8 freq_supp_num; bool input; @@ -1849,6 +1884,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, } for (i = 0; i < num_pins; i++) { + caps = 0; pins[i].idx = i; pins[i].prop.board_label = ice_cgu_get_pin_name(hw, i, input); pins[i].prop.type = ice_cgu_get_pin_type(hw, i, input); @@ -1861,8 +1897,8 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, &dp->input_prio[i]); if (ret) return ret; - pins[i].prop.capabilities |= - DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE; + caps |= (DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE | + DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE); pins[i].prop.phase_range.min = pf->dplls.input_phase_adj_max; pins[i].prop.phase_range.max = @@ -1872,9 +1908,11 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, pf->dplls.output_phase_adj_max; pins[i].prop.phase_range.max = -pf->dplls.output_phase_adj_max; + ret = ice_cgu_get_output_pin_state_caps(hw, i, &caps); + if (ret) + return ret; } - pins[i].prop.capabilities |= - DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; + pins[i].prop.capabilities = caps; ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL); if (ret) return ret; @@ -2084,6 +2122,7 @@ void ice_dpll_init(struct ice_pf *pf) struct ice_dplls *d = &pf->dplls; int err = 0; + mutex_init(&d->lock); err = ice_dpll_init_info(pf, cgu); if (err) goto err_exit; @@ -2096,7 +2135,6 @@ void ice_dpll_init(struct ice_pf *pf) err = ice_dpll_init_pins(pf, cgu); if (err) goto deinit_pps; - mutex_init(&d->lock); if (cgu) { err = ice_dpll_init_worker(pf); if (err) diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h index bb32b6d88373..93172e93995b 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.h +++ b/drivers/net/ethernet/intel/ice/ice_dpll.h @@ -6,7 +6,6 @@ #include "ice.h" -#define ICE_DPLL_PRIO_MAX 0xF #define ICE_DPLL_RCLK_NUM_MAX 4 /** ice_dpll_pin - store info about pins diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index a655d499abfa..b102db8b829a 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -7,70 +7,11 @@ #include "ice_eswitch_br.h" #include "ice_fltr.h" #include "ice_repr.h" -#include "ice_devlink.h" +#include "devlink/devlink.h" #include "ice_tc_lib.h" /** - * ice_eswitch_add_vf_sp_rule - add adv rule with VF's VSI index - * @pf: pointer to PF struct - * @vf: pointer to VF struct - * - * This function adds advanced rule that forwards packets with - * VF's VSI index to the corresponding switchdev ctrl VSI queue. - */ -static int -ice_eswitch_add_vf_sp_rule(struct ice_pf *pf, struct ice_vf *vf) -{ - struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; - struct ice_adv_rule_info rule_info = { 0 }; - struct ice_adv_lkup_elem *list; - struct ice_hw *hw = &pf->hw; - const u16 lkups_cnt = 1; - int err; - - list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); - if (!list) - return -ENOMEM; - - ice_rule_add_src_vsi_metadata(list); - - rule_info.sw_act.flag = ICE_FLTR_TX; - rule_info.sw_act.vsi_handle = ctrl_vsi->idx; - rule_info.sw_act.fltr_act = ICE_FWD_TO_Q; - rule_info.sw_act.fwd_id.q_id = hw->func_caps.common_cap.rxq_first_id + - ctrl_vsi->rxq_map[vf->vf_id]; - rule_info.flags_info.act |= ICE_SINGLE_ACT_LB_ENABLE; - rule_info.flags_info.act_valid = true; - rule_info.tun_type = ICE_SW_TUN_AND_NON_TUN; - rule_info.src_vsi = vf->lan_vsi_idx; - - err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, - &vf->repr->sp_rule); - if (err) - dev_err(ice_pf_to_dev(pf), "Unable to add VF slow-path rule in switchdev mode for VF %d", - vf->vf_id); - - kfree(list); - return err; -} - -/** - * ice_eswitch_del_vf_sp_rule - delete adv rule with VF's VSI index - * @vf: pointer to the VF struct - * - * Delete the advanced rule that was used to forward packets with the VF's VSI - * index to the corresponding switchdev ctrl VSI queue. - */ -static void ice_eswitch_del_vf_sp_rule(struct ice_vf *vf) -{ - if (!vf->repr) - return; - - ice_rem_adv_rule_by_id(&vf->pf->hw, &vf->repr->sp_rule); -} - -/** - * ice_eswitch_setup_env - configure switchdev HW filters + * ice_eswitch_setup_env - configure eswitch HW filters * @pf: pointer to PF struct * * This function adds HW filters configuration specific for switchdev @@ -78,239 +19,153 @@ static void ice_eswitch_del_vf_sp_rule(struct ice_vf *vf) */ static int ice_eswitch_setup_env(struct ice_pf *pf) { - struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi; - struct net_device *uplink_netdev = uplink_vsi->netdev; - struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; + struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi; + struct net_device *netdev = uplink_vsi->netdev; + bool if_running = netif_running(netdev); struct ice_vsi_vlan_ops *vlan_ops; - bool rule_added = false; + + if (if_running && !test_and_set_bit(ICE_VSI_DOWN, uplink_vsi->state)) + if (ice_down(uplink_vsi)) + return -ENODEV; ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx); - netif_addr_lock_bh(uplink_netdev); - __dev_uc_unsync(uplink_netdev, NULL); - __dev_mc_unsync(uplink_netdev, NULL); - netif_addr_unlock_bh(uplink_netdev); + netif_addr_lock_bh(netdev); + __dev_uc_unsync(netdev, NULL); + __dev_mc_unsync(netdev, NULL); + netif_addr_unlock_bh(netdev); 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)) goto err_def_rx; - if (!ice_is_dflt_vsi_in_use(uplink_vsi->port_info)) { - if (ice_set_dflt_vsi(uplink_vsi)) - goto err_def_rx; - rule_added = true; - } + if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true, + ICE_FLTR_TX)) + goto err_def_tx; vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi); if (vlan_ops->dis_rx_filtering(uplink_vsi)) - goto err_dis_rx; + 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_security(ctrl_vsi, ice_vsi_ctx_set_allow_override)) - goto err_override_control; - if (ice_vsi_update_local_lb(uplink_vsi, true)) goto err_override_local_lb; + if (if_running && ice_up(uplink_vsi)) + goto err_up; + return 0; +err_up: + ice_vsi_update_local_lb(uplink_vsi, false); err_override_local_lb: - ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override); -err_override_control: ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); err_override_uplink: vlan_ops->ena_rx_filtering(uplink_vsi); -err_dis_rx: - if (rule_added) - ice_clear_dflt_vsi(uplink_vsi); +err_vlan_filtering: + ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false, + ICE_FLTR_TX); +err_def_tx: + ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false, + ICE_FLTR_RX); err_def_rx: + ice_vsi_del_vlan_zero(uplink_vsi); +err_vlan_zero: ice_fltr_add_mac_and_broadcast(uplink_vsi, uplink_vsi->port_info->mac.perm_addr, ICE_FWD_TO_VSI); - return -ENODEV; -} - -/** - * ice_eswitch_remap_rings_to_vectors - reconfigure rings of switchdev ctrl VSI - * @pf: pointer to PF struct - * - * In switchdev number of allocated Tx/Rx rings is equal. - * - * This function fills q_vectors structures associated with representor and - * move each ring pairs to port representor netdevs. Each port representor - * will have dedicated 1 Tx/Rx ring pair, so number of rings pair is equal to - * number of VFs. - */ -static void ice_eswitch_remap_rings_to_vectors(struct ice_pf *pf) -{ - struct ice_vsi *vsi = pf->switchdev.control_vsi; - int q_id; - - ice_for_each_txq(vsi, q_id) { - struct ice_q_vector *q_vector; - struct ice_tx_ring *tx_ring; - struct ice_rx_ring *rx_ring; - struct ice_repr *repr; - struct ice_vf *vf; - - vf = ice_get_vf_by_id(pf, q_id); - if (WARN_ON(!vf)) - continue; - - repr = vf->repr; - q_vector = repr->q_vector; - tx_ring = vsi->tx_rings[q_id]; - rx_ring = vsi->rx_rings[q_id]; - - q_vector->vsi = vsi; - q_vector->reg_idx = vsi->q_vectors[0]->reg_idx; - - q_vector->num_ring_tx = 1; - q_vector->tx.tx_ring = tx_ring; - tx_ring->q_vector = q_vector; - tx_ring->next = NULL; - tx_ring->netdev = repr->netdev; - /* In switchdev mode, from OS stack perspective, there is only - * one queue for given netdev, so it needs to be indexed as 0. - */ - tx_ring->q_index = 0; - - q_vector->num_ring_rx = 1; - q_vector->rx.rx_ring = rx_ring; - rx_ring->q_vector = q_vector; - rx_ring->next = NULL; - rx_ring->netdev = repr->netdev; + if (if_running) + ice_up(uplink_vsi); - ice_put_vf(vf); - } + return -ENODEV; } /** - * ice_eswitch_release_reprs - clear PR VSIs configuration + * ice_eswitch_release_repr - clear PR VSI configuration * @pf: poiner to PF struct - * @ctrl_vsi: pointer to switchdev control VSI + * @repr: pointer to PR */ static void -ice_eswitch_release_reprs(struct ice_pf *pf, struct ice_vsi *ctrl_vsi) +ice_eswitch_release_repr(struct ice_pf *pf, struct ice_repr *repr) { - struct ice_vf *vf; - unsigned int bkt; - - lockdep_assert_held(&pf->vfs.table_lock); - - ice_for_each_vf(pf, bkt, vf) { - struct ice_vsi *vsi = vf->repr->src_vsi; - - /* Skip VFs that aren't configured */ - if (!vf->repr->dst) - continue; + struct ice_vsi *vsi = repr->src_vsi; - ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); - metadata_dst_free(vf->repr->dst); - vf->repr->dst = NULL; - ice_eswitch_del_vf_sp_rule(vf); - ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, - ICE_FWD_TO_VSI); + /* Skip representors that aren't configured */ + if (!repr->dst) + return; - netif_napi_del(&vf->repr->q_vector->napi); - } + ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); + metadata_dst_free(repr->dst); + repr->dst = NULL; + ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac, + ICE_FWD_TO_VSI); } /** - * ice_eswitch_setup_reprs - configure port reprs to run in switchdev mode + * ice_eswitch_setup_repr - configure PR to run in switchdev mode * @pf: pointer to PF struct + * @repr: pointer to PR struct */ -static int ice_eswitch_setup_reprs(struct ice_pf *pf) +static int ice_eswitch_setup_repr(struct ice_pf *pf, struct ice_repr *repr) { - struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; - int max_vsi_num = 0; - struct ice_vf *vf; - unsigned int bkt; - - lockdep_assert_held(&pf->vfs.table_lock); - - ice_for_each_vf(pf, bkt, vf) { - struct ice_vsi *vsi = vf->repr->src_vsi; - - ice_remove_vsi_fltr(&pf->hw, vsi->idx); - vf->repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, - GFP_KERNEL); - if (!vf->repr->dst) { - ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, - ICE_FWD_TO_VSI); - goto err; - } - - if (ice_eswitch_add_vf_sp_rule(pf, vf)) { - ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, - ICE_FWD_TO_VSI); - goto err; - } - - if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof)) { - ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, - ICE_FWD_TO_VSI); - ice_eswitch_del_vf_sp_rule(vf); - metadata_dst_free(vf->repr->dst); - vf->repr->dst = NULL; - goto err; - } - - if (ice_vsi_add_vlan_zero(vsi)) { - ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, - ICE_FWD_TO_VSI); - ice_eswitch_del_vf_sp_rule(vf); - metadata_dst_free(vf->repr->dst); - vf->repr->dst = NULL; - ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); - goto err; - } + struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi; + struct ice_vsi *vsi = repr->src_vsi; + struct metadata_dst *dst; - if (max_vsi_num < vsi->vsi_num) - max_vsi_num = vsi->vsi_num; + ice_remove_vsi_fltr(&pf->hw, vsi->idx); + repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, + GFP_KERNEL); + if (!repr->dst) + goto err_add_mac_fltr; - netif_napi_add(vf->repr->netdev, &vf->repr->q_vector->napi, - ice_napi_poll); + if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof)) + goto err_dst_free; - netif_keep_dst(vf->repr->netdev); - } + if (ice_vsi_add_vlan_zero(vsi)) + goto err_update_security; - ice_for_each_vf(pf, bkt, vf) { - struct ice_repr *repr = vf->repr; - struct ice_vsi *vsi = repr->src_vsi; - struct metadata_dst *dst; + netif_keep_dst(uplink_vsi->netdev); - dst = repr->dst; - dst->u.port_info.port_id = vsi->vsi_num; - dst->u.port_info.lower_dev = repr->netdev; - ice_repr_set_traffic_vsi(repr, ctrl_vsi); - } + dst = repr->dst; + dst->u.port_info.port_id = vsi->vsi_num; + dst->u.port_info.lower_dev = uplink_vsi->netdev; return 0; -err: - ice_eswitch_release_reprs(pf, ctrl_vsi); +err_update_security: + ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); +err_dst_free: + metadata_dst_free(repr->dst); + repr->dst = NULL; +err_add_mac_fltr: + ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac, ICE_FWD_TO_VSI); return -ENODEV; } /** - * ice_eswitch_update_repr - reconfigure VF port representor - * @vsi: VF VSI for which port representor is configured + * ice_eswitch_update_repr - reconfigure port representor + * @repr_id: representor ID + * @vsi: VSI for which port representor is configured */ -void ice_eswitch_update_repr(struct ice_vsi *vsi) +void ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; struct ice_repr *repr; - struct ice_vf *vf; int ret; if (!ice_is_switchdev_running(pf)) return; - vf = vsi->vf; - repr = vf->repr; + repr = xa_load(&pf->eswitch.reprs, repr_id); + if (!repr) + return; + repr->src_vsi = vsi; repr->dst->u.port_info.port_id = vsi->vsi_num; @@ -319,9 +174,10 @@ void ice_eswitch_update_repr(struct ice_vsi *vsi) ret = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof); if (ret) { - ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); - dev_err(ice_pf_to_dev(pf), "Failed to update VF %d port representor", - vsi->vf->vf_id); + ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac, + ICE_FWD_TO_VSI); + dev_err(ice_pf_to_dev(pf), "Failed to update VSI of port representor %d", + repr->id); } } @@ -335,31 +191,23 @@ void ice_eswitch_update_repr(struct ice_vsi *vsi) netdev_tx_t ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) { - struct ice_netdev_priv *np; - struct ice_repr *repr; - struct ice_vsi *vsi; - - np = netdev_priv(netdev); - vsi = np->vsi; - - if (!vsi || !ice_is_switchdev_running(vsi->back)) - return NETDEV_TX_BUSY; - - if (ice_is_reset_in_progress(vsi->back->state) || - test_bit(ICE_VF_DIS, vsi->back->state)) - return NETDEV_TX_BUSY; + struct ice_repr *repr = ice_netdev_to_repr(netdev); + unsigned int len = skb->len; + int ret; - repr = ice_netdev_to_repr(netdev); skb_dst_drop(skb); dst_hold((struct dst_entry *)repr->dst); skb_dst_set(skb, (struct dst_entry *)repr->dst); - skb->queue_mapping = repr->vf->vf_id; + skb->dev = repr->dst->u.port_info.lower_dev; + + ret = dev_queue_xmit(skb); + ice_repr_inc_tx_stats(repr, len, ret); - return ice_start_xmit(skb, netdev); + return ret; } /** - * ice_eswitch_set_target_vsi - set switchdev context in Tx context descriptor + * ice_eswitch_set_target_vsi - set eswitch context in Tx context descriptor * @skb: pointer to send buffer * @off: pointer to offload struct */ @@ -375,14 +223,14 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb, off->cd_qw1 |= (cd_cmd | ICE_TX_DESC_DTYPE_CTX); } else { cd_cmd = ICE_TX_CTX_DESC_SWTCH_VSI << ICE_TXD_CTX_QW1_CMD_S; - dst_vsi = ((u64)dst->u.port_info.port_id << - ICE_TXD_CTX_QW1_VSI_S) & ICE_TXD_CTX_QW1_VSI_M; + dst_vsi = FIELD_PREP(ICE_TXD_CTX_QW1_VSI_M, + dst->u.port_info.port_id); off->cd_qw1 = cd_cmd | dst_vsi | ICE_TX_DESC_DTYPE_CTX; } } /** - * ice_eswitch_release_env - clear switchdev HW filters + * ice_eswitch_release_env - clear eswitch HW filters * @pf: pointer to PF struct * * This function removes HW filters configuration specific for switchdev @@ -390,91 +238,30 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb, */ static void ice_eswitch_release_env(struct ice_pf *pf) { - struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi; - struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; + struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi; struct ice_vsi_vlan_ops *vlan_ops; vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi); ice_vsi_update_local_lb(uplink_vsi, false); - ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override); ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); vlan_ops->ena_rx_filtering(uplink_vsi); - ice_clear_dflt_vsi(uplink_vsi); + ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false, + ICE_FLTR_TX); + ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false, + ICE_FLTR_RX); ice_fltr_add_mac_and_broadcast(uplink_vsi, uplink_vsi->port_info->mac.perm_addr, ICE_FWD_TO_VSI); } /** - * ice_eswitch_vsi_setup - configure switchdev control VSI - * @pf: pointer to PF structure - * @pi: pointer to port_info structure - */ -static struct ice_vsi * -ice_eswitch_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) -{ - struct ice_vsi_cfg_params params = {}; - - params.type = ICE_VSI_SWITCHDEV_CTRL; - params.pi = pi; - params.flags = ICE_VSI_FLAG_INIT; - - return ice_vsi_setup(pf, ¶ms); -} - -/** - * ice_eswitch_napi_del - remove NAPI handle for all port representors - * @pf: pointer to PF structure - */ -static void ice_eswitch_napi_del(struct ice_pf *pf) -{ - struct ice_vf *vf; - unsigned int bkt; - - lockdep_assert_held(&pf->vfs.table_lock); - - ice_for_each_vf(pf, bkt, vf) - netif_napi_del(&vf->repr->q_vector->napi); -} - -/** - * ice_eswitch_napi_enable - enable NAPI for all port representors - * @pf: pointer to PF structure - */ -static void ice_eswitch_napi_enable(struct ice_pf *pf) -{ - struct ice_vf *vf; - unsigned int bkt; - - lockdep_assert_held(&pf->vfs.table_lock); - - ice_for_each_vf(pf, bkt, vf) - napi_enable(&vf->repr->q_vector->napi); -} - -/** - * ice_eswitch_napi_disable - disable NAPI for all port representors - * @pf: pointer to PF structure - */ -static void ice_eswitch_napi_disable(struct ice_pf *pf) -{ - struct ice_vf *vf; - unsigned int bkt; - - lockdep_assert_held(&pf->vfs.table_lock); - - ice_for_each_vf(pf, bkt, vf) - napi_disable(&vf->repr->q_vector->napi); -} - -/** * ice_eswitch_enable_switchdev - configure eswitch in switchdev mode * @pf: pointer to PF structure */ static int ice_eswitch_enable_switchdev(struct ice_pf *pf) { - struct ice_vsi *ctrl_vsi, *uplink_vsi; + struct ice_vsi *uplink_vsi; uplink_vsi = ice_get_main_vsi(pf); if (!uplink_vsi) @@ -486,59 +273,33 @@ static int ice_eswitch_enable_switchdev(struct ice_pf *pf) return -EINVAL; } - pf->switchdev.control_vsi = ice_eswitch_vsi_setup(pf, pf->hw.port_info); - if (!pf->switchdev.control_vsi) - return -ENODEV; - - ctrl_vsi = pf->switchdev.control_vsi; - pf->switchdev.uplink_vsi = uplink_vsi; + pf->eswitch.uplink_vsi = uplink_vsi; if (ice_eswitch_setup_env(pf)) - goto err_vsi; - - if (ice_repr_add_for_all_vfs(pf)) - goto err_repr_add; - - if (ice_eswitch_setup_reprs(pf)) - goto err_setup_reprs; - - ice_eswitch_remap_rings_to_vectors(pf); - - if (ice_vsi_open(ctrl_vsi)) - goto err_setup_reprs; + return -ENODEV; if (ice_eswitch_br_offloads_init(pf)) goto err_br_offloads; - ice_eswitch_napi_enable(pf); + pf->eswitch.is_running = true; return 0; err_br_offloads: - ice_vsi_close(ctrl_vsi); -err_setup_reprs: - ice_repr_rem_from_all_vfs(pf); -err_repr_add: ice_eswitch_release_env(pf); -err_vsi: - ice_vsi_release(ctrl_vsi); return -ENODEV; } /** - * ice_eswitch_disable_switchdev - disable switchdev resources + * ice_eswitch_disable_switchdev - disable eswitch resources * @pf: pointer to PF structure */ static void ice_eswitch_disable_switchdev(struct ice_pf *pf) { - struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; - - ice_eswitch_napi_disable(pf); ice_eswitch_br_offloads_deinit(pf); ice_eswitch_release_env(pf); - ice_eswitch_release_reprs(pf, ctrl_vsi); - ice_vsi_release(ctrl_vsi); - ice_repr_rem_from_all_vfs(pf); + + pf->eswitch.is_running = false; } /** @@ -566,6 +327,7 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode, case DEVLINK_ESWITCH_MODE_LEGACY: dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to legacy", pf->hw.pf_id); + xa_destroy(&pf->eswitch.reprs); NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to legacy"); break; case DEVLINK_ESWITCH_MODE_SWITCHDEV: @@ -578,6 +340,7 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode, dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to switchdev", pf->hw.pf_id); + xa_init(&pf->eswitch.reprs); NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to switchdev"); break; } @@ -616,74 +379,123 @@ bool ice_is_eswitch_mode_switchdev(struct ice_pf *pf) } /** - * ice_eswitch_release - cleanup eswitch + * ice_eswitch_start_all_tx_queues - start Tx queues of all port representors * @pf: pointer to PF structure */ -void ice_eswitch_release(struct ice_pf *pf) +static void ice_eswitch_start_all_tx_queues(struct ice_pf *pf) { - if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY) + struct ice_repr *repr; + unsigned long id; + + if (test_bit(ICE_DOWN, pf->state)) return; - ice_eswitch_disable_switchdev(pf); - pf->switchdev.is_running = false; + xa_for_each(&pf->eswitch.reprs, id, repr) + ice_repr_start_tx_queues(repr); } /** - * ice_eswitch_configure - configure eswitch + * ice_eswitch_stop_all_tx_queues - stop Tx queues of all port representors * @pf: pointer to PF structure */ -int ice_eswitch_configure(struct ice_pf *pf) +void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf) { - int status; + struct ice_repr *repr; + unsigned long id; - if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY || pf->switchdev.is_running) - return 0; + if (test_bit(ICE_DOWN, pf->state)) + return; - status = ice_eswitch_enable_switchdev(pf); - if (status) - return status; + xa_for_each(&pf->eswitch.reprs, id, repr) + ice_repr_stop_tx_queues(repr); +} - pf->switchdev.is_running = true; - return 0; +static void ice_eswitch_stop_reprs(struct ice_pf *pf) +{ + ice_eswitch_stop_all_tx_queues(pf); } -/** - * ice_eswitch_start_all_tx_queues - start Tx queues of all port representors - * @pf: pointer to PF structure - */ -static void ice_eswitch_start_all_tx_queues(struct ice_pf *pf) +static void ice_eswitch_start_reprs(struct ice_pf *pf) { - struct ice_vf *vf; - unsigned int bkt; + ice_eswitch_start_all_tx_queues(pf); +} - lockdep_assert_held(&pf->vfs.table_lock); +int +ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf) +{ + struct ice_repr *repr; + int err; - if (test_bit(ICE_DOWN, pf->state)) - return; + if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY) + return 0; - ice_for_each_vf(pf, bkt, vf) { - if (vf->repr) - ice_repr_start_tx_queues(vf->repr); + if (xa_empty(&pf->eswitch.reprs)) { + err = ice_eswitch_enable_switchdev(pf); + if (err) + return err; } + + ice_eswitch_stop_reprs(pf); + + repr = ice_repr_add_vf(vf); + if (IS_ERR(repr)) { + err = PTR_ERR(repr); + goto err_create_repr; + } + + err = ice_eswitch_setup_repr(pf, repr); + if (err) + goto err_setup_repr; + + err = xa_insert(&pf->eswitch.reprs, repr->id, repr, GFP_KERNEL); + if (err) + goto err_xa_alloc; + + vf->repr_id = repr->id; + + ice_eswitch_start_reprs(pf); + + return 0; + +err_xa_alloc: + ice_eswitch_release_repr(pf, repr); +err_setup_repr: + ice_repr_rem_vf(repr); +err_create_repr: + if (xa_empty(&pf->eswitch.reprs)) + ice_eswitch_disable_switchdev(pf); + ice_eswitch_start_reprs(pf); + + return err; } -/** - * ice_eswitch_stop_all_tx_queues - stop Tx queues of all port representors - * @pf: pointer to PF structure - */ -void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf) +void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf) { - struct ice_vf *vf; - unsigned int bkt; - - lockdep_assert_held(&pf->vfs.table_lock); + struct ice_repr *repr = xa_load(&pf->eswitch.reprs, vf->repr_id); + struct devlink *devlink = priv_to_devlink(pf); - if (test_bit(ICE_DOWN, pf->state)) + if (!repr) return; - ice_for_each_vf(pf, bkt, vf) { - if (vf->repr) - ice_repr_stop_tx_queues(vf->repr); + ice_eswitch_stop_reprs(pf); + xa_erase(&pf->eswitch.reprs, repr->id); + + if (xa_empty(&pf->eswitch.reprs)) + ice_eswitch_disable_switchdev(pf); + + ice_eswitch_release_repr(pf, repr); + ice_repr_rem_vf(repr); + + if (xa_empty(&pf->eswitch.reprs)) { + /* since all port representors are destroyed, there is + * no point in keeping the nodes + */ + ice_devlink_rate_clear_tx_topology(ice_get_main_vsi(pf)); + devl_lock(devlink); + devl_rate_nodes_destroy(devlink); + devl_unlock(devlink); + } else { + ice_eswitch_start_reprs(pf); } } @@ -691,32 +503,37 @@ void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf) * ice_eswitch_rebuild - rebuild eswitch * @pf: pointer to PF structure */ -int ice_eswitch_rebuild(struct ice_pf *pf) +void ice_eswitch_rebuild(struct ice_pf *pf) { - struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; - int status; - - ice_eswitch_napi_disable(pf); - ice_eswitch_napi_del(pf); - - status = ice_eswitch_setup_env(pf); - if (status) - return status; - - status = ice_eswitch_setup_reprs(pf); - if (status) - return status; + struct ice_repr *repr; + unsigned long id; - ice_eswitch_remap_rings_to_vectors(pf); + if (!ice_is_switchdev_running(pf)) + return; - ice_replay_tc_fltrs(pf); + xa_for_each(&pf->eswitch.reprs, id, repr) + ice_eswitch_detach(pf, repr->vf); +} - status = ice_vsi_open(ctrl_vsi); - if (status) - return status; +/** + * ice_eswitch_get_target - get netdev based on src_vsi from descriptor + * @rx_ring: ring used to receive the packet + * @rx_desc: descriptor used to get src_vsi value + * + * Get src_vsi value from descriptor and load correct representor. If it isn't + * found return rx_ring->netdev. + */ +struct net_device *ice_eswitch_get_target(struct ice_rx_ring *rx_ring, + union ice_32b_rx_flex_desc *rx_desc) +{ + struct ice_eswitch *eswitch = &rx_ring->vsi->back->eswitch; + struct ice_32b_rx_flex_desc_nic_2 *desc; + struct ice_repr *repr; - ice_eswitch_napi_enable(pf); - ice_eswitch_start_all_tx_queues(pf); + desc = (struct ice_32b_rx_flex_desc_nic_2 *)rx_desc; + repr = xa_load(&eswitch->reprs, le16_to_cpu(desc->src_vsi)); + if (!repr) + return rx_ring->netdev; - return 0; + return repr->netdev; } diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h index b18bf83a2f5b..e2e5c0c75e7d 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h @@ -7,9 +7,10 @@ #include <net/devlink.h> #ifdef CONFIG_ICE_SWITCHDEV -void ice_eswitch_release(struct ice_pf *pf); -int ice_eswitch_configure(struct ice_pf *pf); -int ice_eswitch_rebuild(struct ice_pf *pf); +void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf); +int +ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf); +void ice_eswitch_rebuild(struct ice_pf *pf); int ice_eswitch_mode_get(struct devlink *devlink, u16 *mode); int @@ -17,7 +18,7 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode, struct netlink_ext_ack *extack); bool ice_is_eswitch_mode_switchdev(struct ice_pf *pf); -void ice_eswitch_update_repr(struct ice_vsi *vsi); +void ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi); void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf); @@ -25,8 +26,16 @@ void ice_eswitch_set_target_vsi(struct sk_buff *skb, struct ice_tx_offload_params *off); netdev_tx_t ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev); +struct net_device *ice_eswitch_get_target(struct ice_rx_ring *rx_ring, + union ice_32b_rx_flex_desc *rx_desc); #else /* CONFIG_ICE_SWITCHDEV */ -static inline void ice_eswitch_release(struct ice_pf *pf) { } +static inline void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf) { } + +static inline int +ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf) +{ + return -EOPNOTSUPP; +} static inline void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf) { } @@ -34,7 +43,8 @@ static inline void ice_eswitch_set_target_vsi(struct sk_buff *skb, struct ice_tx_offload_params *off) { } -static inline void ice_eswitch_update_repr(struct ice_vsi *vsi) { } +static inline void +ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi) { } static inline int ice_eswitch_configure(struct ice_pf *pf) { @@ -68,5 +78,12 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) { return NETDEV_TX_BUSY; } + +static inline struct net_device * +ice_eswitch_get_target(struct ice_rx_ring *rx_ring, + union ice_32b_rx_flex_desc *rx_desc) +{ + return rx_ring->netdev; +} #endif /* CONFIG_ICE_SWITCHDEV */ #endif /* _ICE_ESWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c index 6ae0269bdf73..ac5beecd028b 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c @@ -893,10 +893,14 @@ ice_eswitch_br_port_deinit(struct ice_esw_br *bridge, ice_eswitch_br_fdb_entry_delete(bridge, fdb_entry); } - if (br_port->type == ICE_ESWITCH_BR_UPLINK_PORT && vsi->back) + if (br_port->type == ICE_ESWITCH_BR_UPLINK_PORT && vsi->back) { vsi->back->br_port = NULL; - else if (vsi->vf && vsi->vf->repr) - vsi->vf->repr->br_port = NULL; + } else { + struct ice_repr *repr = ice_repr_get_by_vsi(vsi); + + if (repr) + repr->br_port = NULL; + } xa_erase(&bridge->ports, br_port->vsi_idx); ice_eswitch_br_port_vlans_flush(br_port); @@ -947,7 +951,7 @@ ice_eswitch_br_vf_repr_port_init(struct ice_esw_br *bridge, static int ice_eswitch_br_uplink_port_init(struct ice_esw_br *bridge, struct ice_pf *pf) { - struct ice_vsi *vsi = pf->switchdev.uplink_vsi; + struct ice_vsi *vsi = pf->eswitch.uplink_vsi; struct ice_esw_br_port *br_port; int err; @@ -1185,7 +1189,7 @@ ice_eswitch_br_port_event(struct notifier_block *nb, static void ice_eswitch_br_offloads_dealloc(struct ice_pf *pf) { - struct ice_esw_br_offloads *br_offloads = pf->switchdev.br_offloads; + struct ice_esw_br_offloads *br_offloads = pf->eswitch.br_offloads; ASSERT_RTNL(); @@ -1194,7 +1198,7 @@ ice_eswitch_br_offloads_dealloc(struct ice_pf *pf) ice_eswitch_br_deinit(br_offloads, br_offloads->bridge); - pf->switchdev.br_offloads = NULL; + pf->eswitch.br_offloads = NULL; kfree(br_offloads); } @@ -1205,14 +1209,14 @@ ice_eswitch_br_offloads_alloc(struct ice_pf *pf) ASSERT_RTNL(); - if (pf->switchdev.br_offloads) + if (pf->eswitch.br_offloads) return ERR_PTR(-EEXIST); br_offloads = kzalloc(sizeof(*br_offloads), GFP_KERNEL); if (!br_offloads) return ERR_PTR(-ENOMEM); - pf->switchdev.br_offloads = br_offloads; + pf->eswitch.br_offloads = br_offloads; br_offloads->pf = pf; return br_offloads; @@ -1223,7 +1227,7 @@ ice_eswitch_br_offloads_deinit(struct ice_pf *pf) { struct ice_esw_br_offloads *br_offloads; - br_offloads = pf->switchdev.br_offloads; + br_offloads = pf->eswitch.br_offloads; if (!br_offloads) return; diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index a34083567e6f..78b833b3e1d7 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -129,7 +129,7 @@ static const struct ice_stats ice_gstrings_pf_stats[] = { ICE_PF_STAT("rx_oversize.nic", stats.rx_oversize), ICE_PF_STAT("rx_jabber.nic", stats.rx_jabber), ICE_PF_STAT("rx_csum_bad.nic", hw_csum_rx_error), - ICE_PF_STAT("rx_length_errors.nic", stats.rx_len_errors), + ICE_PF_STAT("rx_eipe_error.nic", hw_rx_eipe_error), ICE_PF_STAT("rx_dropped.nic", stats.eth.rx_discards), ICE_PF_STAT("rx_crc_errors.nic", stats.crc_errors), ICE_PF_STAT("illegal_bytes.nic", stats.illegal_bytes), @@ -802,7 +802,7 @@ static int ice_lbtest_create_frame(struct ice_pf *pf, u8 **ret_data, u16 size) if (!pf) return -EINVAL; - data = devm_kzalloc(ice_pf_to_dev(pf), size, GFP_KERNEL); + data = kzalloc(size, GFP_KERNEL); if (!data) return -ENOMEM; @@ -941,15 +941,13 @@ static u64 ice_loopback_test(struct net_device *netdev) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *orig_vsi = np->vsi, *test_vsi; struct ice_pf *pf = orig_vsi->back; + u8 *tx_frame __free(kfree) = NULL; u8 broadcast[ETH_ALEN], ret = 0; int num_frames, valid_frames; struct ice_tx_ring *tx_ring; struct ice_rx_ring *rx_ring; - struct device *dev; - u8 *tx_frame; int i; - dev = ice_pf_to_dev(pf); netdev_info(netdev, "loopback test\n"); test_vsi = ice_lb_vsi_setup(pf, pf->hw.port_info); @@ -994,7 +992,7 @@ static u64 ice_loopback_test(struct net_device *netdev) for (i = 0; i < num_frames; i++) { if (ice_diag_send(tx_ring, tx_frame, ICE_LB_FRAME_SIZE)) { ret = 8; - goto lbtest_free_frame; + goto remove_mac_filters; } } @@ -1004,8 +1002,6 @@ static u64 ice_loopback_test(struct net_device *netdev) else if (valid_frames != num_frames) ret = 10; -lbtest_free_frame: - devm_kfree(dev, tx_frame); remove_mac_filters: if (ice_fltr_remove_mac(test_vsi, broadcast, ICE_FWD_TO_VSI)) netdev_err(netdev, "Could not remove MAC filter for the test VSI\n"); @@ -1142,8 +1138,7 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data, switch (stringset) { case ETH_SS_STATS: for (i = 0; i < ICE_VSI_STATS_LEN; i++) - ethtool_sprintf(&p, "%s", - ice_gstrings_vsi_stats[i].stat_string); + ethtool_puts(&p, ice_gstrings_vsi_stats[i].stat_string); if (ice_is_port_repr_netdev(netdev)) return; @@ -1162,8 +1157,7 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data, return; for (i = 0; i < ICE_PF_STATS_LEN; i++) - ethtool_sprintf(&p, "%s", - ice_gstrings_pf_stats[i].stat_string); + ethtool_puts(&p, ice_gstrings_pf_stats[i].stat_string); for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) { ethtool_sprintf(&p, "tx_priority_%u_xon.nic", i); @@ -1179,8 +1173,7 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data, break; case ETH_SS_PRIV_FLAGS: for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) - ethtool_sprintf(&p, "%s", - ice_gstrings_priv_flags[i].name); + ethtool_puts(&p, ice_gstrings_priv_flags[i].name); break; default: break; @@ -1850,14 +1843,14 @@ ice_phy_type_to_ethtool(struct net_device *netdev, linkmode_zero(ks->link_modes.supported); linkmode_zero(ks->link_modes.advertising); - for (i = 0; i < BITS_PER_TYPE(u64); i++) { + for (i = 0; i < ARRAY_SIZE(phy_type_low_lkup); i++) { if (phy_types_low & BIT_ULL(i)) ice_linkmode_set_bit(&phy_type_low_lkup[i], ks, req_speeds, advert_phy_type_lo, i); } - for (i = 0; i < BITS_PER_TYPE(u64); i++) { + for (i = 0; i < ARRAY_SIZE(phy_type_high_lkup); i++) { if (phy_types_high & BIT_ULL(i)) ice_linkmode_set_bit(&phy_type_high_lkup[i], ks, req_speeds, advert_phy_type_hi, @@ -2490,6 +2483,24 @@ static u32 ice_parse_hdrs(struct ethtool_rxnfc *nfc) case SCTP_V4_FLOW: hdrs |= ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4; break; + case GTPU_V4_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV4; + break; + case GTPC_V4_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV4; + break; + case GTPC_TEID_V4_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV4; + break; + case GTPU_EH_V4_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV4; + break; + case GTPU_UL_V4_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV4; + break; + case GTPU_DL_V4_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV4; + break; case TCP_V6_FLOW: hdrs |= ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6; break; @@ -2499,33 +2510,39 @@ static u32 ice_parse_hdrs(struct ethtool_rxnfc *nfc) case SCTP_V6_FLOW: hdrs |= ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6; break; + case GTPU_V6_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV6; + break; + case GTPC_V6_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV6; + break; + case GTPC_TEID_V6_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV6; + break; + case GTPU_EH_V6_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV6; + break; + case GTPU_UL_V6_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV6; + break; + case GTPU_DL_V6_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV6; + break; default: break; } return hdrs; } -#define ICE_FLOW_HASH_FLD_IPV4_SA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) -#define ICE_FLOW_HASH_FLD_IPV6_SA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA) -#define ICE_FLOW_HASH_FLD_IPV4_DA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) -#define ICE_FLOW_HASH_FLD_IPV6_DA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA) -#define ICE_FLOW_HASH_FLD_TCP_SRC_PORT BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT) -#define ICE_FLOW_HASH_FLD_TCP_DST_PORT BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT) -#define ICE_FLOW_HASH_FLD_UDP_SRC_PORT BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT) -#define ICE_FLOW_HASH_FLD_UDP_DST_PORT BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT) -#define ICE_FLOW_HASH_FLD_SCTP_SRC_PORT \ - BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT) -#define ICE_FLOW_HASH_FLD_SCTP_DST_PORT \ - BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT) - /** * ice_parse_hash_flds - parses hash fields from RSS hash input * @nfc: ethtool rxnfc command + * @symm: true if Symmetric Topelitz is set * * This function parses the rxnfc command and returns intended * hash fields for RSS configuration */ -static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc) +static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc, bool symm) { u64 hfld = ICE_HASH_INVALID; @@ -2534,6 +2551,12 @@ static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc) case TCP_V4_FLOW: case UDP_V4_FLOW: case SCTP_V4_FLOW: + case GTPU_V4_FLOW: + case GTPC_V4_FLOW: + case GTPC_TEID_V4_FLOW: + case GTPU_EH_V4_FLOW: + case GTPU_UL_V4_FLOW: + case GTPU_DL_V4_FLOW: if (nfc->data & RXH_IP_SRC) hfld |= ICE_FLOW_HASH_FLD_IPV4_SA; if (nfc->data & RXH_IP_DST) @@ -2542,6 +2565,12 @@ static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc) case TCP_V6_FLOW: case UDP_V6_FLOW: case SCTP_V6_FLOW: + case GTPU_V6_FLOW: + case GTPC_V6_FLOW: + case GTPC_TEID_V6_FLOW: + case GTPU_EH_V6_FLOW: + case GTPU_UL_V6_FLOW: + case GTPU_DL_V6_FLOW: if (nfc->data & RXH_IP_SRC) hfld |= ICE_FLOW_HASH_FLD_IPV6_SA; if (nfc->data & RXH_IP_DST) @@ -2580,6 +2609,33 @@ static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc) } } + if (nfc->data & RXH_GTP_TEID) { + switch (nfc->flow_type) { + case GTPC_TEID_V4_FLOW: + case GTPC_TEID_V6_FLOW: + hfld |= ICE_FLOW_HASH_FLD_GTPC_TEID; + break; + case GTPU_V4_FLOW: + case GTPU_V6_FLOW: + hfld |= ICE_FLOW_HASH_FLD_GTPU_IP_TEID; + break; + case GTPU_EH_V4_FLOW: + case GTPU_EH_V6_FLOW: + hfld |= ICE_FLOW_HASH_FLD_GTPU_EH_TEID; + break; + case GTPU_UL_V4_FLOW: + case GTPU_UL_V6_FLOW: + hfld |= ICE_FLOW_HASH_FLD_GTPU_UP_TEID; + break; + case GTPU_DL_V4_FLOW: + case GTPU_DL_V6_FLOW: + hfld |= ICE_FLOW_HASH_FLD_GTPU_DWN_TEID; + break; + default: + break; + } + } + return hfld; } @@ -2594,9 +2650,11 @@ static int ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) { struct ice_pf *pf = vsi->back; + struct ice_rss_hash_cfg cfg; struct device *dev; u64 hashed_flds; int status; + bool symm; u32 hdrs; dev = ice_pf_to_dev(pf); @@ -2606,7 +2664,8 @@ ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) return -EINVAL; } - hashed_flds = ice_parse_hash_flds(nfc); + symm = !!(vsi->rss_hfunc == ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ); + hashed_flds = ice_parse_hash_flds(nfc, symm); if (hashed_flds == ICE_HASH_INVALID) { dev_dbg(dev, "Invalid hash fields, vsi num = %d\n", vsi->vsi_num); @@ -2620,7 +2679,12 @@ ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) return -EINVAL; } - status = ice_add_rss_cfg(&pf->hw, vsi->idx, hashed_flds, hdrs); + cfg.hash_flds = hashed_flds; + cfg.addl_hdrs = hdrs; + cfg.hdr_type = ICE_RSS_ANY_HEADERS; + cfg.symm = symm; + + status = ice_add_rss_cfg(&pf->hw, vsi, &cfg); if (status) { dev_dbg(dev, "ice_add_rss_cfg failed, vsi num = %d, error = %d\n", vsi->vsi_num, status); @@ -2641,6 +2705,7 @@ ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) struct ice_pf *pf = vsi->back; struct device *dev; u64 hash_flds; + bool symm; u32 hdrs; dev = ice_pf_to_dev(pf); @@ -2659,7 +2724,7 @@ ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) return; } - hash_flds = ice_get_rss_cfg(&pf->hw, vsi->idx, hdrs); + hash_flds = ice_get_rss_cfg(&pf->hw, vsi->idx, hdrs, &symm); if (hash_flds == ICE_HASH_INVALID) { dev_dbg(dev, "No hash fields found for the given header type, vsi num = %d\n", vsi->vsi_num); @@ -2683,6 +2748,13 @@ ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) hash_flds & ICE_FLOW_HASH_FLD_UDP_DST_PORT || hash_flds & ICE_FLOW_HASH_FLD_SCTP_DST_PORT) nfc->data |= (u64)RXH_L4_B_2_3; + + if (hash_flds & ICE_FLOW_HASH_FLD_GTPC_TEID || + hash_flds & ICE_FLOW_HASH_FLD_GTPU_IP_TEID || + hash_flds & ICE_FLOW_HASH_FLD_GTPU_EH_TEID || + hash_flds & ICE_FLOW_HASH_FLD_GTPU_UP_TEID || + hash_flds & ICE_FLOW_HASH_FLD_GTPU_DWN_TEID) + nfc->data |= (u64)RXH_GTP_TEID; } /** @@ -3198,11 +3270,18 @@ static u32 ice_get_rxfh_indir_size(struct net_device *netdev) return np->vsi->rss_table_size; } +/** + * ice_get_rxfh - get the Rx flow hash indirection table + * @netdev: network interface device structure + * @rxfh: pointer to param struct (indir, key, hfunc) + * + * Reads the indirection table directly from the hardware. + */ static int -ice_get_rxfh_context(struct net_device *netdev, u32 *indir, - u8 *key, u8 *hfunc, u32 rss_context) +ice_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh) { struct ice_netdev_priv *np = netdev_priv(netdev); + u32 rss_context = rxfh->rss_context; struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; u16 qcount, offset; @@ -3233,17 +3312,18 @@ ice_get_rxfh_context(struct net_device *netdev, u32 *indir, vsi = vsi->tc_map_vsi[rss_context]; } - if (hfunc) - *hfunc = ETH_RSS_HASH_TOP; + rxfh->hfunc = ETH_RSS_HASH_TOP; + if (vsi->rss_hfunc == ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ) + rxfh->input_xfrm |= RXH_XFRM_SYM_XOR; - if (!indir) + if (!rxfh->indir) return 0; lut = kzalloc(vsi->rss_table_size, GFP_KERNEL); if (!lut) return -ENOMEM; - err = ice_get_rss_key(vsi, key); + err = ice_get_rss_key(vsi, rxfh->key); if (err) goto out; @@ -3253,12 +3333,12 @@ ice_get_rxfh_context(struct net_device *netdev, u32 *indir, if (ice_is_adq_active(pf)) { for (i = 0; i < vsi->rss_table_size; i++) - indir[i] = offset + lut[i] % qcount; + rxfh->indir[i] = offset + lut[i] % qcount; goto out; } for (i = 0; i < vsi->rss_table_size; i++) - indir[i] = lut[i]; + rxfh->indir[i] = lut[i]; out: kfree(lut); @@ -3266,42 +3346,31 @@ out: } /** - * ice_get_rxfh - get the Rx flow hash indirection table - * @netdev: network interface device structure - * @indir: indirection table - * @key: hash key - * @hfunc: hash function - * - * Reads the indirection table directly from the hardware. - */ -static int -ice_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc) -{ - return ice_get_rxfh_context(netdev, indir, key, hfunc, 0); -} - -/** * ice_set_rxfh - set the Rx flow hash indirection table * @netdev: network interface device structure - * @indir: indirection table - * @key: hash key - * @hfunc: hash function + * @rxfh: pointer to param struct (indir, key, hfunc) + * @extack: extended ACK from the Netlink message * * Returns -EINVAL if the table specifies an invalid queue ID, otherwise * returns 0 after programming the table. */ static int -ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key, - const u8 hfunc) +ice_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack) { struct ice_netdev_priv *np = netdev_priv(netdev); + u8 hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ; struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct device *dev; int err; dev = ice_pf_to_dev(pf); - if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) + if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE && + rxfh->hfunc != ETH_RSS_HASH_TOP) + return -EOPNOTSUPP; + + if (rxfh->rss_context) return -EOPNOTSUPP; if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { @@ -3315,7 +3384,15 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key, return -EOPNOTSUPP; } - if (key) { + /* Update the VSI's hash function */ + if (rxfh->input_xfrm & RXH_XFRM_SYM_XOR) + hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ; + + err = ice_set_rss_hfunc(vsi, hfunc); + if (err) + return err; + + if (rxfh->key) { if (!vsi->rss_hkey_user) { vsi->rss_hkey_user = devm_kzalloc(dev, ICE_VSIQF_HKEY_ARRAY_SIZE, @@ -3323,7 +3400,8 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key, if (!vsi->rss_hkey_user) return -ENOMEM; } - memcpy(vsi->rss_hkey_user, key, ICE_VSIQF_HKEY_ARRAY_SIZE); + memcpy(vsi->rss_hkey_user, rxfh->key, + ICE_VSIQF_HKEY_ARRAY_SIZE); err = ice_set_rss_key(vsi, vsi->rss_hkey_user); if (err) @@ -3338,11 +3416,11 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key, } /* Each 32 bits pointed by 'indir' is stored with a lut entry */ - if (indir) { + if (rxfh->indir) { int i; for (i = 0; i < vsi->rss_table_size; i++) - vsi->rss_lut_user[i] = (u8)(indir[i]); + vsi->rss_lut_user[i] = (u8)(rxfh->indir[i]); } else { ice_fill_rss_lut(vsi->rss_lut_user, vsi->rss_table_size, vsi->rss_size); @@ -3361,7 +3439,7 @@ ice_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) struct ice_pf *pf = ice_netdev_to_pf(dev); /* only report timestamping if PTP is enabled */ - if (!test_bit(ICE_FLAG_PTP, pf->flags)) + if (pf->ptp.state != ICE_PTP_READY) return ethtool_op_get_ts_info(dev, info); info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | @@ -4220,9 +4298,11 @@ ice_get_module_eeprom(struct net_device *netdev, } static const struct ethtool_ops ice_ethtool_ops = { + .cap_rss_ctx_supported = true, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE | ETHTOOL_COALESCE_RX_USECS_HIGH, + .cap_rss_sym_xor_supported = true, .get_link_ksettings = ice_get_link_ksettings, .set_link_ksettings = ice_set_link_ksettings, .get_drvinfo = ice_get_drvinfo, @@ -4253,7 +4333,6 @@ static const struct ethtool_ops ice_ethtool_ops = { .set_pauseparam = ice_set_pauseparam, .get_rxfh_key_size = ice_get_rxfh_key_size, .get_rxfh_indir_size = ice_get_rxfh_indir_size, - .get_rxfh_context = ice_get_rxfh_context, .get_rxfh = ice_get_rxfh, .set_rxfh = ice_set_rxfh, .get_channels = ice_get_channels, diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index d151e5bacfec..e3cab8e98f52 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -41,6 +41,8 @@ static struct in6_addr zero_ipv6_addr_mask = { static int ice_fltr_to_ethtool_flow(enum ice_fltr_ptype flow) { switch (flow) { + case ICE_FLTR_PTYPE_NONF_ETH: + return ETHER_FLOW; case ICE_FLTR_PTYPE_NONF_IPV4_TCP: return TCP_V4_FLOW; case ICE_FLTR_PTYPE_NONF_IPV4_UDP: @@ -72,6 +74,8 @@ static int ice_fltr_to_ethtool_flow(enum ice_fltr_ptype flow) static enum ice_fltr_ptype ice_ethtool_flow_to_fltr(int eth) { switch (eth) { + case ETHER_FLOW: + return ICE_FLTR_PTYPE_NONF_ETH; case TCP_V4_FLOW: return ICE_FLTR_PTYPE_NONF_IPV4_TCP; case UDP_V4_FLOW: @@ -137,6 +141,10 @@ int ice_get_ethtool_fdir_entry(struct ice_hw *hw, struct ethtool_rxnfc *cmd) memset(&fsp->m_ext, 0, sizeof(fsp->m_ext)); switch (fsp->flow_type) { + case ETHER_FLOW: + fsp->h_u.ether_spec = rule->eth; + fsp->m_u.ether_spec = rule->eth_mask; + break; case IPV4_USER_FLOW: fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4; fsp->h_u.usr_ip4_spec.proto = 0; @@ -302,9 +310,7 @@ void ice_fdir_rem_adq_chnl(struct ice_hw *hw, u16 vsi_idx) continue; for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) { - u64 prof_id; - - prof_id = flow + tun * ICE_FLTR_PTYPE_MAX; + u64 prof_id = prof->prof_id[tun]; for (i = 0; i < prof->cnt; i++) { if (prof->vsi_h[i] != vsi_idx) @@ -362,10 +368,9 @@ ice_fdir_erase_flow_from_hw(struct ice_hw *hw, enum ice_block blk, int flow) return; for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) { - u64 prof_id; + u64 prof_id = prof->prof_id[tun]; int j; - prof_id = flow + tun * ICE_FLTR_PTYPE_MAX; for (j = 0; j < prof->cnt; j++) { u16 vsi_num; @@ -439,14 +444,12 @@ void ice_fdir_replay_flows(struct ice_hw *hw) for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) { struct ice_flow_prof *hw_prof; struct ice_fd_hw_prof *prof; - u64 prof_id; int j; prof = hw->fdir_prof[flow]; - prof_id = flow + tun * ICE_FLTR_PTYPE_MAX; - ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof_id, + ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof->fdir_seg[tun], TNL_SEG_CNT(tun), - &hw_prof); + false, &hw_prof); for (j = 0; j < prof->cnt; j++) { enum ice_flow_priority prio; u64 entry_h = 0; @@ -454,7 +457,7 @@ void ice_fdir_replay_flows(struct ice_hw *hw) prio = ICE_FLOW_PRIO_NORMAL; err = ice_flow_add_entry(hw, ICE_BLK_FD, - prof_id, + hw_prof->id, prof->vsi_h[0], prof->vsi_h[j], prio, prof->fdir_seg, @@ -464,6 +467,7 @@ void ice_fdir_replay_flows(struct ice_hw *hw) flow); continue; } + prof->prof_id[tun] = hw_prof->id; prof->entry_h[j][tun] = entry_h; } } @@ -507,8 +511,7 @@ ice_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp, return -EINVAL; data->flex_word = value & ICE_USERDEF_FLEX_WORD_M; - data->flex_offset = (value & ICE_USERDEF_FLEX_OFFS_M) >> - ICE_USERDEF_FLEX_OFFS_S; + data->flex_offset = FIELD_GET(ICE_USERDEF_FLEX_OFFS_M, value); if (data->flex_offset > ICE_USERDEF_FLEX_MAX_OFFS_VAL) return -EINVAL; @@ -638,7 +641,6 @@ ice_fdir_set_hw_fltr_rule(struct ice_pf *pf, struct ice_flow_seg_info *seg, u64 entry1_h = 0; u64 entry2_h = 0; bool del_last; - u64 prof_id; int err; int idx; @@ -668,7 +670,7 @@ ice_fdir_set_hw_fltr_rule(struct ice_pf *pf, struct ice_flow_seg_info *seg, * then return error. */ if (hw->fdir_fltr_cnt[flow]) { - dev_err(dev, "Failed to add filter. Flow director filters on each port must have the same input set.\n"); + dev_err(dev, "Failed to add filter. Flow director filters on each port must have the same input set.\n"); return -EINVAL; } @@ -686,23 +688,23 @@ ice_fdir_set_hw_fltr_rule(struct ice_pf *pf, struct ice_flow_seg_info *seg, * That is the final parameters are 1 header (segment), no * actions (NULL) and zero actions 0. */ - prof_id = flow + tun * ICE_FLTR_PTYPE_MAX; - err = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof_id, seg, - TNL_SEG_CNT(tun), &prof); + err = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, seg, + TNL_SEG_CNT(tun), false, &prof); if (err) return err; - err = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, main_vsi->idx, + err = ice_flow_add_entry(hw, ICE_BLK_FD, prof->id, main_vsi->idx, main_vsi->idx, ICE_FLOW_PRIO_NORMAL, seg, &entry1_h); if (err) goto err_prof; - err = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, main_vsi->idx, + err = ice_flow_add_entry(hw, ICE_BLK_FD, prof->id, main_vsi->idx, ctrl_vsi->idx, ICE_FLOW_PRIO_NORMAL, seg, &entry2_h); if (err) goto err_entry; hw_prof->fdir_seg[tun] = seg; + hw_prof->prof_id[tun] = prof->id; hw_prof->entry_h[0][tun] = entry1_h; hw_prof->entry_h[1][tun] = entry2_h; hw_prof->vsi_h[0] = main_vsi->idx; @@ -719,7 +721,7 @@ ice_fdir_set_hw_fltr_rule(struct ice_pf *pf, struct ice_flow_seg_info *seg, entry1_h = 0; vsi_h = main_vsi->tc_map_vsi[idx]->idx; - err = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, + err = ice_flow_add_entry(hw, ICE_BLK_FD, prof->id, main_vsi->idx, vsi_h, ICE_FLOW_PRIO_NORMAL, seg, &entry1_h); @@ -756,7 +758,7 @@ err_unroll: if (!hw_prof->entry_h[idx][tun]) continue; - ice_rem_prof_id_flow(hw, ICE_BLK_FD, vsi_num, prof_id); + ice_rem_prof_id_flow(hw, ICE_BLK_FD, vsi_num, prof->id); ice_flow_rem_entry(hw, ICE_BLK_FD, hw_prof->entry_h[idx][tun]); hw_prof->entry_h[idx][tun] = 0; if (del_last) @@ -766,11 +768,11 @@ err_unroll: hw_prof->cnt = 0; err_entry: ice_rem_prof_id_flow(hw, ICE_BLK_FD, - ice_get_hw_vsi_num(hw, main_vsi->idx), prof_id); + ice_get_hw_vsi_num(hw, main_vsi->idx), prof->id); ice_flow_rem_entry(hw, ICE_BLK_FD, entry1_h); err_prof: - ice_flow_rem_prof(hw, ICE_BLK_FD, prof_id); - dev_err(dev, "Failed to add filter. Flow director filters on each port must have the same input set.\n"); + ice_flow_rem_prof(hw, ICE_BLK_FD, prof->id); + dev_err(dev, "Failed to add filter. Flow director filters on each port must have the same input set.\n"); return err; } @@ -1200,6 +1202,122 @@ ice_set_fdir_ip6_usr_seg(struct ice_flow_seg_info *seg, } /** + * ice_fdir_vlan_valid - validate VLAN data for Flow Director rule + * @dev: network interface device structure + * @fsp: pointer to ethtool Rx flow specification + * + * Return: true if vlan data is valid, false otherwise + */ +static bool ice_fdir_vlan_valid(struct device *dev, + struct ethtool_rx_flow_spec *fsp) +{ + if (fsp->m_ext.vlan_etype && !eth_type_vlan(fsp->h_ext.vlan_etype)) + return false; + + if (fsp->m_ext.vlan_tci && ntohs(fsp->h_ext.vlan_tci) >= VLAN_N_VID) + return false; + + /* proto and vlan must have vlan-etype defined */ + if (fsp->m_u.ether_spec.h_proto && fsp->m_ext.vlan_tci && + !fsp->m_ext.vlan_etype) { + dev_warn(dev, "Filter with proto and vlan require also vlan-etype"); + return false; + } + + return true; +} + +/** + * ice_set_ether_flow_seg - set address and protocol segments for ether flow + * @dev: network interface device structure + * @seg: flow segment for programming + * @eth_spec: mask data from ethtool + * + * Return: 0 on success and errno in case of error. + */ +static int ice_set_ether_flow_seg(struct device *dev, + struct ice_flow_seg_info *seg, + struct ethhdr *eth_spec) +{ + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_ETH); + + /* empty rules are not valid */ + if (is_zero_ether_addr(eth_spec->h_source) && + is_zero_ether_addr(eth_spec->h_dest) && + !eth_spec->h_proto) + return -EINVAL; + + /* Ethertype */ + if (eth_spec->h_proto == htons(0xFFFF)) { + ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_ETH_TYPE, + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, false); + } else if (eth_spec->h_proto) { + dev_warn(dev, "Only 0x0000 or 0xffff proto mask is allowed for flow-type ether"); + return -EOPNOTSUPP; + } + + /* Source MAC address */ + if (is_broadcast_ether_addr(eth_spec->h_source)) + ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_ETH_SA, + ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, false); + else if (!is_zero_ether_addr(eth_spec->h_source)) + goto err_mask; + + /* Destination MAC address */ + if (is_broadcast_ether_addr(eth_spec->h_dest)) + ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_ETH_DA, + ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, false); + else if (!is_zero_ether_addr(eth_spec->h_dest)) + goto err_mask; + + return 0; + +err_mask: + dev_warn(dev, "Only 00:00:00:00:00:00 or ff:ff:ff:ff:ff:ff MAC address mask is allowed for flow-type ether"); + return -EOPNOTSUPP; +} + +/** + * ice_set_fdir_vlan_seg - set vlan segments for ether flow + * @seg: flow segment for programming + * @ext_masks: masks for additional RX flow fields + * + * Return: 0 on success and errno in case of error. + */ +static int +ice_set_fdir_vlan_seg(struct ice_flow_seg_info *seg, + struct ethtool_flow_ext *ext_masks) +{ + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_VLAN); + + if (ext_masks->vlan_etype) { + if (ext_masks->vlan_etype != htons(0xFFFF)) + return -EOPNOTSUPP; + + ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_S_VLAN, + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, false); + } + + if (ext_masks->vlan_tci) { + if (ext_masks->vlan_tci != htons(0xFFFF)) + return -EOPNOTSUPP; + + ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_C_VLAN, + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, false); + } + + return 0; +} + +/** * ice_cfg_fdir_xtrct_seq - Configure extraction sequence for the given filter * @pf: PF structure * @fsp: pointer to ethtool Rx flow specification @@ -1215,7 +1333,7 @@ ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp, struct device *dev = ice_pf_to_dev(pf); enum ice_fltr_ptype fltr_idx; struct ice_hw *hw = &pf->hw; - bool perfect_filter; + bool perfect_filter = false; int ret; seg = devm_kzalloc(dev, sizeof(*seg), GFP_KERNEL); @@ -1268,6 +1386,16 @@ ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp, ret = ice_set_fdir_ip6_usr_seg(seg, &fsp->m_u.usr_ip6_spec, &perfect_filter); break; + case ETHER_FLOW: + ret = ice_set_ether_flow_seg(dev, seg, &fsp->m_u.ether_spec); + if (!ret && (fsp->m_ext.vlan_etype || fsp->m_ext.vlan_tci)) { + if (!ice_fdir_vlan_valid(dev, fsp)) { + ret = -EINVAL; + break; + } + ret = ice_set_fdir_vlan_seg(seg, &fsp->m_ext); + } + break; default: ret = -EINVAL; } @@ -1829,6 +1957,10 @@ ice_set_fdir_input_set(struct ice_vsi *vsi, struct ethtool_rx_flow_spec *fsp, input->mask.v6.tc = fsp->m_u.usr_ip6_spec.tclass; input->mask.v6.proto = fsp->m_u.usr_ip6_spec.l4_proto; break; + case ETHER_FLOW: + input->eth = fsp->h_u.ether_spec; + input->eth_mask = fsp->m_u.ether_spec; + break; default: /* not doing un-parsed flow types */ return -EINVAL; @@ -1853,6 +1985,7 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd) struct ice_pf *pf; struct ice_hw *hw; int fltrs_needed; + u32 max_location; u16 tunnel_port; int ret; @@ -1884,8 +2017,10 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd) if (ret) return ret; - if (fsp->location >= ice_get_fdir_cnt_all(hw)) { - dev_err(dev, "Failed to add filter. The maximum number of flow director filters has been reached.\n"); + max_location = ice_get_fdir_cnt_all(hw); + if (fsp->location >= max_location) { + dev_err(dev, "Failed to add filter. The number of ntuple filters or provided location exceed max %d.\n", + max_location); return -ENOSPC; } @@ -1893,7 +2028,7 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd) fltrs_needed = ice_get_open_tunnel_port(hw, &tunnel_port, TNL_ALL) ? 2 : 1; if (!ice_fdir_find_fltr_by_idx(hw, fsp->location) && ice_fdir_num_avail_fltr(hw, pf->vsi[vsi->idx]) < fltrs_needed) { - dev_err(dev, "Failed to add filter. The maximum number of flow director filters has been reached.\n"); + dev_err(dev, "Failed to add filter. The maximum number of flow director filters has been reached.\n"); return -ENOSPC; } diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c index ae089d32ee9d..26b357c0ae15 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_fdir.c @@ -4,6 +4,8 @@ #include "ice_common.h" /* These are training packet headers used to program flow director filters. */ +static const u8 ice_fdir_eth_pkt[22]; + static const u8 ice_fdir_tcpv4_pkt[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00, @@ -417,6 +419,11 @@ static const u8 ice_fdir_ip6_tun_pkt[] = { /* Flow Director no-op training packet table */ static const struct ice_fdir_base_pkt ice_fdir_pkt[] = { { + ICE_FLTR_PTYPE_NONF_ETH, + sizeof(ice_fdir_eth_pkt), ice_fdir_eth_pkt, + sizeof(ice_fdir_eth_pkt), ice_fdir_eth_pkt, + }, + { ICE_FLTR_PTYPE_NONF_IPV4_TCP, sizeof(ice_fdir_tcpv4_pkt), ice_fdir_tcpv4_pkt, sizeof(ice_fdir_tcp4_tun_pkt), ice_fdir_tcp4_tun_pkt, @@ -604,55 +611,32 @@ ice_set_fd_desc_val(struct ice_fd_fltr_desc_ctx *ctx, u64 qword; /* prep QW0 of FD filter programming desc */ - qword = ((u64)ctx->qindex << ICE_FXD_FLTR_QW0_QINDEX_S) & - ICE_FXD_FLTR_QW0_QINDEX_M; - qword |= ((u64)ctx->comp_q << ICE_FXD_FLTR_QW0_COMP_Q_S) & - ICE_FXD_FLTR_QW0_COMP_Q_M; - qword |= ((u64)ctx->comp_report << ICE_FXD_FLTR_QW0_COMP_REPORT_S) & - ICE_FXD_FLTR_QW0_COMP_REPORT_M; - qword |= ((u64)ctx->fd_space << ICE_FXD_FLTR_QW0_FD_SPACE_S) & - ICE_FXD_FLTR_QW0_FD_SPACE_M; - qword |= ((u64)ctx->cnt_index << ICE_FXD_FLTR_QW0_STAT_CNT_S) & - ICE_FXD_FLTR_QW0_STAT_CNT_M; - qword |= ((u64)ctx->cnt_ena << ICE_FXD_FLTR_QW0_STAT_ENA_S) & - ICE_FXD_FLTR_QW0_STAT_ENA_M; - qword |= ((u64)ctx->evict_ena << ICE_FXD_FLTR_QW0_EVICT_ENA_S) & - ICE_FXD_FLTR_QW0_EVICT_ENA_M; - qword |= ((u64)ctx->toq << ICE_FXD_FLTR_QW0_TO_Q_S) & - ICE_FXD_FLTR_QW0_TO_Q_M; - qword |= ((u64)ctx->toq_prio << ICE_FXD_FLTR_QW0_TO_Q_PRI_S) & - ICE_FXD_FLTR_QW0_TO_Q_PRI_M; - qword |= ((u64)ctx->dpu_recipe << ICE_FXD_FLTR_QW0_DPU_RECIPE_S) & - ICE_FXD_FLTR_QW0_DPU_RECIPE_M; - qword |= ((u64)ctx->drop << ICE_FXD_FLTR_QW0_DROP_S) & - ICE_FXD_FLTR_QW0_DROP_M; - qword |= ((u64)ctx->flex_prio << ICE_FXD_FLTR_QW0_FLEX_PRI_S) & - ICE_FXD_FLTR_QW0_FLEX_PRI_M; - qword |= ((u64)ctx->flex_mdid << ICE_FXD_FLTR_QW0_FLEX_MDID_S) & - ICE_FXD_FLTR_QW0_FLEX_MDID_M; - qword |= ((u64)ctx->flex_val << ICE_FXD_FLTR_QW0_FLEX_VAL_S) & - ICE_FXD_FLTR_QW0_FLEX_VAL_M; + qword = FIELD_PREP(ICE_FXD_FLTR_QW0_QINDEX_M, ctx->qindex); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_COMP_Q_M, ctx->comp_q); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_COMP_REPORT_M, ctx->comp_report); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_FD_SPACE_M, ctx->fd_space); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_STAT_CNT_M, ctx->cnt_index); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_STAT_ENA_M, ctx->cnt_ena); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_EVICT_ENA_M, ctx->evict_ena); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_TO_Q_M, ctx->toq); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_TO_Q_PRI_M, ctx->toq_prio); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_DPU_RECIPE_M, ctx->dpu_recipe); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_DROP_M, ctx->drop); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_FLEX_PRI_M, ctx->flex_prio); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_FLEX_MDID_M, ctx->flex_mdid); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_FLEX_VAL_M, ctx->flex_val); fdir_desc->qidx_compq_space_stat = cpu_to_le64(qword); /* prep QW1 of FD filter programming desc */ - qword = ((u64)ctx->dtype << ICE_FXD_FLTR_QW1_DTYPE_S) & - ICE_FXD_FLTR_QW1_DTYPE_M; - qword |= ((u64)ctx->pcmd << ICE_FXD_FLTR_QW1_PCMD_S) & - ICE_FXD_FLTR_QW1_PCMD_M; - qword |= ((u64)ctx->desc_prof_prio << ICE_FXD_FLTR_QW1_PROF_PRI_S) & - ICE_FXD_FLTR_QW1_PROF_PRI_M; - qword |= ((u64)ctx->desc_prof << ICE_FXD_FLTR_QW1_PROF_S) & - ICE_FXD_FLTR_QW1_PROF_M; - qword |= ((u64)ctx->fd_vsi << ICE_FXD_FLTR_QW1_FD_VSI_S) & - ICE_FXD_FLTR_QW1_FD_VSI_M; - qword |= ((u64)ctx->swap << ICE_FXD_FLTR_QW1_SWAP_S) & - ICE_FXD_FLTR_QW1_SWAP_M; - qword |= ((u64)ctx->fdid_prio << ICE_FXD_FLTR_QW1_FDID_PRI_S) & - ICE_FXD_FLTR_QW1_FDID_PRI_M; - qword |= ((u64)ctx->fdid_mdid << ICE_FXD_FLTR_QW1_FDID_MDID_S) & - ICE_FXD_FLTR_QW1_FDID_MDID_M; - qword |= ((u64)ctx->fdid << ICE_FXD_FLTR_QW1_FDID_S) & - ICE_FXD_FLTR_QW1_FDID_M; + qword = FIELD_PREP(ICE_FXD_FLTR_QW1_DTYPE_M, ctx->dtype); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_PCMD_M, ctx->pcmd); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_PROF_PRI_M, ctx->desc_prof_prio); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_PROF_M, ctx->desc_prof); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_FD_VSI_M, ctx->fd_vsi); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_SWAP_M, ctx->swap); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_FDID_PRI_M, ctx->fdid_prio); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_FDID_MDID_M, ctx->fdid_mdid); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_FDID_M, ctx->fdid); fdir_desc->dtype_cmd_vsi_fdid = cpu_to_le64(qword); } @@ -937,6 +921,21 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, * perspective. The input from user is from Rx filter perspective. */ switch (flow) { + case ICE_FLTR_PTYPE_NONF_ETH: + ice_pkt_insert_mac_addr(loc, input->eth.h_dest); + ice_pkt_insert_mac_addr(loc + ETH_ALEN, input->eth.h_source); + if (input->ext_data.vlan_tag || input->ext_data.vlan_type) { + ice_pkt_insert_u16(loc, ICE_ETH_TYPE_F_OFFSET, + input->ext_data.vlan_type); + ice_pkt_insert_u16(loc, ICE_ETH_VLAN_TCI_OFFSET, + input->ext_data.vlan_tag); + ice_pkt_insert_u16(loc, ICE_ETH_TYPE_VLAN_OFFSET, + input->eth.h_proto); + } else { + ice_pkt_insert_u16(loc, ICE_ETH_TYPE_F_OFFSET, + input->eth.h_proto); + } + break; case ICE_FLTR_PTYPE_NONF_IPV4_TCP: ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET, input->ip.v4.src_ip); @@ -1212,52 +1211,58 @@ static int ice_cmp_ipv6_addr(__be32 *a, __be32 *b) * ice_fdir_comp_rules - compare 2 filters * @a: a Flow Director filter data structure * @b: a Flow Director filter data structure - * @v6: bool true if v6 filter * * Returns true if the filters match */ static bool -ice_fdir_comp_rules(struct ice_fdir_fltr *a, struct ice_fdir_fltr *b, bool v6) +ice_fdir_comp_rules(struct ice_fdir_fltr *a, struct ice_fdir_fltr *b) { enum ice_fltr_ptype flow_type = a->flow_type; /* The calling function already checks that the two filters have the * same flow_type. */ - if (!v6) { - if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV4_SCTP) { - if (a->ip.v4.dst_ip == b->ip.v4.dst_ip && - a->ip.v4.src_ip == b->ip.v4.src_ip && - a->ip.v4.dst_port == b->ip.v4.dst_port && - a->ip.v4.src_port == b->ip.v4.src_port) - return true; - } else if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_OTHER) { - if (a->ip.v4.dst_ip == b->ip.v4.dst_ip && - a->ip.v4.src_ip == b->ip.v4.src_ip && - a->ip.v4.l4_header == b->ip.v4.l4_header && - a->ip.v4.proto == b->ip.v4.proto && - a->ip.v4.ip_ver == b->ip.v4.ip_ver && - a->ip.v4.tos == b->ip.v4.tos) - return true; - } - } else { - if (flow_type == ICE_FLTR_PTYPE_NONF_IPV6_UDP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV6_TCP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV6_SCTP) { - if (a->ip.v6.dst_port == b->ip.v6.dst_port && - a->ip.v6.src_port == b->ip.v6.src_port && - !ice_cmp_ipv6_addr(a->ip.v6.dst_ip, - b->ip.v6.dst_ip) && - !ice_cmp_ipv6_addr(a->ip.v6.src_ip, - b->ip.v6.src_ip)) - return true; - } else if (flow_type == ICE_FLTR_PTYPE_NONF_IPV6_OTHER) { - if (a->ip.v6.dst_port == b->ip.v6.dst_port && - a->ip.v6.src_port == b->ip.v6.src_port) - return true; - } + switch (flow_type) { + case ICE_FLTR_PTYPE_NONF_ETH: + if (!memcmp(&a->eth, &b->eth, sizeof(a->eth))) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV4_TCP: + case ICE_FLTR_PTYPE_NONF_IPV4_UDP: + case ICE_FLTR_PTYPE_NONF_IPV4_SCTP: + if (a->ip.v4.dst_ip == b->ip.v4.dst_ip && + a->ip.v4.src_ip == b->ip.v4.src_ip && + a->ip.v4.dst_port == b->ip.v4.dst_port && + a->ip.v4.src_port == b->ip.v4.src_port) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV4_OTHER: + if (a->ip.v4.dst_ip == b->ip.v4.dst_ip && + a->ip.v4.src_ip == b->ip.v4.src_ip && + a->ip.v4.l4_header == b->ip.v4.l4_header && + a->ip.v4.proto == b->ip.v4.proto && + a->ip.v4.ip_ver == b->ip.v4.ip_ver && + a->ip.v4.tos == b->ip.v4.tos) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV6_UDP: + case ICE_FLTR_PTYPE_NONF_IPV6_TCP: + case ICE_FLTR_PTYPE_NONF_IPV6_SCTP: + if (a->ip.v6.dst_port == b->ip.v6.dst_port && + a->ip.v6.src_port == b->ip.v6.src_port && + !ice_cmp_ipv6_addr(a->ip.v6.dst_ip, + b->ip.v6.dst_ip) && + !ice_cmp_ipv6_addr(a->ip.v6.src_ip, + b->ip.v6.src_ip)) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV6_OTHER: + if (a->ip.v6.dst_port == b->ip.v6.dst_port && + a->ip.v6.src_port == b->ip.v6.src_port) + return true; + break; + default: + break; } return false; @@ -1276,19 +1281,10 @@ bool ice_fdir_is_dup_fltr(struct ice_hw *hw, struct ice_fdir_fltr *input) bool ret = false; list_for_each_entry(rule, &hw->fdir_list_head, fltr_node) { - enum ice_fltr_ptype flow_type; - if (rule->flow_type != input->flow_type) continue; - flow_type = input->flow_type; - if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV4_SCTP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV4_OTHER) - ret = ice_fdir_comp_rules(rule, input, false); - else - ret = ice_fdir_comp_rules(rule, input, true); + ret = ice_fdir_comp_rules(rule, input); if (ret) { if (rule->fltr_id == input->fltr_id && rule->q_index != input->q_index) diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h index 1b9b84490689..021ecbac7848 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.h +++ b/drivers/net/ethernet/intel/ice/ice_fdir.h @@ -8,6 +8,9 @@ #define ICE_FDIR_MAX_RAW_PKT_SIZE (512 + ICE_FDIR_TUN_PKT_OFF) /* macros for offsets into packets for flow director programming */ +#define ICE_ETH_TYPE_F_OFFSET 12 +#define ICE_ETH_VLAN_TCI_OFFSET 14 +#define ICE_ETH_TYPE_VLAN_OFFSET 16 #define ICE_IPV4_SRC_ADDR_OFFSET 26 #define ICE_IPV4_DST_ADDR_OFFSET 30 #define ICE_IPV4_TCP_SRC_PORT_OFFSET 34 @@ -159,6 +162,8 @@ struct ice_fdir_fltr { struct list_head fltr_node; enum ice_fltr_ptype flow_type; + struct ethhdr eth, eth_mask; + union { struct ice_fdir_v4 v4; struct ice_fdir_v6 v6; diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 5ce413965930..20d5db88c99f 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -1218,11 +1218,13 @@ ice_prof_has_mask(struct ice_hw *hw, enum ice_block blk, u8 prof, u16 *masks) * @blk: HW block * @fv: field vector to search for * @masks: masks for FV + * @symm: symmetric setting for RSS flows * @prof_id: receives the profile ID */ static int ice_find_prof_id_with_mask(struct ice_hw *hw, enum ice_block blk, - struct ice_fv_word *fv, u16 *masks, u8 *prof_id) + struct ice_fv_word *fv, u16 *masks, bool symm, + u8 *prof_id) { struct ice_es *es = &hw->blk[blk].es; u8 i; @@ -1236,6 +1238,9 @@ ice_find_prof_id_with_mask(struct ice_hw *hw, enum ice_block blk, for (i = 0; i < (u8)es->count; i++) { u16 off = i * es->fvw; + if (blk == ICE_BLK_RSS && es->symm[i] != symm) + continue; + if (memcmp(&es->t[off], fv, es->fvw * sizeof(*fv))) continue; @@ -1409,13 +1414,13 @@ ice_write_prof_mask_reg(struct ice_hw *hw, enum ice_block blk, u16 mask_idx, switch (blk) { case ICE_BLK_RSS: offset = GLQF_HMASK(mask_idx); - val = (idx << GLQF_HMASK_MSK_INDEX_S) & GLQF_HMASK_MSK_INDEX_M; - val |= (mask << GLQF_HMASK_MASK_S) & GLQF_HMASK_MASK_M; + val = FIELD_PREP(GLQF_HMASK_MSK_INDEX_M, idx); + val |= FIELD_PREP(GLQF_HMASK_MASK_M, mask); break; case ICE_BLK_FD: offset = GLQF_FDMASK(mask_idx); - val = (idx << GLQF_FDMASK_MSK_INDEX_S) & GLQF_FDMASK_MSK_INDEX_M; - val |= (mask << GLQF_FDMASK_MASK_S) & GLQF_FDMASK_MASK_M; + val = FIELD_PREP(GLQF_FDMASK_MSK_INDEX_M, idx); + val |= FIELD_PREP(GLQF_FDMASK_MASK_M, mask); break; default: ice_debug(hw, ICE_DBG_PKG, "No profile masks for block %d\n", @@ -1716,15 +1721,16 @@ ice_update_prof_masking(struct ice_hw *hw, enum ice_block blk, u16 prof_id, } /** - * ice_write_es - write an extraction sequence to hardware + * ice_write_es - write an extraction sequence and symmetric setting to hardware * @hw: pointer to the HW struct * @blk: the block in which to write the extraction sequence * @prof_id: the profile ID to write * @fv: pointer to the extraction sequence to write - NULL to clear extraction + * @symm: symmetric setting for RSS profiles */ static void ice_write_es(struct ice_hw *hw, enum ice_block blk, u8 prof_id, - struct ice_fv_word *fv) + struct ice_fv_word *fv, bool symm) { u16 off; @@ -1737,6 +1743,9 @@ ice_write_es(struct ice_hw *hw, enum ice_block blk, u8 prof_id, memcpy(&hw->blk[blk].es.t[off], fv, hw->blk[blk].es.fvw * sizeof(*fv)); } + + if (blk == ICE_BLK_RSS) + hw->blk[blk].es.symm[prof_id] = symm; } /** @@ -1753,7 +1762,7 @@ ice_prof_dec_ref(struct ice_hw *hw, enum ice_block blk, u8 prof_id) if (hw->blk[blk].es.ref_count[prof_id] > 0) { if (!--hw->blk[blk].es.ref_count[prof_id]) { - ice_write_es(hw, blk, prof_id, NULL); + ice_write_es(hw, blk, prof_id, NULL, false); ice_free_prof_masks(hw, blk, prof_id); return ice_free_prof_id(hw, blk, prof_id); } @@ -2116,8 +2125,10 @@ void ice_free_hw_tbls(struct ice_hw *hw) devm_kfree(ice_hw_to_dev(hw), hw->blk[i].prof_redir.t); devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.t); devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.ref_count); + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.symm); devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.written); devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.mask_ena); + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].prof_id.id); } list_for_each_entry_safe(r, rt, &hw->rss_list_head, l_entry) { @@ -2150,6 +2161,7 @@ void ice_clear_hw_tbls(struct ice_hw *hw) for (i = 0; i < ICE_BLK_COUNT; i++) { struct ice_prof_redir *prof_redir = &hw->blk[i].prof_redir; + struct ice_prof_id *prof_id = &hw->blk[i].prof_id; struct ice_prof_tcam *prof = &hw->blk[i].prof; struct ice_xlt1 *xlt1 = &hw->blk[i].xlt1; struct ice_xlt2 *xlt2 = &hw->blk[i].xlt2; @@ -2178,8 +2190,11 @@ void ice_clear_hw_tbls(struct ice_hw *hw) memset(es->t, 0, es->count * sizeof(*es->t) * es->fvw); memset(es->ref_count, 0, es->count * sizeof(*es->ref_count)); + memset(es->symm, 0, es->count * sizeof(*es->symm)); memset(es->written, 0, es->count * sizeof(*es->written)); memset(es->mask_ena, 0, es->count * sizeof(*es->mask_ena)); + + memset(prof_id->id, 0, prof_id->count * sizeof(*prof_id->id)); } } @@ -2196,6 +2211,7 @@ int ice_init_hw_tbls(struct ice_hw *hw) ice_init_all_prof_masks(hw); for (i = 0; i < ICE_BLK_COUNT; i++) { struct ice_prof_redir *prof_redir = &hw->blk[i].prof_redir; + struct ice_prof_id *prof_id = &hw->blk[i].prof_id; struct ice_prof_tcam *prof = &hw->blk[i].prof; struct ice_xlt1 *xlt1 = &hw->blk[i].xlt1; struct ice_xlt2 *xlt2 = &hw->blk[i].xlt2; @@ -2292,6 +2308,11 @@ int ice_init_hw_tbls(struct ice_hw *hw) if (!es->ref_count) goto err; + es->symm = devm_kcalloc(ice_hw_to_dev(hw), es->count, + sizeof(*es->symm), GFP_KERNEL); + if (!es->symm) + goto err; + es->written = devm_kcalloc(ice_hw_to_dev(hw), es->count, sizeof(*es->written), GFP_KERNEL); if (!es->written) @@ -2301,6 +2322,12 @@ int ice_init_hw_tbls(struct ice_hw *hw) sizeof(*es->mask_ena), GFP_KERNEL); if (!es->mask_ena) goto err; + + prof_id->count = blk_sizes[i].prof_id; + prof_id->id = devm_kcalloc(ice_hw_to_dev(hw), prof_id->count, + sizeof(*prof_id->id), GFP_KERNEL); + if (!prof_id->id) + goto err; } return 0; @@ -2963,6 +2990,7 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, * @attr_cnt: number of elements in attr array * @es: extraction sequence (length of array is determined by the block) * @masks: mask for extraction sequence + * @symm: symmetric setting for RSS profiles * * This function registers a profile, which matches a set of PTYPES with a * particular extraction sequence. While the hardware profile is allocated @@ -2972,7 +3000,7 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, int ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], const struct ice_ptype_attributes *attr, u16 attr_cnt, - struct ice_fv_word *es, u16 *masks) + struct ice_fv_word *es, u16 *masks, bool symm) { u32 bytes = DIV_ROUND_UP(ICE_FLOW_PTYPE_MAX, BITS_PER_BYTE); DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT); @@ -2986,7 +3014,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], mutex_lock(&hw->blk[blk].es.prof_map_lock); /* search for existing profile */ - status = ice_find_prof_id_with_mask(hw, blk, es, masks, &prof_id); + status = ice_find_prof_id_with_mask(hw, blk, es, masks, symm, &prof_id); if (status) { /* allocate profile ID */ status = ice_alloc_prof_id(hw, blk, &prof_id); @@ -3009,7 +3037,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], goto err_ice_add_prof; /* and write new es */ - ice_write_es(hw, blk, prof_id, es); + ice_write_es(hw, blk, prof_id, es, symm); } ice_prof_inc_ref(hw, blk, prof_id); @@ -3097,7 +3125,7 @@ err_ice_add_prof: * This will search for a profile tracking ID which was previously added. * The profile map lock should be held before calling this function. */ -static struct ice_prof_map * +struct ice_prof_map * ice_search_prof_id(struct ice_hw *hw, enum ice_block blk, u64 id) { struct ice_prof_map *entry = NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index 7af7c8e9aa4e..b39d7cdc381f 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -42,7 +42,9 @@ bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype); int ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], const struct ice_ptype_attributes *attr, u16 attr_cnt, - struct ice_fv_word *es, u16 *masks); + struct ice_fv_word *es, u16 *masks, bool symm); +struct ice_prof_map * +ice_search_prof_id(struct ice_hw *hw, enum ice_block blk, u64 id); int ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl); int diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h index 4f42e14ed3ae..817beca591e0 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_type.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h @@ -93,6 +93,7 @@ enum ice_tunnel_type { TNL_GRETAP, TNL_GTPC, TNL_GTPU, + TNL_PFCP, __TNL_TYPE_CNT, TNL_LAST = 0xFF, TNL_ALL = 0xFF, @@ -146,6 +147,7 @@ struct ice_es { u32 *mask_ena; struct list_head prof_map; struct ice_fv_word *t; + u8 *symm; /* symmetric setting per profile (RSS blk)*/ struct mutex prof_map_lock; /* protect access to profiles list */ u8 *written; u8 reverse; /* set to true to reverse FV order */ @@ -304,10 +306,16 @@ struct ice_masks { struct ice_mask masks[ICE_PROF_MASK_COUNT]; }; +struct ice_prof_id { + unsigned long *id; + int count; +}; + /* Tables per block */ struct ice_blk_info { struct ice_xlt1 xlt1; struct ice_xlt2 xlt2; + struct ice_prof_id prof_id; struct ice_prof_tcam prof; struct ice_prof_redir prof_redir; struct ice_es es; @@ -351,7 +359,8 @@ enum ice_prof_type { ICE_PROF_TUN_GRE = 0x4, ICE_PROF_TUN_GTPU = 0x8, ICE_PROF_TUN_GTPC = 0x10, - ICE_PROF_TUN_ALL = 0x1E, + ICE_PROF_TUN_PFCP = 0x20, + ICE_PROF_TUN_ALL = 0x3E, ICE_PROF_ALL = 0xFF, }; diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index fb8b925aaf8b..fc2b58f56279 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -1235,6 +1235,7 @@ ice_flow_proc_segs(struct ice_hw *hw, struct ice_flow_prof_params *params) #define ICE_FLOW_FIND_PROF_CHK_FLDS 0x00000001 #define ICE_FLOW_FIND_PROF_CHK_VSI 0x00000002 #define ICE_FLOW_FIND_PROF_NOT_CHK_DIR 0x00000004 +#define ICE_FLOW_FIND_PROF_CHK_SYMM 0x00000008 /** * ice_flow_find_prof_conds - Find a profile matching headers and conditions @@ -1243,13 +1244,14 @@ ice_flow_proc_segs(struct ice_hw *hw, struct ice_flow_prof_params *params) * @dir: flow direction * @segs: array of one or more packet segments that describe the flow * @segs_cnt: number of packet segments provided + * @symm: symmetric setting for RSS profiles * @vsi_handle: software VSI handle to check VSI (ICE_FLOW_FIND_PROF_CHK_VSI) * @conds: additional conditions to be checked (ICE_FLOW_FIND_PROF_CHK_*) */ static struct ice_flow_prof * ice_flow_find_prof_conds(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir, struct ice_flow_seg_info *segs, - u8 segs_cnt, u16 vsi_handle, u32 conds) + u8 segs_cnt, bool symm, u16 vsi_handle, u32 conds) { struct ice_flow_prof *p, *prof = NULL; @@ -1265,6 +1267,11 @@ ice_flow_find_prof_conds(struct ice_hw *hw, enum ice_block blk, !test_bit(vsi_handle, p->vsis)) continue; + /* Check for symmetric settings */ + if ((conds & ICE_FLOW_FIND_PROF_CHK_SYMM) && + p->symm != symm) + continue; + /* Protocol headers must be checked. Matched fields are * checked if specified. */ @@ -1328,26 +1335,33 @@ ice_flow_rem_entry_sync(struct ice_hw *hw, enum ice_block __always_unused blk, * @hw: pointer to the HW struct * @blk: classification stage * @dir: flow direction - * @prof_id: unique ID to identify this flow profile * @segs: array of one or more packet segments that describe the flow * @segs_cnt: number of packet segments provided + * @symm: symmetric setting for RSS profiles * @prof: stores the returned flow profile added * * Assumption: the caller has acquired the lock to the profile list */ static int ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk, - enum ice_flow_dir dir, u64 prof_id, + enum ice_flow_dir dir, struct ice_flow_seg_info *segs, u8 segs_cnt, - struct ice_flow_prof **prof) + bool symm, struct ice_flow_prof **prof) { struct ice_flow_prof_params *params; + struct ice_prof_id *ids; int status; + u64 prof_id; u8 i; if (!prof) return -EINVAL; + ids = &hw->blk[blk].prof_id; + prof_id = find_first_zero_bit(ids->id, ids->count); + if (prof_id >= ids->count) + return -ENOSPC; + params = kzalloc(sizeof(*params), GFP_KERNEL); if (!params) return -ENOMEM; @@ -1369,6 +1383,7 @@ ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk, params->prof->id = prof_id; params->prof->dir = dir; params->prof->segs_cnt = segs_cnt; + params->prof->symm = symm; /* Make a copy of the segments that need to be persistent in the flow * profile instance @@ -1385,7 +1400,7 @@ ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk, /* Add a HW profile for this flow profile */ status = ice_add_prof(hw, blk, prof_id, (u8 *)params->ptypes, params->attr, params->attr_cnt, params->es, - params->mask); + params->mask, symm); if (status) { ice_debug(hw, ICE_DBG_FLOW, "Error adding a HW flow profile\n"); goto out; @@ -1393,6 +1408,7 @@ ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk, INIT_LIST_HEAD(¶ms->prof->entries); mutex_init(¶ms->prof->entries_lock); + set_bit(prof_id, ids->id); *prof = params->prof; out: @@ -1436,6 +1452,7 @@ ice_flow_rem_prof_sync(struct ice_hw *hw, enum ice_block blk, /* Remove all hardware profiles associated with this flow profile */ status = ice_rem_prof(hw, blk, prof->id); if (!status) { + clear_bit(prof->id, hw->blk[blk].prof_id.id); list_del(&prof->l_entry); mutex_destroy(&prof->entries_lock); devm_kfree(ice_hw_to_dev(hw), prof); @@ -1511,15 +1528,15 @@ ice_flow_disassoc_prof(struct ice_hw *hw, enum ice_block blk, * @hw: pointer to the HW struct * @blk: classification stage * @dir: flow direction - * @prof_id: unique ID to identify this flow profile * @segs: array of one or more packet segments that describe the flow * @segs_cnt: number of packet segments provided + * @symm: symmetric setting for RSS profiles * @prof: stores the returned flow profile added */ int ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir, - u64 prof_id, struct ice_flow_seg_info *segs, u8 segs_cnt, - struct ice_flow_prof **prof) + struct ice_flow_seg_info *segs, u8 segs_cnt, + bool symm, struct ice_flow_prof **prof) { int status; @@ -1538,8 +1555,8 @@ ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir, mutex_lock(&hw->fl_profs_locks[blk]); - status = ice_flow_add_prof_sync(hw, blk, dir, prof_id, segs, segs_cnt, - prof); + status = ice_flow_add_prof_sync(hw, blk, dir, segs, segs_cnt, + symm, prof); if (!status) list_add(&(*prof)->l_entry, &hw->fl_profs[blk]); @@ -1855,37 +1872,49 @@ int ice_flow_rem_vsi_prof(struct ice_hw *hw, u16 vsi_handle, u64 prof_id) /** * ice_flow_set_rss_seg_info - setup packet segments for RSS * @segs: pointer to the flow field segment(s) - * @hash_fields: fields to be hashed on for the segment(s) - * @flow_hdr: protocol header fields within a packet segment + * @seg_cnt: segment count + * @cfg: configure parameters * * Helper function to extract fields from hash bitmap and use flow * header value to set flow field segment for further use in flow * profile entry or removal. */ static int -ice_flow_set_rss_seg_info(struct ice_flow_seg_info *segs, u64 hash_fields, - u32 flow_hdr) +ice_flow_set_rss_seg_info(struct ice_flow_seg_info *segs, u8 seg_cnt, + const struct ice_rss_hash_cfg *cfg) { + struct ice_flow_seg_info *seg; u64 val; - u8 i; + u16 i; - for_each_set_bit(i, (unsigned long *)&hash_fields, - ICE_FLOW_FIELD_IDX_MAX) - ice_flow_set_fld(segs, (enum ice_flow_field)i, + /* set inner most segment */ + seg = &segs[seg_cnt - 1]; + + for_each_set_bit(i, (const unsigned long *)&cfg->hash_flds, + (u16)ICE_FLOW_FIELD_IDX_MAX) + ice_flow_set_fld(seg, (enum ice_flow_field)i, ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL, false); - ICE_FLOW_SET_HDRS(segs, flow_hdr); + ICE_FLOW_SET_HDRS(seg, cfg->addl_hdrs); + + /* set outer most header */ + if (cfg->hdr_type == ICE_RSS_INNER_HEADERS_W_OUTER_IPV4) + segs[ICE_RSS_OUTER_HEADERS].hdrs |= ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER; + else if (cfg->hdr_type == ICE_RSS_INNER_HEADERS_W_OUTER_IPV6) + segs[ICE_RSS_OUTER_HEADERS].hdrs |= ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER; - if (segs->hdrs & ~ICE_FLOW_RSS_SEG_HDR_VAL_MASKS & + if (seg->hdrs & ~ICE_FLOW_RSS_SEG_HDR_VAL_MASKS & ~ICE_FLOW_RSS_HDRS_INNER_MASK & ~ICE_FLOW_SEG_HDR_IPV_OTHER) return -EINVAL; - val = (u64)(segs->hdrs & ICE_FLOW_RSS_SEG_HDR_L3_MASKS); + val = (u64)(seg->hdrs & ICE_FLOW_RSS_SEG_HDR_L3_MASKS); if (val && !is_power_of_2(val)) return -EIO; - val = (u64)(segs->hdrs & ICE_FLOW_RSS_SEG_HDR_L4_MASKS); + val = (u64)(seg->hdrs & ICE_FLOW_RSS_SEG_HDR_L4_MASKS); if (val && !is_power_of_2(val)) return -EIO; @@ -1956,6 +1985,39 @@ int ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle) } /** + * ice_get_rss_hdr_type - get a RSS profile's header type + * @prof: RSS flow profile + */ +static enum ice_rss_cfg_hdr_type +ice_get_rss_hdr_type(struct ice_flow_prof *prof) +{ + if (prof->segs_cnt == ICE_FLOW_SEG_SINGLE) { + return ICE_RSS_OUTER_HEADERS; + } else if (prof->segs_cnt == ICE_FLOW_SEG_MAX) { + const struct ice_flow_seg_info *s; + + s = &prof->segs[ICE_RSS_OUTER_HEADERS]; + if (s->hdrs == ICE_FLOW_SEG_HDR_NONE) + return ICE_RSS_INNER_HEADERS; + if (s->hdrs & ICE_FLOW_SEG_HDR_IPV4) + return ICE_RSS_INNER_HEADERS_W_OUTER_IPV4; + if (s->hdrs & ICE_FLOW_SEG_HDR_IPV6) + return ICE_RSS_INNER_HEADERS_W_OUTER_IPV6; + } + + return ICE_RSS_ANY_HEADERS; +} + +static bool +ice_rss_match_prof(struct ice_rss_cfg *r, struct ice_flow_prof *prof, + enum ice_rss_cfg_hdr_type hdr_type) +{ + return (r->hash.hdr_type == hdr_type && + r->hash.hash_flds == prof->segs[prof->segs_cnt - 1].match && + r->hash.addl_hdrs == prof->segs[prof->segs_cnt - 1].hdrs); +} + +/** * ice_rem_rss_list - remove RSS configuration from list * @hw: pointer to the hardware structure * @vsi_handle: software VSI handle @@ -1966,15 +2028,16 @@ int ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle) static void ice_rem_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof) { + enum ice_rss_cfg_hdr_type hdr_type; struct ice_rss_cfg *r, *tmp; /* Search for RSS hash fields associated to the VSI that match the * hash configurations associated to the flow profile. If found * remove from the RSS entry list of the VSI context and delete entry. */ + hdr_type = ice_get_rss_hdr_type(prof); list_for_each_entry_safe(r, tmp, &hw->rss_list_head, l_entry) - if (r->hashed_flds == prof->segs[prof->segs_cnt - 1].match && - r->packet_hdr == prof->segs[prof->segs_cnt - 1].hdrs) { + if (ice_rss_match_prof(r, prof, hdr_type)) { clear_bit(vsi_handle, r->vsis); if (bitmap_empty(r->vsis, ICE_MAX_VSI)) { list_del(&r->l_entry); @@ -1995,11 +2058,12 @@ ice_rem_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof) static int ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof) { + enum ice_rss_cfg_hdr_type hdr_type; struct ice_rss_cfg *r, *rss_cfg; + hdr_type = ice_get_rss_hdr_type(prof); list_for_each_entry(r, &hw->rss_list_head, l_entry) - if (r->hashed_flds == prof->segs[prof->segs_cnt - 1].match && - r->packet_hdr == prof->segs[prof->segs_cnt - 1].hdrs) { + if (ice_rss_match_prof(r, prof, hdr_type)) { set_bit(vsi_handle, r->vsis); return 0; } @@ -2009,8 +2073,10 @@ ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof) if (!rss_cfg) return -ENOMEM; - rss_cfg->hashed_flds = prof->segs[prof->segs_cnt - 1].match; - rss_cfg->packet_hdr = prof->segs[prof->segs_cnt - 1].hdrs; + rss_cfg->hash.hash_flds = prof->segs[prof->segs_cnt - 1].match; + rss_cfg->hash.addl_hdrs = prof->segs[prof->segs_cnt - 1].hdrs; + rss_cfg->hash.hdr_type = hdr_type; + rss_cfg->hash.symm = prof->symm; set_bit(vsi_handle, rss_cfg->vsis); list_add_tail(&rss_cfg->l_entry, &hw->rss_list_head); @@ -2018,65 +2084,177 @@ ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof) return 0; } -#define ICE_FLOW_PROF_HASH_S 0 -#define ICE_FLOW_PROF_HASH_M (0xFFFFFFFFULL << ICE_FLOW_PROF_HASH_S) -#define ICE_FLOW_PROF_HDR_S 32 -#define ICE_FLOW_PROF_HDR_M (0x3FFFFFFFULL << ICE_FLOW_PROF_HDR_S) -#define ICE_FLOW_PROF_ENCAP_S 63 -#define ICE_FLOW_PROF_ENCAP_M (BIT_ULL(ICE_FLOW_PROF_ENCAP_S)) +/** + * ice_rss_config_xor_word - set the HSYMM registers for one input set word + * @hw: pointer to the hardware structure + * @prof_id: RSS hardware profile id + * @src: the FV index used by the protocol's source field + * @dst: the FV index used by the protocol's destination field + * + * Write to the HSYMM register with the index of @src FV the value of the @dst + * FV index. This will tell the hardware to XOR HSYMM[src] with INSET[dst] + * while calculating the RSS input set. + */ +static void +ice_rss_config_xor_word(struct ice_hw *hw, u8 prof_id, u8 src, u8 dst) +{ + u32 val, reg, bits_shift; + u8 reg_idx; + + reg_idx = src / GLQF_HSYMM_REG_SIZE; + bits_shift = ((src % GLQF_HSYMM_REG_SIZE) << 3); + val = dst | GLQF_HSYMM_ENABLE_BIT; + + reg = rd32(hw, GLQF_HSYMM(prof_id, reg_idx)); + reg = (reg & ~(0xff << bits_shift)) | (val << bits_shift); + wr32(hw, GLQF_HSYMM(prof_id, reg_idx), reg); +} -#define ICE_RSS_OUTER_HEADERS 1 -#define ICE_RSS_INNER_HEADERS 2 +/** + * ice_rss_config_xor - set the symmetric registers for a profile's protocol + * @hw: pointer to the hardware structure + * @prof_id: RSS hardware profile id + * @src: the FV index used by the protocol's source field + * @dst: the FV index used by the protocol's destination field + * @len: length of the source/destination fields in words + */ +static void +ice_rss_config_xor(struct ice_hw *hw, u8 prof_id, u8 src, u8 dst, u8 len) +{ + int fv_last_word = + ICE_FLOW_SW_FIELD_VECTOR_MAX / ICE_FLOW_FV_EXTRACT_SZ - 1; + int i; + + for (i = 0; i < len; i++) { + ice_rss_config_xor_word(hw, prof_id, + /* Yes, field vector in GLQF_HSYMM and + * GLQF_HINSET is inversed! + */ + fv_last_word - (src + i), + fv_last_word - (dst + i)); + ice_rss_config_xor_word(hw, prof_id, + fv_last_word - (dst + i), + fv_last_word - (src + i)); + } +} -/* Flow profile ID format: - * [0:31] - Packet match fields - * [32:62] - Protocol header - * [63] - Encapsulation flag, 0 if non-tunneled, 1 if tunneled +/** + * ice_rss_set_symm - set the symmetric settings for an RSS profile + * @hw: pointer to the hardware structure + * @prof: pointer to flow profile + * + * The symmetric hash will result from XORing the protocol's fields with + * indexes in GLQF_HSYMM and GLQF_HINSET. This function configures the profile's + * GLQF_HSYMM registers. */ -#define ICE_FLOW_GEN_PROFID(hash, hdr, segs_cnt) \ - ((u64)(((u64)(hash) & ICE_FLOW_PROF_HASH_M) | \ - (((u64)(hdr) << ICE_FLOW_PROF_HDR_S) & ICE_FLOW_PROF_HDR_M) | \ - ((u8)((segs_cnt) - 1) ? ICE_FLOW_PROF_ENCAP_M : 0))) +static void ice_rss_set_symm(struct ice_hw *hw, struct ice_flow_prof *prof) +{ + struct ice_prof_map *map; + u8 prof_id, m; + + mutex_lock(&hw->blk[ICE_BLK_RSS].es.prof_map_lock); + map = ice_search_prof_id(hw, ICE_BLK_RSS, prof->id); + if (map) + prof_id = map->prof_id; + mutex_unlock(&hw->blk[ICE_BLK_RSS].es.prof_map_lock); + + if (!map) + return; + + /* clear to default */ + for (m = 0; m < GLQF_HSYMM_REG_PER_PROF; m++) + wr32(hw, GLQF_HSYMM(prof_id, m), 0); + + if (prof->symm) { + struct ice_flow_seg_xtrct *ipv4_src, *ipv4_dst; + struct ice_flow_seg_xtrct *ipv6_src, *ipv6_dst; + struct ice_flow_seg_xtrct *sctp_src, *sctp_dst; + struct ice_flow_seg_xtrct *tcp_src, *tcp_dst; + struct ice_flow_seg_xtrct *udp_src, *udp_dst; + struct ice_flow_seg_info *seg; + + seg = &prof->segs[prof->segs_cnt - 1]; + + ipv4_src = &seg->fields[ICE_FLOW_FIELD_IDX_IPV4_SA].xtrct; + ipv4_dst = &seg->fields[ICE_FLOW_FIELD_IDX_IPV4_DA].xtrct; + + ipv6_src = &seg->fields[ICE_FLOW_FIELD_IDX_IPV6_SA].xtrct; + ipv6_dst = &seg->fields[ICE_FLOW_FIELD_IDX_IPV6_DA].xtrct; + + tcp_src = &seg->fields[ICE_FLOW_FIELD_IDX_TCP_SRC_PORT].xtrct; + tcp_dst = &seg->fields[ICE_FLOW_FIELD_IDX_TCP_DST_PORT].xtrct; + + udp_src = &seg->fields[ICE_FLOW_FIELD_IDX_UDP_SRC_PORT].xtrct; + udp_dst = &seg->fields[ICE_FLOW_FIELD_IDX_UDP_DST_PORT].xtrct; + + sctp_src = &seg->fields[ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT].xtrct; + sctp_dst = &seg->fields[ICE_FLOW_FIELD_IDX_SCTP_DST_PORT].xtrct; + + /* xor IPv4 */ + if (ipv4_src->prot_id != 0 && ipv4_dst->prot_id != 0) + ice_rss_config_xor(hw, prof_id, + ipv4_src->idx, ipv4_dst->idx, 2); + + /* xor IPv6 */ + if (ipv6_src->prot_id != 0 && ipv6_dst->prot_id != 0) + ice_rss_config_xor(hw, prof_id, + ipv6_src->idx, ipv6_dst->idx, 8); + + /* xor TCP */ + if (tcp_src->prot_id != 0 && tcp_dst->prot_id != 0) + ice_rss_config_xor(hw, prof_id, + tcp_src->idx, tcp_dst->idx, 1); + + /* xor UDP */ + if (udp_src->prot_id != 0 && udp_dst->prot_id != 0) + ice_rss_config_xor(hw, prof_id, + udp_src->idx, udp_dst->idx, 1); + + /* xor SCTP */ + if (sctp_src->prot_id != 0 && sctp_dst->prot_id != 0) + ice_rss_config_xor(hw, prof_id, + sctp_src->idx, sctp_dst->idx, 1); + } +} /** * ice_add_rss_cfg_sync - add an RSS configuration * @hw: pointer to the hardware structure * @vsi_handle: software VSI handle - * @hashed_flds: hash bit fields (ICE_FLOW_HASH_*) to configure - * @addl_hdrs: protocol header fields - * @segs_cnt: packet segment count + * @cfg: configure parameters * * Assumption: lock has already been acquired for RSS list */ static int -ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, - u32 addl_hdrs, u8 segs_cnt) +ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, + const struct ice_rss_hash_cfg *cfg) { const enum ice_block blk = ICE_BLK_RSS; struct ice_flow_prof *prof = NULL; struct ice_flow_seg_info *segs; + u8 segs_cnt; int status; - if (!segs_cnt || segs_cnt > ICE_FLOW_SEG_MAX) - return -EINVAL; + segs_cnt = (cfg->hdr_type == ICE_RSS_OUTER_HEADERS) ? + ICE_FLOW_SEG_SINGLE : ICE_FLOW_SEG_MAX; segs = kcalloc(segs_cnt, sizeof(*segs), GFP_KERNEL); if (!segs) return -ENOMEM; /* Construct the packet segment info from the hashed fields */ - status = ice_flow_set_rss_seg_info(&segs[segs_cnt - 1], hashed_flds, - addl_hdrs); + status = ice_flow_set_rss_seg_info(segs, segs_cnt, cfg); if (status) goto exit; - /* Search for a flow profile that has matching headers, hash fields - * and has the input VSI associated to it. If found, no further + /* Search for a flow profile that has matching headers, hash fields, + * symm and has the input VSI associated to it. If found, no further * operations required and exit. */ prof = ice_flow_find_prof_conds(hw, blk, ICE_FLOW_RX, segs, segs_cnt, - vsi_handle, + cfg->symm, vsi_handle, ICE_FLOW_FIND_PROF_CHK_FLDS | + ICE_FLOW_FIND_PROF_CHK_SYMM | ICE_FLOW_FIND_PROF_CHK_VSI); if (prof) goto exit; @@ -2087,7 +2265,8 @@ ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, * the protocol header and new hash field configuration. */ prof = ice_flow_find_prof_conds(hw, blk, ICE_FLOW_RX, segs, segs_cnt, - vsi_handle, ICE_FLOW_FIND_PROF_CHK_VSI); + cfg->symm, vsi_handle, + ICE_FLOW_FIND_PROF_CHK_VSI); if (prof) { status = ice_flow_disassoc_prof(hw, blk, prof, vsi_handle); if (!status) @@ -2103,11 +2282,12 @@ ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, } } - /* Search for a profile that has same match fields only. If this - * exists then associate the VSI to this profile. + /* Search for a profile that has the same match fields and symmetric + * setting. If this exists then associate the VSI to this profile. */ prof = ice_flow_find_prof_conds(hw, blk, ICE_FLOW_RX, segs, segs_cnt, - vsi_handle, + cfg->symm, vsi_handle, + ICE_FLOW_FIND_PROF_CHK_SYMM | ICE_FLOW_FIND_PROF_CHK_FLDS); if (prof) { status = ice_flow_assoc_prof(hw, blk, prof, vsi_handle); @@ -2116,17 +2296,14 @@ ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, goto exit; } - /* Create a new flow profile with generated profile and packet - * segment information. - */ + /* Create a new flow profile with packet segment information. */ status = ice_flow_add_prof(hw, blk, ICE_FLOW_RX, - ICE_FLOW_GEN_PROFID(hashed_flds, - segs[segs_cnt - 1].hdrs, - segs_cnt), - segs, segs_cnt, &prof); + segs, segs_cnt, cfg->symm, &prof); if (status) goto exit; + prof->symm = cfg->symm; + ice_rss_set_symm(hw, prof); status = ice_flow_assoc_prof(hw, blk, prof, vsi_handle); /* If association to a new flow profile failed then this profile can * be removed. @@ -2146,30 +2323,43 @@ exit: /** * ice_add_rss_cfg - add an RSS configuration with specified hashed fields * @hw: pointer to the hardware structure - * @vsi_handle: software VSI handle - * @hashed_flds: hash bit fields (ICE_FLOW_HASH_*) to configure - * @addl_hdrs: protocol header fields + * @vsi: VSI to add the RSS configuration to + * @cfg: configure parameters * * This function will generate a flow profile based on fields associated with * the input fields to hash on, the flow type and use the VSI number to add * a flow entry to the profile. */ int -ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, - u32 addl_hdrs) +ice_add_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi, + const struct ice_rss_hash_cfg *cfg) { + struct ice_rss_hash_cfg local_cfg; + u16 vsi_handle; int status; - if (hashed_flds == ICE_HASH_INVALID || - !ice_is_vsi_valid(hw, vsi_handle)) + if (!vsi) + return -EINVAL; + + vsi_handle = vsi->idx; + if (!ice_is_vsi_valid(hw, vsi_handle) || + !cfg || cfg->hdr_type > ICE_RSS_ANY_HEADERS || + cfg->hash_flds == ICE_HASH_INVALID) return -EINVAL; mutex_lock(&hw->rss_locks); - status = ice_add_rss_cfg_sync(hw, vsi_handle, hashed_flds, addl_hdrs, - ICE_RSS_OUTER_HEADERS); - if (!status) - status = ice_add_rss_cfg_sync(hw, vsi_handle, hashed_flds, - addl_hdrs, ICE_RSS_INNER_HEADERS); + local_cfg = *cfg; + if (cfg->hdr_type < ICE_RSS_ANY_HEADERS) { + status = ice_add_rss_cfg_sync(hw, vsi_handle, &local_cfg); + } else { + local_cfg.hdr_type = ICE_RSS_OUTER_HEADERS; + status = ice_add_rss_cfg_sync(hw, vsi_handle, &local_cfg); + if (!status) { + local_cfg.hdr_type = ICE_RSS_INNER_HEADERS; + status = ice_add_rss_cfg_sync(hw, vsi_handle, + &local_cfg); + } + } mutex_unlock(&hw->rss_locks); return status; @@ -2179,33 +2369,33 @@ ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, * ice_rem_rss_cfg_sync - remove an existing RSS configuration * @hw: pointer to the hardware structure * @vsi_handle: software VSI handle - * @hashed_flds: Packet hash types (ICE_FLOW_HASH_*) to remove - * @addl_hdrs: Protocol header fields within a packet segment - * @segs_cnt: packet segment count + * @cfg: configure parameters * * Assumption: lock has already been acquired for RSS list */ static int -ice_rem_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, - u32 addl_hdrs, u8 segs_cnt) +ice_rem_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, + const struct ice_rss_hash_cfg *cfg) { const enum ice_block blk = ICE_BLK_RSS; struct ice_flow_seg_info *segs; struct ice_flow_prof *prof; + u8 segs_cnt; int status; + segs_cnt = (cfg->hdr_type == ICE_RSS_OUTER_HEADERS) ? + ICE_FLOW_SEG_SINGLE : ICE_FLOW_SEG_MAX; segs = kcalloc(segs_cnt, sizeof(*segs), GFP_KERNEL); if (!segs) return -ENOMEM; /* Construct the packet segment info from the hashed fields */ - status = ice_flow_set_rss_seg_info(&segs[segs_cnt - 1], hashed_flds, - addl_hdrs); + status = ice_flow_set_rss_seg_info(segs, segs_cnt, cfg); if (status) goto out; prof = ice_flow_find_prof_conds(hw, blk, ICE_FLOW_RX, segs, segs_cnt, - vsi_handle, + cfg->symm, vsi_handle, ICE_FLOW_FIND_PROF_CHK_FLDS); if (!prof) { status = -ENOENT; @@ -2233,31 +2423,39 @@ out: * ice_rem_rss_cfg - remove an existing RSS config with matching hashed fields * @hw: pointer to the hardware structure * @vsi_handle: software VSI handle - * @hashed_flds: Packet hash types (ICE_FLOW_HASH_*) to remove - * @addl_hdrs: Protocol header fields within a packet segment + * @cfg: configure parameters * * This function will lookup the flow profile based on the input * hash field bitmap, iterate through the profile entry list of * that profile and find entry associated with input VSI to be - * removed. Calls are made to underlying flow s which will APIs + * removed. Calls are made to underlying flow apis which will in * turn build or update buffers for RSS XLT1 section. */ -int __maybe_unused -ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, - u32 addl_hdrs) +int +ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, + const struct ice_rss_hash_cfg *cfg) { + struct ice_rss_hash_cfg local_cfg; int status; - if (hashed_flds == ICE_HASH_INVALID || - !ice_is_vsi_valid(hw, vsi_handle)) + if (!ice_is_vsi_valid(hw, vsi_handle) || + !cfg || cfg->hdr_type > ICE_RSS_ANY_HEADERS || + cfg->hash_flds == ICE_HASH_INVALID) return -EINVAL; mutex_lock(&hw->rss_locks); - status = ice_rem_rss_cfg_sync(hw, vsi_handle, hashed_flds, addl_hdrs, - ICE_RSS_OUTER_HEADERS); - if (!status) - status = ice_rem_rss_cfg_sync(hw, vsi_handle, hashed_flds, - addl_hdrs, ICE_RSS_INNER_HEADERS); + local_cfg = *cfg; + if (cfg->hdr_type < ICE_RSS_ANY_HEADERS) { + status = ice_rem_rss_cfg_sync(hw, vsi_handle, &local_cfg); + } else { + local_cfg.hdr_type = ICE_RSS_OUTER_HEADERS; + status = ice_rem_rss_cfg_sync(hw, vsi_handle, &local_cfg); + if (!status) { + local_cfg.hdr_type = ICE_RSS_INNER_HEADERS; + status = ice_rem_rss_cfg_sync(hw, vsi_handle, + &local_cfg); + } + } mutex_unlock(&hw->rss_locks); return status; @@ -2298,18 +2496,24 @@ ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, /** * ice_add_avf_rss_cfg - add an RSS configuration for AVF driver * @hw: pointer to the hardware structure - * @vsi_handle: software VSI handle + * @vsi: VF's VSI * @avf_hash: hash bit fields (ICE_AVF_FLOW_FIELD_*) to configure * * This function will take the hash bitmap provided by the AVF driver via a * message, convert it to ICE-compatible values, and configure RSS flow * profiles. */ -int ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 avf_hash) +int ice_add_avf_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi, u64 avf_hash) { + struct ice_rss_hash_cfg hcfg; + u16 vsi_handle; int status = 0; u64 hash_flds; + if (!vsi) + return -EINVAL; + + vsi_handle = vsi->idx; if (avf_hash == ICE_AVF_FLOW_FIELD_INVALID || !ice_is_vsi_valid(hw, vsi_handle)) return -EINVAL; @@ -2379,8 +2583,11 @@ int ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 avf_hash) if (rss_hash == ICE_HASH_INVALID) return -EIO; - status = ice_add_rss_cfg(hw, vsi_handle, rss_hash, - ICE_FLOW_SEG_HDR_NONE); + hcfg.addl_hdrs = ICE_FLOW_SEG_HDR_NONE; + hcfg.hash_flds = rss_hash; + hcfg.hdr_type = ICE_RSS_ANY_HEADERS; + hcfg.symm = false; + status = ice_add_rss_cfg(hw, vsi, &hcfg); if (status) break; } @@ -2388,6 +2595,54 @@ int ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 avf_hash) return status; } +static bool rss_cfg_symm_valid(u64 hfld) +{ + return !((!!(hfld & ICE_FLOW_HASH_FLD_IPV4_SA) ^ + !!(hfld & ICE_FLOW_HASH_FLD_IPV4_DA)) || + (!!(hfld & ICE_FLOW_HASH_FLD_IPV6_SA) ^ + !!(hfld & ICE_FLOW_HASH_FLD_IPV6_DA)) || + (!!(hfld & ICE_FLOW_HASH_FLD_TCP_SRC_PORT) ^ + !!(hfld & ICE_FLOW_HASH_FLD_TCP_DST_PORT)) || + (!!(hfld & ICE_FLOW_HASH_FLD_UDP_SRC_PORT) ^ + !!(hfld & ICE_FLOW_HASH_FLD_UDP_DST_PORT)) || + (!!(hfld & ICE_FLOW_HASH_FLD_SCTP_SRC_PORT) ^ + !!(hfld & ICE_FLOW_HASH_FLD_SCTP_DST_PORT))); +} + +/** + * ice_set_rss_cfg_symm - set symmtery for all VSI's RSS configurations + * @hw: pointer to the hardware structure + * @vsi: VSI to set/unset Symmetric RSS + * @symm: TRUE to set Symmetric RSS hashing + */ +int ice_set_rss_cfg_symm(struct ice_hw *hw, struct ice_vsi *vsi, bool symm) +{ + struct ice_rss_hash_cfg local; + struct ice_rss_cfg *r, *tmp; + u16 vsi_handle = vsi->idx; + int status = 0; + + if (!ice_is_vsi_valid(hw, vsi_handle)) + return -EINVAL; + + mutex_lock(&hw->rss_locks); + list_for_each_entry_safe(r, tmp, &hw->rss_list_head, l_entry) { + if (test_bit(vsi_handle, r->vsis) && r->hash.symm != symm) { + local = r->hash; + local.symm = symm; + if (symm && !rss_cfg_symm_valid(r->hash.hash_flds)) + continue; + + status = ice_add_rss_cfg_sync(hw, vsi_handle, &local); + if (status) + break; + } + } + mutex_unlock(&hw->rss_locks); + + return status; +} + /** * ice_replay_rss_cfg - replay RSS configurations associated with VSI * @hw: pointer to the hardware structure @@ -2404,16 +2659,7 @@ int ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle) mutex_lock(&hw->rss_locks); list_for_each_entry(r, &hw->rss_list_head, l_entry) { if (test_bit(vsi_handle, r->vsis)) { - status = ice_add_rss_cfg_sync(hw, vsi_handle, - r->hashed_flds, - r->packet_hdr, - ICE_RSS_OUTER_HEADERS); - if (status) - break; - status = ice_add_rss_cfg_sync(hw, vsi_handle, - r->hashed_flds, - r->packet_hdr, - ICE_RSS_INNER_HEADERS); + status = ice_add_rss_cfg_sync(hw, vsi_handle, &r->hash); if (status) break; } @@ -2428,11 +2674,12 @@ int ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle) * @hw: pointer to the hardware structure * @vsi_handle: software VSI handle * @hdrs: protocol header type + * @symm: whether the RSS is symmetric (bool, output) * * This function will return the match fields of the first instance of flow * profile having the given header types and containing input VSI */ -u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs) +u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs, bool *symm) { u64 rss_hash = ICE_HASH_INVALID; struct ice_rss_cfg *r; @@ -2444,8 +2691,9 @@ u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs) mutex_lock(&hw->rss_locks); list_for_each_entry(r, &hw->rss_list_head, l_entry) if (test_bit(vsi_handle, r->vsis) && - r->packet_hdr == hdrs) { - rss_hash = r->hashed_flds; + r->hash.addl_hdrs == hdrs) { + rss_hash = r->hash.hash_flds; + *symm = r->hash.symm; break; } mutex_unlock(&hw->rss_locks); diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h index 96923ef0a5a8..2fd2e0cb483d 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.h +++ b/drivers/net/ethernet/intel/ice/ice_flow.h @@ -34,14 +34,16 @@ #define ICE_HASH_TCP_IPV6 (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_TCP_PORT) #define ICE_HASH_UDP_IPV4 (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_UDP_PORT) #define ICE_HASH_UDP_IPV6 (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_UDP_PORT) +#define ICE_HASH_SCTP_IPV4 (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_SCTP_PORT) +#define ICE_HASH_SCTP_IPV6 (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_SCTP_PORT) -#define ICE_FLOW_HASH_GTP_TEID \ +#define ICE_FLOW_HASH_GTP_C_TEID \ (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID)) -#define ICE_FLOW_HASH_GTP_IPV4_TEID \ - (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_TEID) -#define ICE_FLOW_HASH_GTP_IPV6_TEID \ - (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_TEID) +#define ICE_FLOW_HASH_GTP_C_IPV4_TEID \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_C_TEID) +#define ICE_FLOW_HASH_GTP_C_IPV6_TEID \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_C_TEID) #define ICE_FLOW_HASH_GTP_U_TEID \ (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_IP_TEID)) @@ -64,6 +66,20 @@ (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_U_EH_TEID | \ ICE_FLOW_HASH_GTP_U_EH_QFI) +#define ICE_FLOW_HASH_GTP_U_UP \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_UP_TEID)) +#define ICE_FLOW_HASH_GTP_U_DWN \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID)) + +#define ICE_FLOW_HASH_GTP_U_IPV4_UP \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_U_UP) +#define ICE_FLOW_HASH_GTP_U_IPV6_UP \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_U_UP) +#define ICE_FLOW_HASH_GTP_U_IPV4_DWN \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_U_DWN) +#define ICE_FLOW_HASH_GTP_U_IPV6_DWN \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_U_DWN) + #define ICE_FLOW_HASH_PPPOE_SESS_ID \ (BIT_ULL(ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID)) @@ -227,6 +243,26 @@ enum ice_flow_field { ICE_FLOW_FIELD_IDX_MAX }; +#define ICE_FLOW_HASH_FLD_IPV4_SA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) +#define ICE_FLOW_HASH_FLD_IPV6_SA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA) +#define ICE_FLOW_HASH_FLD_IPV4_DA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) +#define ICE_FLOW_HASH_FLD_IPV6_DA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA) +#define ICE_FLOW_HASH_FLD_TCP_SRC_PORT BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT) +#define ICE_FLOW_HASH_FLD_TCP_DST_PORT BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT) +#define ICE_FLOW_HASH_FLD_UDP_SRC_PORT BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT) +#define ICE_FLOW_HASH_FLD_UDP_DST_PORT BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT) +#define ICE_FLOW_HASH_FLD_SCTP_SRC_PORT \ + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT) +#define ICE_FLOW_HASH_FLD_SCTP_DST_PORT \ + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT) + +#define ICE_FLOW_HASH_FLD_GTPC_TEID BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID) +#define ICE_FLOW_HASH_FLD_GTPU_IP_TEID BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_IP_TEID) +#define ICE_FLOW_HASH_FLD_GTPU_EH_TEID BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_EH_TEID) +#define ICE_FLOW_HASH_FLD_GTPU_UP_TEID BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_UP_TEID) +#define ICE_FLOW_HASH_FLD_GTPU_DWN_TEID \ + BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID) + /* Flow headers and fields for AVF support */ enum ice_flow_avf_hdr_field { /* Values 0 - 28 are reserved for future use */ @@ -279,6 +315,24 @@ enum ice_flow_avf_hdr_field { BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV6_UDP) | \ BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV6_UDP)) +enum ice_rss_cfg_hdr_type { + ICE_RSS_OUTER_HEADERS, /* take outer headers as inputset. */ + ICE_RSS_INNER_HEADERS, /* take inner headers as inputset. */ + /* take inner headers as inputset for packet with outer ipv4. */ + ICE_RSS_INNER_HEADERS_W_OUTER_IPV4, + /* take inner headers as inputset for packet with outer ipv6. */ + ICE_RSS_INNER_HEADERS_W_OUTER_IPV6, + /* take outer headers first then inner headers as inputset */ + ICE_RSS_ANY_HEADERS +}; + +struct ice_rss_hash_cfg { + u32 addl_hdrs; /* protocol header fields */ + u64 hash_flds; /* hash bit field (ICE_FLOW_HASH_*) to configure */ + enum ice_rss_cfg_hdr_type hdr_type; /* to specify inner or outer */ + bool symm; /* symmetric or asymmetric hash */ +}; + enum ice_flow_dir { ICE_FLOW_RX = 0x02, }; @@ -289,8 +343,10 @@ enum ice_flow_priority { ICE_FLOW_PRIO_HIGH }; +#define ICE_FLOW_SEG_SINGLE 1 #define ICE_FLOW_SEG_MAX 2 #define ICE_FLOW_SEG_RAW_FLD_MAX 2 +#define ICE_FLOW_SW_FIELD_VECTOR_MAX 48 #define ICE_FLOW_FV_EXTRACT_SZ 2 #define ICE_FLOW_SET_HDRS(seg, val) ((seg)->hdrs |= (u32)(val)) @@ -372,20 +428,21 @@ struct ice_flow_prof { /* software VSI handles referenced by this flow profile */ DECLARE_BITMAP(vsis, ICE_MAX_VSI); + + bool symm; /* Symmetric Hash for RSS */ }; struct ice_rss_cfg { struct list_head l_entry; /* bitmap of VSIs added to the RSS entry */ DECLARE_BITMAP(vsis, ICE_MAX_VSI); - u64 hashed_flds; - u32 packet_hdr; + struct ice_rss_hash_cfg hash; }; int ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir, - u64 prof_id, struct ice_flow_seg_info *segs, u8 segs_cnt, - struct ice_flow_prof **prof); + struct ice_flow_seg_info *segs, u8 segs_cnt, + bool symm, struct ice_flow_prof **prof); int ice_flow_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 prof_id); int ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id, @@ -401,13 +458,13 @@ ice_flow_add_fld_raw(struct ice_flow_seg_info *seg, u16 off, u8 len, int ice_flow_rem_vsi_prof(struct ice_hw *hw, u16 vsi_handle, u64 prof_id); void ice_rem_vsi_rss_list(struct ice_hw *hw, u16 vsi_handle); int ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle); -int ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds); +int ice_set_rss_cfg_symm(struct ice_hw *hw, struct ice_vsi *vsi, bool symm); +int ice_add_avf_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi, + u64 hashed_flds); int ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle); -int -ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, - u32 addl_hdrs); -int -ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, - u32 addl_hdrs); -u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs); +int ice_add_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi, + const struct ice_rss_hash_cfg *cfg); +int ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, + const struct ice_rss_hash_cfg *cfg); +u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs, bool *symm); #endif /* _ICE_FLOW_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index 319a2d6fe26c..f81db6c107c8 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -286,10 +286,9 @@ ice_send_component_table(struct pldmfw *context, struct pldmfw_component *compon * * Returns: zero on success, or a negative error code on failure. */ -static int -ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, - u16 block_size, u8 *block, bool last_cmd, - u8 *reset_level, struct netlink_ext_ack *extack) +int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, + u16 block_size, u8 *block, bool last_cmd, + u8 *reset_level, struct netlink_ext_ack *extack) { u16 completion_module, completion_retval; struct device *dev = ice_pf_to_dev(pf); diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.h b/drivers/net/ethernet/intel/ice/ice_fw_update.h index 750574885716..04b200462757 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.h +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.h @@ -9,5 +9,8 @@ int ice_devlink_flash_update(struct devlink *devlink, struct netlink_ext_ack *extack); int ice_get_pending_updates(struct ice_pf *pf, u8 *pending, struct netlink_ext_ack *extack); +int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, + u16 block_size, u8 *block, bool last_cmd, + u8 *reset_level, struct netlink_ext_ack *extack); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_fwlog.c b/drivers/net/ethernet/intel/ice/ice_fwlog.c new file mode 100644 index 000000000000..4fd15387a7e5 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_fwlog.c @@ -0,0 +1,472 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022, Intel Corporation. */ + +#include <linux/vmalloc.h> +#include "ice.h" +#include "ice_common.h" +#include "ice_fwlog.h" + +bool ice_fwlog_ring_full(struct ice_fwlog_ring *rings) +{ + u16 head, tail; + + head = rings->head; + tail = rings->tail; + + if (head < tail && (tail - head == (rings->size - 1))) + return true; + else if (head > tail && (tail == (head - 1))) + return true; + + return false; +} + +bool ice_fwlog_ring_empty(struct ice_fwlog_ring *rings) +{ + return rings->head == rings->tail; +} + +void ice_fwlog_ring_increment(u16 *item, u16 size) +{ + *item = (*item + 1) & (size - 1); +} + +static int ice_fwlog_alloc_ring_buffs(struct ice_fwlog_ring *rings) +{ + int i, nr_bytes; + u8 *mem; + + nr_bytes = rings->size * ICE_AQ_MAX_BUF_LEN; + mem = vzalloc(nr_bytes); + if (!mem) + return -ENOMEM; + + for (i = 0; i < rings->size; i++) { + struct ice_fwlog_data *ring = &rings->rings[i]; + + ring->data_size = ICE_AQ_MAX_BUF_LEN; + ring->data = mem; + mem += ICE_AQ_MAX_BUF_LEN; + } + + return 0; +} + +static void ice_fwlog_free_ring_buffs(struct ice_fwlog_ring *rings) +{ + int i; + + for (i = 0; i < rings->size; i++) { + struct ice_fwlog_data *ring = &rings->rings[i]; + + /* the first ring is the base memory for the whole range so + * free it + */ + if (!i) + vfree(ring->data); + + ring->data = NULL; + ring->data_size = 0; + } +} + +#define ICE_FWLOG_INDEX_TO_BYTES(n) ((128 * 1024) << (n)) +/** + * ice_fwlog_realloc_rings - reallocate the FW log rings + * @hw: pointer to the HW structure + * @index: the new index to use to allocate memory for the log data + * + */ +void ice_fwlog_realloc_rings(struct ice_hw *hw, int index) +{ + struct ice_fwlog_ring ring; + int status, ring_size; + + /* convert the number of bytes into a number of 4K buffers. externally + * the driver presents the interface to the FW log data as a number of + * bytes because that's easy for users to understand. internally the + * driver uses a ring of buffers because the driver doesn't know where + * the beginning and end of any line of log data is so the driver has + * to overwrite data as complete blocks. when the data is returned to + * the user the driver knows that the data is correct and the FW log + * can be correctly parsed by the tools + */ + ring_size = ICE_FWLOG_INDEX_TO_BYTES(index) / ICE_AQ_MAX_BUF_LEN; + if (ring_size == hw->fwlog_ring.size) + return; + + /* allocate space for the new rings and buffers then release the + * old rings and buffers. that way if we don't have enough + * memory then we at least have what we had before + */ + ring.rings = kcalloc(ring_size, sizeof(*ring.rings), GFP_KERNEL); + if (!ring.rings) + return; + + ring.size = ring_size; + + status = ice_fwlog_alloc_ring_buffs(&ring); + if (status) { + dev_warn(ice_hw_to_dev(hw), "Unable to allocate memory for FW log ring data buffers\n"); + ice_fwlog_free_ring_buffs(&ring); + kfree(ring.rings); + return; + } + + ice_fwlog_free_ring_buffs(&hw->fwlog_ring); + kfree(hw->fwlog_ring.rings); + + hw->fwlog_ring.rings = ring.rings; + hw->fwlog_ring.size = ring.size; + hw->fwlog_ring.index = index; + hw->fwlog_ring.head = 0; + hw->fwlog_ring.tail = 0; +} + +/** + * ice_fwlog_init - Initialize FW logging configuration + * @hw: pointer to the HW structure + * + * This function should be called on driver initialization during + * ice_init_hw(). + */ +int ice_fwlog_init(struct ice_hw *hw) +{ + /* only support fw log commands on PF 0 */ + if (hw->bus.func) + return -EINVAL; + + ice_fwlog_set_supported(hw); + + if (ice_fwlog_supported(hw)) { + int status; + + /* read the current config from the FW and store it */ + status = ice_fwlog_get(hw, &hw->fwlog_cfg); + if (status) + return status; + + hw->fwlog_ring.rings = kcalloc(ICE_FWLOG_RING_SIZE_DFLT, + sizeof(*hw->fwlog_ring.rings), + GFP_KERNEL); + if (!hw->fwlog_ring.rings) { + dev_warn(ice_hw_to_dev(hw), "Unable to allocate memory for FW log rings\n"); + return -ENOMEM; + } + + hw->fwlog_ring.size = ICE_FWLOG_RING_SIZE_DFLT; + hw->fwlog_ring.index = ICE_FWLOG_RING_SIZE_INDEX_DFLT; + + status = ice_fwlog_alloc_ring_buffs(&hw->fwlog_ring); + if (status) { + dev_warn(ice_hw_to_dev(hw), "Unable to allocate memory for FW log ring data buffers\n"); + ice_fwlog_free_ring_buffs(&hw->fwlog_ring); + kfree(hw->fwlog_ring.rings); + return status; + } + + ice_debugfs_fwlog_init(hw->back); + } else { + dev_warn(ice_hw_to_dev(hw), "FW logging is not supported in this NVM image. Please update the NVM to get FW log support\n"); + } + + return 0; +} + +/** + * ice_fwlog_deinit - unroll FW logging configuration + * @hw: pointer to the HW structure + * + * This function should be called in ice_deinit_hw(). + */ +void ice_fwlog_deinit(struct ice_hw *hw) +{ + struct ice_pf *pf = hw->back; + int status; + + /* only support fw log commands on PF 0 */ + if (hw->bus.func) + return; + + ice_debugfs_pf_deinit(hw->back); + + /* make sure FW logging is disabled to not put the FW in a weird state + * for the next driver load + */ + hw->fwlog_cfg.options &= ~ICE_FWLOG_OPTION_ARQ_ENA; + status = ice_fwlog_set(hw, &hw->fwlog_cfg); + if (status) + dev_warn(ice_hw_to_dev(hw), "Unable to turn off FW logging, status: %d\n", + status); + + kfree(pf->ice_debugfs_pf_fwlog_modules); + + pf->ice_debugfs_pf_fwlog_modules = NULL; + + status = ice_fwlog_unregister(hw); + if (status) + dev_warn(ice_hw_to_dev(hw), "Unable to unregister FW logging, status: %d\n", + status); + + if (hw->fwlog_ring.rings) { + ice_fwlog_free_ring_buffs(&hw->fwlog_ring); + kfree(hw->fwlog_ring.rings); + } +} + +/** + * ice_fwlog_supported - Cached for whether FW supports FW logging or not + * @hw: pointer to the HW structure + * + * This will always return false if called before ice_init_hw(), so it must be + * called after ice_init_hw(). + */ +bool ice_fwlog_supported(struct ice_hw *hw) +{ + return hw->fwlog_supported; +} + +/** + * ice_aq_fwlog_set - Set FW logging configuration AQ command (0xFF30) + * @hw: pointer to the HW structure + * @entries: entries to configure + * @num_entries: number of @entries + * @options: options from ice_fwlog_cfg->options structure + * @log_resolution: logging resolution + */ +static int +ice_aq_fwlog_set(struct ice_hw *hw, struct ice_fwlog_module_entry *entries, + u16 num_entries, u16 options, u16 log_resolution) +{ + struct ice_aqc_fw_log_cfg_resp *fw_modules; + struct ice_aqc_fw_log *cmd; + struct ice_aq_desc desc; + int status; + int i; + + fw_modules = kcalloc(num_entries, sizeof(*fw_modules), GFP_KERNEL); + if (!fw_modules) + return -ENOMEM; + + for (i = 0; i < num_entries; i++) { + fw_modules[i].module_identifier = + cpu_to_le16(entries[i].module_id); + fw_modules[i].log_level = entries[i].log_level; + } + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logs_config); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + cmd = &desc.params.fw_log; + + cmd->cmd_flags = ICE_AQC_FW_LOG_CONF_SET_VALID; + cmd->ops.cfg.log_resolution = cpu_to_le16(log_resolution); + cmd->ops.cfg.mdl_cnt = cpu_to_le16(num_entries); + + if (options & ICE_FWLOG_OPTION_ARQ_ENA) + cmd->cmd_flags |= ICE_AQC_FW_LOG_CONF_AQ_EN; + if (options & ICE_FWLOG_OPTION_UART_ENA) + cmd->cmd_flags |= ICE_AQC_FW_LOG_CONF_UART_EN; + + status = ice_aq_send_cmd(hw, &desc, fw_modules, + sizeof(*fw_modules) * num_entries, + NULL); + + kfree(fw_modules); + + return status; +} + +/** + * ice_fwlog_set - Set the firmware logging settings + * @hw: pointer to the HW structure + * @cfg: config used to set firmware logging + * + * This function should be called whenever the driver needs to set the firmware + * logging configuration. It can be called on initialization, reset, or during + * runtime. + * + * If the PF wishes to receive FW logging then it must register via + * ice_fwlog_register. Note, that ice_fwlog_register does not need to be called + * for init. + */ +int ice_fwlog_set(struct ice_hw *hw, struct ice_fwlog_cfg *cfg) +{ + if (!ice_fwlog_supported(hw)) + return -EOPNOTSUPP; + + return ice_aq_fwlog_set(hw, cfg->module_entries, + ICE_AQC_FW_LOG_ID_MAX, cfg->options, + cfg->log_resolution); +} + +/** + * ice_aq_fwlog_get - Get the current firmware logging configuration (0xFF32) + * @hw: pointer to the HW structure + * @cfg: firmware logging configuration to populate + */ +static int ice_aq_fwlog_get(struct ice_hw *hw, struct ice_fwlog_cfg *cfg) +{ + struct ice_aqc_fw_log_cfg_resp *fw_modules; + struct ice_aqc_fw_log *cmd; + struct ice_aq_desc desc; + u16 module_id_cnt; + int status; + void *buf; + int i; + + memset(cfg, 0, sizeof(*cfg)); + + buf = kzalloc(ICE_AQ_MAX_BUF_LEN, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logs_query); + cmd = &desc.params.fw_log; + + cmd->cmd_flags = ICE_AQC_FW_LOG_AQ_QUERY; + + status = ice_aq_send_cmd(hw, &desc, buf, ICE_AQ_MAX_BUF_LEN, NULL); + if (status) { + ice_debug(hw, ICE_DBG_FW_LOG, "Failed to get FW log configuration\n"); + goto status_out; + } + + module_id_cnt = le16_to_cpu(cmd->ops.cfg.mdl_cnt); + if (module_id_cnt < ICE_AQC_FW_LOG_ID_MAX) { + ice_debug(hw, ICE_DBG_FW_LOG, "FW returned less than the expected number of FW log module IDs\n"); + } else if (module_id_cnt > ICE_AQC_FW_LOG_ID_MAX) { + ice_debug(hw, ICE_DBG_FW_LOG, "FW returned more than expected number of FW log module IDs, setting module_id_cnt to software expected max %u\n", + ICE_AQC_FW_LOG_ID_MAX); + module_id_cnt = ICE_AQC_FW_LOG_ID_MAX; + } + + cfg->log_resolution = le16_to_cpu(cmd->ops.cfg.log_resolution); + if (cmd->cmd_flags & ICE_AQC_FW_LOG_CONF_AQ_EN) + cfg->options |= ICE_FWLOG_OPTION_ARQ_ENA; + if (cmd->cmd_flags & ICE_AQC_FW_LOG_CONF_UART_EN) + cfg->options |= ICE_FWLOG_OPTION_UART_ENA; + if (cmd->cmd_flags & ICE_AQC_FW_LOG_QUERY_REGISTERED) + cfg->options |= ICE_FWLOG_OPTION_IS_REGISTERED; + + fw_modules = (struct ice_aqc_fw_log_cfg_resp *)buf; + + for (i = 0; i < module_id_cnt; i++) { + struct ice_aqc_fw_log_cfg_resp *fw_module = &fw_modules[i]; + + cfg->module_entries[i].module_id = + le16_to_cpu(fw_module->module_identifier); + cfg->module_entries[i].log_level = fw_module->log_level; + } + +status_out: + kfree(buf); + return status; +} + +/** + * ice_fwlog_get - Get the firmware logging settings + * @hw: pointer to the HW structure + * @cfg: config to populate based on current firmware logging settings + */ +int ice_fwlog_get(struct ice_hw *hw, struct ice_fwlog_cfg *cfg) +{ + if (!ice_fwlog_supported(hw)) + return -EOPNOTSUPP; + + return ice_aq_fwlog_get(hw, cfg); +} + +/** + * ice_aq_fwlog_register - Register PF for firmware logging events (0xFF31) + * @hw: pointer to the HW structure + * @reg: true to register and false to unregister + */ +static int ice_aq_fwlog_register(struct ice_hw *hw, bool reg) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logs_register); + + if (reg) + desc.params.fw_log.cmd_flags = ICE_AQC_FW_LOG_AQ_REGISTER; + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** + * ice_fwlog_register - Register the PF for firmware logging + * @hw: pointer to the HW structure + * + * After this call the PF will start to receive firmware logging based on the + * configuration set in ice_fwlog_set. + */ +int ice_fwlog_register(struct ice_hw *hw) +{ + int status; + + if (!ice_fwlog_supported(hw)) + return -EOPNOTSUPP; + + status = ice_aq_fwlog_register(hw, true); + if (status) + ice_debug(hw, ICE_DBG_FW_LOG, "Failed to register for firmware logging events over ARQ\n"); + else + hw->fwlog_cfg.options |= ICE_FWLOG_OPTION_IS_REGISTERED; + + return status; +} + +/** + * ice_fwlog_unregister - Unregister the PF from firmware logging + * @hw: pointer to the HW structure + */ +int ice_fwlog_unregister(struct ice_hw *hw) +{ + int status; + + if (!ice_fwlog_supported(hw)) + return -EOPNOTSUPP; + + status = ice_aq_fwlog_register(hw, false); + if (status) + ice_debug(hw, ICE_DBG_FW_LOG, "Failed to unregister from firmware logging events over ARQ\n"); + else + hw->fwlog_cfg.options &= ~ICE_FWLOG_OPTION_IS_REGISTERED; + + return status; +} + +/** + * ice_fwlog_set_supported - Set if FW logging is supported by FW + * @hw: pointer to the HW struct + * + * If FW returns success to the ice_aq_fwlog_get call then it supports FW + * logging, else it doesn't. Set the fwlog_supported flag accordingly. + * + * This function is only meant to be called during driver init to determine if + * the FW support FW logging. + */ +void ice_fwlog_set_supported(struct ice_hw *hw) +{ + struct ice_fwlog_cfg *cfg; + int status; + + hw->fwlog_supported = false; + + cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); + if (!cfg) + return; + + /* don't call ice_fwlog_get() because that would check to see if FW + * logging is supported which is what the driver is determining now + */ + status = ice_aq_fwlog_get(hw, cfg); + if (status) + ice_debug(hw, ICE_DBG_FW_LOG, "ice_aq_fwlog_get failed, FW logging is not supported on this version of FW, status %d\n", + status); + else + hw->fwlog_supported = true; + + kfree(cfg); +} diff --git a/drivers/net/ethernet/intel/ice/ice_fwlog.h b/drivers/net/ethernet/intel/ice/ice_fwlog.h new file mode 100644 index 000000000000..287e71fa4b86 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_fwlog.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2022, Intel Corporation. */ + +#ifndef _ICE_FWLOG_H_ +#define _ICE_FWLOG_H_ +#include "ice_adminq_cmd.h" + +struct ice_hw; + +/* Only a single log level should be set and all log levels under the set value + * are enabled, e.g. if log level is set to ICE_FW_LOG_LEVEL_VERBOSE, then all + * other log levels are included (except ICE_FW_LOG_LEVEL_NONE) + */ +enum ice_fwlog_level { + ICE_FWLOG_LEVEL_NONE = 0, + ICE_FWLOG_LEVEL_ERROR = 1, + ICE_FWLOG_LEVEL_WARNING = 2, + ICE_FWLOG_LEVEL_NORMAL = 3, + ICE_FWLOG_LEVEL_VERBOSE = 4, + ICE_FWLOG_LEVEL_INVALID, /* all values >= this entry are invalid */ +}; + +struct ice_fwlog_module_entry { + /* module ID for the corresponding firmware logging event */ + u16 module_id; + /* verbosity level for the module_id */ + u8 log_level; +}; + +struct ice_fwlog_cfg { + /* list of modules for configuring log level */ + struct ice_fwlog_module_entry module_entries[ICE_AQC_FW_LOG_ID_MAX]; + /* options used to configure firmware logging */ + u16 options; +#define ICE_FWLOG_OPTION_ARQ_ENA BIT(0) +#define ICE_FWLOG_OPTION_UART_ENA BIT(1) + /* set before calling ice_fwlog_init() so the PF registers for firmware + * logging on initialization + */ +#define ICE_FWLOG_OPTION_REGISTER_ON_INIT BIT(2) + /* set in the ice_fwlog_get() response if the PF is registered for FW + * logging events over ARQ + */ +#define ICE_FWLOG_OPTION_IS_REGISTERED BIT(3) + + /* minimum number of log events sent per Admin Receive Queue event */ + u16 log_resolution; +}; + +struct ice_fwlog_data { + u16 data_size; + u8 *data; +}; + +struct ice_fwlog_ring { + struct ice_fwlog_data *rings; + u16 index; + u16 size; + u16 head; + u16 tail; +}; + +#define ICE_FWLOG_RING_SIZE_INDEX_DFLT 3 +#define ICE_FWLOG_RING_SIZE_DFLT 256 +#define ICE_FWLOG_RING_SIZE_MAX 512 + +bool ice_fwlog_ring_full(struct ice_fwlog_ring *rings); +bool ice_fwlog_ring_empty(struct ice_fwlog_ring *rings); +void ice_fwlog_ring_increment(u16 *item, u16 size); +void ice_fwlog_set_supported(struct ice_hw *hw); +bool ice_fwlog_supported(struct ice_hw *hw); +int ice_fwlog_init(struct ice_hw *hw); +void ice_fwlog_deinit(struct ice_hw *hw); +int ice_fwlog_set(struct ice_hw *hw, struct ice_fwlog_cfg *cfg); +int ice_fwlog_get(struct ice_hw *hw, struct ice_fwlog_cfg *cfg); +int ice_fwlog_register(struct ice_hw *hw); +int ice_fwlog_unregister(struct ice_hw *hw); +void ice_fwlog_realloc_rings(struct ice_hw *hw, int index); +#endif /* _ICE_FWLOG_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 86936b758ade..cfac1d432c15 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -200,6 +200,8 @@ #define GLINT_VECT2FUNC_PF_NUM_M ICE_M(0x7, 12) #define GLINT_VECT2FUNC_IS_PF_S 16 #define GLINT_VECT2FUNC_IS_PF_M BIT(16) +#define PFINT_ALLOC 0x001D2600 +#define PFINT_ALLOC_FIRST ICE_M(0x7FF, 0) #define PFINT_FW_CTL 0x0016C800 #define PFINT_FW_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) #define PFINT_FW_CTL_ITR_INDX_S 11 @@ -404,6 +406,10 @@ #define GLQF_HMASK_SEL(_i) (0x00410000 + ((_i) * 4)) #define GLQF_HMASK_SEL_MAX_INDEX 127 #define GLQF_HMASK_SEL_MASK_SEL_S 0 +#define GLQF_HSYMM(_i, _j) (0x0040F000 + ((_i) * 4 + (_j) * 512)) +#define GLQF_HSYMM_REG_SIZE 4 +#define GLQF_HSYMM_REG_PER_PROF 6 +#define GLQF_HSYMM_ENABLE_BIT BIT(7) #define E800_PFQF_FD_CNT_FD_GCNT_M GENMASK(14, 0) #define E830_PFQF_FD_CNT_FD_GCNT_M GENMASK(15, 0) #define E800_PFQF_FD_CNT_FD_BCNT_M GENMASK(30, 16) diff --git a/drivers/net/ethernet/intel/ice/ice_hwmon.c b/drivers/net/ethernet/intel/ice/ice_hwmon.c new file mode 100644 index 000000000000..e4c2c1bff6c0 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_hwmon.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023, Intel Corporation. */ + +#include "ice.h" +#include "ice_hwmon.h" +#include "ice_adminq_cmd.h" + +#include <linux/hwmon.h> + +#define TEMP_FROM_REG(reg) ((reg) * 1000) + +static const struct hwmon_channel_info *ice_hwmon_info[] = { + HWMON_CHANNEL_INFO(temp, + HWMON_T_INPUT | HWMON_T_MAX | + HWMON_T_CRIT | HWMON_T_EMERGENCY), + NULL +}; + +static int ice_hwmon_read(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long *val) +{ + struct ice_aqc_get_sensor_reading_resp resp; + struct ice_pf *pf = dev_get_drvdata(dev); + int ret; + + if (type != hwmon_temp) + return -EOPNOTSUPP; + + ret = ice_aq_get_sensor_reading(&pf->hw, &resp); + if (ret) { + dev_warn_ratelimited(dev, + "%s HW read failure (%d)\n", + __func__, + ret); + return ret; + } + + switch (attr) { + case hwmon_temp_input: + *val = TEMP_FROM_REG(resp.data.s0f0.temp); + break; + case hwmon_temp_max: + *val = TEMP_FROM_REG(resp.data.s0f0.temp_warning_threshold); + break; + case hwmon_temp_crit: + *val = TEMP_FROM_REG(resp.data.s0f0.temp_critical_threshold); + break; + case hwmon_temp_emergency: + *val = TEMP_FROM_REG(resp.data.s0f0.temp_fatal_threshold); + break; + default: + dev_dbg(dev, "%s unsupported attribute (%d)\n", + __func__, attr); + return -EOPNOTSUPP; + } + + return 0; +} + +static umode_t ice_hwmon_is_visible(const void *data, + enum hwmon_sensor_types type, u32 attr, + int channel) +{ + if (type != hwmon_temp) + return 0; + + switch (attr) { + case hwmon_temp_input: + case hwmon_temp_crit: + case hwmon_temp_max: + case hwmon_temp_emergency: + return 0444; + } + + return 0; +} + +static const struct hwmon_ops ice_hwmon_ops = { + .is_visible = ice_hwmon_is_visible, + .read = ice_hwmon_read +}; + +static const struct hwmon_chip_info ice_chip_info = { + .ops = &ice_hwmon_ops, + .info = ice_hwmon_info +}; + +static bool ice_is_internal_reading_supported(struct ice_pf *pf) +{ + /* Only the first PF will report temperature for a chip. + * Note that internal temp reading is not supported + * for older FW (< v4.30). + */ + if (pf->hw.pf_id) + return false; + + unsigned long sensors = pf->hw.dev_caps.supported_sensors; + + return _test_bit(ICE_SENSOR_SUPPORT_E810_INT_TEMP_BIT, &sensors); +}; + +void ice_hwmon_init(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct device *hdev; + + if (!ice_is_internal_reading_supported(pf)) + return; + + hdev = hwmon_device_register_with_info(dev, "ice", pf, &ice_chip_info, + NULL); + if (IS_ERR(hdev)) { + dev_warn(dev, + "hwmon_device_register_with_info returns error (%ld)", + PTR_ERR(hdev)); + return; + } + pf->hwmon_dev = hdev; +} + +void ice_hwmon_exit(struct ice_pf *pf) +{ + if (!pf->hwmon_dev) + return; + hwmon_device_unregister(pf->hwmon_dev); +} diff --git a/drivers/net/ethernet/intel/ice/ice_hwmon.h b/drivers/net/ethernet/intel/ice/ice_hwmon.h new file mode 100644 index 000000000000..d66d40354f5a --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_hwmon.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023, Intel Corporation. */ + +#ifndef _ICE_HWMON_H_ +#define _ICE_HWMON_H_ + +#ifdef CONFIG_ICE_HWMON +void ice_hwmon_init(struct ice_pf *pf); +void ice_hwmon_exit(struct ice_pf *pf); +#else /* CONFIG_ICE_HWMON */ +static inline void ice_hwmon_init(struct ice_pf *pf) { } +static inline void ice_hwmon_exit(struct ice_pf *pf) { } +#endif /* CONFIG_ICE_HWMON */ + +#endif /* _ICE_HWMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index b980f89dc892..1ccb572ce285 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -152,6 +152,27 @@ ice_lag_find_hw_by_lport(struct ice_lag *lag, u8 lport) } /** + * ice_pkg_has_lport_extract - check if lport extraction supported + * @hw: HW struct + */ +static bool ice_pkg_has_lport_extract(struct ice_hw *hw) +{ + int i; + + for (i = 0; i < hw->blk[ICE_BLK_SW].es.count; i++) { + u16 offset; + u8 fv_prot; + + ice_find_prot_off(hw, ICE_BLK_SW, ICE_SW_DEFAULT_PROFILE, i, + &fv_prot, &offset); + if (fv_prot == ICE_FV_PROT_MDID && + offset == ICE_LP_EXT_BUF_OFFSET) + return true; + } + return false; +} + +/** * ice_lag_find_primary - returns pointer to primary interfaces lag struct * @lag: local interfaces lag struct */ @@ -181,11 +202,12 @@ static struct ice_lag *ice_lag_find_primary(struct ice_lag *lag) * @act: rule action * @recipe_id: recipe id for the new rule * @rule_idx: pointer to rule index + * @direction: ICE_FLTR_RX or ICE_FLTR_TX * @add: boolean on whether we are adding filters */ static int ice_lag_cfg_fltr(struct ice_lag *lag, u32 act, u16 recipe_id, u16 *rule_idx, - bool add) + u8 direction, bool add) { struct ice_sw_rule_lkup_rx_tx *s_rule; u16 s_rule_sz, vsi_num; @@ -208,12 +230,18 @@ ice_lag_cfg_fltr(struct ice_lag *lag, u32 act, u16 recipe_id, u16 *rule_idx, eth_hdr = s_rule->hdr_data; ice_fill_eth_hdr(eth_hdr); - act |= (vsi_num << ICE_SINGLE_ACT_VSI_ID_S) & - ICE_SINGLE_ACT_VSI_ID_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, vsi_num); - s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); s_rule->recipe_id = cpu_to_le16(recipe_id); - s_rule->src = cpu_to_le16(hw->port_info->lport); + if (direction == ICE_FLTR_RX) { + s_rule->hdr.type = + cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->src = cpu_to_le16(hw->port_info->lport); + } else { + s_rule->hdr.type = + cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_TX); + s_rule->src = cpu_to_le16(vsi_num); + } s_rule->act = cpu_to_le32(act); s_rule->hdr_len = cpu_to_le16(DUMMY_ETH_HDR_LEN); opc = ice_aqc_opc_add_sw_rules; @@ -246,9 +274,27 @@ ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add) { u32 act = ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT | ICE_SINGLE_ACT_LAN_ENABLE; + int err; + + err = ice_lag_cfg_fltr(lag, act, lag->pf_recipe, &lag->pf_rx_rule_id, + ICE_FLTR_RX, add); + if (err) + goto err_rx; + + act = ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT | + ICE_SINGLE_ACT_LB_ENABLE; + err = ice_lag_cfg_fltr(lag, act, lag->pf_recipe, &lag->pf_tx_rule_id, + ICE_FLTR_TX, add); + if (err) + goto err_tx; + + return 0; - return ice_lag_cfg_fltr(lag, act, lag->pf_recipe, - &lag->pf_rule_id, add); +err_tx: + ice_lag_cfg_fltr(lag, act, lag->pf_recipe, &lag->pf_rx_rule_id, + ICE_FLTR_RX, !add); +err_rx: + return err; } /** @@ -264,7 +310,7 @@ ice_lag_cfg_drop_fltr(struct ice_lag *lag, bool add) ICE_SINGLE_ACT_DROP; return ice_lag_cfg_fltr(lag, act, lag->lport_recipe, - &lag->lport_rule_idx, add); + &lag->lport_rule_idx, ICE_FLTR_RX, add); } /** @@ -290,7 +336,7 @@ ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr) dev = ice_pf_to_dev(lag->pf); /* interface not active - remove old default VSI rule */ - if (bonding_info->slave.state && lag->pf_rule_id) { + if (bonding_info->slave.state && lag->pf_rx_rule_id) { if (ice_lag_cfg_dflt_fltr(lag, false)) dev_err(dev, "Error removing old default VSI filter\n"); if (ice_lag_cfg_drop_fltr(lag, true)) @@ -299,7 +345,7 @@ ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr) } /* interface becoming active - add new default VSI rule */ - if (!bonding_info->slave.state && !lag->pf_rule_id) { + if (!bonding_info->slave.state && !lag->pf_rx_rule_id) { if (ice_lag_cfg_dflt_fltr(lag, true)) dev_err(dev, "Error adding new default VSI filter\n"); if (lag->lport_rule_idx && ice_lag_cfg_drop_fltr(lag, false)) @@ -471,7 +517,7 @@ static void ice_lag_move_vf_node_tc(struct ice_lag *lag, u8 oldport, u8 newport, u16 vsi_num, u8 tc) { - DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + DEFINE_RAW_FLEX(struct ice_aqc_move_elem, buf, teid, 1); struct device *dev = ice_pf_to_dev(lag->pf); u16 numq, valq, num_moved, qbuf_size; u16 buf_size = __struct_size(buf); @@ -570,6 +616,50 @@ resume_traffic: } /** + * ice_lag_build_netdev_list - populate the lag struct's netdev list + * @lag: local lag struct + * @ndlist: pointer to netdev list to populate + */ +static void ice_lag_build_netdev_list(struct ice_lag *lag, + struct ice_lag_netdev_list *ndlist) +{ + struct ice_lag_netdev_list *nl; + struct net_device *tmp_nd; + + INIT_LIST_HEAD(&ndlist->node); + rcu_read_lock(); + for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) { + nl = kzalloc(sizeof(*nl), GFP_ATOMIC); + if (!nl) + break; + + nl->netdev = tmp_nd; + list_add(&nl->node, &ndlist->node); + } + rcu_read_unlock(); + lag->netdev_head = &ndlist->node; +} + +/** + * ice_lag_destroy_netdev_list - free lag struct's netdev list + * @lag: pointer to local lag struct + * @ndlist: pointer to lag struct netdev list + */ +static void ice_lag_destroy_netdev_list(struct ice_lag *lag, + struct ice_lag_netdev_list *ndlist) +{ + struct ice_lag_netdev_list *entry, *n; + + rcu_read_lock(); + list_for_each_entry_safe(entry, n, &ndlist->node, node) { + list_del(&entry->node); + kfree(entry); + } + rcu_read_unlock(); + lag->netdev_head = NULL; +} + +/** * ice_lag_move_single_vf_nodes - Move Tx scheduling nodes for single VF * @lag: primary interface LAG struct * @oldport: lport of previous interface @@ -597,7 +687,6 @@ ice_lag_move_single_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport, void ice_lag_move_new_vf_nodes(struct ice_vf *vf) { struct ice_lag_netdev_list ndlist; - struct list_head *tmp, *n; u8 pri_port, act_port; struct ice_lag *lag; struct ice_vsi *vsi; @@ -621,38 +710,15 @@ void ice_lag_move_new_vf_nodes(struct ice_vf *vf) pri_port = pf->hw.port_info->lport; act_port = lag->active_port; - if (lag->upper_netdev) { - struct ice_lag_netdev_list *nl; - struct net_device *tmp_nd; - - INIT_LIST_HEAD(&ndlist.node); - rcu_read_lock(); - for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) { - nl = kzalloc(sizeof(*nl), GFP_KERNEL); - if (!nl) - break; - - nl->netdev = tmp_nd; - list_add(&nl->node, &ndlist.node); - } - rcu_read_unlock(); - } - - lag->netdev_head = &ndlist.node; + if (lag->upper_netdev) + ice_lag_build_netdev_list(lag, &ndlist); if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) && lag->bonded && lag->primary && pri_port != act_port && !list_empty(lag->netdev_head)) ice_lag_move_single_vf_nodes(lag, pri_port, act_port, vsi->idx); - list_for_each_safe(tmp, n, &ndlist.node) { - struct ice_lag_netdev_list *entry; - - entry = list_entry(tmp, struct ice_lag_netdev_list, node); - list_del(&entry->node); - kfree(entry); - } - lag->netdev_head = NULL; + ice_lag_destroy_netdev_list(lag, &ndlist); new_vf_unlock: mutex_unlock(&pf->lag_mutex); @@ -674,11 +740,33 @@ static void ice_lag_move_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport) pf = lag->pf; ice_for_each_vsi(pf, i) - if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF || - pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL)) + if (pf->vsi[i] && pf->vsi[i]->type == ICE_VSI_VF) ice_lag_move_single_vf_nodes(lag, oldport, newport, i); } +/** + * ice_lag_move_vf_nodes_cfg - move vf nodes outside LAG netdev event context + * @lag: local lag struct + * @src_prt: lport value for source port + * @dst_prt: lport value for destination port + * + * This function is used to move nodes during an out-of-netdev-event situation, + * primarily when the driver needs to reconfigure or recreate resources. + * + * Must be called while holding the lag_mutex to avoid lag events from + * processing while out-of-sync moves are happening. Also, paired moves, + * such as used in a reset flow, should both be called under the same mutex + * lock to avoid changes between start of reset and end of reset. + */ +void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt) +{ + struct ice_lag_netdev_list ndlist; + + ice_lag_build_netdev_list(lag, &ndlist); + ice_lag_move_vf_nodes(lag, src_prt, dst_prt); + ice_lag_destroy_netdev_list(lag, &ndlist); +} + #define ICE_LAG_SRIOV_CP_RECIPE 10 #define ICE_LAG_SRIOV_TRAIN_PKT_LEN 16 @@ -711,9 +799,7 @@ ice_lag_cfg_cp_fltr(struct ice_lag *lag, bool add) s_rule->act = cpu_to_le32(ICE_FWD_TO_VSI | ICE_SINGLE_ACT_LAN_ENABLE | ICE_SINGLE_ACT_VALID_BIT | - ((vsi->vsi_num << - ICE_SINGLE_ACT_VSI_ID_S) & - ICE_SINGLE_ACT_VSI_ID_M)); + FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, vsi->vsi_num)); s_rule->hdr_len = cpu_to_le16(ICE_LAG_SRIOV_TRAIN_PKT_LEN); memcpy(s_rule->hdr_data, lacp_train_pkt, LACP_TRAIN_PKT_LEN); opc = ice_aqc_opc_add_sw_rules; @@ -788,7 +874,7 @@ static void ice_lag_reclaim_vf_tc(struct ice_lag *lag, struct ice_hw *src_hw, u16 vsi_num, u8 tc) { - DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + DEFINE_RAW_FLEX(struct ice_aqc_move_elem, buf, teid, 1); struct device *dev = ice_pf_to_dev(lag->pf); u16 numq, valq, num_moved, qbuf_size; u16 buf_size = __struct_size(buf); @@ -892,8 +978,7 @@ ice_lag_reclaim_vf_nodes(struct ice_lag *lag, struct ice_hw *src_hw) pf = lag->pf; ice_for_each_vsi(pf, i) - if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF || - pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL)) + if (pf->vsi[i] && pf->vsi[i]->type == ICE_VSI_VF) ice_for_each_traffic_class(tc) ice_lag_reclaim_vf_tc(lag, src_hw, i, tc); } @@ -1166,7 +1251,7 @@ static void ice_lag_del_prune_list(struct ice_lag *lag, struct ice_pf *event_pf) } /** - * ice_lag_init_feature_support_flag - Check for NVM support for LAG + * ice_lag_init_feature_support_flag - Check for package and NVM support for LAG * @pf: PF struct */ static void ice_lag_init_feature_support_flag(struct ice_pf *pf) @@ -1179,7 +1264,7 @@ static void ice_lag_init_feature_support_flag(struct ice_pf *pf) else ice_clear_feature_support(pf, ICE_F_ROCE_LAG); - if (caps->sriov_lag) + if (caps->sriov_lag && ice_pkg_has_lport_extract(&pf->hw)) ice_set_feature_support(pf, ICE_F_SRIOV_LAG); else ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); @@ -1555,18 +1640,12 @@ static void ice_lag_chk_disabled_bond(struct ice_lag *lag, void *ptr) */ static void ice_lag_disable_sriov_bond(struct ice_lag *lag) { - struct ice_lag_netdev_list *entry; struct ice_netdev_priv *np; - struct net_device *netdev; struct ice_pf *pf; - list_for_each_entry(entry, lag->netdev_head, node) { - netdev = entry->netdev; - np = netdev_priv(netdev); - pf = np->vsi->back; - - ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); - } + np = netdev_priv(lag->netdev); + pf = np->vsi->back; + ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); } /** @@ -1698,7 +1777,7 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event, rcu_read_lock(); for_each_netdev_in_bond_rcu(upper_netdev, tmp_nd) { - nd_list = kzalloc(sizeof(*nd_list), GFP_KERNEL); + nd_list = kzalloc(sizeof(*nd_list), GFP_ATOMIC); if (!nd_list) break; @@ -1818,7 +1897,7 @@ static void ice_lag_move_vf_nodes_tc_sync(struct ice_lag *lag, struct ice_hw *dest_hw, u16 vsi_num, u8 tc) { - DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + DEFINE_RAW_FLEX(struct ice_aqc_move_elem, buf, teid, 1); struct device *dev = ice_pf_to_dev(lag->pf); u16 numq, valq, num_moved, qbuf_size; u16 buf_size = __struct_size(buf); @@ -1921,8 +2000,7 @@ ice_lag_move_vf_nodes_sync(struct ice_lag *lag, struct ice_hw *dest_hw) pf = lag->pf; ice_for_each_vsi(pf, i) - if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF || - pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL)) + if (pf->vsi[i] && pf->vsi[i]->type == ICE_VSI_VF) ice_for_each_traffic_class(tc) ice_lag_move_vf_nodes_tc_sync(lag, dest_hw, i, tc); @@ -1944,6 +2022,8 @@ int ice_init_lag(struct ice_pf *pf) int n, err; ice_lag_init_feature_support_flag(pf); + if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) + return 0; pf->lag = kzalloc(sizeof(*lag), GFP_KERNEL); if (!pf->lag) @@ -1984,7 +2064,7 @@ int ice_init_lag(struct ice_pf *pf) /* associate recipes to profiles */ for (n = 0; n < ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER; n++) { err = ice_aq_get_recipe_to_profile(&pf->hw, n, - (u8 *)&recipe_bits, NULL); + &recipe_bits, NULL); if (err) continue; @@ -1992,7 +2072,7 @@ int ice_init_lag(struct ice_pf *pf) recipe_bits |= BIT(lag->pf_recipe) | BIT(lag->lport_recipe); ice_aq_map_recipe_to_profile(&pf->hw, n, - (u8 *)&recipe_bits, NULL); + recipe_bits, NULL); } } @@ -2057,7 +2137,6 @@ void ice_lag_rebuild(struct ice_pf *pf) { struct ice_lag_netdev_list ndlist; struct ice_lag *lag, *prim_lag; - struct list_head *tmp, *n; u8 act_port, loc_port; if (!pf->lag || !pf->lag->bonded) @@ -2069,21 +2148,7 @@ void ice_lag_rebuild(struct ice_pf *pf) if (lag->primary) { prim_lag = lag; } else { - struct ice_lag_netdev_list *nl; - struct net_device *tmp_nd; - - INIT_LIST_HEAD(&ndlist.node); - rcu_read_lock(); - for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) { - nl = kzalloc(sizeof(*nl), GFP_KERNEL); - if (!nl) - break; - - nl->netdev = tmp_nd; - list_add(&nl->node, &ndlist.node); - } - rcu_read_unlock(); - lag->netdev_head = &ndlist.node; + ice_lag_build_netdev_list(lag, &ndlist); prim_lag = ice_lag_find_primary(lag); } @@ -2107,19 +2172,13 @@ void ice_lag_rebuild(struct ice_pf *pf) ice_lag_cfg_cp_fltr(lag, true); - if (lag->pf_rule_id) + if (lag->pf_rx_rule_id) if (ice_lag_cfg_dflt_fltr(lag, true)) dev_err(ice_pf_to_dev(pf), "Error adding default VSI rule in rebuild\n"); ice_clear_rdma_cap(pf); lag_rebuild_out: - list_for_each_safe(tmp, n, &ndlist.node) { - struct ice_lag_netdev_list *entry; - - entry = list_entry(tmp, struct ice_lag_netdev_list, node); - list_del(&entry->node); - kfree(entry); - } + ice_lag_destroy_netdev_list(lag, &ndlist); mutex_unlock(&pf->lag_mutex); } diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h index 9557e8605a07..bab2c83142a1 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.h +++ b/drivers/net/ethernet/intel/ice/ice_lag.h @@ -17,6 +17,9 @@ enum ice_lag_role { #define ICE_LAG_INVALID_PORT 0xFF #define ICE_LAG_RESET_RETRIES 5 +#define ICE_SW_DEFAULT_PROFILE 0 +#define ICE_FV_PROT_MDID 255 +#define ICE_LP_EXT_BUF_OFFSET 32 struct ice_pf; struct ice_vf; @@ -40,7 +43,8 @@ struct ice_lag { u8 primary:1; /* this is primary */ u16 pf_recipe; u16 lport_recipe; - u16 pf_rule_id; + u16 pf_rx_rule_id; + u16 pf_tx_rule_id; u16 cp_rule_idx; u16 lport_rule_idx; u8 role; @@ -65,4 +69,5 @@ int ice_init_lag(struct ice_pf *pf); void ice_deinit_lag(struct ice_pf *pf); void ice_lag_rebuild(struct ice_pf *pf); bool ice_lag_is_switchdev_running(struct ice_pf *pf); +void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt); #endif /* _ICE_LAG_H_ */ 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 89f986a75cc8..611577ebc29d 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -160,64 +160,6 @@ struct ice_fltr_desc { (0x1ULL << ICE_FXD_FLTR_WB_QW1_FAIL_PROF_S) #define ICE_FXD_FLTR_WB_QW1_FAIL_PROF_YES 0x1ULL -struct ice_rx_ptype_decoded { - u32 known:1; - u32 outer_ip:1; - u32 outer_ip_ver:2; - u32 outer_frag:1; - u32 tunnel_type:3; - u32 tunnel_end_prot:2; - u32 tunnel_end_frag:1; - u32 inner_prot:4; - u32 payload_layer:3; -}; - -enum ice_rx_ptype_outer_ip { - ICE_RX_PTYPE_OUTER_L2 = 0, - ICE_RX_PTYPE_OUTER_IP = 1, -}; - -enum ice_rx_ptype_outer_ip_ver { - ICE_RX_PTYPE_OUTER_NONE = 0, - ICE_RX_PTYPE_OUTER_IPV4 = 1, - ICE_RX_PTYPE_OUTER_IPV6 = 2, -}; - -enum ice_rx_ptype_outer_fragmented { - ICE_RX_PTYPE_NOT_FRAG = 0, - ICE_RX_PTYPE_FRAG = 1, -}; - -enum ice_rx_ptype_tunnel_type { - ICE_RX_PTYPE_TUNNEL_NONE = 0, - ICE_RX_PTYPE_TUNNEL_IP_IP = 1, - ICE_RX_PTYPE_TUNNEL_IP_GRENAT = 2, - ICE_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3, - ICE_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4, -}; - -enum ice_rx_ptype_tunnel_end_prot { - ICE_RX_PTYPE_TUNNEL_END_NONE = 0, - ICE_RX_PTYPE_TUNNEL_END_IPV4 = 1, - ICE_RX_PTYPE_TUNNEL_END_IPV6 = 2, -}; - -enum ice_rx_ptype_inner_prot { - ICE_RX_PTYPE_INNER_PROT_NONE = 0, - ICE_RX_PTYPE_INNER_PROT_UDP = 1, - ICE_RX_PTYPE_INNER_PROT_TCP = 2, - ICE_RX_PTYPE_INNER_PROT_SCTP = 3, - ICE_RX_PTYPE_INNER_PROT_ICMP = 4, - ICE_RX_PTYPE_INNER_PROT_TIMESYNC = 5, -}; - -enum ice_rx_ptype_payload_layer { - ICE_RX_PTYPE_PAYLOAD_LAYER_NONE = 0, - ICE_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1, - ICE_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2, - ICE_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3, -}; - /* Rx Flex Descriptor * This descriptor is used instead of the legacy version descriptor when * ice_rlan_ctx.adv_desc is set @@ -651,262 +593,4 @@ struct ice_tlan_ctx { u8 int_q_state; /* width not needed - internal - DO NOT WRITE!!! */ }; -/* The ice_ptype_lkup table is used to convert from the 10-bit ptype in the - * hardware to a bit-field that can be used by SW to more easily determine the - * packet type. - * - * Macros are used to shorten the table lines and make this table human - * readable. - * - * We store the PTYPE in the top byte of the bit field - this is just so that - * we can check that the table doesn't have a row missing, as the index into - * the table should be the PTYPE. - * - * Typical work flow: - * - * IF NOT ice_ptype_lkup[ptype].known - * THEN - * Packet is unknown - * ELSE IF ice_ptype_lkup[ptype].outer_ip == ICE_RX_PTYPE_OUTER_IP - * Use the rest of the fields to look at the tunnels, inner protocols, etc - * ELSE - * Use the enum ice_rx_l2_ptype to decode the packet type - * ENDIF - */ - -/* macro to make the table lines short, use explicit indexing with [PTYPE] */ -#define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ - [PTYPE] = { \ - 1, \ - ICE_RX_PTYPE_OUTER_##OUTER_IP, \ - ICE_RX_PTYPE_OUTER_##OUTER_IP_VER, \ - ICE_RX_PTYPE_##OUTER_FRAG, \ - ICE_RX_PTYPE_TUNNEL_##T, \ - ICE_RX_PTYPE_TUNNEL_END_##TE, \ - ICE_RX_PTYPE_##TEF, \ - ICE_RX_PTYPE_INNER_PROT_##I, \ - ICE_RX_PTYPE_PAYLOAD_LAYER_##PL } - -#define ICE_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } - -/* shorter macros makes the table fit but are terse */ -#define ICE_RX_PTYPE_NOF ICE_RX_PTYPE_NOT_FRAG -#define ICE_RX_PTYPE_FRG ICE_RX_PTYPE_FRAG - -/* Lookup table mapping in the 10-bit HW PTYPE to the bit field for decoding */ -static const struct ice_rx_ptype_decoded ice_ptype_lkup[BIT(10)] = { - /* L2 Packet types */ - ICE_PTT_UNUSED_ENTRY(0), - ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - ICE_PTT_UNUSED_ENTRY(2), - ICE_PTT_UNUSED_ENTRY(3), - ICE_PTT_UNUSED_ENTRY(4), - ICE_PTT_UNUSED_ENTRY(5), - ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), - ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), - ICE_PTT_UNUSED_ENTRY(8), - ICE_PTT_UNUSED_ENTRY(9), - ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), - ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), - ICE_PTT_UNUSED_ENTRY(12), - ICE_PTT_UNUSED_ENTRY(13), - ICE_PTT_UNUSED_ENTRY(14), - ICE_PTT_UNUSED_ENTRY(15), - ICE_PTT_UNUSED_ENTRY(16), - ICE_PTT_UNUSED_ENTRY(17), - ICE_PTT_UNUSED_ENTRY(18), - ICE_PTT_UNUSED_ENTRY(19), - ICE_PTT_UNUSED_ENTRY(20), - ICE_PTT_UNUSED_ENTRY(21), - - /* Non Tunneled IPv4 */ - ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), - ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), - ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(25), - ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), - ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), - ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv4 --> IPv4 */ - ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(32), - ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> IPv6 */ - ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(39), - ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT */ - ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> IPv4 */ - ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(47), - ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> IPv6 */ - ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(54), - ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC */ - ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ - ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(62), - ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ - ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(69), - ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC/VLAN */ - ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ - ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(77), - ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ - ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(84), - ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - - /* Non Tunneled IPv6 */ - ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), - ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), - ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(91), - ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), - ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), - ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv6 --> IPv4 */ - ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(98), - ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> IPv6 */ - ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(105), - ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT */ - ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> IPv4 */ - ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(113), - ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> IPv6 */ - ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(120), - ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC */ - ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ - ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(128), - ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ - ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(135), - ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN */ - ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ - ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(143), - ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ - ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(150), - ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - - /* unused entries */ - [154 ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } -}; - -static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype) -{ - return ice_ptype_lkup[ptype]; -} - - #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 4b1e56396293..5371e91f6bbb 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -7,7 +7,6 @@ #include "ice_lib.h" #include "ice_fltr.h" #include "ice_dcb_lib.h" -#include "ice_devlink.h" #include "ice_vsi_vlan_ops.h" /** @@ -27,8 +26,6 @@ const char *ice_vsi_type_str(enum ice_vsi_type vsi_type) return "ICE_VSI_CHNL"; case ICE_VSI_LB: return "ICE_VSI_LB"; - case ICE_VSI_SWITCHDEV_CTRL: - return "ICE_VSI_SWITCHDEV_CTRL"; default: return "unknown"; } @@ -144,7 +141,6 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) { switch (vsi->type) { case ICE_VSI_PF: - case ICE_VSI_SWITCHDEV_CTRL: case ICE_VSI_CTRL: case ICE_VSI_LB: /* a user could change the values of num_[tr]x_desc using @@ -211,14 +207,6 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) max_t(int, vsi->alloc_rxq, vsi->alloc_txq)); break; - case ICE_VSI_SWITCHDEV_CTRL: - /* The number of queues for ctrl VSI is equal to number of VFs. - * Each ring is associated to the corresponding VF_PR netdev. - */ - vsi->alloc_txq = ice_get_num_vfs(pf); - vsi->alloc_rxq = vsi->alloc_txq; - vsi->num_q_vectors = 1; - break; case ICE_VSI_VF: if (vf->num_req_qs) vf->num_vf_qs = vf->num_req_qs; @@ -515,24 +503,6 @@ static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data) return IRQ_HANDLED; } -static irqreturn_t ice_eswitch_msix_clean_rings(int __always_unused irq, void *data) -{ - struct ice_q_vector *q_vector = (struct ice_q_vector *)data; - struct ice_pf *pf = q_vector->vsi->back; - struct ice_vf *vf; - unsigned int bkt; - - if (!q_vector->tx.tx_ring && !q_vector->rx.rx_ring) - return IRQ_HANDLED; - - rcu_read_lock(); - ice_for_each_vf_rcu(pf, bkt, vf) - napi_schedule(&vf->repr->q_vector->napi); - rcu_read_unlock(); - - return IRQ_HANDLED; -} - /** * ice_vsi_alloc_stat_arrays - Allocate statistics arrays * @vsi: VSI pointer @@ -595,10 +565,6 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch) } switch (vsi->type) { - case ICE_VSI_SWITCHDEV_CTRL: - /* Setup eswitch MSIX irq handler for VSI */ - vsi->irq_handler = ice_eswitch_msix_clean_rings; - break; case ICE_VSI_PF: /* Setup default MSIX irq handler for VSI */ vsi->irq_handler = ice_msix_clean_rings; @@ -928,11 +894,6 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) max_rss_size); vsi->rss_lut_type = ICE_LUT_PF; break; - case ICE_VSI_SWITCHDEV_CTRL: - vsi->rss_table_size = ICE_LUT_VSI_SIZE; - vsi->rss_size = min_t(u16, num_online_cpus(), max_rss_size); - vsi->rss_lut_type = ICE_LUT_VSI; - break; case ICE_VSI_VF: /* VF VSI will get a small RSS table. * For VSI_LUT, LUT size should be set to 64 bytes. @@ -969,9 +930,8 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt) /* Traffic from VSI can be sent to LAN */ ctxt->info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA; /* allow all untagged/tagged packets by default on Tx */ - ctxt->info.inner_vlan_flags = ((ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL & - ICE_AQ_VSI_INNER_VLAN_TX_MODE_M) >> - ICE_AQ_VSI_INNER_VLAN_TX_MODE_S); + ctxt->info.inner_vlan_flags = FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_TX_MODE_M, + ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL); /* SVM - by default bits 3 and 4 in inner_vlan_flags are 0's which * results in legacy behavior (show VLAN, DEI, and UP) in descriptor. * @@ -979,15 +939,14 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt) */ if (ice_is_dvm_ena(hw)) { ctxt->info.inner_vlan_flags |= - ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING; + FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M, + ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING); ctxt->info.outer_vlan_flags = - (ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M; + FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M, + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL); ctxt->info.outer_vlan_flags |= - (ICE_AQ_VSI_OUTER_TAG_VLAN_8100 << - ICE_AQ_VSI_OUTER_TAG_TYPE_S) & - ICE_AQ_VSI_OUTER_TAG_TYPE_M; + FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M, + ICE_AQ_VSI_OUTER_TAG_VLAN_8100); ctxt->info.outer_vlan_flags |= FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_EMODE_M, ICE_AQ_VSI_OUTER_VLAN_EMODE_NOTHING); @@ -1066,10 +1025,8 @@ static int ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) vsi->tc_cfg.tc_info[i].qcount_tx = num_txq_per_tc; vsi->tc_cfg.tc_info[i].netdev_tc = netdev_tc++; - qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & - ICE_AQ_VSI_TC_Q_OFFSET_M) | - ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & - ICE_AQ_VSI_TC_Q_NUM_M); + qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset); + qmap |= FIELD_PREP(ICE_AQ_VSI_TC_Q_NUM_M, pow); offset += num_rxq_per_tc; tx_count += num_txq_per_tc; ctxt->info.tc_mapping[i] = cpu_to_le16(qmap); @@ -1152,18 +1109,14 @@ static void ice_set_fd_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) ctxt->info.max_fd_fltr_shared = cpu_to_le16(vsi->num_bfltr); /* default queue index within the VSI of the default FD */ - val = ((dflt_q << ICE_AQ_VSI_FD_DEF_Q_S) & - ICE_AQ_VSI_FD_DEF_Q_M); + val = FIELD_PREP(ICE_AQ_VSI_FD_DEF_Q_M, dflt_q); /* target queue or queue group to the FD filter */ - val |= ((dflt_q_group << ICE_AQ_VSI_FD_DEF_GRP_S) & - ICE_AQ_VSI_FD_DEF_GRP_M); + val |= FIELD_PREP(ICE_AQ_VSI_FD_DEF_GRP_M, dflt_q_group); ctxt->info.fd_def_q = cpu_to_le16(val); /* queue index on which FD filter completion is reported */ - val = ((report_q << ICE_AQ_VSI_FD_REPORT_Q_S) & - ICE_AQ_VSI_FD_REPORT_Q_M); + val = FIELD_PREP(ICE_AQ_VSI_FD_REPORT_Q_M, report_q); /* priority of the default qindex action */ - val |= ((dflt_q_prio << ICE_AQ_VSI_FD_DEF_PRIORITY_S) & - ICE_AQ_VSI_FD_DEF_PRIORITY_M); + val |= FIELD_PREP(ICE_AQ_VSI_FD_DEF_PRIORITY_M, dflt_q_prio); ctxt->info.fd_report_opt = cpu_to_le16(val); } @@ -1186,12 +1139,10 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) case ICE_VSI_PF: /* PF VSI will inherit RSS instance of PF */ lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF; - hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; break; case ICE_VSI_VF: /* VF VSI will gets a small RSS table which is a VSI LUT type */ lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; - hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; break; default: dev_dbg(dev, "Unsupported VSI type %s\n", @@ -1199,9 +1150,12 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) return; } - ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) & - ICE_AQ_VSI_Q_OPT_RSS_LUT_M) | - (hash_type & ICE_AQ_VSI_Q_OPT_RSS_HASH_M); + hash_type = ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ; + vsi->rss_hfunc = hash_type; + + ctxt->info.q_opt_rss = + FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_LUT_M, lut_type) | + FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hash_type); } static void @@ -1215,10 +1169,8 @@ ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) qcount = min_t(int, vsi->num_rxq, pf->num_lan_msix); pow = order_base_2(qcount); - qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & - ICE_AQ_VSI_TC_Q_OFFSET_M) | - ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & - ICE_AQ_VSI_TC_Q_NUM_M); + qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset); + qmap |= FIELD_PREP(ICE_AQ_VSI_TC_Q_NUM_M, pow); ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); ctxt->info.mapping_flags |= cpu_to_le16(ICE_AQ_VSI_Q_MAP_CONTIG); @@ -1267,7 +1219,6 @@ static int ice_vsi_init(struct ice_vsi *vsi, u32 vsi_flags) case ICE_VSI_PF: ctxt->flags = ICE_AQ_VSI_TYPE_PF; break; - case ICE_VSI_SWITCHDEV_CTRL: case ICE_VSI_CHNL: ctxt->flags = ICE_AQ_VSI_TYPE_VMDQ2; break; @@ -1600,12 +1551,81 @@ static void ice_vsi_set_vf_rss_flow_fld(struct ice_vsi *vsi) return; } - status = ice_add_avf_rss_cfg(&pf->hw, vsi->idx, ICE_DEFAULT_RSS_HENA); + status = ice_add_avf_rss_cfg(&pf->hw, vsi, ICE_DEFAULT_RSS_HENA); if (status) dev_dbg(dev, "ice_add_avf_rss_cfg failed for vsi = %d, error = %d\n", vsi->vsi_num, status); } +static const struct ice_rss_hash_cfg default_rss_cfgs[] = { + /* configure RSS for IPv4 with input set IP src/dst */ + {ICE_FLOW_SEG_HDR_IPV4, ICE_FLOW_HASH_IPV4, ICE_RSS_ANY_HEADERS, false}, + /* configure RSS for IPv6 with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_IPV6, ICE_FLOW_HASH_IPV6, ICE_RSS_ANY_HEADERS, false}, + /* configure RSS for tcp4 with input set IP src/dst, TCP src/dst */ + {ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV4, + ICE_HASH_TCP_IPV4, ICE_RSS_ANY_HEADERS, false}, + /* configure RSS for udp4 with input set IP src/dst, UDP src/dst */ + {ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV4, + ICE_HASH_UDP_IPV4, ICE_RSS_ANY_HEADERS, false}, + /* configure RSS for sctp4 with input set IP src/dst - only support + * RSS on SCTPv4 on outer headers (non-tunneled) + */ + {ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4, + ICE_HASH_SCTP_IPV4, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpc4 with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_IPV4, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpc4t with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_C_IPV4_TEID, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu4 with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_U_IPV4_TEID, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu4e with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_U_IPV4_EH, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu4u with input set IPv4 src/dst */ + { ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_U_IPV4_UP, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu4d with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_U_IPV4_DWN, ICE_RSS_OUTER_HEADERS, false}, + + /* configure RSS for tcp6 with input set IPv6 src/dst, TCP src/dst */ + {ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6, + ICE_HASH_TCP_IPV6, ICE_RSS_ANY_HEADERS, false}, + /* configure RSS for udp6 with input set IPv6 src/dst, UDP src/dst */ + {ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV6, + ICE_HASH_UDP_IPV6, ICE_RSS_ANY_HEADERS, false}, + /* configure RSS for sctp6 with input set IPv6 src/dst - only support + * RSS on SCTPv6 on outer headers (non-tunneled) + */ + {ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6, + ICE_HASH_SCTP_IPV6, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for IPSEC ESP SPI with input set MAC_IPV4_SPI */ + {ICE_FLOW_SEG_HDR_ESP, + ICE_FLOW_HASH_ESP_SPI, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpc6 with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_IPV6, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpc6t with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_C_IPV6_TEID, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu6 with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_U_IPV6_TEID, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu6e with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_U_IPV6_EH, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu6u with input set IPv6 src/dst */ + { ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_U_IPV6_UP, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu6d with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_U_IPV6_DWN, ICE_RSS_OUTER_HEADERS, false}, +}; + /** * ice_vsi_set_rss_flow_fld - Sets RSS input set for different flows * @vsi: VSI to be configured @@ -1619,11 +1639,12 @@ static void ice_vsi_set_vf_rss_flow_fld(struct ice_vsi *vsi) */ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) { - u16 vsi_handle = vsi->idx, vsi_num = vsi->vsi_num; + u16 vsi_num = vsi->vsi_num; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; struct device *dev; int status; + u32 i; dev = ice_pf_to_dev(pf); if (ice_is_safe_mode(pf)) { @@ -1631,87 +1652,14 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) vsi_num); return; } - /* configure RSS for IPv4 with input set IP src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4, - ICE_FLOW_SEG_HDR_IPV4); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for ipv4 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for IPv6 with input set IPv6 src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6, - ICE_FLOW_SEG_HDR_IPV6); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for ipv6 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for tcp4 with input set IP src/dst, TCP src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV4, - ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV4); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for tcp4 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for udp4 with input set IP src/dst, UDP src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV4, - ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV4); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for udp4 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for sctp4 with input set IP src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4, - ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for sctp4 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for tcp6 with input set IPv6 src/dst, TCP src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV6, - ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for tcp6 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for udp6 with input set IPv6 src/dst, UDP src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV6, - ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV6); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for udp6 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for sctp6 with input set IPv6 src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6, - ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for sctp6 flow, vsi = %d, error = %d\n", - vsi_num, status); - - status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_ESP_SPI, - ICE_FLOW_SEG_HDR_ESP); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for esp/spi flow, vsi = %d, error = %d\n", - vsi_num, status); -} + for (i = 0; i < ARRAY_SIZE(default_rss_cfgs); i++) { + const struct ice_rss_hash_cfg *cfg = &default_rss_cfgs[i]; -/** - * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length - * @vsi: VSI - */ -static void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) -{ - if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { - vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX; - vsi->rx_buf_len = ICE_RXBUF_1664; -#if (PAGE_SIZE < 8192) - } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && - (vsi->netdev->mtu <= ETH_DATA_LEN)) { - vsi->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; - vsi->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN; -#endif - } else { - vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; - vsi->rx_buf_len = ICE_RXBUF_3072; + status = ice_add_rss_cfg(hw, vsi, cfg); + if (status) + dev_dbg(dev, "ice_add_rss_cfg failed, addl_hdrs = %x, hash_flds = %llx, hdr_type = %d, symm = %d\n", + cfg->addl_hdrs, cfg->hash_flds, + cfg->hdr_type, cfg->symm); } } @@ -1808,11 +1756,8 @@ ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, QRXFLXP_CNTXT_RXDID_PRIO_M | QRXFLXP_CNTXT_TS_M); - regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) & - QRXFLXP_CNTXT_RXDID_IDX_M; - - regval |= (prio << QRXFLXP_CNTXT_RXDID_PRIO_S) & - QRXFLXP_CNTXT_RXDID_PRIO_M; + regval |= FIELD_PREP(QRXFLXP_CNTXT_RXDID_IDX_M, rxdid); + regval |= FIELD_PREP(QRXFLXP_CNTXT_RXDID_PRIO_M, prio); if (ena_ts) /* Enable TimeSync on this queue */ @@ -1821,114 +1766,6 @@ ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, wr32(hw, QRXFLXP_CNTXT(pf_q), regval); } -int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) -{ - if (q_idx >= vsi->num_rxq) - return -EINVAL; - - return ice_vsi_cfg_rxq(vsi->rx_rings[q_idx]); -} - -int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, u16 q_idx) -{ - DEFINE_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); - - if (q_idx >= vsi->alloc_txq || !tx_rings || !tx_rings[q_idx]) - return -EINVAL; - - qg_buf->num_txqs = 1; - - return ice_vsi_cfg_txq(vsi, tx_rings[q_idx], qg_buf); -} - -/** - * ice_vsi_cfg_rxqs - Configure the VSI for Rx - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - * Configure the Rx VSI for operation. - */ -int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) -{ - u16 i; - - if (vsi->type == ICE_VSI_VF) - goto setup_rings; - - ice_vsi_cfg_frame_size(vsi); -setup_rings: - /* set up individual rings */ - ice_for_each_rxq(vsi, i) { - int err = ice_vsi_cfg_rxq(vsi->rx_rings[i]); - - if (err) - return err; - } - - return 0; -} - -/** - * ice_vsi_cfg_txqs - Configure the VSI for Tx - * @vsi: the VSI being configured - * @rings: Tx ring array to be configured - * @count: number of Tx ring array elements - * - * Return 0 on success and a negative value on error - * Configure the Tx VSI for operation. - */ -static int -ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_tx_ring **rings, u16 count) -{ - DEFINE_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); - int err = 0; - u16 q_idx; - - qg_buf->num_txqs = 1; - - for (q_idx = 0; q_idx < count; q_idx++) { - err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf); - if (err) - break; - } - - return err; -} - -/** - * ice_vsi_cfg_lan_txqs - Configure the VSI for Tx - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - * Configure the Tx VSI for operation. - */ -int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi) -{ - return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, vsi->num_txq); -} - -/** - * ice_vsi_cfg_xdp_txqs - Configure Tx queues dedicated for XDP in given VSI - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - * Configure the Tx queues dedicated for XDP in given VSI for operation. - */ -int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) -{ - int ret; - int i; - - ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings, vsi->num_xdp_txq); - if (ret) - return ret; - - ice_for_each_rxq(vsi, i) - ice_tx_xsk_pool(vsi, i); - - return 0; -} - /** * ice_intrl_usec_to_reg - convert interrupt rate limit to register value * @intrl: interrupt rate limit in usecs @@ -2263,7 +2100,6 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) case ICE_VSI_CHNL: case ICE_VSI_LB: case ICE_VSI_PF: - case ICE_VSI_SWITCHDEV_CTRL: max_agg_nodes = ICE_MAX_PF_AGG_NODES; agg_node_id_start = ICE_PF_AGG_NODE_ID_START; agg_node_iter = &pf->pf_agg_node[0]; @@ -2371,6 +2207,9 @@ static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi) } else { max_txqs[i] = vsi->alloc_txq; } + + if (vsi->type == ICE_VSI_PF) + max_txqs[i] += vsi->num_xdp_txq; } dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc); @@ -2388,10 +2227,8 @@ static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi) /** * ice_vsi_cfg_def - configure default VSI based on the type * @vsi: pointer to VSI - * @params: the parameters to configure this VSI with */ -static int -ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) +static int ice_vsi_cfg_def(struct ice_vsi *vsi) { struct device *dev = ice_pf_to_dev(vsi->back); struct ice_pf *pf = vsi->back; @@ -2399,7 +2236,7 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) vsi->vsw = pf->first_sw; - ret = ice_vsi_alloc_def(vsi, params->ch); + ret = ice_vsi_alloc_def(vsi, vsi->ch); if (ret) return ret; @@ -2424,7 +2261,7 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) ice_vsi_set_tc_cfg(vsi); /* create the VSI */ - ret = ice_vsi_init(vsi, params->flags); + ret = ice_vsi_init(vsi, vsi->flags); if (ret) goto unroll_get_qs; @@ -2432,7 +2269,6 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) switch (vsi->type) { case ICE_VSI_CTRL: - case ICE_VSI_SWITCHDEV_CTRL: case ICE_VSI_PF: ret = ice_vsi_alloc_q_vectors(vsi); if (ret) @@ -2447,6 +2283,10 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) goto unroll_vector_base; ice_vsi_map_rings_to_vectors(vsi); + + /* Associate q_vector rings to napi */ + ice_vsi_set_napi_queues(vsi); + vsi->stat_offsets_loaded = false; if (ice_is_xdp_ena_vsi(vsi)) { @@ -2541,23 +2381,16 @@ unroll_vsi_alloc: /** * ice_vsi_cfg - configure a previously allocated VSI * @vsi: pointer to VSI - * @params: parameters used to configure this VSI */ -int ice_vsi_cfg(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) +int ice_vsi_cfg(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; int ret; - if (WARN_ON(params->type == ICE_VSI_VF && !params->vf)) + if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf)) return -EINVAL; - vsi->type = params->type; - vsi->port_info = params->pi; - - /* For VSIs which don't have a connected VF, this will be NULL */ - vsi->vf = params->vf; - - ret = ice_vsi_cfg_def(vsi, params); + ret = ice_vsi_cfg_def(vsi); if (ret) return ret; @@ -2620,10 +2453,6 @@ void ice_vsi_decfg(struct ice_vsi *vsi) if (vsi->type == ICE_VSI_VF && vsi->agg_node && vsi->agg_node->valid) vsi->agg_node->num_vsis--; - if (vsi->agg_node) { - vsi->agg_node->valid = false; - vsi->agg_node->agg_id = 0; - } } /** @@ -2647,7 +2476,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params) * a port_info structure for it. */ if (WARN_ON(!(params->flags & ICE_VSI_FLAG_INIT)) || - WARN_ON(!params->pi)) + WARN_ON(!params->port_info)) return NULL; vsi = ice_vsi_alloc(pf); @@ -2656,7 +2485,8 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params) return NULL; } - ret = ice_vsi_cfg(vsi, params); + vsi->params = *params; + ret = ice_vsi_cfg(vsi); if (ret) goto err_vsi_cfg; @@ -2865,65 +2695,126 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) } else { ice_vsi_close(vsi); } - } else if (vsi->type == ICE_VSI_CTRL || - vsi->type == ICE_VSI_SWITCHDEV_CTRL) { + } else if (vsi->type == ICE_VSI_CTRL) { ice_vsi_close(vsi); } } /** - * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI - * @vsi: the VSI being un-configured + * __ice_queue_set_napi - Set the napi instance for the queue + * @dev: device to which NAPI and queue belong + * @queue_index: Index of queue + * @type: queue type as RX or TX + * @napi: NAPI context + * @locked: is the rtnl_lock already held + * + * Set the napi instance for the queue. Caller indicates the lock status. */ -void ice_vsi_dis_irq(struct ice_vsi *vsi) +static void +__ice_queue_set_napi(struct net_device *dev, unsigned int queue_index, + enum netdev_queue_type type, struct napi_struct *napi, + bool locked) +{ + if (!locked) + rtnl_lock(); + netif_queue_set_napi(dev, queue_index, type, napi); + if (!locked) + rtnl_unlock(); +} + +/** + * ice_queue_set_napi - Set the napi instance for the queue + * @vsi: VSI being configured + * @queue_index: Index of queue + * @type: queue type as RX or TX + * @napi: NAPI context + * + * Set the napi instance for the queue. The rtnl lock state is derived from the + * execution path. + */ +void +ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index, + enum netdev_queue_type type, struct napi_struct *napi) { struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; - u32 val; - int i; - /* disable interrupt causation from each queue */ - if (vsi->tx_rings) { - ice_for_each_txq(vsi, i) { - if (vsi->tx_rings[i]) { - u16 reg; + if (!vsi->netdev) + return; - reg = vsi->tx_rings[i]->reg_idx; - val = rd32(hw, QINT_TQCTL(reg)); - val &= ~QINT_TQCTL_CAUSE_ENA_M; - wr32(hw, QINT_TQCTL(reg), val); - } - } - } + if (current_work() == &pf->serv_task || + test_bit(ICE_PREPARED_FOR_RESET, pf->state) || + test_bit(ICE_DOWN, pf->state) || + test_bit(ICE_SUSPENDED, pf->state)) + __ice_queue_set_napi(vsi->netdev, queue_index, type, napi, + false); + else + __ice_queue_set_napi(vsi->netdev, queue_index, type, napi, + true); +} - if (vsi->rx_rings) { - ice_for_each_rxq(vsi, i) { - if (vsi->rx_rings[i]) { - u16 reg; +/** + * __ice_q_vector_set_napi_queues - Map queue[s] associated with the napi + * @q_vector: q_vector pointer + * @locked: is the rtnl_lock already held + * + * Associate the q_vector napi with all the queue[s] on the vector. + * Caller indicates the lock status. + */ +void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked) +{ + struct ice_rx_ring *rx_ring; + struct ice_tx_ring *tx_ring; - reg = vsi->rx_rings[i]->reg_idx; - val = rd32(hw, QINT_RQCTL(reg)); - val &= ~QINT_RQCTL_CAUSE_ENA_M; - wr32(hw, QINT_RQCTL(reg), val); - } - } - } + ice_for_each_rx_ring(rx_ring, q_vector->rx) + __ice_queue_set_napi(q_vector->vsi->netdev, rx_ring->q_index, + NETDEV_QUEUE_TYPE_RX, &q_vector->napi, + locked); - /* disable each interrupt */ - ice_for_each_q_vector(vsi, i) { - if (!vsi->q_vectors[i]) - continue; - wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0); - } + ice_for_each_tx_ring(tx_ring, q_vector->tx) + __ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index, + NETDEV_QUEUE_TYPE_TX, &q_vector->napi, + locked); + /* Also set the interrupt number for the NAPI */ + netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq); +} - ice_flush(hw); +/** + * ice_q_vector_set_napi_queues - Map queue[s] associated with the napi + * @q_vector: q_vector pointer + * + * Associate the q_vector napi with all the queue[s] on the vector + */ +void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector) +{ + struct ice_rx_ring *rx_ring; + struct ice_tx_ring *tx_ring; - /* don't call synchronize_irq() for VF's from the host */ - if (vsi->type == ICE_VSI_VF) + ice_for_each_rx_ring(rx_ring, q_vector->rx) + ice_queue_set_napi(q_vector->vsi, rx_ring->q_index, + NETDEV_QUEUE_TYPE_RX, &q_vector->napi); + + ice_for_each_tx_ring(tx_ring, q_vector->tx) + ice_queue_set_napi(q_vector->vsi, tx_ring->q_index, + NETDEV_QUEUE_TYPE_TX, &q_vector->napi); + /* Also set the interrupt number for the NAPI */ + netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq); +} + +/** + * ice_vsi_set_napi_queues + * @vsi: VSI pointer + * + * Associate queue[s] with napi for all vectors + */ +void ice_vsi_set_napi_queues(struct ice_vsi *vsi) +{ + int i; + + if (!vsi->netdev) return; ice_for_each_q_vector(vsi, i) - synchronize_irq(vsi->q_vectors[i]->irq.virq); + ice_q_vector_set_napi_queues(vsi->q_vectors[i]); } /** @@ -3071,27 +2962,26 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, } /** - * ice_vsi_realloc_stat_arrays - Frees unused stat structures + * ice_vsi_realloc_stat_arrays - Frees unused stat structures or alloc new ones * @vsi: VSI pointer - * @prev_txq: Number of Tx rings before ring reallocation - * @prev_rxq: Number of Rx rings before ring reallocation */ -static void -ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq) +static int +ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi) { + u16 req_txq = vsi->req_txq ? vsi->req_txq : vsi->alloc_txq; + u16 req_rxq = vsi->req_rxq ? vsi->req_rxq : vsi->alloc_rxq; + struct ice_ring_stats **tx_ring_stats; + struct ice_ring_stats **rx_ring_stats; struct ice_vsi_stats *vsi_stat; struct ice_pf *pf = vsi->back; + u16 prev_txq = vsi->alloc_txq; + u16 prev_rxq = vsi->alloc_rxq; int i; - if (!prev_txq || !prev_rxq) - return; - if (vsi->type == ICE_VSI_CHNL) - return; - vsi_stat = pf->vsi_stats[vsi->idx]; - if (vsi->num_txq < prev_txq) { - for (i = vsi->num_txq; i < prev_txq; i++) { + if (req_txq < prev_txq) { + for (i = req_txq; i < prev_txq; i++) { if (vsi_stat->tx_ring_stats[i]) { kfree_rcu(vsi_stat->tx_ring_stats[i], rcu); WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL); @@ -3099,14 +2989,36 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq) } } - if (vsi->num_rxq < prev_rxq) { - for (i = vsi->num_rxq; i < prev_rxq; i++) { + tx_ring_stats = vsi_stat->tx_ring_stats; + vsi_stat->tx_ring_stats = + krealloc_array(vsi_stat->tx_ring_stats, req_txq, + sizeof(*vsi_stat->tx_ring_stats), + GFP_KERNEL | __GFP_ZERO); + if (!vsi_stat->tx_ring_stats) { + vsi_stat->tx_ring_stats = tx_ring_stats; + return -ENOMEM; + } + + if (req_rxq < prev_rxq) { + for (i = req_rxq; i < prev_rxq; i++) { if (vsi_stat->rx_ring_stats[i]) { kfree_rcu(vsi_stat->rx_ring_stats[i], rcu); WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL); } } } + + rx_ring_stats = vsi_stat->rx_ring_stats; + vsi_stat->rx_ring_stats = + krealloc_array(vsi_stat->rx_ring_stats, req_rxq, + sizeof(*vsi_stat->rx_ring_stats), + GFP_KERNEL | __GFP_ZERO); + if (!vsi_stat->rx_ring_stats) { + vsi_stat->rx_ring_stats = rx_ring_stats; + return -ENOMEM; + } + + return 0; } /** @@ -3121,22 +3033,28 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq) */ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) { - struct ice_vsi_cfg_params params = {}; struct ice_coalesce_stored *coalesce; - int ret, prev_txq, prev_rxq; - int prev_num_q_vectors = 0; + int prev_num_q_vectors; struct ice_pf *pf; + int ret; if (!vsi) return -EINVAL; - params = ice_vsi_to_params(vsi); - params.flags = vsi_flags; - + vsi->flags = vsi_flags; pf = vsi->back; if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf)) return -EINVAL; + ret = ice_vsi_realloc_stat_arrays(vsi); + if (ret) + goto err_vsi_cfg; + + ice_vsi_decfg(vsi); + ret = ice_vsi_cfg_def(vsi); + if (ret) + goto err_vsi_cfg; + coalesce = kcalloc(vsi->num_q_vectors, sizeof(struct ice_coalesce_stored), GFP_KERNEL); if (!coalesce) @@ -3144,14 +3062,6 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce); - prev_txq = vsi->num_txq; - prev_rxq = vsi->num_rxq; - - ice_vsi_decfg(vsi); - ret = ice_vsi_cfg_def(vsi, ¶ms); - if (ret) - goto err_vsi_cfg; - ret = ice_vsi_cfg_tc_lan(pf, vsi); if (ret) { if (vsi_flags & ICE_VSI_FLAG_INIT) { @@ -3163,8 +3073,6 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) return ice_schedule_reset(pf, ICE_RESET_PFR); } - ice_vsi_realloc_stat_arrays(vsi, prev_txq, prev_rxq); - ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors); kfree(coalesce); @@ -3172,8 +3080,8 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) err_vsi_cfg_tc_lan: ice_vsi_decfg(vsi); -err_vsi_cfg: kfree(coalesce); +err_vsi_cfg: return ret; } @@ -3316,9 +3224,8 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt, vsi->tc_cfg.ena_tc = ena_tc ? ena_tc : 1; pow = order_base_2(tc0_qcount); - qmap = ((tc0_offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & - ICE_AQ_VSI_TC_Q_OFFSET_M) | - ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & ICE_AQ_VSI_TC_Q_NUM_M); + qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, tc0_offset); + qmap |= FIELD_PREP(ICE_AQ_VSI_TC_Q_NUM_M, pow); ice_for_each_traffic_class(i) { if (!(vsi->tc_cfg.ena_tc & BIT(i))) { diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index f24f5d1e6f9c..94ce8964dda6 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -11,57 +11,12 @@ #define ICE_VSI_FLAG_INIT BIT(0) #define ICE_VSI_FLAG_NO_INIT 0 -/** - * struct ice_vsi_cfg_params - VSI configuration parameters - * @pi: pointer to the port_info instance for the VSI - * @ch: pointer to the channel structure for the VSI, may be NULL - * @vf: pointer to the VF associated with this VSI, may be NULL - * @type: the type of VSI to configure - * @flags: VSI flags used for rebuild and configuration - * - * Parameter structure used when configuring a new VSI. - */ -struct ice_vsi_cfg_params { - struct ice_port_info *pi; - struct ice_channel *ch; - struct ice_vf *vf; - enum ice_vsi_type type; - u32 flags; -}; - -/** - * ice_vsi_to_params - Get parameters for an existing VSI - * @vsi: the VSI to get parameters for - * - * Fill a parameter structure for reconfiguring a VSI with its current - * parameters, such as during a rebuild operation. - */ -static inline struct ice_vsi_cfg_params ice_vsi_to_params(struct ice_vsi *vsi) -{ - struct ice_vsi_cfg_params params = {}; - - params.pi = vsi->port_info; - params.ch = vsi->ch; - params.vf = vsi->vf; - params.type = vsi->type; - - return params; -} - const char *ice_vsi_type_str(enum ice_vsi_type vsi_type); bool ice_pf_state_is_nominal(struct ice_pf *pf); void ice_update_eth_stats(struct ice_vsi *vsi); -int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx); - -int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, u16 q_idx); - -int ice_vsi_cfg_rxqs(struct ice_vsi *vsi); - -int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi); - void ice_vsi_cfg_msix(struct ice_vsi *vsi); int ice_vsi_start_all_rx_rings(struct ice_vsi *vsi); @@ -72,8 +27,6 @@ int ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, u16 rel_vmvf_num); -int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi); - int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi); void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); @@ -91,6 +44,16 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc); struct ice_vsi * ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params); +void +ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index, + enum netdev_queue_type type, struct napi_struct *napi); + +void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked); + +void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector); + +void ice_vsi_set_napi_queues(struct ice_vsi *vsi); + int ice_vsi_release(struct ice_vsi *vsi); void ice_vsi_close(struct ice_vsi *vsi); @@ -101,7 +64,7 @@ void ice_vsi_decfg(struct ice_vsi *vsi); void ice_dis_vsi(struct ice_vsi *vsi, bool locked); int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags); -int ice_vsi_cfg(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params); +int ice_vsi_cfg(struct ice_vsi *vsi); bool ice_is_reset_in_progress(unsigned long *state); int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout); @@ -110,8 +73,6 @@ void ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, bool ena_ts); -void ice_vsi_dis_irq(struct ice_vsi *vsi); - void ice_vsi_free_irq(struct ice_vsi *vsi); void ice_vsi_free_rx_rings(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 6607fa6fe556..f60c022f7960 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -13,7 +13,9 @@ #include "ice_fltr.h" #include "ice_dcb_lib.h" #include "ice_dcb_nl.h" -#include "ice_devlink.h" +#include "devlink/devlink.h" +#include "devlink/devlink_port.h" +#include "ice_hwmon.h" /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the * ice tracepoint functions. This must be done exactly once across the * ice driver. @@ -35,6 +37,7 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation."; MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); +MODULE_IMPORT_NS(LIBIE); MODULE_LICENSE("GPL v2"); MODULE_FIRMWARE(ICE_DDP_PKG_FILE); @@ -612,7 +615,7 @@ skip: ice_pf_dis_all_vsi(pf, false); if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) - ice_ptp_prepare_for_reset(pf); + ice_ptp_prepare_for_reset(pf, reset_type); if (ice_is_feature_supported(pf, ICE_F_GNSS)) ice_gnss_exit(pf); @@ -979,7 +982,7 @@ static void ice_set_dflt_mib(struct ice_pf *pf) * Octets 13 - 20 are TSA values - leave as zeros */ buf[5] = 0x64; - len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S; + len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); offset += len + 2; tlv = (struct ice_lldp_org_tlv *) ((char *)tlv + sizeof(tlv->typelen) + len); @@ -1013,7 +1016,7 @@ static void ice_set_dflt_mib(struct ice_pf *pf) /* Octet 1 left as all zeros - PFC disabled */ buf[0] = 0x08; - len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S; + len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); offset += len + 2; if (ice_aq_set_lldp_mib(hw, mib_type, (void *)lldpmib, offset, NULL)) @@ -1252,6 +1255,32 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event) } /** + * ice_get_fwlog_data - copy the FW log data from ARQ event + * @pf: PF that the FW log event is associated with + * @event: event structure containing FW log data + */ +static void +ice_get_fwlog_data(struct ice_pf *pf, struct ice_rq_event_info *event) +{ + struct ice_fwlog_data *fwlog; + struct ice_hw *hw = &pf->hw; + + fwlog = &hw->fwlog_ring.rings[hw->fwlog_ring.tail]; + + memset(fwlog->data, 0, PAGE_SIZE); + fwlog->data_size = le16_to_cpu(event->desc.datalen); + + memcpy(fwlog->data, event->msg_buf, fwlog->data_size); + ice_fwlog_ring_increment(&hw->fwlog_ring.tail, hw->fwlog_ring.size); + + if (ice_fwlog_ring_full(&hw->fwlog_ring)) { + /* the rings are full so bump the head to create room */ + ice_fwlog_ring_increment(&hw->fwlog_ring.head, + hw->fwlog_ring.size); + } +} + +/** * ice_aq_prep_for_event - Prepare to wait for an AdminQ event from firmware * @pf: pointer to the PF private structure * @task: intermediate helper storage and identifier for waiting @@ -1532,8 +1561,8 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) ice_vc_process_vf_msg(pf, &event, &data); break; - case ice_aqc_opc_fw_logging: - ice_output_fw_log(hw, &event.desc, event.msg_buf); + case ice_aqc_opc_fw_logs_event: + ice_get_fwlog_data(pf, &event); break; case ice_aqc_opc_lldp_set_mib_change: ice_dcb_process_lldp_set_mib_change(pf, &event); @@ -1622,8 +1651,10 @@ static void ice_clean_sbq_subtask(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; - /* Nothing to do here if sideband queue is not supported */ - if (!ice_is_sbq_supported(hw)) { + /* if mac_type is not generic, sideband is not supported + * and there's nothing to do here + */ + if (!ice_is_generic_mac(hw)) { clear_bit(ICE_SIDEBANDQ_EVENT_PENDING, pf->state); return; } @@ -1716,6 +1747,39 @@ static void ice_service_timer(struct timer_list *t) } /** + * ice_mdd_maybe_reset_vf - reset VF after MDD event + * @pf: pointer to the PF structure + * @vf: pointer to the VF structure + * @reset_vf_tx: whether Tx MDD has occurred + * @reset_vf_rx: whether Rx MDD has occurred + * + * Since the queue can get stuck on VF MDD events, the PF can be configured to + * automatically reset the VF by enabling the private ethtool flag + * mdd-auto-reset-vf. + */ +static void ice_mdd_maybe_reset_vf(struct ice_pf *pf, struct ice_vf *vf, + bool reset_vf_tx, bool reset_vf_rx) +{ + struct device *dev = ice_pf_to_dev(pf); + + if (!test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)) + return; + + /* VF MDD event counters will be cleared by reset, so print the event + * prior to reset. + */ + if (reset_vf_tx) + ice_print_vf_tx_mdd_event(vf); + + if (reset_vf_rx) + ice_print_vf_rx_mdd_event(vf); + + dev_info(dev, "PF-to-VF reset on PF %d VF %d due to MDD event\n", + pf->hw.pf_id, vf->vf_id); + ice_reset_vf(vf, ICE_VF_RESET_NOTIFY | ICE_VF_RESET_LOCK); +} + +/** * ice_handle_mdd_event - handle malicious driver detect event * @pf: pointer to the PF structure * @@ -1744,14 +1808,10 @@ static void ice_handle_mdd_event(struct ice_pf *pf) /* find what triggered an MDD event */ reg = rd32(hw, GL_MDET_TX_PQM); if (reg & GL_MDET_TX_PQM_VALID_M) { - u8 pf_num = (reg & GL_MDET_TX_PQM_PF_NUM_M) >> - GL_MDET_TX_PQM_PF_NUM_S; - u16 vf_num = (reg & GL_MDET_TX_PQM_VF_NUM_M) >> - GL_MDET_TX_PQM_VF_NUM_S; - u8 event = (reg & GL_MDET_TX_PQM_MAL_TYPE_M) >> - GL_MDET_TX_PQM_MAL_TYPE_S; - u16 queue = ((reg & GL_MDET_TX_PQM_QNUM_M) >> - GL_MDET_TX_PQM_QNUM_S); + u8 pf_num = FIELD_GET(GL_MDET_TX_PQM_PF_NUM_M, reg); + u16 vf_num = FIELD_GET(GL_MDET_TX_PQM_VF_NUM_M, reg); + u8 event = FIELD_GET(GL_MDET_TX_PQM_MAL_TYPE_M, reg); + u16 queue = FIELD_GET(GL_MDET_TX_PQM_QNUM_M, reg); if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", @@ -1761,14 +1821,10 @@ static void ice_handle_mdd_event(struct ice_pf *pf) reg = rd32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw)); if (reg & GL_MDET_TX_TCLAN_VALID_M) { - u8 pf_num = (reg & GL_MDET_TX_TCLAN_PF_NUM_M) >> - GL_MDET_TX_TCLAN_PF_NUM_S; - u16 vf_num = (reg & GL_MDET_TX_TCLAN_VF_NUM_M) >> - GL_MDET_TX_TCLAN_VF_NUM_S; - u8 event = (reg & GL_MDET_TX_TCLAN_MAL_TYPE_M) >> - GL_MDET_TX_TCLAN_MAL_TYPE_S; - u16 queue = ((reg & GL_MDET_TX_TCLAN_QNUM_M) >> - GL_MDET_TX_TCLAN_QNUM_S); + u8 pf_num = FIELD_GET(GL_MDET_TX_TCLAN_PF_NUM_M, reg); + u16 vf_num = FIELD_GET(GL_MDET_TX_TCLAN_VF_NUM_M, reg); + u8 event = FIELD_GET(GL_MDET_TX_TCLAN_MAL_TYPE_M, reg); + u16 queue = FIELD_GET(GL_MDET_TX_TCLAN_QNUM_M, reg); if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", @@ -1778,14 +1834,10 @@ static void ice_handle_mdd_event(struct ice_pf *pf) reg = rd32(hw, GL_MDET_RX); if (reg & GL_MDET_RX_VALID_M) { - u8 pf_num = (reg & GL_MDET_RX_PF_NUM_M) >> - GL_MDET_RX_PF_NUM_S; - u16 vf_num = (reg & GL_MDET_RX_VF_NUM_M) >> - GL_MDET_RX_VF_NUM_S; - u8 event = (reg & GL_MDET_RX_MAL_TYPE_M) >> - GL_MDET_RX_MAL_TYPE_S; - u16 queue = ((reg & GL_MDET_RX_QNUM_M) >> - GL_MDET_RX_QNUM_S); + u8 pf_num = FIELD_GET(GL_MDET_RX_PF_NUM_M, reg); + u16 vf_num = FIELD_GET(GL_MDET_RX_VF_NUM_M, reg); + u8 event = FIELD_GET(GL_MDET_RX_MAL_TYPE_M, reg); + u16 queue = FIELD_GET(GL_MDET_RX_QNUM_M, reg); if (netif_msg_rx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n", @@ -1820,6 +1872,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) */ mutex_lock(&pf->vfs.table_lock); ice_for_each_vf(pf, bkt, vf) { + bool reset_vf_tx = false, reset_vf_rx = false; + reg = rd32(hw, VP_MDET_TX_PQM(vf->vf_id)); if (reg & VP_MDET_TX_PQM_VALID_M) { wr32(hw, VP_MDET_TX_PQM(vf->vf_id), 0xFFFF); @@ -1828,6 +1882,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_PQM detected on VF %d\n", vf->vf_id); + + reset_vf_tx = true; } reg = rd32(hw, VP_MDET_TX_TCLAN(vf->vf_id)); @@ -1838,6 +1894,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_TCLAN detected on VF %d\n", vf->vf_id); + + reset_vf_tx = true; } reg = rd32(hw, VP_MDET_TX_TDPU(vf->vf_id)); @@ -1848,6 +1906,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_TDPU detected on VF %d\n", vf->vf_id); + + reset_vf_tx = true; } reg = rd32(hw, VP_MDET_RX(vf->vf_id)); @@ -1859,18 +1919,12 @@ static void ice_handle_mdd_event(struct ice_pf *pf) dev_info(dev, "Malicious Driver Detection event RX detected on VF %d\n", vf->vf_id); - /* Since the queue is disabled on VF Rx MDD events, the - * PF can be configured to reset the VF through ethtool - * private flag mdd-auto-reset-vf. - */ - if (test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)) { - /* VF MDD event counters will be cleared by - * reset, so print the event prior to reset. - */ - ice_print_vf_rx_mdd_event(vf); - ice_reset_vf(vf, ICE_VF_RESET_LOCK); - } + reset_vf_rx = true; } + + if (reset_vf_tx || reset_vf_rx) + ice_mdd_maybe_reset_vf(pf, vf, reset_vf_tx, + reset_vf_rx); } mutex_unlock(&pf->vfs.table_lock); @@ -2146,7 +2200,7 @@ static int ice_configure_phy(struct ice_vsi *vsi) /* Ensure we have media as we cannot configure a medialess port */ if (!(phy->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) - return -EPERM; + return -ENOMEDIUM; ice_print_topo_conflict(vsi); @@ -3031,6 +3085,7 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp) static void ice_ena_misc_vector(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; + u32 pf_intr_start_offset; u32 val; /* Disable anti-spoof detection interrupt to prevent spurious event @@ -3059,6 +3114,47 @@ static void ice_ena_misc_vector(struct ice_pf *pf) /* SW_ITR_IDX = 0, but don't change INTENA */ wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index), GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M); + + if (!pf->hw.dev_caps.ts_dev_info.ts_ll_int_read) + return; + pf_intr_start_offset = rd32(hw, PFINT_ALLOC) & PFINT_ALLOC_FIRST; + wr32(hw, GLINT_DYN_CTL(pf->ll_ts_irq.index + pf_intr_start_offset), + GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M); +} + +/** + * ice_ll_ts_intr - ll_ts interrupt handler + * @irq: interrupt number + * @data: pointer to a q_vector + */ +static irqreturn_t ice_ll_ts_intr(int __always_unused irq, void *data) +{ + struct ice_pf *pf = data; + u32 pf_intr_start_offset; + struct ice_ptp_tx *tx; + unsigned long flags; + struct ice_hw *hw; + u32 val; + u8 idx; + + hw = &pf->hw; + tx = &pf->ptp.port.tx; + spin_lock_irqsave(&tx->lock, flags); + ice_ptp_complete_tx_single_tstamp(tx); + + 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); + + val = GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M | + (ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); + pf_intr_start_offset = rd32(hw, PFINT_ALLOC) & PFINT_ALLOC_FIRST; + wr32(hw, GLINT_DYN_CTL(pf->ll_ts_irq.index + pf_intr_start_offset), + val); + + return IRQ_HANDLED; } /** @@ -3069,6 +3165,7 @@ static void ice_ena_misc_vector(struct ice_pf *pf) static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) { struct ice_pf *pf = (struct ice_pf *)data; + irqreturn_t ret = IRQ_HANDLED; struct ice_hw *hw = &pf->hw; struct device *dev; u32 oicr, ena_mask; @@ -3108,8 +3205,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) /* we have a reset warning */ ena_mask &= ~PFINT_OICR_GRST_M; - reset = (rd32(hw, GLGEN_RSTAT) & GLGEN_RSTAT_RESET_TYPE_M) >> - GLGEN_RSTAT_RESET_TYPE_S; + reset = FIELD_GET(GLGEN_RSTAT_RESET_TYPE_M, + rd32(hw, GLGEN_RSTAT)); if (reset == ICE_RESET_CORER) pf->corer_count++; @@ -3150,8 +3247,22 @@ 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 (!hw->reset_ongoing && ice_ptp_pf_handles_tx_interrupt(pf)) + 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; + } } if (oicr & PFINT_OICR_TSYN_EVNT_M) { @@ -3167,7 +3278,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) GLTSYN_STAT_EVENT1_M | GLTSYN_STAT_EVENT2_M); - set_bit(ICE_MISC_THREAD_EXTTS_EVENT, pf->misc_thread); + ice_ptp_extts_event(pf); } } @@ -3190,8 +3301,11 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) set_bit(ICE_PFR_REQ, pf->state); } } + ice_service_task_schedule(pf); + if (ret == IRQ_HANDLED) + ice_irq_dynamic_ena(hw, NULL, NULL); - return IRQ_WAKE_THREAD; + return ret; } /** @@ -3207,12 +3321,7 @@ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data) hw = &pf->hw; if (ice_is_reset_in_progress(pf->state)) - return IRQ_HANDLED; - - ice_service_task_schedule(pf); - - if (test_and_clear_bit(ICE_MISC_THREAD_EXTTS_EVENT, pf->misc_thread)) - ice_ptp_extts_event(pf); + goto skip_irq; if (test_and_clear_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread)) { /* Process outstanding Tx timestamps. If there is more work, @@ -3224,6 +3333,7 @@ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data) } } +skip_irq: ice_irq_dynamic_ena(hw, NULL, NULL); return IRQ_HANDLED; @@ -3254,6 +3364,20 @@ static void ice_dis_ctrlq_interrupts(struct ice_hw *hw) } /** + * ice_free_irq_msix_ll_ts- Unroll ll_ts vector setup + * @pf: board private structure + */ +static void ice_free_irq_msix_ll_ts(struct ice_pf *pf) +{ + int irq_num = pf->ll_ts_irq.virq; + + synchronize_irq(irq_num); + devm_free_irq(ice_pf_to_dev(pf), irq_num, pf); + + ice_free_irq(pf, pf->ll_ts_irq); +} + +/** * ice_free_irq_msix_misc - Unroll misc vector setup * @pf: board private structure */ @@ -3272,6 +3396,8 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf) devm_free_irq(ice_pf_to_dev(pf), misc_irq_num, pf); ice_free_irq(pf, pf->oicr_irq); + if (pf->hw.dev_caps.ts_dev_info.ts_ll_int_read) + ice_free_irq_msix_ll_ts(pf); } /** @@ -3297,10 +3423,12 @@ static void ice_ena_ctrlq_interrupts(struct ice_hw *hw, u16 reg_idx) PFINT_MBX_CTL_CAUSE_ENA_M); wr32(hw, PFINT_MBX_CTL, val); - /* This enables Sideband queue Interrupt causes */ - val = ((reg_idx & PFINT_SB_CTL_MSIX_INDX_M) | - PFINT_SB_CTL_CAUSE_ENA_M); - wr32(hw, PFINT_SB_CTL, val); + if (!hw->dev_caps.ts_dev_info.ts_ll_int_read) { + /* enable Sideband queue Interrupt causes */ + val = ((reg_idx & PFINT_SB_CTL_MSIX_INDX_M) | + PFINT_SB_CTL_CAUSE_ENA_M); + wr32(hw, PFINT_SB_CTL, val); + } ice_flush(hw); } @@ -3317,13 +3445,17 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - struct msi_map oicr_irq; + u32 pf_intr_start_offset; + struct msi_map irq; int err = 0; if (!pf->int_name[0]) snprintf(pf->int_name, sizeof(pf->int_name) - 1, "%s-%s:misc", dev_driver_string(dev), dev_name(dev)); + if (!pf->int_name_ll_ts[0]) + snprintf(pf->int_name_ll_ts, sizeof(pf->int_name_ll_ts) - 1, + "%s-%s:ll_ts", dev_driver_string(dev), dev_name(dev)); /* Do not request IRQ but do enable OICR interrupt since settings are * lost during reset. Note that this function is called only during * rebuild path and not while reset is in progress. @@ -3332,11 +3464,11 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf) goto skip_req_irq; /* reserve one vector in irq_tracker for misc interrupts */ - oicr_irq = ice_alloc_irq(pf, false); - if (oicr_irq.index < 0) - return oicr_irq.index; + irq = ice_alloc_irq(pf, false); + if (irq.index < 0) + return irq.index; - pf->oicr_irq = oicr_irq; + pf->oicr_irq = irq; err = devm_request_threaded_irq(dev, pf->oicr_irq.virq, ice_misc_intr, ice_misc_intr_thread_fn, 0, pf->int_name, pf); @@ -3347,10 +3479,34 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf) return err; } + /* reserve one vector in irq_tracker for ll_ts interrupt */ + if (!pf->hw.dev_caps.ts_dev_info.ts_ll_int_read) + goto skip_req_irq; + + irq = ice_alloc_irq(pf, false); + if (irq.index < 0) + return irq.index; + + pf->ll_ts_irq = irq; + err = devm_request_irq(dev, pf->ll_ts_irq.virq, ice_ll_ts_intr, 0, + pf->int_name_ll_ts, pf); + if (err) { + dev_err(dev, "devm_request_irq for %s failed: %d\n", + pf->int_name_ll_ts, err); + ice_free_irq(pf, pf->ll_ts_irq); + return err; + } + skip_req_irq: ice_ena_misc_vector(pf); ice_ena_ctrlq_interrupts(hw, pf->oicr_irq.index); + /* This enables LL TS interrupt */ + pf_intr_start_offset = rd32(hw, PFINT_ALLOC) & PFINT_ALLOC_FIRST; + if (pf->hw.dev_caps.ts_dev_info.ts_ll_int_read) + wr32(hw, PFINT_SB_CTL, + ((pf->ll_ts_irq.index + pf_intr_start_offset) & + PFINT_SB_CTL_MSIX_INDX_M) | PFINT_SB_CTL_CAUSE_ENA_M); wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_irq.index), ITR_REG_ALIGN(ICE_ITR_8K) >> ICE_ITR_GRAN_S); @@ -3375,9 +3531,11 @@ static void ice_napi_add(struct ice_vsi *vsi) if (!vsi->netdev) return; - ice_for_each_q_vector(vsi, v_idx) + ice_for_each_q_vector(vsi, v_idx) { netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi, ice_napi_poll); + __ice_q_vector_set_napi_queues(vsi->q_vectors[v_idx], false); + } } /** @@ -3397,6 +3555,7 @@ static void ice_set_ops(struct ice_vsi *vsi) netdev->netdev_ops = &ice_netdev_ops; netdev->udp_tunnel_nic_info = &pf->hw.udp_tunnel_nic; + netdev->xdp_metadata_ops = &ice_xdp_md_ops; ice_set_ethtool_ops(netdev); if (vsi->type != ICE_VSI_PF) @@ -3526,7 +3685,7 @@ ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) struct ice_vsi_cfg_params params = {}; params.type = ICE_VSI_PF; - params.pi = pi; + params.port_info = pi; params.flags = ICE_VSI_FLAG_INIT; return ice_vsi_setup(pf, ¶ms); @@ -3539,7 +3698,7 @@ ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, struct ice_vsi_cfg_params params = {}; params.type = ICE_VSI_CHNL; - params.pi = pi; + params.port_info = pi; params.ch = ch; params.flags = ICE_VSI_FLAG_INIT; @@ -3560,7 +3719,7 @@ ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) struct ice_vsi_cfg_params params = {}; params.type = ICE_VSI_CTRL; - params.pi = pi; + params.port_info = pi; params.flags = ICE_VSI_FLAG_INIT; return ice_vsi_setup(pf, ¶ms); @@ -3580,7 +3739,7 @@ ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) struct ice_vsi_cfg_params params = {}; params.type = ICE_VSI_LB; - params.pi = pi; + params.port_info = pi; params.flags = ICE_VSI_FLAG_INIT; return ice_vsi_setup(pf, ¶ms); @@ -4295,11 +4454,13 @@ static char *ice_get_opt_fw_name(struct ice_pf *pf) /** * ice_request_fw - Device initialization routine * @pf: pointer to the PF instance + * @firmware: double pointer to firmware struct + * + * Return: zero when successful, negative values otherwise. */ -static void ice_request_fw(struct ice_pf *pf) +static int ice_request_fw(struct ice_pf *pf, const struct firmware **firmware) { char *opt_fw_filename = ice_get_opt_fw_name(pf); - const struct firmware *firmware = NULL; struct device *dev = ice_pf_to_dev(pf); int err = 0; @@ -4308,29 +4469,95 @@ static void ice_request_fw(struct ice_pf *pf) * and warning messages for other errors. */ if (opt_fw_filename) { - err = firmware_request_nowarn(&firmware, opt_fw_filename, dev); - if (err) { - kfree(opt_fw_filename); - goto dflt_pkg_load; - } - - /* request for firmware was successful. Download to device */ - ice_load_pkg(firmware, pf); + err = firmware_request_nowarn(firmware, opt_fw_filename, dev); kfree(opt_fw_filename); - release_firmware(firmware); - return; + if (!err) + return err; + } + err = request_firmware(firmware, ICE_DDP_PKG_FILE, dev); + if (err) + dev_err(dev, "The DDP package file was not found or could not be read. Entering Safe Mode\n"); + + return err; +} + +/** + * ice_init_tx_topology - performs Tx topology initialization + * @hw: pointer to the hardware structure + * @firmware: pointer to firmware structure + * + * Return: zero when init was successful, negative values otherwise. + */ +static int +ice_init_tx_topology(struct ice_hw *hw, const struct firmware *firmware) +{ + u8 num_tx_sched_layers = hw->num_tx_sched_layers; + struct ice_pf *pf = hw->back; + struct device *dev; + u8 *buf_copy; + int err; + + dev = ice_pf_to_dev(pf); + /* ice_cfg_tx_topo buf argument is not a constant, + * so we have to make a copy + */ + buf_copy = kmemdup(firmware->data, firmware->size, GFP_KERNEL); + + err = ice_cfg_tx_topo(hw, buf_copy, firmware->size); + if (!err) { + if (hw->num_tx_sched_layers > num_tx_sched_layers) + dev_info(dev, "Tx scheduling layers switching feature disabled\n"); + else + dev_info(dev, "Tx scheduling layers switching feature enabled\n"); + /* if there was a change in topology ice_cfg_tx_topo triggered + * a CORER and we need to re-init hw + */ + ice_deinit_hw(hw); + err = ice_init_hw(hw); + + return err; + } else if (err == -EIO) { + dev_info(dev, "DDP package does not support Tx scheduling layers switching feature - please update to the latest DDP package and try again\n"); } -dflt_pkg_load: - err = request_firmware(&firmware, ICE_DDP_PKG_FILE, dev); + return 0; +} + +/** + * ice_init_ddp_config - DDP related configuration + * @hw: pointer to the hardware structure + * @pf: pointer to pf structure + * + * This function loads DDP file from the disk, then initializes Tx + * topology. At the end DDP package is loaded on the card. + * + * Return: zero when init was successful, negative values otherwise. + */ +static int ice_init_ddp_config(struct ice_hw *hw, struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + const struct firmware *firmware = NULL; + int err; + + err = ice_request_fw(pf, &firmware); if (err) { - dev_err(dev, "The DDP package file was not found or could not be read. Entering Safe Mode\n"); - return; + dev_err(dev, "Fail during requesting FW: %d\n", err); + return err; } - /* request for firmware was successful. Download to device */ + err = ice_init_tx_topology(hw, firmware); + if (err) { + dev_err(dev, "Fail during initialization of Tx topology: %d\n", + err); + release_firmware(firmware); + return err; + } + + /* Download firmware to device */ ice_load_pkg(firmware, pf); release_firmware(firmware); + + return 0; } /** @@ -4361,6 +4588,19 @@ static void ice_print_wake_reason(struct ice_pf *pf) } /** + * ice_pf_fwlog_update_module - update 1 module + * @pf: pointer to the PF struct + * @log_level: log_level to use for the @module + * @module: module to update + */ +void ice_pf_fwlog_update_module(struct ice_pf *pf, int log_level, int module) +{ + struct ice_hw *hw = &pf->hw; + + hw->fwlog_cfg.module_entries[module].log_level = log_level; +} + +/** * ice_register_netdev - register netdev * @vsi: pointer to the VSI struct */ @@ -4439,90 +4679,6 @@ static void ice_decfg_netdev(struct ice_vsi *vsi) vsi->netdev = NULL; } -static int ice_start_eth(struct ice_vsi *vsi) -{ - int err; - - err = ice_init_mac_fltr(vsi->back); - if (err) - return err; - - err = ice_vsi_open(vsi); - if (err) - ice_fltr_remove_all(vsi); - - return err; -} - -static void ice_stop_eth(struct ice_vsi *vsi) -{ - ice_fltr_remove_all(vsi); - ice_vsi_close(vsi); -} - -static int ice_init_eth(struct ice_pf *pf) -{ - struct ice_vsi *vsi = ice_get_main_vsi(pf); - int err; - - if (!vsi) - return -EINVAL; - - /* init channel list */ - INIT_LIST_HEAD(&vsi->ch_list); - - err = ice_cfg_netdev(vsi); - if (err) - return err; - /* Setup DCB netlink interface */ - ice_dcbnl_setup(vsi); - - err = ice_init_mac_fltr(pf); - if (err) - goto err_init_mac_fltr; - - err = ice_devlink_create_pf_port(pf); - if (err) - goto err_devlink_create_pf_port; - - SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port); - - err = ice_register_netdev(vsi); - if (err) - goto err_register_netdev; - - err = ice_tc_indir_block_register(vsi); - if (err) - goto err_tc_indir_block_register; - - ice_napi_add(vsi); - - return 0; - -err_tc_indir_block_register: - ice_unregister_netdev(vsi); -err_register_netdev: - ice_devlink_destroy_pf_port(pf); -err_devlink_create_pf_port: -err_init_mac_fltr: - ice_decfg_netdev(vsi); - return err; -} - -static void ice_deinit_eth(struct ice_pf *pf) -{ - struct ice_vsi *vsi = ice_get_main_vsi(pf); - - if (!vsi) - return; - - ice_vsi_close(vsi); - ice_unregister_netdev(vsi); - ice_devlink_destroy_pf_port(pf); - ice_tc_indir_block_unregister(vsi); - ice_decfg_netdev(vsi); -} - /** * ice_wait_for_fw - wait for full FW readiness * @hw: pointer to the hardware structure @@ -4548,7 +4704,7 @@ static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout) return -ETIMEDOUT; } -static int ice_init_dev(struct ice_pf *pf) +int ice_init_dev(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; @@ -4574,9 +4730,11 @@ static int ice_init_dev(struct ice_pf *pf) ice_init_feature_support(pf); - ice_request_fw(pf); + err = ice_init_ddp_config(hw, pf); + if (err) + return err; - /* if ice_request_fw fails, ICE_FLAG_ADV_FEATURES bit won't be + /* if ice_init_ddp_config fails, ICE_FLAG_ADV_FEATURES bit won't be * set in pf->state, which will cause ice_is_safe_mode to return * true */ @@ -4641,7 +4799,7 @@ err_init_pf: return err; } -static void ice_deinit_dev(struct ice_pf *pf) +void ice_deinit_dev(struct ice_pf *pf) { ice_free_irq_msix_misc(pf); ice_deinit_pf(pf); @@ -4685,6 +4843,8 @@ static void ice_init_features(struct ice_pf *pf) if (ice_init_lag(pf)) dev_warn(dev, "Failed to init link aggregation support\n"); + + ice_hwmon_init(pf); } static void ice_deinit_features(struct ice_pf *pf) @@ -4702,6 +4862,8 @@ static void ice_deinit_features(struct ice_pf *pf) ice_ptp_release(pf); if (test_bit(ICE_FLAG_DPLL, pf->flags)) ice_dpll_deinit(pf); + if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) + xa_destroy(&pf->eswitch.reprs); } static void ice_init_wakeup(struct ice_pf *pf) @@ -4942,31 +5104,47 @@ static void ice_deinit(struct ice_pf *pf) /** * ice_load - load pf by init hw and starting VSI * @pf: pointer to the pf instance + * + * This function has to be called under devl_lock. */ int ice_load(struct ice_pf *pf) { - struct ice_vsi_cfg_params params = {}; struct ice_vsi *vsi; int err; - err = ice_init_dev(pf); + devl_assert_locked(priv_to_devlink(pf)); + + vsi = ice_get_main_vsi(pf); + + /* init channel list */ + INIT_LIST_HEAD(&vsi->ch_list); + + err = ice_cfg_netdev(vsi); if (err) return err; - vsi = ice_get_main_vsi(pf); + /* Setup DCB netlink interface */ + ice_dcbnl_setup(vsi); - params = ice_vsi_to_params(vsi); - params.flags = ICE_VSI_FLAG_INIT; + err = ice_init_mac_fltr(pf); + if (err) + goto err_init_mac_fltr; - rtnl_lock(); - err = ice_vsi_cfg(vsi, ¶ms); + err = ice_devlink_create_pf_port(pf); if (err) - goto err_vsi_cfg; + goto err_devlink_create_pf_port; + + SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port); - err = ice_start_eth(ice_get_main_vsi(pf)); + err = ice_register_netdev(vsi); if (err) - goto err_start_eth; - rtnl_unlock(); + goto err_register_netdev; + + err = ice_tc_indir_block_register(vsi); + if (err) + goto err_tc_indir_block_register; + + ice_napi_add(vsi); err = ice_init_rdma(pf); if (err) @@ -4980,29 +5158,35 @@ int ice_load(struct ice_pf *pf) return 0; err_init_rdma: - ice_vsi_close(ice_get_main_vsi(pf)); - rtnl_lock(); -err_start_eth: - ice_vsi_decfg(ice_get_main_vsi(pf)); -err_vsi_cfg: - rtnl_unlock(); - ice_deinit_dev(pf); + ice_tc_indir_block_unregister(vsi); +err_tc_indir_block_register: + ice_unregister_netdev(vsi); +err_register_netdev: + ice_devlink_destroy_pf_port(pf); +err_devlink_create_pf_port: +err_init_mac_fltr: + ice_decfg_netdev(vsi); return err; } /** * ice_unload - unload pf by stopping VSI and deinit hw * @pf: pointer to the pf instance + * + * This function has to be called under devl_lock. */ void ice_unload(struct ice_pf *pf) { + struct ice_vsi *vsi = ice_get_main_vsi(pf); + + devl_assert_locked(priv_to_devlink(pf)); + ice_deinit_features(pf); ice_deinit_rdma(pf); - rtnl_lock(); - ice_stop_eth(ice_get_main_vsi(pf)); - ice_vsi_decfg(ice_get_main_vsi(pf)); - rtnl_unlock(); - ice_deinit_dev(pf); + ice_tc_indir_block_unregister(vsi); + ice_unregister_netdev(vsi); + ice_devlink_destroy_pf_port(pf); + ice_decfg_netdev(vsi); } /** @@ -5016,6 +5200,7 @@ static int ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) { struct device *dev = &pdev->dev; + struct ice_adapter *adapter; struct ice_pf *pf; struct ice_hw *hw; int err; @@ -5068,7 +5253,12 @@ 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 */ @@ -5100,29 +5290,25 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) if (err) goto err_init; - err = ice_init_eth(pf); + devl_lock(priv_to_devlink(pf)); + err = ice_load(pf); if (err) - goto err_init_eth; - - err = ice_init_rdma(pf); - if (err) - goto err_init_rdma; + goto err_load; err = ice_init_devlink(pf); if (err) goto err_init_devlink; - - ice_init_features(pf); + devl_unlock(priv_to_devlink(pf)); return 0; err_init_devlink: - ice_deinit_rdma(pf); -err_init_rdma: - ice_deinit_eth(pf); -err_init_eth: + ice_unload(pf); +err_load: + devl_unlock(priv_to_devlink(pf)); ice_deinit(pf); err_init: + ice_adapter_put(pdev); pci_disable_device(pdev); return err; } @@ -5208,23 +5394,28 @@ static void ice_remove(struct pci_dev *pdev) ice_free_vfs(pf); } + ice_hwmon_exit(pf); + ice_service_task_stop(pf); ice_aq_cancel_waiting_tasks(pf); set_bit(ICE_DOWN, pf->state); if (!ice_is_safe_mode(pf)) ice_remove_arfs(pf); - ice_deinit_features(pf); + + devl_lock(priv_to_devlink(pf)); ice_deinit_devlink(pf); - ice_deinit_rdma(pf); - ice_deinit_eth(pf); - ice_deinit(pf); + ice_unload(pf); + devl_unlock(priv_to_devlink(pf)); + + ice_deinit(pf); ice_vsi_release_all(pf); ice_setup_mc_magic_wake(pf); ice_set_wake(pf); + ice_adapter_put(pdev); pci_disable_device(pdev); } @@ -5244,7 +5435,6 @@ static void ice_shutdown(struct pci_dev *pdev) } } -#ifdef CONFIG_PM /** * ice_prepare_for_shutdown - prep for PCI shutdown * @pf: board private structure @@ -5306,6 +5496,7 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf) if (ret) goto err_reinit; ice_vsi_map_rings_to_vectors(pf->vsi[v]); + ice_vsi_set_napi_queues(pf->vsi[v]); } ret = ice_req_irq_msix_misc(pf); @@ -5332,7 +5523,7 @@ err_reinit: * Power Management callback to quiesce the device and prepare * for D3 transition. */ -static int __maybe_unused ice_suspend(struct device *dev) +static int ice_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct ice_pf *pf; @@ -5399,7 +5590,7 @@ static int __maybe_unused ice_suspend(struct device *dev) * ice_resume - PM callback for waking up from D3 * @dev: generic device information structure */ -static int __maybe_unused ice_resume(struct device *dev) +static int ice_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); enum ice_reset_req reset_type; @@ -5450,7 +5641,6 @@ static int __maybe_unused ice_resume(struct device *dev) return 0; } -#endif /* CONFIG_PM */ /** * ice_pci_err_detected - warning that PCI error has been detected @@ -5611,16 +5801,26 @@ static const struct pci_device_id ice_pci_tbl[] = { { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_1GBE) }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_QSFP) }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822_SI_DFLT) }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_BACKPLANE) }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_QSFP56) }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_SFP) }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_SFP_DD) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_BACKPLANE), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_QSFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_SFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_SGMII), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_QSFP56) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_SFP_DD) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_BACKPLANE), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_BACKPLANE), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_QSFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_QSFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_SFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_SFP), }, /* required last entry */ {} }; MODULE_DEVICE_TABLE(pci, ice_pci_tbl); -static __maybe_unused SIMPLE_DEV_PM_OPS(ice_pm_ops, ice_suspend, ice_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(ice_pm_ops, ice_suspend, ice_resume); static const struct pci_error_handlers ice_pci_err_handler = { .error_detected = ice_pci_err_detected, @@ -5635,9 +5835,7 @@ static struct pci_driver ice_driver = { .id_table = ice_pci_tbl, .probe = ice_probe, .remove = ice_remove, -#ifdef CONFIG_PM - .driver.pm = &ice_pm_ops, -#endif /* CONFIG_PM */ + .driver.pm = pm_sleep_ptr(&ice_pm_ops), .shutdown = ice_shutdown, .sriov_configure = ice_sriov_configure, .sriov_get_vf_total_msix = ice_sriov_get_vf_total_msix, @@ -5672,6 +5870,8 @@ static int __init ice_module_init(void) goto err_dest_wq; } + ice_debugfs_init(); + status = pci_register_driver(&ice_driver); if (status) { pr_err("failed to register PCI driver, err %d\n", status); @@ -5682,6 +5882,7 @@ static int __init ice_module_init(void) err_dest_lag_wq: destroy_workqueue(ice_lag_wq); + ice_debugfs_exit(); err_dest_wq: destroy_workqueue(ice_wq); return status; @@ -5697,6 +5898,7 @@ module_init(ice_module_init); static void __exit ice_module_exit(void) { pci_unregister_driver(&ice_driver); + ice_debugfs_exit(); destroy_workqueue(ice_wq); destroy_workqueue(ice_lag_wq); pr_info("module unloaded\n"); @@ -6041,6 +6243,23 @@ ice_fix_features(struct net_device *netdev, netdev_features_t features) } /** + * ice_set_rx_rings_vlan_proto - update rings with new stripped VLAN proto + * @vsi: PF's VSI + * @vlan_ethertype: VLAN ethertype (802.1Q or 802.1ad) in network byte order + * + * Store current stripped VLAN proto in ring packet context, + * so it can be accessed more efficiently by packet processing code. + */ +static void +ice_set_rx_rings_vlan_proto(struct ice_vsi *vsi, __be16 vlan_ethertype) +{ + u16 i; + + ice_for_each_alloc_rxq(vsi, i) + vsi->rx_rings[i]->pkt_ctx.vlan_proto = vlan_ethertype; +} + +/** * ice_set_vlan_offload_features - set VLAN offload features for the PF VSI * @vsi: PF's VSI * @features: features used to determine VLAN offload settings @@ -6082,6 +6301,9 @@ ice_set_vlan_offload_features(struct ice_vsi *vsi, netdev_features_t features) if (strip_err || insert_err) return -EIO; + ice_set_rx_rings_vlan_proto(vsi, enable_stripping ? + htons(vlan_ethertype) : 0); + return 0; } @@ -6572,6 +6794,7 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) { struct rtnl_link_stats64 *net_stats, *stats_prev; struct rtnl_link_stats64 *vsi_stats; + struct ice_pf *pf = vsi->back; u64 pkts, bytes; int i; @@ -6617,21 +6840,18 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) net_stats = &vsi->net_stats; stats_prev = &vsi->net_stats_prev; - /* clear prev counters after reset */ - if (vsi_stats->tx_packets < stats_prev->tx_packets || - vsi_stats->rx_packets < stats_prev->rx_packets) { - stats_prev->tx_packets = 0; - stats_prev->tx_bytes = 0; - stats_prev->rx_packets = 0; - stats_prev->rx_bytes = 0; + /* Update netdev counters, but keep in mind that values could start at + * random value after PF reset. And as we increase the reported stat by + * diff of Prev-Cur, we need to be sure that Prev is valid. If it's not, + * let's skip this round. + */ + if (likely(pf->stat_prev_loaded)) { + net_stats->tx_packets += vsi_stats->tx_packets - stats_prev->tx_packets; + net_stats->tx_bytes += vsi_stats->tx_bytes - stats_prev->tx_bytes; + net_stats->rx_packets += vsi_stats->rx_packets - stats_prev->rx_packets; + net_stats->rx_bytes += vsi_stats->rx_bytes - stats_prev->rx_bytes; } - /* update netdev counters */ - net_stats->tx_packets += vsi_stats->tx_packets - stats_prev->tx_packets; - net_stats->tx_bytes += vsi_stats->tx_bytes - stats_prev->tx_bytes; - net_stats->rx_packets += vsi_stats->rx_packets - stats_prev->rx_packets; - net_stats->rx_bytes += vsi_stats->rx_bytes - stats_prev->rx_bytes; - stats_prev->tx_packets = vsi_stats->tx_packets; stats_prev->tx_bytes = vsi_stats->tx_bytes; stats_prev->rx_packets = vsi_stats->rx_packets; @@ -6670,13 +6890,11 @@ void ice_update_vsi_stats(struct ice_vsi *vsi) cur_ns->rx_crc_errors = pf->stats.crc_errors; cur_ns->rx_errors = pf->stats.crc_errors + pf->stats.illegal_bytes + - pf->stats.rx_len_errors + pf->stats.rx_undersize + pf->hw_csum_rx_error + pf->stats.rx_jabber + pf->stats.rx_fragments + pf->stats.rx_oversize; - cur_ns->rx_length_errors = pf->stats.rx_len_errors; /* record drops from the port level */ cur_ns->rx_missed_errors = pf->stats.eth.rx_discards; } @@ -6816,9 +7034,6 @@ void ice_update_pf_stats(struct ice_pf *pf) &prev_ps->mac_remote_faults, &cur_ps->mac_remote_faults); - ice_stat_update32(hw, GLPRT_RLEC(port), pf->stat_prev_loaded, - &prev_ps->rx_len_errors, &cur_ps->rx_len_errors); - ice_stat_update32(hw, GLPRT_RUC(port), pf->stat_prev_loaded, &prev_ps->rx_undersize, &cur_ps->rx_undersize); @@ -6901,6 +7116,50 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) } /** + * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI + * @vsi: the VSI being un-configured + */ +static void ice_vsi_dis_irq(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + u32 val; + int i; + + /* disable interrupt causation from each Rx queue; Tx queues are + * handled in ice_vsi_stop_tx_ring() + */ + if (vsi->rx_rings) { + ice_for_each_rxq(vsi, i) { + if (vsi->rx_rings[i]) { + u16 reg; + + reg = vsi->rx_rings[i]->reg_idx; + val = rd32(hw, QINT_RQCTL(reg)); + val &= ~QINT_RQCTL_CAUSE_ENA_M; + wr32(hw, QINT_RQCTL(reg), val); + } + } + } + + /* disable each interrupt */ + ice_for_each_q_vector(vsi, i) { + if (!vsi->q_vectors[i]) + continue; + wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0); + } + + ice_flush(hw); + + /* don't call synchronize_irq() for VF's from the host */ + if (vsi->type == ICE_VSI_VF) + return; + + ice_for_each_q_vector(vsi, i) + synchronize_irq(vsi->q_vectors[i]->irq.virq); +} + +/** * ice_down - Shutdown the connection * @vsi: The VSI being stopped * @@ -6912,13 +7171,11 @@ int ice_down(struct ice_vsi *vsi) WARN_ON(!test_bit(ICE_VSI_DOWN, vsi->state)); - if (vsi->netdev && vsi->type == ICE_VSI_PF) { + if (vsi->netdev) { vlan_err = ice_vsi_del_vlan_zero(vsi); ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false); netif_carrier_off(vsi->netdev); netif_tx_disable(vsi->netdev); - } else if (vsi->type == ICE_VSI_SWITCHDEV_CTRL) { - ice_eswitch_stop_all_tx_queues(vsi->back); } ice_vsi_dis_irq(vsi); @@ -7389,7 +7646,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) * fail. */ if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) - ice_ptp_reset(pf); + ice_ptp_rebuild(pf, reset_type); if (ice_is_feature_supported(pf, ICE_F_GNSS)) ice_gnss_init(pf); @@ -7401,20 +7658,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) goto err_vsi_rebuild; } - /* configure PTP timestamping after VSI rebuild */ - if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) { - if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_SELF) - ice_ptp_cfg_timestamp(pf, false); - else if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_ALL) - /* for E82x PHC owner always need to have interrupts */ - ice_ptp_cfg_timestamp(pf, true); - } - - err = ice_vsi_rebuild_by_type(pf, ICE_VSI_SWITCHDEV_CTRL); - if (err) { - dev_err(dev, "Switchdev CTRL VSI rebuild failed: %d\n", err); - goto err_vsi_rebuild; - } + ice_eswitch_rebuild(pf); if (reset_type == ICE_RESET_PFR) { err = ice_rebuild_channels(pf); @@ -7461,6 +7705,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ice_plug_aux_dev(pf); if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) ice_lag_rebuild(pf); + + /* Restore timestamp mode settings after VSI rebuild */ + ice_ptp_restore_timestamp_mode(pf); return; err_vsi_rebuild: @@ -7529,7 +7776,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) return -EBUSY; } - netdev->mtu = (unsigned int)new_mtu; + WRITE_ONCE(netdev->mtu, (unsigned int)new_mtu); err = ice_down_up(vsi); if (err) return err; @@ -7710,6 +7957,59 @@ int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed) } /** + * ice_set_rss_hfunc - Set RSS HASH function + * @vsi: Pointer to VSI structure + * @hfunc: hash function (ICE_AQ_VSI_Q_OPT_RSS_*) + * + * Returns 0 on success, negative on failure + */ +int ice_set_rss_hfunc(struct ice_vsi *vsi, u8 hfunc) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctx; + bool symm; + int err; + + if (hfunc == vsi->rss_hfunc) + return 0; + + if (hfunc != ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ && + hfunc != ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ) + return -EOPNOTSUPP; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID); + ctx->info.q_opt_rss = vsi->info.q_opt_rss; + ctx->info.q_opt_rss &= ~ICE_AQ_VSI_Q_OPT_RSS_HASH_M; + ctx->info.q_opt_rss |= + FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hfunc); + ctx->info.q_opt_tc = vsi->info.q_opt_tc; + ctx->info.q_opt_flags = vsi->info.q_opt_rss; + + err = ice_update_vsi(hw, vsi->idx, ctx, NULL); + if (err) { + dev_err(ice_pf_to_dev(vsi->back), "Failed to configure RSS hash for VSI %d, error %d\n", + vsi->vsi_num, err); + } else { + vsi->info.q_opt_rss = ctx->info.q_opt_rss; + vsi->rss_hfunc = hfunc; + netdev_info(vsi->netdev, "Hash function set to: %sToeplitz\n", + hfunc == ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ ? + "Symmetric " : ""); + } + kfree(ctx); + if (err) + return err; + + /* Fix the symmetry setting for all existing RSS configurations */ + symm = !!(hfunc == ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ); + return ice_set_rss_cfg_symm(hw, vsi, symm); +} + +/** * ice_bridge_getlink - Get the hardware bridge mode * @skb: skb buff * @pid: process ID @@ -7806,13 +8106,12 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, pf_sw = pf->first_sw; /* find the attribute in the netlink message */ br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!br_spec) + return -EINVAL; - nla_for_each_nested(attr, br_spec, rem) { - __u16 mode; + nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) { + __u16 mode = nla_get_u16(attr); - if (nla_type(attr) != IFLA_BRIDGE_MODE) - continue; - mode = nla_get_u16(attr); if (mode != BRIDGE_MODE_VEPA && mode != BRIDGE_MODE_VEB) return -EINVAL; /* Continue if bridge mode is not being flipped */ @@ -7895,8 +8194,8 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) struct ice_hw *hw = &pf->hw; u32 head, val = 0; - head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue])) & - QTX_COMM_HEAD_HEAD_M) >> QTX_COMM_HEAD_HEAD_S; + 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)); @@ -8144,13 +8443,12 @@ static int ice_add_vsi_to_fdir(struct ice_pf *pf, struct ice_vsi *vsi) for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) { enum ice_flow_priority prio; - u64 prof_id; /* add this VSI to FDir profile for this flow */ prio = ICE_FLOW_PRIO_NORMAL; prof = hw->fdir_prof[flow]; - prof_id = flow + tun * ICE_FLTR_PTYPE_MAX; - status = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, + status = ice_flow_add_entry(hw, ICE_BLK_FD, + prof->prof_id[tun], prof->vsi_h[0], vsi->idx, prio, prof->fdir_seg[tun], &entry_h); @@ -9193,8 +9491,14 @@ int ice_stop(struct net_device *netdev) int link_err = ice_force_phys_link_state(vsi, false); if (link_err) { - netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", - vsi->vsi_num, link_err); + if (link_err == -ENOMEDIUM) + netdev_info(vsi->netdev, "Skipping link reconfig - no media attached, VSI %d\n", + vsi->vsi_num); + else + netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", + vsi->vsi_num, link_err); + + ice_vsi_close(vsi); return -EIO; } } diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index f6f52a248066..84eab92dc03c 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -18,10 +18,9 @@ * * Read the NVM using the admin queue commands (0x0701) */ -static int -ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, u16 length, - void *data, bool last_command, bool read_shadow_ram, - struct ice_sq_cd *cd) +int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, + u16 length, void *data, bool last_command, + bool read_shadow_ram, struct ice_sq_cd *cd) { struct ice_aq_desc desc; struct ice_aqc_nvm *cmd; @@ -571,8 +570,8 @@ ice_get_nvm_ver_info(struct ice_hw *hw, enum ice_bank_select bank, struct ice_nv return status; } - nvm->major = (ver & ICE_NVM_VER_HI_MASK) >> ICE_NVM_VER_HI_SHIFT; - nvm->minor = (ver & ICE_NVM_VER_LO_MASK) >> ICE_NVM_VER_LO_SHIFT; + nvm->major = FIELD_GET(ICE_NVM_VER_HI_MASK, ver); + nvm->minor = FIELD_GET(ICE_NVM_VER_LO_MASK, ver); status = ice_read_nvm_sr_copy(hw, bank, ICE_SR_NVM_EETRACK_LO, &eetrack_lo); if (status) { @@ -706,9 +705,9 @@ ice_get_orom_ver_info(struct ice_hw *hw, enum ice_bank_select bank, struct ice_o combo_ver = le32_to_cpu(civd.combo_ver); - orom->major = (u8)((combo_ver & ICE_OROM_VER_MASK) >> ICE_OROM_VER_SHIFT); - orom->patch = (u8)(combo_ver & ICE_OROM_VER_PATCH_MASK); - orom->build = (u16)((combo_ver & ICE_OROM_VER_BUILD_MASK) >> ICE_OROM_VER_BUILD_SHIFT); + orom->major = FIELD_GET(ICE_OROM_VER_MASK, combo_ver); + orom->patch = FIELD_GET(ICE_OROM_VER_PATCH_MASK, combo_ver); + orom->build = FIELD_GET(ICE_OROM_VER_BUILD_MASK, combo_ver); return 0; } @@ -950,7 +949,8 @@ static int ice_determine_active_flash_banks(struct ice_hw *hw) } /* Check that the control word indicates validity */ - if ((ctrl_word & ICE_SR_CTRL_WORD_1_M) >> ICE_SR_CTRL_WORD_1_S != ICE_SR_CTRL_WORD_VALID) { + if (FIELD_GET(ICE_SR_CTRL_WORD_1_M, ctrl_word) != + ICE_SR_CTRL_WORD_VALID) { ice_debug(hw, ICE_DBG_NVM, "Shadow RAM control word is invalid\n"); return -EIO; } @@ -1027,7 +1027,7 @@ int ice_init_nvm(struct ice_hw *hw) * as the blank mode may be used in the factory line. */ gens_stat = rd32(hw, GLNVM_GENS); - sr_size = (gens_stat & GLNVM_GENS_SR_SIZE_M) >> GLNVM_GENS_SR_SIZE_S; + sr_size = FIELD_GET(GLNVM_GENS_SR_SIZE_M, gens_stat); /* Switching to words (sr_size contains power of 2) */ flash->sr_words = BIT(sr_size) * ICE_SR_WORDS_IN_1KB; diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.h b/drivers/net/ethernet/intel/ice/ice_nvm.h index 774c2317967d..63cdc6bdac58 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.h +++ b/drivers/net/ethernet/intel/ice/ice_nvm.h @@ -14,6 +14,9 @@ struct ice_orom_civd_info { int ice_acquire_nvm(struct ice_hw *hw, enum ice_aq_res_access_type access); void ice_release_nvm(struct ice_hw *hw); +int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, + u16 length, void *data, bool last_command, + bool read_shadow_ram, struct ice_sq_cd *cd); int ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data, bool read_shadow_ram); diff --git a/drivers/net/ethernet/intel/ice/ice_osdep.h b/drivers/net/ethernet/intel/ice/ice_osdep.h index 82bc54fec7f3..a2562f04267f 100644 --- a/drivers/net/ethernet/intel/ice/ice_osdep.h +++ b/drivers/net/ethernet/intel/ice/ice_osdep.h @@ -24,7 +24,7 @@ #define rd64(a, reg) readq((a)->hw_addr + (reg)) #define ice_flush(a) rd32((a), GLGEN_STAT) -#define ICE_M(m, s) ((m) << (s)) +#define ICE_M(m, s) ((m ## U) << (s)) struct ice_dma_mem { void *va; diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index f6f27361c3cf..755a9c55267c 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -43,6 +43,7 @@ enum ice_protocol_type { ICE_NVGRE, ICE_GTP, ICE_GTP_NO_PAY, + ICE_PFCP, ICE_PPPOE, ICE_L2TPV3, ICE_VLAN_EX, @@ -61,6 +62,7 @@ enum ice_sw_tunnel_type { ICE_SW_TUN_NVGRE, ICE_SW_TUN_GTPU, ICE_SW_TUN_GTPC, + ICE_SW_TUN_PFCP, ICE_ALL_TUNNELS /* All tunnel types including NVGRE */ }; @@ -202,6 +204,15 @@ struct ice_udp_gtp_hdr { u8 rsvrd; }; +struct ice_pfcp_hdr { + u8 flags; + u8 msg_type; + __be16 length; + __be64 seid; + __be32 seq; + u8 spare; +} __packed __aligned(__alignof__(u16)); + struct ice_pppoe_hdr { u8 rsrvd_ver_type; u8 rsrvd_code; @@ -418,6 +429,7 @@ union ice_prot_hdr { struct ice_udp_tnl_hdr tnl_hdr; struct ice_nvgre_hdr nvgre_hdr; struct ice_udp_gtp_hdr gtp_hdr; + struct ice_pfcp_hdr pfcp_hdr; struct ice_pppoe_hdr pppoe_hdr; struct ice_l2tpv3_sess_hdr l2tpv3_sess_hdr; struct ice_hw_metadata metadata; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 1eddcbe89b0c..0f17fc1181d2 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -7,7 +7,7 @@ #define E810_OUT_PROP_DELAY_NS 1 -#define UNKNOWN_INCVAL_E822 0x100000000ULL +#define UNKNOWN_INCVAL_E82X 0x100000000ULL static const struct ptp_pin_desc ice_pin_desc_e810t[] = { /* name idx func chan */ @@ -256,48 +256,42 @@ ice_verify_pin_e810t(struct ptp_clock_info *info, unsigned int pin, } /** - * ice_ptp_configure_tx_tstamp - Enable or disable Tx timestamp interrupt - * @pf: The PF pointer to search in - * @on: bool value for whether timestamp interrupt is enabled or disabled + * ice_ptp_cfg_tx_interrupt - Configure Tx timestamp interrupt for the device + * @pf: Board private structure + * + * Program the device to respond appropriately to the Tx timestamp interrupt + * cause. */ -static void ice_ptp_configure_tx_tstamp(struct ice_pf *pf, bool on) +static void ice_ptp_cfg_tx_interrupt(struct ice_pf *pf) { + struct ice_hw *hw = &pf->hw; + bool enable; u32 val; + switch (pf->ptp.tx_interrupt_mode) { + case ICE_PTP_TX_INTERRUPT_ALL: + /* React to interrupts across all quads. */ + wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x1f); + enable = true; + break; + case ICE_PTP_TX_INTERRUPT_NONE: + /* Do not react to interrupts on any quad. */ + wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x0); + enable = false; + break; + case ICE_PTP_TX_INTERRUPT_SELF: + default: + enable = pf->ptp.tstamp_config.tx_type == HWTSTAMP_TX_ON; + break; + } + /* Configure the Tx timestamp interrupt */ - val = rd32(&pf->hw, PFINT_OICR_ENA); - if (on) + val = rd32(hw, PFINT_OICR_ENA); + if (enable) val |= PFINT_OICR_TSYN_TX_M; else val &= ~PFINT_OICR_TSYN_TX_M; - wr32(&pf->hw, PFINT_OICR_ENA, val); -} - -/** - * ice_set_tx_tstamp - Enable or disable Tx timestamping - * @pf: The PF pointer to search in - * @on: bool value for whether timestamps are enabled or disabled - */ -static void ice_set_tx_tstamp(struct ice_pf *pf, bool on) -{ - struct ice_vsi *vsi; - u16 i; - - vsi = ice_get_main_vsi(pf); - if (!vsi) - return; - - /* Set the timestamp enable flag for all the Tx rings */ - ice_for_each_txq(vsi, i) { - if (!vsi->tx_rings[i]) - continue; - vsi->tx_rings[i]->ptp_tx = on; - } - - if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_SELF) - ice_ptp_configure_tx_tstamp(pf, on); - - pf->ptp.tstamp_config.tx_type = on ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + wr32(hw, PFINT_OICR_ENA, val); } /** @@ -311,7 +305,7 @@ static void ice_set_rx_tstamp(struct ice_pf *pf, bool on) u16 i; vsi = ice_get_main_vsi(pf); - if (!vsi) + if (!vsi || !vsi->rx_rings) return; /* Set the timestamp flag for all the Rx rings */ @@ -320,23 +314,50 @@ static void ice_set_rx_tstamp(struct ice_pf *pf, bool on) continue; vsi->rx_rings[i]->ptp_rx = on; } +} - pf->ptp.tstamp_config.rx_filter = on ? HWTSTAMP_FILTER_ALL : - HWTSTAMP_FILTER_NONE; +/** + * ice_ptp_disable_timestamp_mode - Disable current timestamp mode + * @pf: Board private structure + * + * Called during preparation for reset to temporarily disable timestamping on + * the device. Called during remove to disable timestamping while cleaning up + * driver resources. + */ +static void ice_ptp_disable_timestamp_mode(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + u32 val; + + val = rd32(hw, PFINT_OICR_ENA); + val &= ~PFINT_OICR_TSYN_TX_M; + wr32(hw, PFINT_OICR_ENA, val); + + ice_set_rx_tstamp(pf, false); } /** - * ice_ptp_cfg_timestamp - Configure timestamp for init/deinit + * ice_ptp_restore_timestamp_mode - Restore timestamp configuration * @pf: Board private structure - * @ena: bool value to enable or disable time stamp * - * This function will configure timestamping during PTP initialization - * and deinitialization + * Called at the end of rebuild to restore timestamp configuration after + * a device reset. */ -void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena) +void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) { - ice_set_tx_tstamp(pf, ena); - ice_set_rx_tstamp(pf, ena); + struct ice_hw *hw = &pf->hw; + bool enable_rx; + + ice_ptp_cfg_tx_interrupt(pf); + + enable_rx = pf->ptp.tstamp_config.rx_filter == HWTSTAMP_FILTER_ALL; + ice_set_rx_tstamp(pf, enable_rx); + + /* Trigger an immediate software interrupt to ensure that timestamps + * which occurred during reset are handled now. + */ + wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); + ice_flush(hw); } /** @@ -353,6 +374,7 @@ ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) u8 tmr_idx; 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); @@ -504,6 +526,115 @@ ice_ptp_is_tx_tracker_up(struct ice_ptp_tx *tx) } /** + * ice_ptp_req_tx_single_tstamp - Request Tx timestamp for a port from FW + * @tx: the PTP Tx timestamp tracker + * @idx: index of the timestamp to request + */ +void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) +{ + struct ice_ptp_port *ptp_port; + struct sk_buff *skb; + struct ice_pf *pf; + + if (!tx->init) + return; + + ptp_port = container_of(tx, struct ice_ptp_port, tx); + pf = ptp_port_to_pf(ptp_port); + + /* Drop packets which have waited for more than 2 seconds */ + if (time_is_before_jiffies(tx->tstamps[idx].start + 2 * HZ)) { + /* Count the number of Tx timestamps that timed out */ + pf->ptp.tx_hwtstamp_timeouts++; + + skb = tx->tstamps[idx].skb; + tx->tstamps[idx].skb = NULL; + clear_bit(idx, tx->in_use); + + dev_kfree_skb_any(skb); + return; + } + + ice_trace(tx_tstamp_fw_req, tx->tstamps[idx].skb, idx); + + /* 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); + tx->last_ll_ts_idx_read = idx; +} + +/** + * ice_ptp_complete_tx_single_tstamp - Complete Tx timestamp for a port + * @tx: the PTP Tx timestamp tracker + */ +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_ptp_port *ptp_port; + u64 raw_tstamp, tstamp; + bool drop_ts = false; + struct sk_buff *skb; + struct ice_pf *pf; + u32 val; + + 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); + + ice_trace(tx_tstamp_fw_done, tx->tstamps[idx].skb, idx); + + val = rd32(&pf->hw, PF_SB_ATQBAL); + + /* When the bit is cleared, the TS is ready in the register */ + if (val & TS_LL_READ_TS) { + 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); + + /* Devices using this interface always verify the timestamp differs + * relative to the last cached timestamp value. + */ + if (raw_tstamp == tx->tstamps[idx].cached_tstamp) + return; + + tx->tstamps[idx].cached_tstamp = raw_tstamp; + clear_bit(idx, tx->in_use); + skb = tx->tstamps[idx].skb; + tx->tstamps[idx].skb = NULL; + if (test_and_clear_bit(idx, tx->stale)) + drop_ts = true; + + if (!skb) + return; + + if (drop_ts) { + dev_kfree_skb_any(skb); + return; + } + + /* Extend the timestamp using cached PHC time */ + tstamp = ice_ptp_extend_40b_ts(pf, raw_tstamp); + if (tstamp) { + shhwtstamps.hwtstamp = ns_to_ktime(tstamp); + ice_trace(tx_tstamp_complete, skb, idx); + } + + skb_tstamp_tx(skb, &shhwtstamps); + dev_kfree_skb_any(skb); +} + +/** * ice_ptp_process_tx_tstamp - Process Tx timestamps for a port * @tx: the PTP Tx timestamp tracker * @@ -554,6 +685,7 @@ ice_ptp_is_tx_tracker_up(struct ice_ptp_tx *tx) static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) { struct ice_ptp_port *ptp_port; + unsigned long flags; struct ice_pf *pf; struct ice_hw *hw; u64 tstamp_ready; @@ -566,9 +698,11 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) hw = &pf->hw; /* Read the Tx ready status first */ - err = ice_get_phy_tx_tstamp_ready(hw, tx->block, &tstamp_ready); - if (err) - return; + if (tx->has_ready_bitmap) { + err = ice_get_phy_tx_tstamp_ready(hw, tx->block, &tstamp_ready); + if (err) + return; + } /* Drop packets if the link went down */ link_up = ptp_port->link_up; @@ -596,7 +730,8 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) * If we do not, the hardware logic for generating a new * interrupt can get stuck on some devices. */ - if (!(tstamp_ready & BIT_ULL(phy_idx))) { + if (tx->has_ready_bitmap && + !(tstamp_ready & BIT_ULL(phy_idx))) { if (drop_ts) goto skip_ts_read; @@ -616,7 +751,7 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) * from the last cached timestamp. If it is not, skip this for * now assuming it hasn't yet been captured by hardware. */ - if (!drop_ts && tx->verify_cached && + if (!drop_ts && !tx->has_ready_bitmap && raw_tstamp == tx->tstamps[idx].cached_tstamp) continue; @@ -625,15 +760,15 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) drop_ts = true; skip_ts_read: - spin_lock(&tx->lock); - if (tx->verify_cached && raw_tstamp) + spin_lock_irqsave(&tx->lock, flags); + if (!tx->has_ready_bitmap && raw_tstamp) tx->tstamps[idx].cached_tstamp = raw_tstamp; clear_bit(idx, tx->in_use); skb = tx->tstamps[idx].skb; tx->tstamps[idx].skb = NULL; if (test_and_clear_bit(idx, tx->stale)) drop_ts = true; - spin_unlock(&tx->lock); + spin_unlock_irqrestore(&tx->lock, flags); /* It is unlikely but possible that the SKB will have been * flushed at this point due to link change or teardown. @@ -684,7 +819,9 @@ static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf) /* Read the Tx ready status first */ err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready); - if (err || tstamp_ready) + if (err) + break; + else if (tstamp_ready) return ICE_TX_TSTAMP_WORK_PENDING; } @@ -701,6 +838,7 @@ static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf) static enum ice_tx_tstamp_work ice_ptp_tx_tstamp(struct ice_ptp_tx *tx) { bool more_timestamps; + unsigned long flags; if (!tx->init) return ICE_TX_TSTAMP_WORK_DONE; @@ -709,9 +847,9 @@ static enum ice_tx_tstamp_work ice_ptp_tx_tstamp(struct ice_ptp_tx *tx) ice_ptp_process_tx_tstamp(tx); /* Check if there are outstanding Tx timestamps */ - spin_lock(&tx->lock); + spin_lock_irqsave(&tx->lock, flags); more_timestamps = tx->init && !bitmap_empty(tx->in_use, tx->len); - spin_unlock(&tx->lock); + spin_unlock_irqrestore(&tx->lock, flags); if (more_timestamps) return ICE_TX_TSTAMP_WORK_PENDING; @@ -748,6 +886,7 @@ ice_ptp_alloc_tx_tracker(struct ice_ptp_tx *tx) tx->in_use = in_use; tx->stale = stale; tx->init = 1; + tx->last_ll_ts_idx_read = -1; spin_lock_init(&tx->lock); @@ -765,6 +904,7 @@ static void ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) { struct ice_hw *hw = &pf->hw; + unsigned long flags; u64 tstamp_ready; int err; u8 idx; @@ -788,12 +928,12 @@ ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) if (!hw->reset_ongoing && (tstamp_ready & BIT_ULL(phy_idx))) ice_clear_phy_tstamp(hw, tx->block, phy_idx); - spin_lock(&tx->lock); + spin_lock_irqsave(&tx->lock, flags); skb = tx->tstamps[idx].skb; tx->tstamps[idx].skb = NULL; clear_bit(idx, tx->in_use); clear_bit(idx, tx->stale); - spin_unlock(&tx->lock); + spin_unlock_irqrestore(&tx->lock, flags); /* Count the number of Tx timestamps flushed */ pf->ptp.tx_hwtstamp_flushed++; @@ -817,9 +957,27 @@ ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) static void ice_ptp_mark_tx_tracker_stale(struct ice_ptp_tx *tx) { - spin_lock(&tx->lock); + unsigned long flags; + + spin_lock_irqsave(&tx->lock, flags); bitmap_or(tx->stale, tx->stale, tx->in_use, tx->len); - spin_unlock(&tx->lock); + spin_unlock_irqrestore(&tx->lock, flags); +} + +/** + * ice_ptp_flush_all_tx_tracker - Flush all timestamp trackers on this clock + * @pf: Board private structure + * + * Called by the clock owner to flush all the Tx timestamp trackers associated + * with the clock. + */ +static void +ice_ptp_flush_all_tx_tracker(struct ice_pf *pf) +{ + struct ice_ptp_port *port; + + list_for_each_entry(port, &pf->ptp.ports_owner.ports, list_member) + ice_ptp_flush_tx_tracker(ptp_port_to_pf(port), &port->tx); } /** @@ -832,9 +990,11 @@ ice_ptp_mark_tx_tracker_stale(struct ice_ptp_tx *tx) static void ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) { - spin_lock(&tx->lock); + unsigned long flags; + + spin_lock_irqsave(&tx->lock, flags); tx->init = 0; - spin_unlock(&tx->lock); + spin_unlock_irqrestore(&tx->lock, flags); /* wait for potentially outstanding interrupt to complete */ synchronize_irq(pf->oicr_irq.virq); @@ -854,7 +1014,7 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) } /** - * ice_ptp_init_tx_e822 - Initialize tracking for Tx timestamps + * ice_ptp_init_tx_e82x - Initialize tracking for Tx timestamps * @pf: Board private structure * @tx: the Tx tracking structure to initialize * @port: the port this structure tracks @@ -865,12 +1025,12 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) * registers into chunks based on the port number. */ static int -ice_ptp_init_tx_e822(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) +ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) { tx->block = port / ICE_PORTS_PER_QUAD; - tx->offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT_E822; - tx->len = INDEX_PER_PORT_E822; - tx->verify_cached = 0; + tx->offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT_E82X; + tx->len = INDEX_PER_PORT_E82X; + tx->has_ready_bitmap = 1; return ice_ptp_alloc_tx_tracker(tx); } @@ -893,7 +1053,7 @@ ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx) * verify new timestamps against cached copy of the last read * timestamp. */ - tx->verify_cached = 1; + tx->has_ready_bitmap = 0; return ice_ptp_alloc_tx_tracker(tx); } @@ -1007,26 +1167,6 @@ static void ice_ptp_reset_cached_phctime(struct ice_pf *pf) } /** - * ice_ptp_read_time - Read the time from the device - * @pf: Board private structure - * @ts: timespec structure to hold the current time value - * @sts: Optional parameter for holding a pair of system timestamps from - * the system clock. Will be ignored if NULL is given. - * - * This function reads the source clock registers and stores them in a timespec. - * However, since the registers are 64 bits of nanoseconds, we must convert the - * result to a timespec before we can return. - */ -static void -ice_ptp_read_time(struct ice_pf *pf, struct timespec64 *ts, - struct ptp_system_timestamp *sts) -{ - u64 time_ns = ice_ptp_read_src_clk_reg(pf, sts); - - *ts = ns_to_timespec64(time_ns); -} - -/** * ice_ptp_write_init - Set PHC time to provided value * @pf: Board private structure * @ts: timespec structure that holds the new time value @@ -1072,10 +1212,10 @@ static u64 ice_base_incval(struct ice_pf *pf) if (ice_is_e810(hw)) incval = ICE_PTP_NOMINAL_INCVAL_E810; - else if (ice_e822_time_ref(hw) < NUM_ICE_TIME_REF_FREQ) - incval = ice_e822_nominal_incval(ice_e822_time_ref(hw)); + else if (ice_e82x_time_ref(hw) < NUM_ICE_TIME_REF_FREQ) + incval = ice_e82x_nominal_incval(ice_e82x_time_ref(hw)); else - incval = UNKNOWN_INCVAL_E822; + incval = UNKNOWN_INCVAL_E82X; dev_dbg(ice_pf_to_dev(pf), "PTP: using base increment value of 0x%016llx\n", incval); @@ -1104,10 +1244,10 @@ static int ice_ptp_check_tx_fifo(struct ice_ptp_port *port) /* need to read FIFO state */ if (offs == 0 || offs == 1) - err = ice_read_quad_reg_e822(hw, quad, Q_REG_FIFO01_STATUS, + err = ice_read_quad_reg_e82x(hw, quad, Q_REG_FIFO01_STATUS, &val); else - err = ice_read_quad_reg_e822(hw, quad, Q_REG_FIFO23_STATUS, + err = ice_read_quad_reg_e82x(hw, quad, Q_REG_FIFO23_STATUS, &val); if (err) { @@ -1117,9 +1257,9 @@ static int ice_ptp_check_tx_fifo(struct ice_ptp_port *port) } if (offs & 0x1) - phy_sts = (val & Q_REG_FIFO13_M) >> Q_REG_FIFO13_S; + phy_sts = FIELD_GET(Q_REG_FIFO13_M, val); else - phy_sts = (val & Q_REG_FIFO02_M) >> Q_REG_FIFO02_S; + phy_sts = FIELD_GET(Q_REG_FIFO02_M, val); if (phy_sts & FIFO_EMPTY) { port->tx_fifo_busy_cnt = FIFO_OK; @@ -1135,7 +1275,7 @@ static int ice_ptp_check_tx_fifo(struct ice_ptp_port *port) dev_dbg(ice_pf_to_dev(pf), "Port %d Tx FIFO still not empty; resetting quad %d\n", port->port_num, quad); - ice_ptp_reset_ts_memory_quad_e822(hw, quad); + ice_ptp_reset_ts_memory_quad_e82x(hw, quad); port->tx_fifo_busy_cnt = FIFO_OK; return 0; } @@ -1180,8 +1320,8 @@ static void ice_ptp_wait_for_offsets(struct kthread_work *work) tx_err = ice_ptp_check_tx_fifo(port); if (!tx_err) - tx_err = ice_phy_cfg_tx_offset_e822(hw, port->port_num); - rx_err = ice_phy_cfg_rx_offset_e822(hw, port->port_num); + tx_err = ice_phy_cfg_tx_offset_e82x(hw, port->port_num); + rx_err = ice_phy_cfg_rx_offset_e82x(hw, port->port_num); if (tx_err || rx_err) { /* Tx and/or Rx offset not yet configured, try again later */ kthread_queue_delayed_work(pf->ptp.kworker, @@ -1210,7 +1350,7 @@ ice_ptp_port_phy_stop(struct ice_ptp_port *ptp_port) kthread_cancel_delayed_work_sync(&ptp_port->ov_work); - err = ice_stop_phy_timer_e822(hw, port, true); + err = ice_stop_phy_timer_e82x(hw, port, true); if (err) dev_err(ice_pf_to_dev(pf), "PTP failed to set PHY port %d down, err %d\n", port, err); @@ -1234,6 +1374,7 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port) struct ice_pf *pf = ptp_port_to_pf(ptp_port); u8 port = ptp_port->port_num; struct ice_hw *hw = &pf->hw; + unsigned long flags; int err; if (ice_is_e810(hw)) @@ -1247,20 +1388,20 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port) kthread_cancel_delayed_work_sync(&ptp_port->ov_work); /* temporarily disable Tx timestamps while calibrating PHY offset */ - spin_lock(&ptp_port->tx.lock); + spin_lock_irqsave(&ptp_port->tx.lock, flags); ptp_port->tx.calibrating = true; - spin_unlock(&ptp_port->tx.lock); + spin_unlock_irqrestore(&ptp_port->tx.lock, flags); ptp_port->tx_fifo_busy_cnt = 0; /* Start the PHY timer in Vernier mode */ - err = ice_start_phy_timer_e822(hw, port); + err = ice_start_phy_timer_e82x(hw, port); if (err) goto out_unlock; /* Enable Tx timestamps right away */ - spin_lock(&ptp_port->tx.lock); + spin_lock_irqsave(&ptp_port->tx.lock, flags); ptp_port->tx.calibrating = false; - spin_unlock(&ptp_port->tx.lock); + spin_unlock_irqrestore(&ptp_port->tx.lock, flags); kthread_queue_delayed_work(pf->ptp.kworker, &ptp_port->ov_work, 0); @@ -1285,7 +1426,7 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) struct ice_ptp_port *ptp_port; struct ice_hw *hw = &pf->hw; - if (!test_bit(ICE_FLAG_PTP, pf->flags)) + if (pf->ptp.state != ICE_PTP_READY) return; if (WARN_ON_ONCE(port >= ICE_NUM_EXTERNAL_PORTS)) @@ -1302,7 +1443,7 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) case ICE_PHY_E810: /* Do not reconfigure E810 PHY */ return; - case ICE_PHY_E822: + case ICE_PHY_E82X: ice_ptp_port_phy_restart(ptp_port); return; default: @@ -1311,14 +1452,14 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) } /** - * ice_ptp_tx_ena_intr - Enable or disable the Tx timestamp interrupt + * ice_ptp_cfg_phy_interrupt - Configure PHY interrupt settings * @pf: PF private structure * @ena: bool value to enable or disable interrupt * @threshold: Minimum number of packets at which intr is triggered * * Utility function to enable or disable Tx timestamp interrupt and threshold */ -static int ice_ptp_tx_ena_intr(struct ice_pf *pf, bool ena, u32 threshold) +static int ice_ptp_cfg_phy_interrupt(struct ice_pf *pf, bool ena, u32 threshold) { struct ice_hw *hw = &pf->hw; int err = 0; @@ -1328,7 +1469,7 @@ static int ice_ptp_tx_ena_intr(struct ice_pf *pf, bool ena, u32 threshold) ice_ptp_reset_ts_memory(hw); for (quad = 0; quad < ICE_MAX_QUAD; quad++) { - err = ice_read_quad_reg_e822(hw, quad, Q_REG_TX_MEM_GBL_CFG, + err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, &val); if (err) break; @@ -1336,13 +1477,13 @@ static int ice_ptp_tx_ena_intr(struct ice_pf *pf, bool ena, u32 threshold) if (ena) { val |= Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M; val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_THR_M; - val |= ((threshold << Q_REG_TX_MEM_GBL_CFG_INTR_THR_S) & - Q_REG_TX_MEM_GBL_CFG_INTR_THR_M); + val |= FIELD_PREP(Q_REG_TX_MEM_GBL_CFG_INTR_THR_M, + threshold); } else { val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M; } - err = ice_write_quad_reg_e822(hw, quad, Q_REG_TX_MEM_GBL_CFG, + err = ice_write_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, val); if (err) break; @@ -1482,8 +1623,7 @@ ice_ptp_cfg_extts(struct ice_pf *pf, bool ena, unsigned int chan, u32 gpio_pin, * + num_in_channels * tmr_idx */ func = 1 + chan + (tmr_idx * 3); - gpio_reg = ((func << GLGEN_GPIO_CTL_PIN_FUNC_S) & - GLGEN_GPIO_CTL_PIN_FUNC_M); + gpio_reg = FIELD_PREP(GLGEN_GPIO_CTL_PIN_FUNC_M, func); pf->ptp.ext_ts_chan |= (1 << chan); } else { /* clear the values we set to reset defaults */ @@ -1580,7 +1720,7 @@ static int ice_ptp_cfg_clkout(struct ice_pf *pf, unsigned int chan, if (ice_is_e810(hw)) start_time -= E810_OUT_PROP_DELAY_NS; else - start_time -= ice_e822_pps_delay(ice_e822_time_ref(hw)); + start_time -= ice_e82x_pps_delay(ice_e82x_time_ref(hw)); /* 2. Write TARGET time */ wr32(hw, GLTSYN_TGT_L(chan, tmr_idx), lower_32_bits(start_time)); @@ -1593,7 +1733,7 @@ static int ice_ptp_cfg_clkout(struct ice_pf *pf, unsigned int chan, /* 4. write GPIO CTL reg */ func = 8 + chan + (tmr_idx * 4); val = GLGEN_GPIO_CTL_PIN_DIR_M | - ((func << GLGEN_GPIO_CTL_PIN_FUNC_S) & GLGEN_GPIO_CTL_PIN_FUNC_M); + FIELD_PREP(GLGEN_GPIO_CTL_PIN_FUNC_M, func); wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val); /* Store the value if requested */ @@ -1766,16 +1906,10 @@ ice_ptp_gettimex64(struct ptp_clock_info *info, struct timespec64 *ts, struct ptp_system_timestamp *sts) { struct ice_pf *pf = ptp_info_to_pf(info); - struct ice_hw *hw = &pf->hw; - - if (!ice_ptp_lock(hw)) { - dev_err(ice_pf_to_dev(pf), "PTP failed to get time\n"); - return -EBUSY; - } - - ice_ptp_read_time(pf, ts, sts); - ice_ptp_unlock(hw); + u64 time_ns; + time_ns = ice_ptp_read_src_clk_reg(pf, sts); + *ts = ns_to_timespec64(time_ns); return 0; } @@ -1819,7 +1953,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) ice_ptp_enable_all_clkout(pf); /* Recalibrate and re-enable timestamp blocks for E822/E823 */ - if (hw->phy_model == ICE_PHY_E822) + if (hw->phy_model == ICE_PHY_E82X) ice_ptp_restart_all_phy(pf); exit: if (err) { @@ -2018,7 +2152,7 @@ int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr) { struct hwtstamp_config *config; - if (!test_bit(ICE_FLAG_PTP, pf->flags)) + if (pf->ptp.state != ICE_PTP_READY) return -EIO; config = &pf->ptp.tstamp_config; @@ -2037,10 +2171,10 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) { switch (config->tx_type) { case HWTSTAMP_TX_OFF: - ice_set_tx_tstamp(pf, false); + pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_OFF; break; case HWTSTAMP_TX_ON: - ice_set_tx_tstamp(pf, true); + pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_ON; break; default: return -ERANGE; @@ -2048,7 +2182,7 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: - ice_set_rx_tstamp(pf, false); + pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; break; case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: @@ -2064,12 +2198,15 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: case HWTSTAMP_FILTER_ALL: - ice_set_rx_tstamp(pf, true); + pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_ALL; break; default: return -ERANGE; } + /* Immediately update the device timestamping mode */ + ice_ptp_restore_timestamp_mode(pf); + return 0; } @@ -2085,7 +2222,7 @@ int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr) struct hwtstamp_config config; int err; - if (!test_bit(ICE_FLAG_PTP, pf->flags)) + if (pf->ptp.state != ICE_PTP_READY) return -EAGAIN; if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) @@ -2103,30 +2240,26 @@ int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr) } /** - * ice_ptp_rx_hwtstamp - Check for an Rx timestamp - * @rx_ring: Ring to get the VSI info + * ice_ptp_get_rx_hwts - Get packet Rx timestamp in ns * @rx_desc: Receive descriptor - * @skb: Particular skb to send timestamp with + * @pkt_ctx: Packet context to get the cached time * * The driver receives a notification in the receive descriptor with timestamp. - * The timestamp is in ns, so we must convert the result first. */ -void -ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, - union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) +u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, + const struct ice_pkt_ctx *pkt_ctx) { - struct skb_shared_hwtstamps *hwtstamps; u64 ts_ns, cached_time; u32 ts_high; if (!(rx_desc->wb.time_stamp_low & ICE_PTP_TS_VALID)) - return; + return 0; - cached_time = READ_ONCE(rx_ring->cached_phctime); + cached_time = READ_ONCE(pkt_ctx->cached_phctime); /* Do not report a timestamp if we don't have a cached PHC time */ if (!cached_time) - return; + return 0; /* Use ice_ptp_extend_32b_ts directly, using the ring-specific cached * PHC value, rather than accessing the PF. This also allows us to @@ -2137,9 +2270,7 @@ ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, ts_high = le32_to_cpu(rx_desc->wb.flex_ts.ts_high); ts_ns = ice_ptp_extend_32b_ts(cached_time, ts_high); - hwtstamps = skb_hwtstamps(skb); - memset(hwtstamps, 0, sizeof(*hwtstamps)); - hwtstamps->hwtstamp = ns_to_ktime(ts_ns); + return ts_ns; } /** @@ -2354,18 +2485,23 @@ static long ice_ptp_create_clock(struct ice_pf *pf) */ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) { + unsigned long flags; u8 idx; - spin_lock(&tx->lock); + spin_lock_irqsave(&tx->lock, flags); /* Check that this tracker is accepting new timestamp requests */ if (!ice_ptp_is_tx_tracker_up(tx)) { - spin_unlock(&tx->lock); + spin_unlock_irqrestore(&tx->lock, flags); return -1; } /* Find and set the first available index */ - idx = find_first_zero_bit(tx->in_use, tx->len); + idx = find_next_zero_bit(tx->in_use, tx->len, + tx->last_ll_ts_idx_read + 1); + if (idx == tx->len) + idx = find_first_zero_bit(tx->in_use, tx->len); + if (idx < tx->len) { /* We got a valid index that no other thread could have set. Store * a reference to the skb and the start time to allow discarding old @@ -2379,7 +2515,7 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) ice_trace(tx_tstamp_request, skb, idx); } - spin_unlock(&tx->lock); + spin_unlock_irqrestore(&tx->lock, flags); /* return the appropriate PHY timestamp register index, -1 if no * indexes were available. @@ -2416,55 +2552,139 @@ enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf) } } +/** + * ice_ptp_maybe_trigger_tx_interrupt - Trigger Tx timstamp interrupt + * @pf: Board private structure + * + * The device PHY issues Tx timestamp interrupts to the driver for processing + * timestamp data from the PHY. It will not interrupt again until all + * current timestamp data is read. In rare circumstances, it is possible that + * the driver fails to read all outstanding data. + * + * To avoid getting permanently stuck, periodically check if the PHY has + * outstanding timestamp data. If so, trigger an interrupt from software to + * process this data. + */ +static void ice_ptp_maybe_trigger_tx_interrupt(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + bool trigger_oicr = false; + unsigned int i; + + if (ice_is_e810(hw)) + return; + + if (!ice_pf_src_tmr_owned(pf)) + return; + + for (i = 0; i < ICE_MAX_QUAD; i++) { + u64 tstamp_ready; + int err; + + err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready); + if (!err && tstamp_ready) { + trigger_oicr = true; + break; + } + } + + if (trigger_oicr) { + /* Trigger a software interrupt, to ensure this data + * gets processed. + */ + dev_dbg(dev, "PTP periodic task detected waiting timestamps. Triggering Tx timestamp interrupt now.\n"); + + wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); + ice_flush(hw); + } +} + static void ice_ptp_periodic_work(struct kthread_work *work) { struct ice_ptp *ptp = container_of(work, struct ice_ptp, work.work); struct ice_pf *pf = container_of(ptp, struct ice_pf, ptp); int err; - if (!test_bit(ICE_FLAG_PTP, pf->flags)) + if (pf->ptp.state != ICE_PTP_READY) return; err = ice_ptp_update_cached_phctime(pf); + ice_ptp_maybe_trigger_tx_interrupt(pf); + /* Run twice a second or reschedule if phc update failed */ kthread_queue_delayed_work(ptp->kworker, &ptp->work, msecs_to_jiffies(err ? 10 : 500)); } /** - * ice_ptp_reset - Initialize PTP hardware clock support after reset + * ice_ptp_prepare_for_reset - Prepare PTP for reset * @pf: Board private structure + * @reset_type: the reset type being performed */ -void ice_ptp_reset(struct ice_pf *pf) +void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) +{ + struct ice_ptp *ptp = &pf->ptp; + u8 src_tmr; + + if (ptp->state != ICE_PTP_READY) + return; + + ptp->state = ICE_PTP_RESETTING; + + /* Disable timestamping for both Tx and Rx */ + ice_ptp_disable_timestamp_mode(pf); + + kthread_cancel_delayed_work_sync(&ptp->work); + + if (reset_type == ICE_RESET_PFR) + return; + + ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx); + + /* Disable periodic outputs */ + ice_ptp_disable_all_clkout(pf); + + src_tmr = ice_get_ptp_src_clock_index(&pf->hw); + + /* Disable source clock */ + wr32(&pf->hw, GLTSYN_ENA(src_tmr), (u32)~GLTSYN_ENA_TSYN_ENA_M); + + /* Acquire PHC and system timer to restore after reset */ + ptp->reset_time = ktime_get_real_ns(); +} + +/** + * ice_ptp_rebuild_owner - Initialize PTP clock owner after reset + * @pf: Board private structure + * + * Companion function for ice_ptp_rebuild() which handles tasks that only the + * PTP clock owner instance should perform. + */ +static int ice_ptp_rebuild_owner(struct ice_pf *pf) { struct ice_ptp *ptp = &pf->ptp; struct ice_hw *hw = &pf->hw; struct timespec64 ts; - int err, itr = 1; u64 time_diff; - - if (test_bit(ICE_PFR_REQ, pf->state)) - goto pfr; - - if (!ice_pf_src_tmr_owned(pf)) - goto reset_ts; + int err; err = ice_ptp_init_phc(hw); if (err) - goto err; + return err; /* Acquire the global hardware lock */ if (!ice_ptp_lock(hw)) { err = -EBUSY; - goto err; + return err; } /* Write the increment time value to PHY and LAN */ err = ice_ptp_write_incval(hw, ice_base_incval(pf)); if (err) { ice_ptp_unlock(hw); - goto err; + return err; } /* Write the initial Time value to PHY and LAN using the cached PHC @@ -2480,37 +2700,54 @@ void ice_ptp_reset(struct ice_pf *pf) err = ice_ptp_write_init(pf, &ts); if (err) { ice_ptp_unlock(hw); - goto err; + return err; } /* Release the global hardware lock */ ice_ptp_unlock(hw); + /* Flush software tracking of any outstanding timestamps since we're + * about to flush the PHY timestamp block. + */ + ice_ptp_flush_all_tx_tracker(pf); + if (!ice_is_e810(hw)) { /* Enable quad interrupts */ - err = ice_ptp_tx_ena_intr(pf, true, itr); + err = ice_ptp_cfg_phy_interrupt(pf, true, 1); if (err) - goto err; + return err; + + ice_ptp_restart_all_phy(pf); } -reset_ts: - /* Restart the PHY timestamping block */ - ice_ptp_reset_phy_timestamping(pf); + return 0; +} -pfr: - /* Init Tx structures */ - if (ice_is_e810(&pf->hw)) { - err = ice_ptp_init_tx_e810(pf, &ptp->port.tx); - } else { - kthread_init_delayed_work(&ptp->port.ov_work, - ice_ptp_wait_for_offsets); - err = ice_ptp_init_tx_e822(pf, &ptp->port.tx, - ptp->port.port_num); - } - if (err) +/** + * ice_ptp_rebuild - Initialize PTP hardware clock support after reset + * @pf: Board private structure + * @reset_type: the reset type being performed + */ +void ice_ptp_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) +{ + struct ice_ptp *ptp = &pf->ptp; + int err; + + if (ptp->state == ICE_PTP_READY) { + ice_ptp_prepare_for_reset(pf, reset_type); + } else if (ptp->state != ICE_PTP_RESETTING) { + err = -EINVAL; + dev_err(ice_pf_to_dev(pf), "PTP was not initialized\n"); goto err; + } + + if (ice_pf_src_tmr_owned(pf) && reset_type != ICE_RESET_PFR) { + err = ice_ptp_rebuild_owner(pf); + if (err) + goto err; + } - set_bit(ICE_FLAG_PTP, pf->flags); + ptp->state = ICE_PTP_READY; /* Start periodic work going */ kthread_queue_delayed_work(ptp->kworker, &ptp->work, 0); @@ -2519,6 +2756,7 @@ pfr: return; err: + ptp->state = ICE_PTP_ERROR; dev_err(ice_pf_to_dev(pf), "PTP reset failed %d\n", err); } @@ -2668,6 +2906,8 @@ static int ice_ptp_register_auxbus_driver(struct ice_pf *pf) name = devm_kasprintf(dev, GFP_KERNEL, "ptp_aux_dev_%u_%u_clk%u", pf->pdev->bus->number, PCI_SLOT(pf->pdev->devfn), ice_get_ptp_src_clock_index(&pf->hw)); + if (!name) + return -ENOMEM; aux_driver->name = name; aux_driver->shutdown = ice_ptp_auxbus_shutdown; @@ -2726,39 +2966,6 @@ int ice_ptp_clock_index(struct ice_pf *pf) } /** - * ice_ptp_prepare_for_reset - Prepare PTP for reset - * @pf: Board private structure - */ -void ice_ptp_prepare_for_reset(struct ice_pf *pf) -{ - struct ice_ptp *ptp = &pf->ptp; - u8 src_tmr; - - clear_bit(ICE_FLAG_PTP, pf->flags); - - /* Disable timestamping for both Tx and Rx */ - ice_ptp_cfg_timestamp(pf, false); - - kthread_cancel_delayed_work_sync(&ptp->work); - - if (test_bit(ICE_PFR_REQ, pf->state)) - return; - - ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx); - - /* Disable periodic outputs */ - ice_ptp_disable_all_clkout(pf); - - src_tmr = ice_get_ptp_src_clock_index(&pf->hw); - - /* Disable source clock */ - wr32(&pf->hw, GLTSYN_ENA(src_tmr), (u32)~GLTSYN_ENA_TSYN_ENA_M); - - /* Acquire PHC and system timer to restore after reset */ - ptp->reset_time = ktime_get_real_ns(); -} - -/** * ice_ptp_init_owner - Initialize PTP_1588_CLOCK device * @pf: Board private structure * @@ -2770,7 +2977,7 @@ static int ice_ptp_init_owner(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; struct timespec64 ts; - int err, itr = 1; + int err; err = ice_ptp_init_phc(hw); if (err) { @@ -2803,17 +3010,9 @@ static int ice_ptp_init_owner(struct ice_pf *pf) /* Release the global hardware lock */ ice_ptp_unlock(hw); - if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_ALL) { - /* The clock owner for this device type handles the timestamp - * interrupt for all ports. - */ - ice_ptp_configure_tx_tstamp(pf, true); - - /* React on all quads interrupts for E82x */ - wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x1f); - + if (!ice_is_e810(hw)) { /* Enable quad interrupts */ - err = ice_ptp_tx_ena_intr(pf, true, itr); + err = ice_ptp_cfg_phy_interrupt(pf, true, 1); if (err) goto err_exit; } @@ -2880,18 +3079,11 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) switch (hw->phy_model) { case ICE_PHY_E810: return ice_ptp_init_tx_e810(pf, &ptp_port->tx); - case ICE_PHY_E822: - /* Non-owner PFs don't react to any interrupts on E82x, - * neither on own quad nor on others - */ - if (!ice_ptp_pf_handles_tx_interrupt(pf)) { - ice_ptp_configure_tx_tstamp(pf, false); - wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x0); - } + case ICE_PHY_E82X: kthread_init_delayed_work(&ptp_port->ov_work, ice_ptp_wait_for_offsets); - return ice_ptp_init_tx_e822(pf, &ptp_port->tx, + return ice_ptp_init_tx_e82x(pf, &ptp_port->tx, ptp_port->port_num); default: return -ENODEV; @@ -2929,6 +3121,8 @@ static int ice_ptp_create_auxbus_device(struct ice_pf *pf) name = devm_kasprintf(dev, GFP_KERNEL, "ptp_aux_dev_%u_%u_clk%u", pf->pdev->bus->number, PCI_SLOT(pf->pdev->devfn), ice_get_ptp_src_clock_index(&pf->hw)); + if (!name) + return -ENOMEM; aux_dev->name = name; aux_dev->id = id; @@ -2978,7 +3172,7 @@ static void ice_ptp_remove_auxbus_device(struct ice_pf *pf) static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf) { switch (pf->hw.phy_model) { - case ICE_PHY_E822: + case ICE_PHY_E82X: /* E822 based PHY has the clock owner process the interrupt * for all ports. */ @@ -3011,6 +3205,8 @@ void ice_ptp_init(struct ice_pf *pf) struct ice_hw *hw = &pf->hw; int err; + ptp->state = ICE_PTP_INITIALIZING; + ice_ptp_init_phy_model(hw); ice_ptp_init_tx_interrupt_mode(pf); @@ -3032,12 +3228,16 @@ void ice_ptp_init(struct ice_pf *pf) /* Start the PHY timestamping block */ ice_ptp_reset_phy_timestamping(pf); - set_bit(ICE_FLAG_PTP, pf->flags); - err = ice_ptp_init_work(pf, ptp); + /* Configure initial Tx interrupt settings */ + ice_ptp_cfg_tx_interrupt(pf); + + err = ice_ptp_create_auxbus_device(pf); if (err) goto err; - err = ice_ptp_create_auxbus_device(pf); + ptp->state = ICE_PTP_READY; + + err = ice_ptp_init_work(pf, ptp); if (err) goto err; @@ -3050,7 +3250,7 @@ err: ptp_clock_unregister(ptp->clock); pf->ptp.clock = NULL; } - clear_bit(ICE_FLAG_PTP, pf->flags); + ptp->state = ICE_PTP_ERROR; dev_err(ice_pf_to_dev(pf), "PTP failed %d\n", err); } @@ -3063,18 +3263,18 @@ err: */ void ice_ptp_release(struct ice_pf *pf) { - if (!test_bit(ICE_FLAG_PTP, pf->flags)) + if (pf->ptp.state != ICE_PTP_READY) return; + pf->ptp.state = ICE_PTP_UNINIT; + /* Disable timestamping for both Tx and Rx */ - ice_ptp_cfg_timestamp(pf, false); + ice_ptp_disable_timestamp_mode(pf); ice_ptp_remove_auxbus_device(pf); ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx); - clear_bit(ICE_FLAG_PTP, pf->flags); - kthread_cancel_delayed_work_sync(&pf->ptp.work); ice_ptp_port_phy_stop(&pf->ptp.port); @@ -3084,6 +3284,9 @@ void ice_ptp_release(struct ice_pf *pf) pf->ptp.kworker = NULL; } + if (ice_pf_src_tmr_owned(pf)) + ice_ptp_unregister_auxbus_driver(pf); + if (!pf->ptp.clock) return; @@ -3093,7 +3296,5 @@ void ice_ptp_release(struct ice_pf *pf) ptp_clock_unregister(pf->ptp.clock); pf->ptp.clock = NULL; - ice_ptp_unregister_auxbus_driver(pf); - dev_info(ice_pf_to_dev(pf), "Removed PTP clock\n"); } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 8f6f94392756..3af20025043a 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -100,7 +100,7 @@ struct ice_perout_channel { * the last timestamp we read for a given index. If the current timestamp * value is the same as the cached value, we assume a new timestamp hasn't * been captured. This avoids reporting stale timestamps to the stack. This is - * only done if the verify_cached flag is set in ice_ptp_tx structure. + * only done if the has_ready_bitmap flag is not set in ice_ptp_tx structure. */ struct ice_tx_tstamp { struct sk_buff *skb; @@ -130,7 +130,10 @@ enum ice_tx_tstamp_work { * @init: if true, the tracker is initialized; * @calibrating: if true, the PHY is calibrating the Tx offset. During this * window, timestamps are temporarily disabled. - * @verify_cached: if true, verify new timestamp differs from last read value + * @has_ready_bitmap: if true, the hardware has a valid Tx timestamp ready + * bitmap register. If false, fall back to verifying new + * timestamp values against previously cached copy. + * @last_ll_ts_idx_read: index of the last LL TS read by the FW */ struct ice_ptp_tx { spinlock_t lock; /* lock protecting in_use bitmap */ @@ -142,12 +145,13 @@ struct ice_ptp_tx { u8 len; u8 init : 1; u8 calibrating : 1; - u8 verify_cached : 1; + u8 has_ready_bitmap : 1; + s8 last_ll_ts_idx_read; }; /* Quad and port information for initializing timestamp blocks */ #define INDEX_PER_QUAD 64 -#define INDEX_PER_PORT_E822 16 +#define INDEX_PER_PORT_E82X 16 #define INDEX_PER_PORT_E810 64 /** @@ -201,8 +205,17 @@ struct ice_ptp_port_owner { #define GLTSYN_TGT_H_IDX_MAX 4 +enum ice_ptp_state { + ICE_PTP_UNINIT = 0, + ICE_PTP_INITIALIZING, + ICE_PTP_READY, + ICE_PTP_RESETTING, + ICE_PTP_ERROR, +}; + /** * struct ice_ptp - data used for integrating with CONFIG_PTP_1588_CLOCK + * @state: current state of PTP state machine * @tx_interrupt_mode: the TX interrupt mode for the PTP clock * @port: data for the PHY port initialization procedure * @ports_owner: data for the auxiliary driver owner @@ -225,6 +238,7 @@ struct ice_ptp_port_owner { * @late_cached_phc_updates: number of times cached PHC update is late */ struct ice_ptp { + enum ice_ptp_state state; enum ice_ptp_tx_interrupt tx_interrupt_mode; struct ice_ptp_port port; struct ice_ptp_port_owner ports_owner; @@ -292,17 +306,19 @@ int ice_ptp_clock_index(struct ice_pf *pf); struct ice_pf; int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr); int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr); -void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena); +void ice_ptp_restore_timestamp_mode(struct ice_pf *pf); void ice_ptp_extts_event(struct ice_pf *pf); 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); -void -ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, - union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb); -void ice_ptp_reset(struct ice_pf *pf); -void ice_ptp_prepare_for_reset(struct ice_pf *pf); +u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, + const struct ice_pkt_ctx *pkt_ctx); +void ice_ptp_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type); +void ice_ptp_prepare_for_reset(struct ice_pf *pf, + enum ice_reset_req reset_type); void ice_ptp_init(struct ice_pf *pf); void ice_ptp_release(struct ice_pf *pf); void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup); @@ -317,8 +333,7 @@ static inline int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr) return -EOPNOTSUPP; } -static inline void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena) { } - +static inline void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) { } static inline void ice_ptp_extts_event(struct ice_pf *pf) { } static inline s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) @@ -326,15 +341,32 @@ ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) return -1; } +static inline void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) +{ } + +static inline void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx) { } + static inline bool ice_ptp_process_ts(struct ice_pf *pf) { return true; } -static inline void -ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, - union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) { } -static inline void ice_ptp_reset(struct ice_pf *pf) { } -static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf) { } + +static inline u64 +ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, + const struct ice_pkt_ctx *pkt_ctx) +{ + return 0; +} + +static inline void ice_ptp_rebuild(struct ice_pf *pf, + enum ice_reset_req reset_type) +{ +} + +static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf, + enum ice_reset_req reset_type) +{ +} static inline void ice_ptp_init(struct ice_pf *pf) { } static inline void ice_ptp_release(struct ice_pf *pf) { } static inline void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h index 4109aa3b2fcd..2c4dab0c48ab 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h @@ -9,17 +9,17 @@ */ /* Constants defined for the PTP 1588 clock hardware. */ -/* struct ice_time_ref_info_e822 +/* struct ice_time_ref_info_e82x * * E822 hardware can use different sources as the reference for the PTP * hardware clock. Each clock has different characteristics such as a slightly * different frequency, etc. * * This lookup table defines several constants that depend on the current time - * reference. See the struct ice_time_ref_info_e822 for information about the + * reference. See the struct ice_time_ref_info_e82x for information about the * meaning of each constant. */ -const struct ice_time_ref_info_e822 e822_time_ref[NUM_ICE_TIME_REF_FREQ] = { +const struct ice_time_ref_info_e82x e822_time_ref[NUM_ICE_TIME_REF_FREQ] = { /* ICE_TIME_REF_FREQ_25_000 -> 25 MHz */ { /* pll_freq */ @@ -81,7 +81,7 @@ const struct ice_time_ref_info_e822 e822_time_ref[NUM_ICE_TIME_REF_FREQ] = { }, }; -const struct ice_cgu_pll_params_e822 e822_cgu_params[NUM_ICE_TIME_REF_FREQ] = { +const struct ice_cgu_pll_params_e82x e822_cgu_params[NUM_ICE_TIME_REF_FREQ] = { /* ICE_TIME_REF_FREQ_25_000 -> 25 MHz */ { /* refclk_pre_div */ @@ -155,7 +155,7 @@ const struct ice_cgu_pll_params_e822 e822_cgu_params[NUM_ICE_TIME_REF_FREQ] = { }, }; -/* struct ice_vernier_info_e822 +/* struct ice_vernier_info_e82x * * E822 hardware calibrates the delay of the timestamp indication from the * actual packet transmission or reception during the initialization of the @@ -168,7 +168,7 @@ const struct ice_cgu_pll_params_e822 e822_cgu_params[NUM_ICE_TIME_REF_FREQ] = { * used by this link speed, and that the register should be cleared by writing * 0. Other values specify the clock frequency in Hz. */ -const struct ice_vernier_info_e822 e822_vernier[NUM_ICE_PTP_LNK_SPD] = { +const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD] = { /* ICE_PTP_LNK_SPD_1G */ { /* tx_par_clk */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 6d573908de7a..2b9423a173bb 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -274,6 +274,9 @@ void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) */ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw) { + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); + + guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock); wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD); ice_flush(hw); } @@ -284,19 +287,19 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw) */ /** - * ice_fill_phy_msg_e822 - Fill message data for a PHY register access + * ice_fill_phy_msg_e82x - Fill message data for a PHY register access * @msg: the PHY message buffer to fill in * @port: the port to access * @offset: the register offset */ static void -ice_fill_phy_msg_e822(struct ice_sbq_msg_input *msg, u8 port, u16 offset) +ice_fill_phy_msg_e82x(struct ice_sbq_msg_input *msg, u8 port, u16 offset) { int phy_port, phy, quadtype; - phy_port = port % ICE_PORTS_PER_PHY_E822; - phy = port / ICE_PORTS_PER_PHY_E822; - quadtype = (port / ICE_PORTS_PER_QUAD) % ICE_QUADS_PER_PHY_E822; + phy_port = port % ICE_PORTS_PER_PHY_E82X; + phy = port / ICE_PORTS_PER_PHY_E82X; + quadtype = (port / ICE_PORTS_PER_QUAD) % ICE_QUADS_PER_PHY_E82X; if (quadtype == 0) { msg->msg_addr_low = P_Q0_L(P_0_BASE + offset, phy_port); @@ -315,7 +318,7 @@ ice_fill_phy_msg_e822(struct ice_sbq_msg_input *msg, u8 port, u16 offset) } /** - * ice_is_64b_phy_reg_e822 - Check if this is a 64bit PHY register + * ice_is_64b_phy_reg_e82x - Check if this is a 64bit PHY register * @low_addr: the low address to check * @high_addr: on return, contains the high address of the 64bit register * @@ -323,7 +326,7 @@ ice_fill_phy_msg_e822(struct ice_sbq_msg_input *msg, u8 port, u16 offset) * represented as two 32bit registers. If it is, return the appropriate high * register offset to use. */ -static bool ice_is_64b_phy_reg_e822(u16 low_addr, u16 *high_addr) +static bool ice_is_64b_phy_reg_e82x(u16 low_addr, u16 *high_addr) { switch (low_addr) { case P_REG_PAR_PCS_TX_OFFSET_L: @@ -368,7 +371,7 @@ static bool ice_is_64b_phy_reg_e822(u16 low_addr, u16 *high_addr) } /** - * ice_is_40b_phy_reg_e822 - Check if this is a 40bit PHY register + * ice_is_40b_phy_reg_e82x - Check if this is a 40bit PHY register * @low_addr: the low address to check * @high_addr: on return, contains the high address of the 40bit value * @@ -377,7 +380,7 @@ static bool ice_is_64b_phy_reg_e822(u16 low_addr, u16 *high_addr) * upper 32 bits in the high register. If it is, return the appropriate high * register offset to use. */ -static bool ice_is_40b_phy_reg_e822(u16 low_addr, u16 *high_addr) +static bool ice_is_40b_phy_reg_e82x(u16 low_addr, u16 *high_addr) { switch (low_addr) { case P_REG_TIMETUS_L: @@ -413,7 +416,7 @@ static bool ice_is_40b_phy_reg_e822(u16 low_addr, u16 *high_addr) } /** - * ice_read_phy_reg_e822 - Read a PHY register + * ice_read_phy_reg_e82x - Read a PHY register * @hw: pointer to the HW struct * @port: PHY port to read from * @offset: PHY register offset to read @@ -422,12 +425,12 @@ static bool ice_is_40b_phy_reg_e822(u16 low_addr, u16 *high_addr) * Read a PHY register for the given port over the device sideband queue. */ static int -ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val) +ice_read_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 *val) { struct ice_sbq_msg_input msg = {0}; int err; - ice_fill_phy_msg_e822(&msg, port, offset); + ice_fill_phy_msg_e82x(&msg, port, offset); msg.opcode = ice_sbq_msg_rd; err = ice_sbq_rw_reg(hw, &msg); @@ -443,7 +446,7 @@ ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val) } /** - * ice_read_64b_phy_reg_e822 - Read a 64bit value from PHY registers + * ice_read_64b_phy_reg_e82x - Read a 64bit value from PHY registers * @hw: pointer to the HW struct * @port: PHY port to read from * @low_addr: offset of the lower register to read from @@ -455,7 +458,7 @@ ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val) * known to be two parts of a 64bit value. */ static int -ice_read_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val) +ice_read_64b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val) { u32 low, high; u16 high_addr; @@ -464,20 +467,20 @@ ice_read_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val) /* Only operate on registers known to be split into two 32bit * registers. */ - if (!ice_is_64b_phy_reg_e822(low_addr, &high_addr)) { + if (!ice_is_64b_phy_reg_e82x(low_addr, &high_addr)) { ice_debug(hw, ICE_DBG_PTP, "Invalid 64b register addr 0x%08x\n", low_addr); return -EINVAL; } - err = ice_read_phy_reg_e822(hw, port, low_addr, &low); + err = ice_read_phy_reg_e82x(hw, port, low_addr, &low); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read from low register 0x%08x\n, err %d", low_addr, err); return err; } - err = ice_read_phy_reg_e822(hw, port, high_addr, &high); + err = ice_read_phy_reg_e82x(hw, port, high_addr, &high); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read from high register 0x%08x\n, err %d", high_addr, err); @@ -490,7 +493,7 @@ ice_read_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val) } /** - * ice_write_phy_reg_e822 - Write a PHY register + * ice_write_phy_reg_e82x - Write a PHY register * @hw: pointer to the HW struct * @port: PHY port to write to * @offset: PHY register offset to write @@ -499,12 +502,12 @@ ice_read_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val) * Write a PHY register for the given port over the device sideband queue. */ static int -ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val) +ice_write_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 val) { struct ice_sbq_msg_input msg = {0}; int err; - ice_fill_phy_msg_e822(&msg, port, offset); + ice_fill_phy_msg_e82x(&msg, port, offset); msg.opcode = ice_sbq_msg_wr; msg.data = val; @@ -519,7 +522,7 @@ ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val) } /** - * ice_write_40b_phy_reg_e822 - Write a 40b value to the PHY + * ice_write_40b_phy_reg_e82x - Write a 40b value to the PHY * @hw: pointer to the HW struct * @port: port to write to * @low_addr: offset of the low register @@ -529,7 +532,7 @@ ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val) * it up into two chunks, the lower 8 bits and the upper 32 bits. */ static int -ice_write_40b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) +ice_write_40b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) { u32 low, high; u16 high_addr; @@ -538,7 +541,7 @@ ice_write_40b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) /* Only operate on registers known to be split into a lower 8 bit * register and an upper 32 bit register. */ - if (!ice_is_40b_phy_reg_e822(low_addr, &high_addr)) { + if (!ice_is_40b_phy_reg_e82x(low_addr, &high_addr)) { ice_debug(hw, ICE_DBG_PTP, "Invalid 40b register addr 0x%08x\n", low_addr); return -EINVAL; @@ -547,14 +550,14 @@ ice_write_40b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) low = (u32)(val & P_REG_40B_LOW_M); high = (u32)(val >> P_REG_40B_HIGH_S); - err = ice_write_phy_reg_e822(hw, port, low_addr, low); + err = ice_write_phy_reg_e82x(hw, port, low_addr, low); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to write to low register 0x%08x\n, err %d", low_addr, err); return err; } - err = ice_write_phy_reg_e822(hw, port, high_addr, high); + err = ice_write_phy_reg_e82x(hw, port, high_addr, high); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to write to high register 0x%08x\n, err %d", high_addr, err); @@ -565,7 +568,7 @@ ice_write_40b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) } /** - * ice_write_64b_phy_reg_e822 - Write a 64bit value to PHY registers + * ice_write_64b_phy_reg_e82x - Write a 64bit value to PHY registers * @hw: pointer to the HW struct * @port: PHY port to read from * @low_addr: offset of the lower register to read from @@ -577,7 +580,7 @@ ice_write_40b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) * a 64bit value. */ static int -ice_write_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) +ice_write_64b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) { u32 low, high; u16 high_addr; @@ -586,7 +589,7 @@ ice_write_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) /* Only operate on registers known to be split into two 32bit * registers. */ - if (!ice_is_64b_phy_reg_e822(low_addr, &high_addr)) { + if (!ice_is_64b_phy_reg_e82x(low_addr, &high_addr)) { ice_debug(hw, ICE_DBG_PTP, "Invalid 64b register addr 0x%08x\n", low_addr); return -EINVAL; @@ -595,14 +598,14 @@ ice_write_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) low = lower_32_bits(val); high = upper_32_bits(val); - err = ice_write_phy_reg_e822(hw, port, low_addr, low); + err = ice_write_phy_reg_e82x(hw, port, low_addr, low); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to write to low register 0x%08x\n, err %d", low_addr, err); return err; } - err = ice_write_phy_reg_e822(hw, port, high_addr, high); + err = ice_write_phy_reg_e82x(hw, port, high_addr, high); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to write to high register 0x%08x\n, err %d", high_addr, err); @@ -613,7 +616,7 @@ ice_write_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) } /** - * ice_fill_quad_msg_e822 - Fill message data for quad register access + * ice_fill_quad_msg_e82x - Fill message data for quad register access * @msg: the PHY message buffer to fill in * @quad: the quad to access * @offset: the register offset @@ -622,7 +625,7 @@ ice_write_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) * multiple PHYs. */ static int -ice_fill_quad_msg_e822(struct ice_sbq_msg_input *msg, u8 quad, u16 offset) +ice_fill_quad_msg_e82x(struct ice_sbq_msg_input *msg, u8 quad, u16 offset) { u32 addr; @@ -631,7 +634,7 @@ ice_fill_quad_msg_e822(struct ice_sbq_msg_input *msg, u8 quad, u16 offset) msg->dest_dev = rmn_0; - if ((quad % ICE_QUADS_PER_PHY_E822) == 0) + if ((quad % ICE_QUADS_PER_PHY_E82X) == 0) addr = Q_0_BASE + offset; else addr = Q_1_BASE + offset; @@ -643,7 +646,7 @@ ice_fill_quad_msg_e822(struct ice_sbq_msg_input *msg, u8 quad, u16 offset) } /** - * ice_read_quad_reg_e822 - Read a PHY quad register + * ice_read_quad_reg_e82x - Read a PHY quad register * @hw: pointer to the HW struct * @quad: quad to read from * @offset: quad register offset to read @@ -653,12 +656,12 @@ ice_fill_quad_msg_e822(struct ice_sbq_msg_input *msg, u8 quad, u16 offset) * shared between multiple PHYs. */ int -ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val) +ice_read_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 *val) { struct ice_sbq_msg_input msg = {0}; int err; - err = ice_fill_quad_msg_e822(&msg, quad, offset); + err = ice_fill_quad_msg_e82x(&msg, quad, offset); if (err) return err; @@ -677,7 +680,7 @@ ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val) } /** - * ice_write_quad_reg_e822 - Write a PHY quad register + * ice_write_quad_reg_e82x - Write a PHY quad register * @hw: pointer to the HW struct * @quad: quad to write to * @offset: quad register offset to write @@ -687,12 +690,12 @@ ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val) * shared between multiple PHYs. */ int -ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val) +ice_write_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 val) { struct ice_sbq_msg_input msg = {0}; int err; - err = ice_fill_quad_msg_e822(&msg, quad, offset); + err = ice_fill_quad_msg_e82x(&msg, quad, offset); if (err) return err; @@ -710,7 +713,7 @@ ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val) } /** - * ice_read_phy_tstamp_e822 - Read a PHY timestamp out of the quad block + * ice_read_phy_tstamp_e82x - Read a PHY timestamp out of the quad block * @hw: pointer to the HW struct * @quad: the quad to read from * @idx: the timestamp index to read @@ -721,7 +724,7 @@ ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val) * family of devices. */ static int -ice_read_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp) +ice_read_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp) { u16 lo_addr, hi_addr; u32 lo, hi; @@ -730,14 +733,14 @@ ice_read_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp) lo_addr = (u16)TS_L(Q_REG_TX_MEMORY_BANK_START, idx); hi_addr = (u16)TS_H(Q_REG_TX_MEMORY_BANK_START, idx); - err = ice_read_quad_reg_e822(hw, quad, lo_addr, &lo); + err = ice_read_quad_reg_e82x(hw, quad, lo_addr, &lo); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read low PTP timestamp register, err %d\n", err); return err; } - err = ice_read_quad_reg_e822(hw, quad, hi_addr, &hi); + err = ice_read_quad_reg_e82x(hw, quad, hi_addr, &hi); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read high PTP timestamp register, err %d\n", err); @@ -754,7 +757,7 @@ ice_read_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp) } /** - * ice_clear_phy_tstamp_e822 - Clear a timestamp from the quad block + * ice_clear_phy_tstamp_e82x - Clear a timestamp from the quad block * @hw: pointer to the HW struct * @quad: the quad to read from * @idx: the timestamp index to reset @@ -770,18 +773,18 @@ ice_read_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp) * * To directly clear the contents of the timestamp block entirely, discarding * all timestamp data at once, software should instead use - * ice_ptp_reset_ts_memory_quad_e822(). + * ice_ptp_reset_ts_memory_quad_e82x(). * * This function should only be called on an idx whose bit is set according to * ice_get_phy_tx_tstamp_ready(). */ static int -ice_clear_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx) +ice_clear_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx) { u64 unused_tstamp; int err; - err = ice_read_phy_tstamp_e822(hw, quad, idx, &unused_tstamp); + err = ice_read_phy_tstamp_e82x(hw, quad, idx, &unused_tstamp); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read the timestamp register for quad %u, idx %u, err %d\n", quad, idx, err); @@ -792,33 +795,33 @@ ice_clear_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx) } /** - * ice_ptp_reset_ts_memory_quad_e822 - Clear all timestamps from the quad block + * ice_ptp_reset_ts_memory_quad_e82x - Clear all timestamps from the quad block * @hw: pointer to the HW struct * @quad: the quad to read from * * Clear all timestamps from the PHY quad block that is shared between the * internal PHYs on the E822 devices. */ -void ice_ptp_reset_ts_memory_quad_e822(struct ice_hw *hw, u8 quad) +void ice_ptp_reset_ts_memory_quad_e82x(struct ice_hw *hw, u8 quad) { - ice_write_quad_reg_e822(hw, quad, Q_REG_TS_CTRL, Q_REG_TS_CTRL_M); - ice_write_quad_reg_e822(hw, quad, Q_REG_TS_CTRL, ~(u32)Q_REG_TS_CTRL_M); + ice_write_quad_reg_e82x(hw, quad, Q_REG_TS_CTRL, Q_REG_TS_CTRL_M); + ice_write_quad_reg_e82x(hw, quad, Q_REG_TS_CTRL, ~(u32)Q_REG_TS_CTRL_M); } /** - * ice_ptp_reset_ts_memory_e822 - Clear all timestamps from all quad blocks + * ice_ptp_reset_ts_memory_e82x - Clear all timestamps from all quad blocks * @hw: pointer to the HW struct */ -static void ice_ptp_reset_ts_memory_e822(struct ice_hw *hw) +static void ice_ptp_reset_ts_memory_e82x(struct ice_hw *hw) { unsigned int quad; for (quad = 0; quad < ICE_MAX_QUAD; quad++) - ice_ptp_reset_ts_memory_quad_e822(hw, quad); + ice_ptp_reset_ts_memory_quad_e82x(hw, quad); } /** - * ice_read_cgu_reg_e822 - Read a CGU register + * ice_read_cgu_reg_e82x - Read a CGU register * @hw: pointer to the HW struct * @addr: Register address to read * @val: storage for register value read @@ -827,7 +830,7 @@ static void ice_ptp_reset_ts_memory_e822(struct ice_hw *hw) * applicable to E822 devices. */ static int -ice_read_cgu_reg_e822(struct ice_hw *hw, u32 addr, u32 *val) +ice_read_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 *val) { struct ice_sbq_msg_input cgu_msg; int err; @@ -850,7 +853,7 @@ ice_read_cgu_reg_e822(struct ice_hw *hw, u32 addr, u32 *val) } /** - * ice_write_cgu_reg_e822 - Write a CGU register + * ice_write_cgu_reg_e82x - Write a CGU register * @hw: pointer to the HW struct * @addr: Register address to write * @val: value to write into the register @@ -859,7 +862,7 @@ ice_read_cgu_reg_e822(struct ice_hw *hw, u32 addr, u32 *val) * applicable to E822 devices. */ static int -ice_write_cgu_reg_e822(struct ice_hw *hw, u32 addr, u32 val) +ice_write_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 val) { struct ice_sbq_msg_input cgu_msg; int err; @@ -925,7 +928,7 @@ static const char *ice_clk_src_str(u8 clk_src) } /** - * ice_cfg_cgu_pll_e822 - Configure the Clock Generation Unit + * ice_cfg_cgu_pll_e82x - Configure the Clock Generation Unit * @hw: pointer to the HW struct * @clk_freq: Clock frequency to program * @clk_src: Clock source to select (TIME_REF, or TCX0) @@ -934,7 +937,7 @@ static const char *ice_clk_src_str(u8 clk_src) * time reference, enabling the PLL which drives the PTP hardware clock. */ static int -ice_cfg_cgu_pll_e822(struct ice_hw *hw, enum ice_time_ref_freq clk_freq, +ice_cfg_cgu_pll_e82x(struct ice_hw *hw, enum ice_time_ref_freq clk_freq, enum ice_clk_src clk_src) { union tspll_ro_bwm_lf bwm_lf; @@ -963,15 +966,15 @@ ice_cfg_cgu_pll_e822(struct ice_hw *hw, enum ice_time_ref_freq clk_freq, return -EINVAL; } - err = ice_read_cgu_reg_e822(hw, NAC_CGU_DWORD9, &dw9.val); + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD9, &dw9.val); if (err) return err; - err = ice_read_cgu_reg_e822(hw, NAC_CGU_DWORD24, &dw24.val); + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val); if (err) return err; - err = ice_read_cgu_reg_e822(hw, TSPLL_RO_BWM_LF, &bwm_lf.val); + err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val); if (err) return err; @@ -986,43 +989,43 @@ ice_cfg_cgu_pll_e822(struct ice_hw *hw, enum ice_time_ref_freq clk_freq, if (dw24.field.ts_pll_enable) { dw24.field.ts_pll_enable = 0; - err = ice_write_cgu_reg_e822(hw, NAC_CGU_DWORD24, dw24.val); + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val); if (err) return err; } /* Set the frequency */ dw9.field.time_ref_freq_sel = clk_freq; - err = ice_write_cgu_reg_e822(hw, NAC_CGU_DWORD9, dw9.val); + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD9, dw9.val); if (err) return err; /* Configure the TS PLL feedback divisor */ - err = ice_read_cgu_reg_e822(hw, NAC_CGU_DWORD19, &dw19.val); + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD19, &dw19.val); if (err) return err; dw19.field.tspll_fbdiv_intgr = e822_cgu_params[clk_freq].feedback_div; dw19.field.tspll_ndivratio = 1; - err = ice_write_cgu_reg_e822(hw, NAC_CGU_DWORD19, dw19.val); + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD19, dw19.val); if (err) return err; /* Configure the TS PLL post divisor */ - err = ice_read_cgu_reg_e822(hw, NAC_CGU_DWORD22, &dw22.val); + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD22, &dw22.val); if (err) return err; dw22.field.time1588clk_div = e822_cgu_params[clk_freq].post_pll_div; dw22.field.time1588clk_sel_div2 = 0; - err = ice_write_cgu_reg_e822(hw, NAC_CGU_DWORD22, dw22.val); + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD22, dw22.val); if (err) return err; /* Configure the TS PLL pre divisor and clock source */ - err = ice_read_cgu_reg_e822(hw, NAC_CGU_DWORD24, &dw24.val); + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val); if (err) return err; @@ -1030,21 +1033,21 @@ ice_cfg_cgu_pll_e822(struct ice_hw *hw, enum ice_time_ref_freq clk_freq, dw24.field.tspll_fbdiv_frac = e822_cgu_params[clk_freq].frac_n_div; dw24.field.time_ref_sel = clk_src; - err = ice_write_cgu_reg_e822(hw, NAC_CGU_DWORD24, dw24.val); + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val); if (err) return err; /* Finally, enable the PLL */ dw24.field.ts_pll_enable = 1; - err = ice_write_cgu_reg_e822(hw, NAC_CGU_DWORD24, dw24.val); + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val); if (err) return err; /* Wait to verify if the PLL locks */ usleep_range(1000, 5000); - err = ice_read_cgu_reg_e822(hw, TSPLL_RO_BWM_LF, &bwm_lf.val); + err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val); if (err) return err; @@ -1064,18 +1067,18 @@ ice_cfg_cgu_pll_e822(struct ice_hw *hw, enum ice_time_ref_freq clk_freq, } /** - * ice_init_cgu_e822 - Initialize CGU with settings from firmware + * ice_init_cgu_e82x - Initialize CGU with settings from firmware * @hw: pointer to the HW structure * * Initialize the Clock Generation Unit of the E822 device. */ -static int ice_init_cgu_e822(struct ice_hw *hw) +static int ice_init_cgu_e82x(struct ice_hw *hw) { struct ice_ts_func_info *ts_info = &hw->func_caps.ts_func_info; union tspll_cntr_bist_settings cntr_bist; int err; - err = ice_read_cgu_reg_e822(hw, TSPLL_CNTR_BIST_SETTINGS, + err = ice_read_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS, &cntr_bist.val); if (err) return err; @@ -1084,7 +1087,7 @@ static int ice_init_cgu_e822(struct ice_hw *hw) cntr_bist.field.i_plllock_sel_0 = 0; cntr_bist.field.i_plllock_sel_1 = 0; - err = ice_write_cgu_reg_e822(hw, TSPLL_CNTR_BIST_SETTINGS, + err = ice_write_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS, cntr_bist.val); if (err) return err; @@ -1092,7 +1095,7 @@ static int ice_init_cgu_e822(struct ice_hw *hw) /* Configure the CGU PLL using the parameters from the function * capabilities. */ - err = ice_cfg_cgu_pll_e822(hw, ts_info->time_ref, + err = ice_cfg_cgu_pll_e82x(hw, ts_info->time_ref, (enum ice_clk_src)ts_info->clk_src); if (err) return err; @@ -1113,7 +1116,7 @@ static int ice_ptp_set_vernier_wl(struct ice_hw *hw) for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { int err; - err = ice_write_phy_reg_e822(hw, port, P_REG_WL, + err = ice_write_phy_reg_e82x(hw, port, P_REG_WL, PTP_VERNIER_WL); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to set vernier window length for port %u, err %d\n", @@ -1126,12 +1129,12 @@ static int ice_ptp_set_vernier_wl(struct ice_hw *hw) } /** - * ice_ptp_init_phc_e822 - Perform E822 specific PHC initialization + * ice_ptp_init_phc_e82x - Perform E822 specific PHC initialization * @hw: pointer to HW struct * * Perform PHC initialization steps specific to E822 devices. */ -static int ice_ptp_init_phc_e822(struct ice_hw *hw) +static int ice_ptp_init_phc_e82x(struct ice_hw *hw) { int err; u32 regval; @@ -1145,7 +1148,7 @@ static int ice_ptp_init_phc_e822(struct ice_hw *hw) wr32(hw, PF_SB_REM_DEV_CTL, regval); /* Initialize the Clock Generation Unit */ - err = ice_init_cgu_e822(hw); + err = ice_init_cgu_e82x(hw); if (err) return err; @@ -1154,7 +1157,7 @@ static int ice_ptp_init_phc_e822(struct ice_hw *hw) } /** - * ice_ptp_prep_phy_time_e822 - Prepare PHY port with initial time + * ice_ptp_prep_phy_time_e82x - Prepare PHY port with initial time * @hw: pointer to the HW struct * @time: Time to initialize the PHY port clocks to * @@ -1164,7 +1167,7 @@ static int ice_ptp_init_phc_e822(struct ice_hw *hw) * units of nominal nanoseconds. */ static int -ice_ptp_prep_phy_time_e822(struct ice_hw *hw, u32 time) +ice_ptp_prep_phy_time_e82x(struct ice_hw *hw, u32 time) { u64 phy_time; u8 port; @@ -1177,14 +1180,14 @@ ice_ptp_prep_phy_time_e822(struct ice_hw *hw, u32 time) for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { /* Tx case */ - err = ice_write_64b_phy_reg_e822(hw, port, + err = ice_write_64b_phy_reg_e82x(hw, port, P_REG_TX_TIMER_INC_PRE_L, phy_time); if (err) goto exit_err; /* Rx case */ - err = ice_write_64b_phy_reg_e822(hw, port, + err = ice_write_64b_phy_reg_e82x(hw, port, P_REG_RX_TIMER_INC_PRE_L, phy_time); if (err) @@ -1201,7 +1204,7 @@ exit_err: } /** - * ice_ptp_prep_port_adj_e822 - Prepare a single port for time adjust + * ice_ptp_prep_port_adj_e82x - Prepare a single port for time adjust * @hw: pointer to HW struct * @port: Port number to be programmed * @time: time in cycles to adjust the port Tx and Rx clocks @@ -1216,7 +1219,7 @@ exit_err: * Negative adjustments are supported using 2s complement arithmetic. */ static int -ice_ptp_prep_port_adj_e822(struct ice_hw *hw, u8 port, s64 time) +ice_ptp_prep_port_adj_e82x(struct ice_hw *hw, u8 port, s64 time) { u32 l_time, u_time; int err; @@ -1225,23 +1228,23 @@ ice_ptp_prep_port_adj_e822(struct ice_hw *hw, u8 port, s64 time) u_time = upper_32_bits(time); /* Tx case */ - err = ice_write_phy_reg_e822(hw, port, P_REG_TX_TIMER_INC_PRE_L, + err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_TIMER_INC_PRE_L, l_time); if (err) goto exit_err; - err = ice_write_phy_reg_e822(hw, port, P_REG_TX_TIMER_INC_PRE_U, + err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_TIMER_INC_PRE_U, u_time); if (err) goto exit_err; /* Rx case */ - err = ice_write_phy_reg_e822(hw, port, P_REG_RX_TIMER_INC_PRE_L, + err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_TIMER_INC_PRE_L, l_time); if (err) goto exit_err; - err = ice_write_phy_reg_e822(hw, port, P_REG_RX_TIMER_INC_PRE_U, + err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_TIMER_INC_PRE_U, u_time); if (err) goto exit_err; @@ -1255,7 +1258,7 @@ exit_err: } /** - * ice_ptp_prep_phy_adj_e822 - Prep PHY ports for a time adjustment + * ice_ptp_prep_phy_adj_e82x - Prep PHY ports for a time adjustment * @hw: pointer to HW struct * @adj: adjustment in nanoseconds * @@ -1264,7 +1267,7 @@ exit_err: * ICE_PTP_ADJ_TIME or ICE_PTP_ADJ_TIME_AT_TIME sync command. */ static int -ice_ptp_prep_phy_adj_e822(struct ice_hw *hw, s32 adj) +ice_ptp_prep_phy_adj_e82x(struct ice_hw *hw, s32 adj) { s64 cycles; u8 port; @@ -1281,7 +1284,7 @@ ice_ptp_prep_phy_adj_e822(struct ice_hw *hw, s32 adj) for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { int err; - err = ice_ptp_prep_port_adj_e822(hw, port, cycles); + err = ice_ptp_prep_port_adj_e82x(hw, port, cycles); if (err) return err; } @@ -1290,7 +1293,7 @@ ice_ptp_prep_phy_adj_e822(struct ice_hw *hw, s32 adj) } /** - * ice_ptp_prep_phy_incval_e822 - Prepare PHY ports for time adjustment + * ice_ptp_prep_phy_incval_e82x - Prepare PHY ports for time adjustment * @hw: pointer to HW struct * @incval: new increment value to prepare * @@ -1299,13 +1302,13 @@ ice_ptp_prep_phy_adj_e822(struct ice_hw *hw, s32 adj) * issuing an ICE_PTP_INIT_INCVAL command. */ static int -ice_ptp_prep_phy_incval_e822(struct ice_hw *hw, u64 incval) +ice_ptp_prep_phy_incval_e82x(struct ice_hw *hw, u64 incval) { int err; u8 port; for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { - err = ice_write_40b_phy_reg_e822(hw, port, P_REG_TIMETUS_L, + err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_TIMETUS_L, incval); if (err) goto exit_err; @@ -1337,7 +1340,7 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts) int err; /* Tx case */ - err = ice_read_64b_phy_reg_e822(hw, port, P_REG_TX_CAPTURE_L, tx_ts); + err = ice_read_64b_phy_reg_e82x(hw, port, P_REG_TX_CAPTURE_L, tx_ts); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read REG_TX_CAPTURE, err %d\n", err); @@ -1348,7 +1351,7 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts) (unsigned long long)*tx_ts); /* Rx case */ - err = ice_read_64b_phy_reg_e822(hw, port, P_REG_RX_CAPTURE_L, rx_ts); + err = ice_read_64b_phy_reg_e82x(hw, port, P_REG_RX_CAPTURE_L, rx_ts); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_CAPTURE, err %d\n", err); @@ -1362,7 +1365,7 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts) } /** - * ice_ptp_write_port_cmd_e822 - Prepare a single PHY port for a timer command + * ice_ptp_write_port_cmd_e82x - Prepare a single PHY port for a timer command * @hw: pointer to HW struct * @port: Port to which cmd has to be sent * @cmd: Command to be sent to the port @@ -1372,8 +1375,8 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts) * Do not use this function directly. If you want to configure exactly one * port, use ice_ptp_one_port_cmd() instead. */ -static int -ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) +static int ice_ptp_write_port_cmd_e82x(struct ice_hw *hw, u8 port, + enum ice_ptp_tmr_cmd cmd) { u32 cmd_val, val; u8 tmr_idx; @@ -1403,7 +1406,7 @@ ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd /* Tx case */ /* Read, modify, write */ - err = ice_read_phy_reg_e822(hw, port, P_REG_TX_TMR_CMD, &val); + err = ice_read_phy_reg_e82x(hw, port, P_REG_TX_TMR_CMD, &val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_TMR_CMD, err %d\n", err); @@ -1414,7 +1417,7 @@ ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd val &= ~TS_CMD_MASK; val |= cmd_val; - err = ice_write_phy_reg_e822(hw, port, P_REG_TX_TMR_CMD, val); + err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_TMR_CMD, val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to write back TX_TMR_CMD, err %d\n", err); @@ -1423,7 +1426,7 @@ ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd /* Rx case */ /* Read, modify, write */ - err = ice_read_phy_reg_e822(hw, port, P_REG_RX_TMR_CMD, &val); + err = ice_read_phy_reg_e82x(hw, port, P_REG_RX_TMR_CMD, &val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_TMR_CMD, err %d\n", err); @@ -1434,7 +1437,7 @@ ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd val &= ~TS_CMD_MASK; val |= cmd_val; - err = ice_write_phy_reg_e822(hw, port, P_REG_RX_TMR_CMD, val); + err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_TMR_CMD, val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to write back RX_TMR_CMD, err %d\n", err); @@ -1469,7 +1472,7 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port, else cmd = ICE_PTP_NOP; - err = ice_ptp_write_port_cmd_e822(hw, port, cmd); + err = ice_ptp_write_port_cmd_e82x(hw, port, cmd); if (err) return err; } @@ -1478,7 +1481,7 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port, } /** - * ice_ptp_port_cmd_e822 - Prepare all ports for a timer command + * ice_ptp_port_cmd_e82x - Prepare all ports for a timer command * @hw: pointer to the HW struct * @cmd: timer command to prepare * @@ -1486,14 +1489,14 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port, * command. */ static int -ice_ptp_port_cmd_e822(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +ice_ptp_port_cmd_e82x(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) { u8 port; for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { int err; - err = ice_ptp_write_port_cmd_e822(hw, port, cmd); + err = ice_ptp_write_port_cmd_e82x(hw, port, cmd); if (err) return err; } @@ -1509,7 +1512,7 @@ ice_ptp_port_cmd_e822(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) */ /** - * ice_phy_get_speed_and_fec_e822 - Get link speed and FEC based on serdes mode + * ice_phy_get_speed_and_fec_e82x - Get link speed and FEC based on serdes mode * @hw: pointer to HW struct * @port: the port to read from * @link_out: if non-NULL, holds link speed on success @@ -1519,7 +1522,7 @@ ice_ptp_port_cmd_e822(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) * algorithm. */ static int -ice_phy_get_speed_and_fec_e822(struct ice_hw *hw, u8 port, +ice_phy_get_speed_and_fec_e82x(struct ice_hw *hw, u8 port, enum ice_ptp_link_spd *link_out, enum ice_ptp_fec_mode *fec_out) { @@ -1528,7 +1531,7 @@ ice_phy_get_speed_and_fec_e822(struct ice_hw *hw, u8 port, u32 serdes; int err; - err = ice_read_phy_reg_e822(hw, port, P_REG_LINK_SPEED, &serdes); + err = ice_read_phy_reg_e82x(hw, port, P_REG_LINK_SPEED, &serdes); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read serdes info\n"); return err; @@ -1585,18 +1588,18 @@ ice_phy_get_speed_and_fec_e822(struct ice_hw *hw, u8 port, } /** - * ice_phy_cfg_lane_e822 - Configure PHY quad for single/multi-lane timestamp + * ice_phy_cfg_lane_e82x - Configure PHY quad for single/multi-lane timestamp * @hw: pointer to HW struct * @port: to configure the quad for */ -static void ice_phy_cfg_lane_e822(struct ice_hw *hw, u8 port) +static void ice_phy_cfg_lane_e82x(struct ice_hw *hw, u8 port) { enum ice_ptp_link_spd link_spd; int err; u32 val; u8 quad; - err = ice_phy_get_speed_and_fec_e822(hw, port, &link_spd, NULL); + err = ice_phy_get_speed_and_fec_e82x(hw, port, &link_spd, NULL); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to get PHY link speed, err %d\n", err); @@ -1605,7 +1608,7 @@ static void ice_phy_cfg_lane_e822(struct ice_hw *hw, u8 port) quad = port / ICE_PORTS_PER_QUAD; - err = ice_read_quad_reg_e822(hw, quad, Q_REG_TX_MEM_GBL_CFG, &val); + err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, &val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_MEM_GLB_CFG, err %d\n", err); @@ -1617,7 +1620,7 @@ static void ice_phy_cfg_lane_e822(struct ice_hw *hw, u8 port) else val |= Q_REG_TX_MEM_GBL_CFG_LANE_TYPE_M; - err = ice_write_quad_reg_e822(hw, quad, Q_REG_TX_MEM_GBL_CFG, val); + err = ice_write_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to write back TX_MEM_GBL_CFG, err %d\n", err); @@ -1626,7 +1629,7 @@ static void ice_phy_cfg_lane_e822(struct ice_hw *hw, u8 port) } /** - * ice_phy_cfg_uix_e822 - Configure Serdes UI to TU conversion for E822 + * ice_phy_cfg_uix_e82x - Configure Serdes UI to TU conversion for E822 * @hw: pointer to the HW structure * @port: the port to configure * @@ -1671,12 +1674,12 @@ static void ice_phy_cfg_lane_e822(struct ice_hw *hw, u8 port) * a divide by 390,625,000. This does lose some precision, but avoids * miscalculation due to arithmetic overflow. */ -static int ice_phy_cfg_uix_e822(struct ice_hw *hw, u8 port) +static int ice_phy_cfg_uix_e82x(struct ice_hw *hw, u8 port) { u64 cur_freq, clk_incval, tu_per_sec, uix; int err; - cur_freq = ice_e822_pll_freq(ice_e822_time_ref(hw)); + cur_freq = ice_e82x_pll_freq(ice_e82x_time_ref(hw)); clk_incval = ice_ptp_read_src_incval(hw); /* Calculate TUs per second divided by 256 */ @@ -1688,7 +1691,7 @@ static int ice_phy_cfg_uix_e822(struct ice_hw *hw, u8 port) /* Program the 10Gb/40Gb conversion ratio */ uix = div_u64(tu_per_sec * LINE_UI_10G_40G, 390625000); - err = ice_write_64b_phy_reg_e822(hw, port, P_REG_UIX66_10G_40G_L, + err = ice_write_64b_phy_reg_e82x(hw, port, P_REG_UIX66_10G_40G_L, uix); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to write UIX66_10G_40G, err %d\n", @@ -1699,7 +1702,7 @@ static int ice_phy_cfg_uix_e822(struct ice_hw *hw, u8 port) /* Program the 25Gb/100Gb conversion ratio */ uix = div_u64(tu_per_sec * LINE_UI_25G_100G, 390625000); - err = ice_write_64b_phy_reg_e822(hw, port, P_REG_UIX66_25G_100G_L, + err = ice_write_64b_phy_reg_e82x(hw, port, P_REG_UIX66_25G_100G_L, uix); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to write UIX66_25G_100G, err %d\n", @@ -1711,7 +1714,7 @@ static int ice_phy_cfg_uix_e822(struct ice_hw *hw, u8 port) } /** - * ice_phy_cfg_parpcs_e822 - Configure TUs per PAR/PCS clock cycle + * ice_phy_cfg_parpcs_e82x - Configure TUs per PAR/PCS clock cycle * @hw: pointer to the HW struct * @port: port to configure * @@ -1753,18 +1756,18 @@ static int ice_phy_cfg_uix_e822(struct ice_hw *hw, u8 port) * frequency is ~29 bits, so multiplying them together should fit within the * 64 bit arithmetic. */ -static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port) +static int ice_phy_cfg_parpcs_e82x(struct ice_hw *hw, u8 port) { u64 cur_freq, clk_incval, tu_per_sec, phy_tus; enum ice_ptp_link_spd link_spd; enum ice_ptp_fec_mode fec_mode; int err; - err = ice_phy_get_speed_and_fec_e822(hw, port, &link_spd, &fec_mode); + err = ice_phy_get_speed_and_fec_e82x(hw, port, &link_spd, &fec_mode); if (err) return err; - cur_freq = ice_e822_pll_freq(ice_e822_time_ref(hw)); + cur_freq = ice_e82x_pll_freq(ice_e82x_time_ref(hw)); clk_incval = ice_ptp_read_src_incval(hw); /* Calculate TUs per cycle of the PHC clock */ @@ -1784,7 +1787,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port) else phy_tus = 0; - err = ice_write_40b_phy_reg_e822(hw, port, P_REG_PAR_TX_TUS_L, + err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_PAR_TX_TUS_L, phy_tus); if (err) return err; @@ -1796,7 +1799,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port) else phy_tus = 0; - err = ice_write_40b_phy_reg_e822(hw, port, P_REG_PAR_RX_TUS_L, + err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_PAR_RX_TUS_L, phy_tus); if (err) return err; @@ -1808,7 +1811,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port) else phy_tus = 0; - err = ice_write_40b_phy_reg_e822(hw, port, P_REG_PCS_TX_TUS_L, + err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_PCS_TX_TUS_L, phy_tus); if (err) return err; @@ -1820,7 +1823,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port) else phy_tus = 0; - err = ice_write_40b_phy_reg_e822(hw, port, P_REG_PCS_RX_TUS_L, + err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_PCS_RX_TUS_L, phy_tus); if (err) return err; @@ -1832,7 +1835,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port) else phy_tus = 0; - err = ice_write_40b_phy_reg_e822(hw, port, P_REG_DESK_PAR_TX_TUS_L, + err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_DESK_PAR_TX_TUS_L, phy_tus); if (err) return err; @@ -1844,7 +1847,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port) else phy_tus = 0; - err = ice_write_40b_phy_reg_e822(hw, port, P_REG_DESK_PAR_RX_TUS_L, + err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_DESK_PAR_RX_TUS_L, phy_tus); if (err) return err; @@ -1856,7 +1859,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port) else phy_tus = 0; - err = ice_write_40b_phy_reg_e822(hw, port, P_REG_DESK_PCS_TX_TUS_L, + err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_DESK_PCS_TX_TUS_L, phy_tus); if (err) return err; @@ -1868,23 +1871,23 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port) else phy_tus = 0; - return ice_write_40b_phy_reg_e822(hw, port, P_REG_DESK_PCS_RX_TUS_L, + return ice_write_40b_phy_reg_e82x(hw, port, P_REG_DESK_PCS_RX_TUS_L, phy_tus); } /** - * ice_calc_fixed_tx_offset_e822 - Calculated Fixed Tx offset for a port + * ice_calc_fixed_tx_offset_e82x - Calculated Fixed Tx offset for a port * @hw: pointer to the HW struct * @link_spd: the Link speed to calculate for * * Calculate the fixed offset due to known static latency data. */ static u64 -ice_calc_fixed_tx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd) +ice_calc_fixed_tx_offset_e82x(struct ice_hw *hw, enum ice_ptp_link_spd link_spd) { u64 cur_freq, clk_incval, tu_per_sec, fixed_offset; - cur_freq = ice_e822_pll_freq(ice_e822_time_ref(hw)); + cur_freq = ice_e82x_pll_freq(ice_e82x_time_ref(hw)); clk_incval = ice_ptp_read_src_incval(hw); /* Calculate TUs per second */ @@ -1904,7 +1907,7 @@ ice_calc_fixed_tx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd) } /** - * ice_phy_cfg_tx_offset_e822 - Configure total Tx timestamp offset + * ice_phy_cfg_tx_offset_e82x - Configure total Tx timestamp offset * @hw: pointer to the HW struct * @port: the PHY port to configure * @@ -1926,7 +1929,7 @@ ice_calc_fixed_tx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd) * Returns zero on success, -EBUSY if the hardware vernier offset * calibration has not completed, or another error code on failure. */ -int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port) +int ice_phy_cfg_tx_offset_e82x(struct ice_hw *hw, u8 port) { enum ice_ptp_link_spd link_spd; enum ice_ptp_fec_mode fec_mode; @@ -1935,7 +1938,7 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port) u32 reg; /* Nothing to do if we've already programmed the offset */ - err = ice_read_phy_reg_e822(hw, port, P_REG_TX_OR, ®); + err = ice_read_phy_reg_e82x(hw, port, P_REG_TX_OR, ®); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_OR for port %u, err %d\n", port, err); @@ -1945,7 +1948,7 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port) if (reg) return 0; - err = ice_read_phy_reg_e822(hw, port, P_REG_TX_OV_STATUS, ®); + err = ice_read_phy_reg_e82x(hw, port, P_REG_TX_OV_STATUS, ®); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_OV_STATUS for port %u, err %d\n", port, err); @@ -1955,11 +1958,11 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port) if (!(reg & P_REG_TX_OV_STATUS_OV_M)) return -EBUSY; - err = ice_phy_get_speed_and_fec_e822(hw, port, &link_spd, &fec_mode); + err = ice_phy_get_speed_and_fec_e82x(hw, port, &link_spd, &fec_mode); if (err) return err; - total_offset = ice_calc_fixed_tx_offset_e822(hw, link_spd); + total_offset = ice_calc_fixed_tx_offset_e82x(hw, link_spd); /* Read the first Vernier offset from the PHY register and add it to * the total offset. @@ -1970,7 +1973,7 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port) link_spd == ICE_PTP_LNK_SPD_25G_RS || link_spd == ICE_PTP_LNK_SPD_40G || link_spd == ICE_PTP_LNK_SPD_50G) { - err = ice_read_64b_phy_reg_e822(hw, port, + err = ice_read_64b_phy_reg_e82x(hw, port, P_REG_PAR_PCS_TX_OFFSET_L, &val); if (err) @@ -1985,7 +1988,7 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port) */ if (link_spd == ICE_PTP_LNK_SPD_50G_RS || link_spd == ICE_PTP_LNK_SPD_100G_RS) { - err = ice_read_64b_phy_reg_e822(hw, port, + err = ice_read_64b_phy_reg_e82x(hw, port, P_REG_PAR_TX_TIME_L, &val); if (err) @@ -1998,12 +2001,12 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port) * PHY and indicate that the Tx offset is ready. After this, * timestamps will be enabled. */ - err = ice_write_64b_phy_reg_e822(hw, port, P_REG_TOTAL_TX_OFFSET_L, + err = ice_write_64b_phy_reg_e82x(hw, port, P_REG_TOTAL_TX_OFFSET_L, total_offset); if (err) return err; - err = ice_write_phy_reg_e822(hw, port, P_REG_TX_OR, 1); + err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_OR, 1); if (err) return err; @@ -2014,7 +2017,7 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port) } /** - * ice_phy_calc_pmd_adj_e822 - Calculate PMD adjustment for Rx + * ice_phy_calc_pmd_adj_e82x - Calculate PMD adjustment for Rx * @hw: pointer to the HW struct * @port: the PHY port to adjust for * @link_spd: the current link speed of the PHY @@ -2026,7 +2029,7 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port) * various delays caused when receiving a packet. */ static int -ice_phy_calc_pmd_adj_e822(struct ice_hw *hw, u8 port, +ice_phy_calc_pmd_adj_e82x(struct ice_hw *hw, u8 port, enum ice_ptp_link_spd link_spd, enum ice_ptp_fec_mode fec_mode, u64 *pmd_adj) { @@ -2035,7 +2038,7 @@ ice_phy_calc_pmd_adj_e822(struct ice_hw *hw, u8 port, u32 val; int err; - err = ice_read_phy_reg_e822(hw, port, P_REG_PMD_ALIGNMENT, &val); + err = ice_read_phy_reg_e82x(hw, port, P_REG_PMD_ALIGNMENT, &val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read PMD alignment, err %d\n", err); @@ -2044,7 +2047,7 @@ ice_phy_calc_pmd_adj_e822(struct ice_hw *hw, u8 port, pmd_align = (u8)val; - cur_freq = ice_e822_pll_freq(ice_e822_time_ref(hw)); + cur_freq = ice_e82x_pll_freq(ice_e82x_time_ref(hw)); clk_incval = ice_ptp_read_src_incval(hw); /* Calculate TUs per second */ @@ -2123,7 +2126,7 @@ ice_phy_calc_pmd_adj_e822(struct ice_hw *hw, u8 port, u64 cycle_adj; u8 rx_cycle; - err = ice_read_phy_reg_e822(hw, port, P_REG_RX_40_TO_160_CNT, + err = ice_read_phy_reg_e82x(hw, port, P_REG_RX_40_TO_160_CNT, &val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read 25G-RS Rx cycle count, err %d\n", @@ -2145,7 +2148,7 @@ ice_phy_calc_pmd_adj_e822(struct ice_hw *hw, u8 port, u64 cycle_adj; u8 rx_cycle; - err = ice_read_phy_reg_e822(hw, port, P_REG_RX_80_TO_160_CNT, + err = ice_read_phy_reg_e82x(hw, port, P_REG_RX_80_TO_160_CNT, &val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read 50G-RS Rx cycle count, err %d\n", @@ -2172,18 +2175,18 @@ ice_phy_calc_pmd_adj_e822(struct ice_hw *hw, u8 port, } /** - * ice_calc_fixed_rx_offset_e822 - Calculated the fixed Rx offset for a port + * ice_calc_fixed_rx_offset_e82x - Calculated the fixed Rx offset for a port * @hw: pointer to HW struct * @link_spd: The Link speed to calculate for * * Determine the fixed Rx latency for a given link speed. */ static u64 -ice_calc_fixed_rx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd) +ice_calc_fixed_rx_offset_e82x(struct ice_hw *hw, enum ice_ptp_link_spd link_spd) { u64 cur_freq, clk_incval, tu_per_sec, fixed_offset; - cur_freq = ice_e822_pll_freq(ice_e822_time_ref(hw)); + cur_freq = ice_e82x_pll_freq(ice_e82x_time_ref(hw)); clk_incval = ice_ptp_read_src_incval(hw); /* Calculate TUs per second */ @@ -2203,7 +2206,7 @@ ice_calc_fixed_rx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd) } /** - * ice_phy_cfg_rx_offset_e822 - Configure total Rx timestamp offset + * ice_phy_cfg_rx_offset_e82x - Configure total Rx timestamp offset * @hw: pointer to the HW struct * @port: the PHY port to configure * @@ -2229,7 +2232,7 @@ ice_calc_fixed_rx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd) * Returns zero on success, -EBUSY if the hardware vernier offset * calibration has not completed, or another error code on failure. */ -int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) +int ice_phy_cfg_rx_offset_e82x(struct ice_hw *hw, u8 port) { enum ice_ptp_link_spd link_spd; enum ice_ptp_fec_mode fec_mode; @@ -2238,7 +2241,7 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) u32 reg; /* Nothing to do if we've already programmed the offset */ - err = ice_read_phy_reg_e822(hw, port, P_REG_RX_OR, ®); + err = ice_read_phy_reg_e82x(hw, port, P_REG_RX_OR, ®); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_OR for port %u, err %d\n", port, err); @@ -2248,7 +2251,7 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) if (reg) return 0; - err = ice_read_phy_reg_e822(hw, port, P_REG_RX_OV_STATUS, ®); + err = ice_read_phy_reg_e82x(hw, port, P_REG_RX_OV_STATUS, ®); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_OV_STATUS for port %u, err %d\n", port, err); @@ -2258,16 +2261,16 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) if (!(reg & P_REG_RX_OV_STATUS_OV_M)) return -EBUSY; - err = ice_phy_get_speed_and_fec_e822(hw, port, &link_spd, &fec_mode); + err = ice_phy_get_speed_and_fec_e82x(hw, port, &link_spd, &fec_mode); if (err) return err; - total_offset = ice_calc_fixed_rx_offset_e822(hw, link_spd); + total_offset = ice_calc_fixed_rx_offset_e82x(hw, link_spd); /* Read the first Vernier offset from the PHY register and add it to * the total offset. */ - err = ice_read_64b_phy_reg_e822(hw, port, + err = ice_read_64b_phy_reg_e82x(hw, port, P_REG_PAR_PCS_RX_OFFSET_L, &val); if (err) @@ -2282,7 +2285,7 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) link_spd == ICE_PTP_LNK_SPD_50G || link_spd == ICE_PTP_LNK_SPD_50G_RS || link_spd == ICE_PTP_LNK_SPD_100G_RS) { - err = ice_read_64b_phy_reg_e822(hw, port, + err = ice_read_64b_phy_reg_e82x(hw, port, P_REG_PAR_RX_TIME_L, &val); if (err) @@ -2292,7 +2295,7 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) } /* In addition, Rx must account for the PMD alignment */ - err = ice_phy_calc_pmd_adj_e822(hw, port, link_spd, fec_mode, &pmd); + err = ice_phy_calc_pmd_adj_e82x(hw, port, link_spd, fec_mode, &pmd); if (err) return err; @@ -2308,12 +2311,12 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) * PHY and indicate that the Rx offset is ready. After this, * timestamps will be enabled. */ - err = ice_write_64b_phy_reg_e822(hw, port, P_REG_TOTAL_RX_OFFSET_L, + err = ice_write_64b_phy_reg_e82x(hw, port, P_REG_TOTAL_RX_OFFSET_L, total_offset); if (err) return err; - err = ice_write_phy_reg_e822(hw, port, P_REG_RX_OR, 1); + err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_OR, 1); if (err) return err; @@ -2324,7 +2327,7 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) } /** - * ice_read_phy_and_phc_time_e822 - Simultaneously capture PHC and PHY time + * ice_read_phy_and_phc_time_e82x - Simultaneously capture PHC and PHY time * @hw: pointer to the HW struct * @port: the PHY port to read * @phy_time: on return, the 64bit PHY timer value @@ -2334,7 +2337,7 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) * and PHC timer values. */ static int -ice_read_phy_and_phc_time_e822(struct ice_hw *hw, u8 port, u64 *phy_time, +ice_read_phy_and_phc_time_e82x(struct ice_hw *hw, u8 port, u64 *phy_time, u64 *phc_time) { u64 tx_time, rx_time; @@ -2381,7 +2384,7 @@ ice_read_phy_and_phc_time_e822(struct ice_hw *hw, u8 port, u64 *phy_time, } /** - * ice_sync_phy_timer_e822 - Synchronize the PHY timer with PHC timer + * ice_sync_phy_timer_e82x - Synchronize the PHY timer with PHC timer * @hw: pointer to the HW struct * @port: the PHY port to synchronize * @@ -2392,7 +2395,7 @@ ice_read_phy_and_phc_time_e822(struct ice_hw *hw, u8 port, u64 *phy_time, * to the PHY timer in order to ensure it reads the same value as the * primary PHC timer. */ -static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port) +static int ice_sync_phy_timer_e82x(struct ice_hw *hw, u8 port) { u64 phc_time, phy_time, difference; int err; @@ -2402,7 +2405,7 @@ static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port) return -EBUSY; } - err = ice_read_phy_and_phc_time_e822(hw, port, &phy_time, &phc_time); + err = ice_read_phy_and_phc_time_e82x(hw, port, &phy_time, &phc_time); if (err) goto err_unlock; @@ -2416,7 +2419,7 @@ static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port) */ difference = phc_time - phy_time; - err = ice_ptp_prep_port_adj_e822(hw, port, (s64)difference); + err = ice_ptp_prep_port_adj_e82x(hw, port, (s64)difference); if (err) goto err_unlock; @@ -2433,7 +2436,7 @@ static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port) /* Re-capture the timer values to flush the command registers and * verify that the time was properly adjusted. */ - err = ice_read_phy_and_phc_time_e822(hw, port, &phy_time, &phc_time); + err = ice_read_phy_and_phc_time_e82x(hw, port, &phy_time, &phc_time); if (err) goto err_unlock; @@ -2452,7 +2455,7 @@ err_unlock: } /** - * ice_stop_phy_timer_e822 - Stop the PHY clock timer + * ice_stop_phy_timer_e82x - Stop the PHY clock timer * @hw: pointer to the HW struct * @port: the PHY port to stop * @soft_reset: if true, hold the SOFT_RESET bit of P_REG_PS @@ -2462,36 +2465,36 @@ err_unlock: * initialized or when link speed changes. */ int -ice_stop_phy_timer_e822(struct ice_hw *hw, u8 port, bool soft_reset) +ice_stop_phy_timer_e82x(struct ice_hw *hw, u8 port, bool soft_reset) { int err; u32 val; - err = ice_write_phy_reg_e822(hw, port, P_REG_TX_OR, 0); + err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_OR, 0); if (err) return err; - err = ice_write_phy_reg_e822(hw, port, P_REG_RX_OR, 0); + err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_OR, 0); if (err) return err; - err = ice_read_phy_reg_e822(hw, port, P_REG_PS, &val); + err = ice_read_phy_reg_e82x(hw, port, P_REG_PS, &val); if (err) return err; val &= ~P_REG_PS_START_M; - err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val); + err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val); if (err) return err; val &= ~P_REG_PS_ENA_CLK_M; - err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val); + err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val); if (err) return err; if (soft_reset) { val |= P_REG_PS_SFT_RESET_M; - err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val); + err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val); if (err) return err; } @@ -2502,7 +2505,7 @@ ice_stop_phy_timer_e822(struct ice_hw *hw, u8 port, bool soft_reset) } /** - * ice_start_phy_timer_e822 - Start the PHY clock timer + * ice_start_phy_timer_e82x - Start the PHY clock timer * @hw: pointer to the HW struct * @port: the PHY port to start * @@ -2512,7 +2515,7 @@ ice_stop_phy_timer_e822(struct ice_hw *hw, u8 port, bool soft_reset) * * Hardware will take Vernier measurements on Tx or Rx of packets. */ -int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port) +int ice_start_phy_timer_e82x(struct ice_hw *hw, u8 port) { u32 lo, hi, val; u64 incval; @@ -2521,17 +2524,17 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port) tmr_idx = ice_get_ptp_src_clock_index(hw); - err = ice_stop_phy_timer_e822(hw, port, false); + err = ice_stop_phy_timer_e82x(hw, port, false); if (err) return err; - ice_phy_cfg_lane_e822(hw, port); + ice_phy_cfg_lane_e82x(hw, port); - err = ice_phy_cfg_uix_e822(hw, port); + err = ice_phy_cfg_uix_e82x(hw, port); if (err) return err; - err = ice_phy_cfg_parpcs_e822(hw, port); + err = ice_phy_cfg_parpcs_e82x(hw, port); if (err) return err; @@ -2539,7 +2542,7 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port) hi = rd32(hw, GLTSYN_INCVAL_H(tmr_idx)); incval = (u64)hi << 32 | lo; - err = ice_write_40b_phy_reg_e822(hw, port, P_REG_TIMETUS_L, incval); + err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_TIMETUS_L, incval); if (err) return err; @@ -2552,22 +2555,22 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port) ice_ptp_exec_tmr_cmd(hw); - err = ice_read_phy_reg_e822(hw, port, P_REG_PS, &val); + err = ice_read_phy_reg_e82x(hw, port, P_REG_PS, &val); if (err) return err; val |= P_REG_PS_SFT_RESET_M; - err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val); + err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val); if (err) return err; val |= P_REG_PS_START_M; - err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val); + err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val); if (err) return err; val &= ~P_REG_PS_SFT_RESET_M; - err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val); + err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val); if (err) return err; @@ -2578,18 +2581,18 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port) ice_ptp_exec_tmr_cmd(hw); val |= P_REG_PS_ENA_CLK_M; - err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val); + err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val); if (err) return err; val |= P_REG_PS_LOAD_OFFSET_M; - err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val); + err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val); if (err) return err; ice_ptp_exec_tmr_cmd(hw); - err = ice_sync_phy_timer_e822(hw, port); + err = ice_sync_phy_timer_e82x(hw, port); if (err) return err; @@ -2599,7 +2602,7 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port) } /** - * ice_get_phy_tx_tstamp_ready_e822 - Read Tx memory status register + * ice_get_phy_tx_tstamp_ready_e82x - Read Tx memory status register * @hw: pointer to the HW struct * @quad: the timestamp quad to read from * @tstamp_ready: contents of the Tx memory status register @@ -2609,19 +2612,19 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port) * ready to be captured from the PHY timestamp block. */ static int -ice_get_phy_tx_tstamp_ready_e822(struct ice_hw *hw, u8 quad, u64 *tstamp_ready) +ice_get_phy_tx_tstamp_ready_e82x(struct ice_hw *hw, u8 quad, u64 *tstamp_ready) { u32 hi, lo; int err; - err = ice_read_quad_reg_e822(hw, quad, Q_REG_TX_MEMORY_STATUS_U, &hi); + err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEMORY_STATUS_U, &hi); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_MEMORY_STATUS_U for quad %u, err %d\n", quad, err); return err; } - err = ice_read_quad_reg_e822(hw, quad, Q_REG_TX_MEMORY_STATUS_L, &lo); + err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEMORY_STATUS_L, &lo); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_MEMORY_STATUS_L for quad %u, err %d\n", quad, err); @@ -3307,7 +3310,7 @@ void ice_ptp_init_phy_model(struct ice_hw *hw) if (ice_is_e810(hw)) hw->phy_model = ICE_PHY_E810; else - hw->phy_model = ICE_PHY_E822; + hw->phy_model = ICE_PHY_E82X; } /** @@ -3332,8 +3335,8 @@ static int ice_ptp_tmr_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) case ICE_PHY_E810: err = ice_ptp_port_cmd_e810(hw, cmd); break; - case ICE_PHY_E822: - err = ice_ptp_port_cmd_e822(hw, cmd); + case ICE_PHY_E82X: + err = ice_ptp_port_cmd_e82x(hw, cmd); break; default: err = -EOPNOTSUPP; @@ -3384,8 +3387,8 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time) case ICE_PHY_E810: err = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF); break; - case ICE_PHY_E822: - err = ice_ptp_prep_phy_time_e822(hw, time & 0xFFFFFFFF); + case ICE_PHY_E82X: + err = ice_ptp_prep_phy_time_e82x(hw, time & 0xFFFFFFFF); break; default: err = -EOPNOTSUPP; @@ -3426,8 +3429,8 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval) case ICE_PHY_E810: err = ice_ptp_prep_phy_incval_e810(hw, incval); break; - case ICE_PHY_E822: - err = ice_ptp_prep_phy_incval_e822(hw, incval); + case ICE_PHY_E82X: + err = ice_ptp_prep_phy_incval_e82x(hw, incval); break; default: err = -EOPNOTSUPP; @@ -3492,8 +3495,8 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) case ICE_PHY_E810: err = ice_ptp_prep_phy_adj_e810(hw, adj); break; - case ICE_PHY_E822: - err = ice_ptp_prep_phy_adj_e822(hw, adj); + case ICE_PHY_E82X: + err = ice_ptp_prep_phy_adj_e82x(hw, adj); break; default: err = -EOPNOTSUPP; @@ -3521,8 +3524,8 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) switch (hw->phy_model) { case ICE_PHY_E810: return ice_read_phy_tstamp_e810(hw, block, idx, tstamp); - case ICE_PHY_E822: - return ice_read_phy_tstamp_e822(hw, block, idx, tstamp); + case ICE_PHY_E82X: + return ice_read_phy_tstamp_e82x(hw, block, idx, tstamp); default: return -EOPNOTSUPP; } @@ -3549,8 +3552,8 @@ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) switch (hw->phy_model) { case ICE_PHY_E810: return ice_clear_phy_tstamp_e810(hw, block, idx); - case ICE_PHY_E822: - return ice_clear_phy_tstamp_e822(hw, block, idx); + case ICE_PHY_E82X: + return ice_clear_phy_tstamp_e82x(hw, block, idx); default: return -EOPNOTSUPP; } @@ -3608,8 +3611,8 @@ static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx) void ice_ptp_reset_ts_memory(struct ice_hw *hw) { switch (hw->phy_model) { - case ICE_PHY_E822: - ice_ptp_reset_ts_memory_e822(hw); + case ICE_PHY_E82X: + ice_ptp_reset_ts_memory_e82x(hw); break; case ICE_PHY_E810: default: @@ -3636,8 +3639,8 @@ int ice_ptp_init_phc(struct ice_hw *hw) switch (hw->phy_model) { case ICE_PHY_E810: return ice_ptp_init_phc_e810(hw); - case ICE_PHY_E822: - return ice_ptp_init_phc_e822(hw); + case ICE_PHY_E82X: + return ice_ptp_init_phc_e82x(hw); default: return -EOPNOTSUPP; } @@ -3660,8 +3663,8 @@ int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready) case ICE_PHY_E810: return ice_get_phy_tx_tstamp_ready_e810(hw, block, tstamp_ready); - case ICE_PHY_E822: - return ice_get_phy_tx_tstamp_ready_e822(hw, block, + case ICE_PHY_E82X: + return ice_get_phy_tx_tstamp_ready_e82x(hw, block, tstamp_ready); break; default: @@ -3942,7 +3945,7 @@ int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num) case ICE_DEV_ID_E823C_QSFP: case ICE_DEV_ID_E823C_SFP: case ICE_DEV_ID_E823C_SGMII: - *pin_num = ICE_E822_RCLK_PINS_NUM; + *pin_num = ICE_E82X_RCLK_PINS_NUM; ret = 0; if (hw->cgu_part_number == ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032) @@ -3961,3 +3964,57 @@ int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num) return ret; } + +/** + * ice_cgu_get_output_pin_state_caps - get output pin state capabilities + * @hw: pointer to the hw struct + * @pin_id: id of a pin + * @caps: capabilities to modify + * + * Return: + * * 0 - success, state capabilities were modified + * * negative - failure, capabilities were not modified + */ +int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id, + unsigned long *caps) +{ + bool can_change = true; + + switch (hw->device_id) { + case ICE_DEV_ID_E810C_SFP: + if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3) + can_change = false; + break; + case ICE_DEV_ID_E810C_QSFP: + if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3 || pin_id == ZL_OUT4) + can_change = false; + break; + case ICE_DEV_ID_E823L_10G_BASE_T: + case ICE_DEV_ID_E823L_1GBE: + case ICE_DEV_ID_E823L_BACKPLANE: + case ICE_DEV_ID_E823L_QSFP: + case ICE_DEV_ID_E823L_SFP: + case ICE_DEV_ID_E823C_10G_BASE_T: + case ICE_DEV_ID_E823C_BACKPLANE: + case ICE_DEV_ID_E823C_QSFP: + case ICE_DEV_ID_E823C_SFP: + case ICE_DEV_ID_E823C_SGMII: + if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032 && + pin_id == ZL_OUT2) + can_change = false; + else if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384 && + pin_id == SI_OUT1) + can_change = false; + break; + default: + return -EINVAL; + } + if (can_change) + *caps |= DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; + else + *caps &= ~DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; + + return 0; +} diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 36aeeef99ec0..1f3e03124430 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -42,7 +42,7 @@ enum ice_ptp_fec_mode { }; /** - * struct ice_time_ref_info_e822 + * 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 @@ -50,14 +50,14 @@ enum ice_ptp_fec_mode { * Characteristic information for the various TIME_REF sources possible in the * E822 devices */ -struct ice_time_ref_info_e822 { +struct ice_time_ref_info_e82x { u64 pll_freq; u64 nominal_incval; u8 pps_delay; }; /** - * struct ice_vernier_info_e822 + * struct ice_vernier_info_e82x * @tx_par_clk: Frequency used to calculate P_REG_PAR_TX_TUS * @rx_par_clk: Frequency used to calculate P_REG_PAR_RX_TUS * @tx_pcs_clk: Frequency used to calculate P_REG_PCS_TX_TUS @@ -80,7 +80,7 @@ struct ice_time_ref_info_e822 { * different link speeds, either the deskew marker for multi-lane link speeds * or the Reed Solomon gearbox marker for RS-FEC. */ -struct ice_vernier_info_e822 { +struct ice_vernier_info_e82x { u32 tx_par_clk; u32 rx_par_clk; u32 tx_pcs_clk; @@ -95,7 +95,7 @@ struct ice_vernier_info_e822 { }; /** - * struct ice_cgu_pll_params_e822 + * struct ice_cgu_pll_params_e82x * @refclk_pre_div: Reference clock pre-divisor * @feedback_div: Feedback divisor * @frac_n_div: Fractional divisor @@ -104,7 +104,7 @@ struct ice_vernier_info_e822 { * Clock Generation Unit parameters used to program the PLL based on the * selected TIME_REF frequency. */ -struct ice_cgu_pll_params_e822 { +struct ice_cgu_pll_params_e82x { u32 refclk_pre_div; u32 feedback_div; u32 frac_n_div; @@ -124,7 +124,7 @@ enum ice_phy_rclk_pins { }; #define ICE_E810_RCLK_PINS_NUM (ICE_RCLKB_PIN + 1) -#define ICE_E822_RCLK_PINS_NUM (ICE_RCLKA_PIN + 1) +#define ICE_E82X_RCLK_PINS_NUM (ICE_RCLKA_PIN + 1) #define E810T_CGU_INPUT_C827(_phy, _pin) ((_phy) * ICE_E810_RCLK_PINS_NUM + \ (_pin) + ZL_REF1P) @@ -183,16 +183,16 @@ struct ice_cgu_pin_desc { }; extern const struct -ice_cgu_pll_params_e822 e822_cgu_params[NUM_ICE_TIME_REF_FREQ]; +ice_cgu_pll_params_e82x e822_cgu_params[NUM_ICE_TIME_REF_FREQ]; #define E810C_QSFP_C827_0_HANDLE 2 #define E810C_QSFP_C827_1_HANDLE 3 /* Table of constants related to possible TIME_REF sources */ -extern const struct ice_time_ref_info_e822 e822_time_ref[NUM_ICE_TIME_REF_FREQ]; +extern const struct ice_time_ref_info_e82x e822_time_ref[NUM_ICE_TIME_REF_FREQ]; /* Table of constants for Vernier calibration on E822 */ -extern const struct ice_vernier_info_e822 e822_vernier[NUM_ICE_PTP_LNK_SPD]; +extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD]; /* Increment value to generate nanoseconds in the GLTSYN_TIME_L register for * the E810 devices. Based off of a PLL with an 812.5 MHz frequency. @@ -215,23 +215,23 @@ 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); /* E822 family functions */ -int ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val); -int ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val); -void ice_ptp_reset_ts_memory_quad_e822(struct ice_hw *hw, u8 quad); +int ice_read_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 *val); +int ice_write_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 val); +void ice_ptp_reset_ts_memory_quad_e82x(struct ice_hw *hw, u8 quad); /** - * ice_e822_time_ref - Get the current TIME_REF from capabilities + * ice_e82x_time_ref - Get the current TIME_REF from capabilities * @hw: pointer to the HW structure * * Returns the current TIME_REF from the capabilities structure. */ -static inline enum ice_time_ref_freq ice_e822_time_ref(struct ice_hw *hw) +static inline enum ice_time_ref_freq ice_e82x_time_ref(struct ice_hw *hw) { return hw->func_caps.ts_func_info.time_ref; } /** - * ice_set_e822_time_ref - Set new TIME_REF + * ice_set_e82x_time_ref - Set new TIME_REF * @hw: pointer to the HW structure * @time_ref: new TIME_REF to set * @@ -239,31 +239,31 @@ static inline enum ice_time_ref_freq ice_e822_time_ref(struct ice_hw *hw) * change, such as an update to the CGU registers. */ static inline void -ice_set_e822_time_ref(struct ice_hw *hw, enum ice_time_ref_freq time_ref) +ice_set_e82x_time_ref(struct ice_hw *hw, enum ice_time_ref_freq time_ref) { hw->func_caps.ts_func_info.time_ref = time_ref; } -static inline u64 ice_e822_pll_freq(enum ice_time_ref_freq time_ref) +static inline u64 ice_e82x_pll_freq(enum ice_time_ref_freq time_ref) { return e822_time_ref[time_ref].pll_freq; } -static inline u64 ice_e822_nominal_incval(enum ice_time_ref_freq time_ref) +static inline u64 ice_e82x_nominal_incval(enum ice_time_ref_freq time_ref) { return e822_time_ref[time_ref].nominal_incval; } -static inline u64 ice_e822_pps_delay(enum ice_time_ref_freq time_ref) +static inline u64 ice_e82x_pps_delay(enum ice_time_ref_freq time_ref) { return e822_time_ref[time_ref].pps_delay; } /* E822 Vernier calibration functions */ -int ice_stop_phy_timer_e822(struct ice_hw *hw, u8 port, bool soft_reset); -int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port); -int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port); -int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port); +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); +int ice_phy_cfg_tx_offset_e82x(struct ice_hw *hw, u8 port); +int ice_phy_cfg_rx_offset_e82x(struct ice_hw *hw, u8 port); /* E810 family functions */ int ice_ptp_init_phy_e810(struct ice_hw *hw); @@ -282,6 +282,8 @@ int ice_get_cgu_state(struct ice_hw *hw, u8 dpll_idx, int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num); void ice_ptp_init_phy_model(struct ice_hw *hw); +int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id, + unsigned long *caps); #define PFTSYN_SEM_BYTES 4 @@ -507,6 +509,7 @@ void ice_ptp_init_phy_model(struct ice_hw *hw); #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) /* Internal PHY timestamp address */ diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index c686ac0935eb..d367f4c66dcd 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -3,42 +3,51 @@ #include "ice.h" #include "ice_eswitch.h" -#include "ice_devlink.h" +#include "devlink/devlink.h" +#include "devlink/devlink_port.h" #include "ice_sriov.h" #include "ice_tc_lib.h" #include "ice_dcb_lib.h" /** - * ice_repr_get_sw_port_id - get port ID associated with representor - * @repr: pointer to port representor + * ice_repr_inc_tx_stats - increment Tx statistic by one packet + * @repr: repr to increment stats on + * @len: length of the packet + * @xmit_status: value returned by xmit function */ -static int ice_repr_get_sw_port_id(struct ice_repr *repr) +void ice_repr_inc_tx_stats(struct ice_repr *repr, unsigned int len, + int xmit_status) { - return repr->vf->pf->hw.port_info->lport; + struct ice_repr_pcpu_stats *stats; + + if (unlikely(xmit_status != NET_XMIT_SUCCESS && + xmit_status != NET_XMIT_CN)) { + this_cpu_inc(repr->stats->tx_drops); + return; + } + + stats = this_cpu_ptr(repr->stats); + u64_stats_update_begin(&stats->syncp); + stats->tx_packets++; + stats->tx_bytes += len; + u64_stats_update_end(&stats->syncp); } /** - * ice_repr_get_phys_port_name - get phys port name - * @netdev: pointer to port representor netdev - * @buf: write here port name - * @len: max length of buf + * ice_repr_inc_rx_stats - increment Rx statistic by one packet + * @netdev: repr netdev to increment stats on + * @len: length of the packet */ -static int -ice_repr_get_phys_port_name(struct net_device *netdev, char *buf, size_t len) +void ice_repr_inc_rx_stats(struct net_device *netdev, unsigned int len) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_repr *repr = np->repr; - int res; - - /* Devlink port is registered and devlink core is taking care of name formatting. */ - if (repr->vf->devlink_port.devlink) - return -EOPNOTSUPP; + struct ice_repr *repr = ice_netdev_to_repr(netdev); + struct ice_repr_pcpu_stats *stats; - res = snprintf(buf, len, "pf%dvfr%d", ice_repr_get_sw_port_id(repr), - repr->vf->vf_id); - if (res <= 0) - return -EOPNOTSUPP; - return 0; + stats = this_cpu_ptr(repr->stats); + u64_stats_update_begin(&stats->syncp); + stats->rx_packets++; + stats->rx_bytes += len; + u64_stats_update_end(&stats->syncp); } /** @@ -76,7 +85,7 @@ ice_repr_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) * ice_netdev_to_repr - Get port representor for given netdevice * @netdev: pointer to port representor netdev */ -struct ice_repr *ice_netdev_to_repr(struct net_device *netdev) +struct ice_repr *ice_netdev_to_repr(const struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); @@ -139,38 +148,35 @@ static int ice_repr_stop(struct net_device *netdev) * ice_repr_sp_stats64 - get slow path stats for port representor * @dev: network interface device structure * @stats: netlink stats structure - * - * RX/TX stats are being swapped here to be consistent with VF stats. In slow - * path, port representor receives data when the corresponding VF is sending it - * (and vice versa), TX and RX bytes/packets are effectively swapped on port - * representor. */ static int ice_repr_sp_stats64(const struct net_device *dev, struct rtnl_link_stats64 *stats) { - struct ice_netdev_priv *np = netdev_priv(dev); - int vf_id = np->repr->vf->vf_id; - struct ice_tx_ring *tx_ring; - struct ice_rx_ring *rx_ring; - u64 pkts, bytes; - - tx_ring = np->vsi->tx_rings[vf_id]; - ice_fetch_u64_stats_per_ring(&tx_ring->ring_stats->syncp, - tx_ring->ring_stats->stats, - &pkts, &bytes); - stats->rx_packets = pkts; - stats->rx_bytes = bytes; - - rx_ring = np->vsi->rx_rings[vf_id]; - ice_fetch_u64_stats_per_ring(&rx_ring->ring_stats->syncp, - rx_ring->ring_stats->stats, - &pkts, &bytes); - stats->tx_packets = pkts; - stats->tx_bytes = bytes; - stats->tx_dropped = rx_ring->ring_stats->rx_stats.alloc_page_failed + - rx_ring->ring_stats->rx_stats.alloc_buf_failed; - + struct ice_repr *repr = ice_netdev_to_repr(dev); + int i; + + for_each_possible_cpu(i) { + u64 tbytes, tpkts, tdrops, rbytes, rpkts; + struct ice_repr_pcpu_stats *repr_stats; + unsigned int start; + + repr_stats = per_cpu_ptr(repr->stats, i); + do { + start = u64_stats_fetch_begin(&repr_stats->syncp); + tbytes = repr_stats->tx_bytes; + tpkts = repr_stats->tx_packets; + tdrops = repr_stats->tx_drops; + rbytes = repr_stats->rx_bytes; + rpkts = repr_stats->rx_packets; + } while (u64_stats_fetch_retry(&repr_stats->syncp, start)); + + stats->tx_bytes += tbytes; + stats->tx_packets += tpkts; + stats->tx_dropped += tdrops; + stats->rx_bytes += rbytes; + stats->rx_packets += rpkts; + } return 0; } @@ -240,7 +246,6 @@ ice_repr_setup_tc(struct net_device *netdev, enum tc_setup_type type, } static const struct net_device_ops ice_repr_netdev_ops = { - .ndo_get_phys_port_name = ice_repr_get_phys_port_name, .ndo_get_stats64 = ice_repr_get_stats64, .ndo_open = ice_repr_open, .ndo_stop = ice_repr_stop, @@ -278,25 +283,66 @@ ice_repr_reg_netdev(struct net_device *netdev) return register_netdev(netdev); } +static void ice_repr_remove_node(struct devlink_port *devlink_port) +{ + devl_lock(devlink_port->devlink); + devl_rate_leaf_destroy(devlink_port); + devl_unlock(devlink_port->devlink); +} + /** - * ice_repr_add - add representor for VF - * @vf: pointer to VF structure + * ice_repr_rem - remove representor from VF + * @repr: pointer to representor structure */ -static int ice_repr_add(struct ice_vf *vf) +static void ice_repr_rem(struct ice_repr *repr) +{ + free_percpu(repr->stats); + free_netdev(repr->netdev); + kfree(repr); +} + +/** + * ice_repr_rem_vf - remove representor from VF + * @repr: pointer to representor structure + */ +void ice_repr_rem_vf(struct ice_repr *repr) +{ + ice_repr_remove_node(&repr->vf->devlink_port); + unregister_netdev(repr->netdev); + ice_devlink_destroy_vf_port(repr->vf); + ice_virtchnl_set_dflt_ops(repr->vf); + ice_repr_rem(repr); +} + +static void ice_repr_set_tx_topology(struct ice_pf *pf) +{ + struct devlink *devlink; + + /* only export if ADQ and DCB disabled and eswitch enabled*/ + if (ice_is_adq_active(pf) || ice_is_dcb_active(pf) || + !ice_is_switchdev_running(pf)) + return; + + devlink = priv_to_devlink(pf); + ice_devlink_rate_init_tx_topology(devlink, ice_get_main_vsi(pf)); +} + +/** + * ice_repr_add - add representor for generic VSI + * @pf: pointer to PF structure + * @src_vsi: pointer to VSI structure of device to represent + * @parent_mac: device MAC address + */ +static struct ice_repr * +ice_repr_add(struct ice_pf *pf, struct ice_vsi *src_vsi, const u8 *parent_mac) { - struct ice_q_vector *q_vector; struct ice_netdev_priv *np; struct ice_repr *repr; - struct ice_vsi *vsi; int err; - vsi = ice_get_vf_vsi(vf); - if (!vsi) - return -EINVAL; - repr = kzalloc(sizeof(*repr), GFP_KERNEL); if (!repr) - return -ENOMEM; + return ERR_PTR(-ENOMEM); repr->netdev = alloc_etherdev(sizeof(struct ice_netdev_priv)); if (!repr->netdev) { @@ -304,22 +350,49 @@ static int ice_repr_add(struct ice_vf *vf) goto err_alloc; } - repr->src_vsi = vsi; - repr->vf = vf; - vf->repr = repr; + repr->stats = netdev_alloc_pcpu_stats(struct ice_repr_pcpu_stats); + if (!repr->stats) { + err = -ENOMEM; + goto err_stats; + } + + repr->src_vsi = src_vsi; + repr->id = src_vsi->vsi_num; np = netdev_priv(repr->netdev); np->repr = repr; - q_vector = kzalloc(sizeof(*q_vector), GFP_KERNEL); - if (!q_vector) { - err = -ENOMEM; - goto err_alloc_q_vector; - } - repr->q_vector = q_vector; + ether_addr_copy(repr->parent_mac, parent_mac); + + return repr; + +err_stats: + free_netdev(repr->netdev); +err_alloc: + kfree(repr); + return ERR_PTR(err); +} + +struct ice_repr *ice_repr_add_vf(struct ice_vf *vf) +{ + struct ice_repr *repr; + struct ice_vsi *vsi; + int err; + + vsi = ice_get_vf_vsi(vf); + if (!vsi) + return ERR_PTR(-ENOENT); err = ice_devlink_create_vf_port(vf); if (err) - goto err_devlink; + return ERR_PTR(err); + + repr = ice_repr_add(vf->pf, vsi, vf->hw_lan_addr); + if (IS_ERR(repr)) { + err = PTR_ERR(repr); + goto err_repr_add; + } + + repr->vf = vf; repr->netdev->min_mtu = ETH_MIN_MTU; repr->netdev->max_mtu = ICE_MAX_MTU; @@ -331,100 +404,23 @@ static int ice_repr_add(struct ice_vf *vf) goto err_netdev; ice_virtchnl_set_repr_ops(vf); + ice_repr_set_tx_topology(vf->pf); - return 0; + return repr; err_netdev: + ice_repr_rem(repr); +err_repr_add: ice_devlink_destroy_vf_port(vf); -err_devlink: - kfree(repr->q_vector); - vf->repr->q_vector = NULL; -err_alloc_q_vector: - free_netdev(repr->netdev); - repr->netdev = NULL; -err_alloc: - kfree(repr); - vf->repr = NULL; - return err; + return ERR_PTR(err); } -/** - * ice_repr_rem - remove representor from VF - * @vf: pointer to VF structure - */ -static void ice_repr_rem(struct ice_vf *vf) +struct ice_repr *ice_repr_get_by_vsi(struct ice_vsi *vsi) { - if (!vf->repr) - return; + if (!vsi->vf) + return NULL; - kfree(vf->repr->q_vector); - vf->repr->q_vector = NULL; - unregister_netdev(vf->repr->netdev); - ice_devlink_destroy_vf_port(vf); - free_netdev(vf->repr->netdev); - vf->repr->netdev = NULL; - kfree(vf->repr); - vf->repr = NULL; - - ice_virtchnl_set_dflt_ops(vf); -} - -/** - * ice_repr_rem_from_all_vfs - remove port representor for all VFs - * @pf: pointer to PF structure - */ -void ice_repr_rem_from_all_vfs(struct ice_pf *pf) -{ - struct devlink *devlink; - struct ice_vf *vf; - unsigned int bkt; - - lockdep_assert_held(&pf->vfs.table_lock); - - ice_for_each_vf(pf, bkt, vf) - ice_repr_rem(vf); - - /* since all port representors are destroyed, there is - * no point in keeping the nodes - */ - devlink = priv_to_devlink(pf); - devl_lock(devlink); - devl_rate_nodes_destroy(devlink); - devl_unlock(devlink); -} - -/** - * ice_repr_add_for_all_vfs - add port representor for all VFs - * @pf: pointer to PF structure - */ -int ice_repr_add_for_all_vfs(struct ice_pf *pf) -{ - struct devlink *devlink; - struct ice_vf *vf; - unsigned int bkt; - int err; - - lockdep_assert_held(&pf->vfs.table_lock); - - ice_for_each_vf(pf, bkt, vf) { - err = ice_repr_add(vf); - if (err) - goto err; - } - - /* only export if ADQ and DCB disabled */ - if (ice_is_adq_active(pf) || ice_is_dcb_active(pf)) - return 0; - - devlink = priv_to_devlink(pf); - ice_devlink_rate_init_tx_topology(devlink, ice_get_main_vsi(pf)); - - return 0; - -err: - ice_repr_rem_from_all_vfs(pf); - - return err; + return xa_load(&vsi->back->eswitch.reprs, vsi->vf->repr_id); } /** @@ -446,15 +442,3 @@ void ice_repr_stop_tx_queues(struct ice_repr *repr) netif_carrier_off(repr->netdev); netif_tx_stop_all_queues(repr->netdev); } - -/** - * ice_repr_set_traffic_vsi - set traffic VSI for port representor - * @repr: repr on with VSI will be set - * @vsi: pointer to VSI that will be used by port representor to pass traffic - */ -void ice_repr_set_traffic_vsi(struct ice_repr *repr, struct ice_vsi *vsi) -{ - struct ice_netdev_priv *np = netdev_priv(repr->netdev); - - np->vsi = vsi; -} diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h index e1ee2d2c1d2d..cff730b15ca0 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.h +++ b/drivers/net/ethernet/intel/ice/ice_repr.h @@ -6,27 +6,38 @@ #include <net/dst_metadata.h> +struct ice_repr_pcpu_stats { + struct u64_stats_sync syncp; + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + u64 tx_drops; +}; + struct ice_repr { struct ice_vsi *src_vsi; struct ice_vf *vf; - struct ice_q_vector *q_vector; struct net_device *netdev; struct metadata_dst *dst; struct ice_esw_br_port *br_port; -#ifdef CONFIG_ICE_SWITCHDEV - /* info about slow path rule */ - struct ice_rule_query_data sp_rule; -#endif + struct ice_repr_pcpu_stats __percpu *stats; + u32 id; + u8 parent_mac[ETH_ALEN]; }; -int ice_repr_add_for_all_vfs(struct ice_pf *pf); -void ice_repr_rem_from_all_vfs(struct ice_pf *pf); +struct ice_repr *ice_repr_add_vf(struct ice_vf *vf); +void ice_repr_rem_vf(struct ice_repr *repr); void ice_repr_start_tx_queues(struct ice_repr *repr); void ice_repr_stop_tx_queues(struct ice_repr *repr); -void ice_repr_set_traffic_vsi(struct ice_repr *repr, struct ice_vsi *vsi); - -struct ice_repr *ice_netdev_to_repr(struct net_device *netdev); +struct ice_repr *ice_netdev_to_repr(const struct net_device *netdev); bool ice_is_port_repr_netdev(const struct net_device *netdev); + +struct ice_repr *ice_repr_get_by_vsi(struct ice_vsi *vsi); + +void ice_repr_inc_tx_stats(struct ice_repr *repr, unsigned int len, + int xmit_status); +void ice_repr_inc_rx_stats(struct net_device *netdev, unsigned int len); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 2f4a621254e8..ecf8f5d60292 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -237,7 +237,7 @@ static int ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent, u32 node_teid) { - DEFINE_FLEX(struct ice_aqc_delete_elem, buf, teid, 1); + DEFINE_RAW_FLEX(struct ice_aqc_delete_elem, buf, teid, 1); u16 buf_size = __struct_size(buf); u16 num_groups_removed = 0; int status; @@ -1128,12 +1128,11 @@ u8 ice_sched_get_vsi_layer(struct ice_hw *hw) * 5 or less sw_entry_point_layer */ /* calculate the VSI layer based on number of layers. */ - if (hw->num_tx_sched_layers > ICE_VSI_LAYER_OFFSET + 1) { - u8 layer = hw->num_tx_sched_layers - ICE_VSI_LAYER_OFFSET; - - if (layer > hw->sw_entry_point_layer) - return layer; - } + if (hw->num_tx_sched_layers == ICE_SCHED_9_LAYERS) + return hw->num_tx_sched_layers - ICE_VSI_LAYER_OFFSET; + else if (hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS) + /* qgroup and VSI layers are same */ + return hw->num_tx_sched_layers - ICE_QGRP_LAYER_OFFSET; return hw->sw_entry_point_layer; } @@ -1150,13 +1149,10 @@ u8 ice_sched_get_agg_layer(struct ice_hw *hw) * 7 or less sw_entry_point_layer */ /* calculate the aggregator layer based on number of layers. */ - if (hw->num_tx_sched_layers > ICE_AGG_LAYER_OFFSET + 1) { - u8 layer = hw->num_tx_sched_layers - ICE_AGG_LAYER_OFFSET; - - if (layer > hw->sw_entry_point_layer) - return layer; - } - return hw->sw_entry_point_layer; + if (hw->num_tx_sched_layers == ICE_SCHED_9_LAYERS) + return hw->num_tx_sched_layers - ICE_AGG_LAYER_OFFSET; + else + return hw->sw_entry_point_layer; } /** @@ -1387,8 +1383,7 @@ void ice_sched_get_psm_clk_freq(struct ice_hw *hw) u32 val, clk_src; val = rd32(hw, GLGEN_CLKSTAT_SRC); - clk_src = (val & GLGEN_CLKSTAT_SRC_PSM_CLK_SRC_M) >> - GLGEN_CLKSTAT_SRC_PSM_CLK_SRC_S; + clk_src = FIELD_GET(GLGEN_CLKSTAT_SRC_PSM_CLK_SRC_M, val); #define PSM_CLK_SRC_367_MHZ 0x0 #define PSM_CLK_SRC_416_MHZ 0x1 @@ -1511,10 +1506,11 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, { struct ice_sched_node *vsi_node, *qgrp_node; struct ice_vsi_ctx *vsi_ctx; + u8 qgrp_layer, vsi_layer; u16 max_children; - u8 qgrp_layer; qgrp_layer = ice_sched_get_qgrp_layer(pi->hw); + vsi_layer = ice_sched_get_vsi_layer(pi->hw); max_children = pi->hw->max_children[qgrp_layer]; vsi_ctx = ice_get_vsi_ctx(pi->hw, vsi_handle); @@ -1525,6 +1521,12 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, if (!vsi_node) return NULL; + /* If the queue group and VSI layer are same then queues + * are all attached directly to VSI + */ + if (qgrp_layer == vsi_layer) + return vsi_node; + /* 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) { @@ -2220,7 +2222,7 @@ int ice_sched_move_nodes(struct ice_port_info *pi, struct ice_sched_node *parent, u16 num_items, u32 *list) { - DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + DEFINE_RAW_FLEX(struct ice_aqc_move_elem, buf, teid, 1); u16 buf_len = __struct_size(buf); struct ice_sched_node *node; u16 i, grps_movd = 0; @@ -3200,7 +3202,7 @@ ice_sched_add_rl_profile(struct ice_port_info *pi, u8 profile_type; int status; - if (layer_num >= ICE_AQC_TOPO_MAX_LEVEL_NUM) + if (!pi || layer_num >= pi->hw->num_tx_sched_layers) return NULL; switch (rl_type) { case ICE_MIN_BW: @@ -3216,8 +3218,6 @@ ice_sched_add_rl_profile(struct ice_port_info *pi, return NULL; } - if (!pi) - return NULL; hw = pi->hw; list_for_each_entry(rl_prof_elem, &pi->rl_prof_list[layer_num], list_entry) @@ -3447,7 +3447,7 @@ ice_sched_rm_rl_profile(struct ice_port_info *pi, u8 layer_num, u8 profile_type, struct ice_aqc_rl_profile_info *rl_prof_elem; int status = 0; - if (layer_num >= ICE_AQC_TOPO_MAX_LEVEL_NUM) + if (layer_num >= pi->hw->num_tx_sched_layers) return -EINVAL; /* Check the existing list for RL profile */ list_for_each_entry(rl_prof_elem, &pi->rl_prof_list[layer_num], diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h index 1aef05ea5a57..7b668083be07 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.h +++ b/drivers/net/ethernet/intel/ice/ice_sched.h @@ -6,6 +6,17 @@ #include "ice_common.h" +/** + * DOC: ice_sched.h + * + * This header file stores everything that is needed for broadly understood + * scheduler. It consists of defines related to layers, structures related to + * aggregator, functions declarations and others. + */ + +#define ICE_SCHED_5_LAYERS 5 +#define ICE_SCHED_9_LAYERS 9 + #define SCHED_NODE_NAME_MAX_LEN 32 #define ICE_QGRP_LAYER_OFFSET 2 diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 2a5e6616cc0a..067712f4923f 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -106,10 +106,8 @@ static void ice_dis_vf_mappings(struct ice_vf *vf) for (v = first; v <= last; v++) { u32 reg; - reg = (((1 << GLINT_VECT2FUNC_IS_PF_S) & - GLINT_VECT2FUNC_IS_PF_M) | - ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & - GLINT_VECT2FUNC_PF_NUM_M)); + reg = FIELD_PREP(GLINT_VECT2FUNC_IS_PF_M, 1) | + FIELD_PREP(GLINT_VECT2FUNC_PF_NUM_M, hw->pf_id); wr32(hw, GLINT_VECT2FUNC(v), reg); } @@ -174,11 +172,10 @@ void ice_free_vfs(struct ice_pf *pf) mutex_lock(&vfs->table_lock); - ice_eswitch_release(pf); - ice_for_each_vf(pf, bkt, vf) { mutex_lock(&vf->cfg_lock); + ice_eswitch_detach(pf, vf); ice_dis_vf_qs(vf); if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { @@ -228,7 +225,7 @@ static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf) struct ice_vsi *vsi; params.type = ICE_VSI_VF; - params.pi = ice_vf_get_port_info(vf); + params.port_info = ice_vf_get_port_info(vf); params.vf = vf; params.flags = ICE_VSI_FLAG_INIT; @@ -241,7 +238,6 @@ static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf) } vf->lan_vsi_idx = vsi->idx; - vf->lan_vsi_num = vsi->vsi_num; return vsi; } @@ -274,24 +270,20 @@ static void ice_ena_vf_msix_mappings(struct ice_vf *vf) (device_based_first_msix + vf->num_msix) - 1; device_based_vf_id = vf->vf_id + hw->func_caps.vf_base_id; - reg = (((device_based_first_msix << VPINT_ALLOC_FIRST_S) & - VPINT_ALLOC_FIRST_M) | - ((device_based_last_msix << VPINT_ALLOC_LAST_S) & - VPINT_ALLOC_LAST_M) | VPINT_ALLOC_VALID_M); + reg = FIELD_PREP(VPINT_ALLOC_FIRST_M, device_based_first_msix) | + FIELD_PREP(VPINT_ALLOC_LAST_M, device_based_last_msix) | + VPINT_ALLOC_VALID_M; wr32(hw, VPINT_ALLOC(vf->vf_id), reg); - reg = (((device_based_first_msix << VPINT_ALLOC_PCI_FIRST_S) - & VPINT_ALLOC_PCI_FIRST_M) | - ((device_based_last_msix << VPINT_ALLOC_PCI_LAST_S) & - VPINT_ALLOC_PCI_LAST_M) | VPINT_ALLOC_PCI_VALID_M); + reg = FIELD_PREP(VPINT_ALLOC_PCI_FIRST_M, device_based_first_msix) | + FIELD_PREP(VPINT_ALLOC_PCI_LAST_M, device_based_last_msix) | + VPINT_ALLOC_PCI_VALID_M; wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), reg); /* map the interrupts to its functions */ for (v = pf_based_first_msix; v <= pf_based_last_msix; v++) { - reg = (((device_based_vf_id << GLINT_VECT2FUNC_VF_NUM_S) & - GLINT_VECT2FUNC_VF_NUM_M) | - ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & - GLINT_VECT2FUNC_PF_NUM_M)); + reg = FIELD_PREP(GLINT_VECT2FUNC_VF_NUM_M, device_based_vf_id) | + FIELD_PREP(GLINT_VECT2FUNC_PF_NUM_M, hw->pf_id); wr32(hw, GLINT_VECT2FUNC(v), reg); } @@ -324,10 +316,8 @@ static void ice_ena_vf_q_mappings(struct ice_vf *vf, u16 max_txq, u16 max_rxq) * VFNUMQ value should be set to (number of queues - 1). A value * of 0 means 1 queue and a value of 255 means 256 queues */ - reg = (((vsi->txq_map[0] << VPLAN_TX_QBASE_VFFIRSTQ_S) & - VPLAN_TX_QBASE_VFFIRSTQ_M) | - (((max_txq - 1) << VPLAN_TX_QBASE_VFNUMQ_S) & - VPLAN_TX_QBASE_VFNUMQ_M)); + reg = FIELD_PREP(VPLAN_TX_QBASE_VFFIRSTQ_M, vsi->txq_map[0]) | + FIELD_PREP(VPLAN_TX_QBASE_VFNUMQ_M, max_txq - 1); wr32(hw, VPLAN_TX_QBASE(vf->vf_id), reg); } else { dev_err(dev, "Scattered mode for VF Tx queues is not yet implemented\n"); @@ -342,10 +332,8 @@ static void ice_ena_vf_q_mappings(struct ice_vf *vf, u16 max_txq, u16 max_rxq) * VFNUMQ value should be set to (number of queues - 1). A value * of 0 means 1 queue and a value of 255 means 256 queues */ - reg = (((vsi->rxq_map[0] << VPLAN_RX_QBASE_VFFIRSTQ_S) & - VPLAN_RX_QBASE_VFFIRSTQ_M) | - (((max_rxq - 1) << VPLAN_RX_QBASE_VFNUMQ_S) & - VPLAN_RX_QBASE_VFNUMQ_M)); + reg = FIELD_PREP(VPLAN_RX_QBASE_VFFIRSTQ_M, vsi->rxq_map[0]) | + FIELD_PREP(VPLAN_RX_QBASE_VFNUMQ_M, max_rxq - 1); wr32(hw, VPLAN_RX_QBASE(vf->vf_id), reg); } else { dev_err(dev, "Scattered mode for VF Rx queues is not yet implemented\n"); @@ -372,18 +360,14 @@ static void ice_ena_vf_mappings(struct ice_vf *vf) * @vf: VF to calculate the register index for * @q_vector: a q_vector associated to the VF */ -int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector) +void ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector) { - struct ice_pf *pf; - if (!vf || !q_vector) - return -EINVAL; - - pf = vf->pf; + return; /* always add one to account for the OICR being the first MSIX */ - return pf->sriov_base_vector + pf->vfs.num_msix_per * vf->vf_id + - q_vector->v_idx + 1; + q_vector->vf_reg_idx = q_vector->v_idx + ICE_NONQ_VECS_VF; + q_vector->reg_idx = vf->first_vector_idx + q_vector->vf_reg_idx; } /** @@ -614,6 +598,14 @@ static int ice_start_vfs(struct ice_pf *pf) goto teardown; } + retval = ice_eswitch_attach(pf, vf); + if (retval) { + dev_err(ice_pf_to_dev(pf), "Failed to attach VF %d to eswitch, error %d", + vf->vf_id, retval); + ice_vf_vsi_release(vf); + goto teardown; + } + set_bit(ICE_VF_STATE_INIT, vf->vf_states); ice_ena_vf_mappings(vf); wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE); @@ -768,24 +760,6 @@ static void ice_sriov_clear_reset_trigger(struct ice_vf *vf) } /** - * ice_sriov_create_vsi - Create a new VSI for a VF - * @vf: VF to create the VSI for - * - * This is called by ice_vf_recreate_vsi to create the new VSI after the old - * VSI has been released. - */ -static int ice_sriov_create_vsi(struct ice_vf *vf) -{ - struct ice_vsi *vsi; - - vsi = ice_vf_vsi_setup(vf); - if (!vsi) - return -ENOMEM; - - return 0; -} - -/** * ice_sriov_post_vsi_rebuild - tasks to do after the VF's VSI have been rebuilt * @vf: VF to perform tasks on */ @@ -804,7 +778,6 @@ static const struct ice_vf_ops ice_sriov_vf_ops = { .poll_reset_status = ice_sriov_poll_reset_status, .clear_reset_trigger = ice_sriov_clear_reset_trigger, .irq_close = NULL, - .create_vsi = ice_sriov_create_vsi, .post_vsi_rebuild = ice_sriov_post_vsi_rebuild, }; @@ -859,11 +832,6 @@ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs) pci_dev_get(vfdev); - /* set default number of MSI-X */ - vf->num_msix = pf->vfs.num_msix_per; - vf->num_vf_qs = pf->vfs.num_qps_per; - ice_vc_set_default_allowlist(vf); - hash_add_rcu(vfs->table, &vf->entry, vf_id); } @@ -932,12 +900,6 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) clear_bit(ICE_VF_DIS, pf->state); - ret = ice_eswitch_configure(pf); - if (ret) { - dev_err(dev, "Failed to configure eswitch, err %d\n", ret); - goto err_unroll_sriov; - } - /* rearm global interrupts */ if (test_and_clear_bit(ICE_OICR_INTR_DIS, pf->state)) ice_irq_dynamic_ena(hw, NULL, NULL); @@ -1098,6 +1060,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) struct ice_pf *pf = pci_get_drvdata(pdev); u16 prev_msix, prev_queues, queues; bool needs_rebuild = false; + struct ice_vsi *vsi; struct ice_vf *vf; int id; @@ -1132,6 +1095,10 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) if (!vf) return -ENOENT; + vsi = ice_get_vf_vsi(vf); + if (!vsi) + return -ENOENT; + prev_msix = vf->num_msix; prev_queues = vf->num_vf_qs; @@ -1152,8 +1119,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) if (vf->first_vector_idx < 0) goto unroll; - ice_vf_vsi_release(vf); - if (vf->vf_ops->create_vsi(vf)) { + if (ice_vf_reconfig_vsi(vf) || ice_vf_init_host_cfg(vf, vsi)) { /* Try to rebuild with previous values */ needs_rebuild = true; goto unroll; @@ -1179,8 +1145,10 @@ unroll: if (vf->first_vector_idx < 0) return -EINVAL; - if (needs_rebuild) - vf->vf_ops->create_vsi(vf); + if (needs_rebuild) { + ice_vf_reconfig_vsi(vf); + ice_vf_init_host_cfg(vf, vsi); + } ice_ena_vf_mappings(vf); ice_put_vf(vf); @@ -1329,8 +1297,7 @@ ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) dev_dbg(ice_pf_to_dev(pf), "GLDCB_RTCTQ: 0x%08x\n", gldcb_rtctq); /* event returns device global Rx queue number */ - queue = (gldcb_rtctq & GLDCB_RTCTQ_RXQNUM_M) >> - GLDCB_RTCTQ_RXQNUM_S; + queue = FIELD_GET(GLDCB_RTCTQ_RXQNUM_M, gldcb_rtctq); vf = ice_get_vf_from_pfq(pf, ice_globalq_to_pfq(pf, queue)); if (!vf) @@ -1895,6 +1862,24 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf) } /** + * ice_print_vf_tx_mdd_event - print VF Tx malicious driver detect event + * @vf: pointer to the VF structure + */ +void ice_print_vf_tx_mdd_event(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct device *dev; + + dev = ice_pf_to_dev(pf); + + dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n", + vf->mdd_tx_events.count, pf->hw.pf_id, vf->vf_id, + vf->dev_lan_addr, + test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags) + ? "on" : "off"); +} + +/** * ice_print_vfs_mdd_events - print VFs malicious driver detect event * @pf: pointer to the PF structure * @@ -1902,8 +1887,6 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf) */ void ice_print_vfs_mdd_events(struct ice_pf *pf) { - struct device *dev = ice_pf_to_dev(pf); - struct ice_hw *hw = &pf->hw; struct ice_vf *vf; unsigned int bkt; @@ -1930,10 +1913,7 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf) if (vf->mdd_tx_events.count != vf->mdd_tx_events.last_printed) { vf->mdd_tx_events.last_printed = vf->mdd_tx_events.count; - - dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM.\n", - vf->mdd_tx_events.count, hw->pf_id, vf->vf_id, - vf->dev_lan_addr); + ice_print_vf_tx_mdd_event(vf); } } mutex_unlock(&pf->vfs.table_lock); diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h index 8488df38b586..8f22313474d6 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.h +++ b/drivers/net/ethernet/intel/ice/ice_sriov.h @@ -49,7 +49,7 @@ int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state); int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena); -int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector); +void ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector); int ice_get_vf_stats(struct net_device *netdev, int vf_id, @@ -58,6 +58,7 @@ void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event); void ice_print_vfs_mdd_events(struct ice_pf *pf); void ice_print_vf_rx_mdd_event(struct ice_vf *vf); +void ice_print_vf_tx_mdd_event(struct ice_vf *vf); bool ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto); u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev); @@ -69,6 +70,7 @@ static inline void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) { } static inline void ice_print_vfs_mdd_events(struct ice_pf *pf) { } static inline void ice_print_vf_rx_mdd_event(struct ice_vf *vf) { } +static inline void ice_print_vf_tx_mdd_event(struct ice_vf *vf) { } static inline void ice_restore_all_vfs_msi_state(struct ice_pf *pf) { } static inline int @@ -130,11 +132,10 @@ ice_set_vf_bw(struct net_device __always_unused *netdev, return -EOPNOTSUPP; } -static inline int +static inline void ice_calc_vf_reg_idx(struct ice_vf __always_unused *vf, struct ice_q_vector __always_unused *q_vector) { - return 0; } static inline int diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index ee19f3aa3d19..94d6670d0901 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -42,6 +42,7 @@ enum { ICE_PKT_KMALLOC = BIT(9), ICE_PKT_PPPOE = BIT(10), ICE_PKT_L2TPV3 = BIT(11), + ICE_PKT_PFCP = BIT(12), }; struct ice_dummy_pkt_offsets { @@ -1110,6 +1111,77 @@ ICE_DECLARE_PKT_TEMPLATE(ipv6_gtp) = { 0x00, 0x00, }; +ICE_DECLARE_PKT_OFFSETS(pfcp_session_ipv4) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_UDP_ILOS, 34 }, + { ICE_PFCP, 42 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(pfcp_session_ipv4) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_OL 12 */ + + 0x45, 0x00, 0x00, 0x2c, /* ICE_IPV4_OFOS 14 */ + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x22, 0x65, /* ICE_UDP_ILOS 34 */ + 0x00, 0x18, 0x00, 0x00, + + 0x21, 0x01, 0x00, 0x0c, /* ICE_PFCP 42 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +ICE_DECLARE_PKT_OFFSETS(pfcp_session_ipv6) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV6_OFOS, 14 }, + { ICE_UDP_ILOS, 54 }, + { ICE_PFCP, 62 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(pfcp_session_ipv6) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x86, 0xdd, /* ICE_ETYPE_OL 12 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 14 */ + 0x00, 0x10, 0x11, 0x00, /* Next header UDP */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x22, 0x65, /* ICE_UDP_ILOS 54 */ + 0x00, 0x18, 0x00, 0x00, + + 0x21, 0x01, 0x00, 0x0c, /* ICE_PFCP 62 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + ICE_DECLARE_PKT_OFFSETS(pppoe_ipv4_tcp) = { { ICE_MAC_OFOS, 0 }, { ICE_ETYPE_OL, 12 }, @@ -1343,6 +1415,8 @@ static const struct ice_dummy_pkt_profile ice_dummy_pkt_profiles[] = { ICE_PKT_PROFILE(ipv4_gtpu_ipv4_tcp, ICE_PKT_TUN_GTPU), ICE_PKT_PROFILE(ipv6_gtp, ICE_PKT_TUN_GTPC | ICE_PKT_OUTER_IPV6), ICE_PKT_PROFILE(ipv4_gtpu_ipv4, ICE_PKT_TUN_GTPC), + ICE_PKT_PROFILE(pfcp_session_ipv6, ICE_PKT_PFCP | ICE_PKT_OUTER_IPV6), + ICE_PKT_PROFILE(pfcp_session_ipv4, ICE_PKT_PFCP), ICE_PKT_PROFILE(pppoe_ipv6_udp, ICE_PKT_PPPOE | ICE_PKT_OUTER_IPV6 | ICE_PKT_INNER_UDP), ICE_PKT_PROFILE(pppoe_ipv6_tcp, ICE_PKT_PPPOE | ICE_PKT_OUTER_IPV6), @@ -1812,7 +1886,7 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, enum ice_sw_lkup_type lkup_type, enum ice_adminq_opc opc) { - DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); + DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); u16 buf_len = __struct_size(sw_buf); struct ice_aqc_res_elem *vsi_ele; int status; @@ -2025,12 +2099,12 @@ error_out: * ice_aq_map_recipe_to_profile - Map recipe to packet profile * @hw: pointer to the HW struct * @profile_id: package profile ID to associate the recipe with - * @r_bitmap: Recipe bitmap filled in and need to be returned as response + * @r_assoc: Recipe bitmap filled in and need to be returned as response * @cd: pointer to command details structure or NULL * Recipe to profile association (0x0291) */ int -ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, +ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 r_assoc, struct ice_sq_cd *cd) { struct ice_aqc_recipe_to_profile *cmd; @@ -2042,7 +2116,7 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, /* Set the recipe ID bit in the bitmask to let the device know which * profile we are associating the recipe to */ - memcpy(cmd->recipe_assoc, r_bitmap, sizeof(cmd->recipe_assoc)); + cmd->recipe_assoc = cpu_to_le64(r_assoc); return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); } @@ -2051,12 +2125,12 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, * ice_aq_get_recipe_to_profile - Map recipe to packet profile * @hw: pointer to the HW struct * @profile_id: package profile ID to associate the recipe with - * @r_bitmap: Recipe bitmap filled in and need to be returned as response + * @r_assoc: Recipe bitmap filled in and need to be returned as response * @cd: pointer to command details structure or NULL * Associate profile ID with given recipe (0x0293) */ int -ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, +ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 *r_assoc, struct ice_sq_cd *cd) { struct ice_aqc_recipe_to_profile *cmd; @@ -2069,26 +2143,42 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); if (!status) - memcpy(r_bitmap, cmd->recipe_assoc, sizeof(cmd->recipe_assoc)); + *r_assoc = le64_to_cpu(cmd->recipe_assoc); return status; } /** + * ice_init_chk_recipe_reuse_support - check if recipe reuse is supported + * @hw: pointer to the hardware structure + */ +void ice_init_chk_recipe_reuse_support(struct ice_hw *hw) +{ + struct ice_nvm_info *nvm = &hw->flash.nvm; + + hw->recp_reuse = (nvm->major == 0x4 && nvm->minor >= 0x30) || + nvm->major > 0x4; +} + +/** * ice_alloc_recipe - add recipe resource * @hw: pointer to the hardware structure * @rid: recipe ID returned as response to AQ call */ int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) { - DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); + DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); u16 buf_len = __struct_size(sw_buf); + u16 res_type; int status; sw_buf->num_elems = cpu_to_le16(1); - sw_buf->res_type = cpu_to_le16((ICE_AQC_RES_TYPE_RECIPE << - ICE_AQC_RES_TYPE_S) | - ICE_AQC_RES_TYPE_FLAG_SHARED); + res_type = FIELD_PREP(ICE_AQC_RES_TYPE_M, ICE_AQC_RES_TYPE_RECIPE); + if (hw->recp_reuse) + res_type |= ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_SHARED; + else + res_type |= ICE_AQC_RES_TYPE_FLAG_SHARED; + sw_buf->res_type = cpu_to_le16(res_type); status = ice_aq_alloc_free_res(hw, sw_buf, buf_len, ice_aqc_opc_alloc_res); if (!status) @@ -2098,6 +2188,70 @@ int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) } /** + * ice_free_recipe_res - free recipe resource + * @hw: pointer to the hardware structure + * @rid: recipe ID to free + * + * Return: 0 on success, and others on error + */ +static int ice_free_recipe_res(struct ice_hw *hw, u16 rid) +{ + return ice_free_hw_res(hw, ICE_AQC_RES_TYPE_RECIPE, 1, &rid); +} + +/** + * ice_release_recipe_res - disassociate and free recipe resource + * @hw: pointer to the hardware structure + * @recp: the recipe struct resource to unassociate and free + * + * Return: 0 on success, and others on error + */ +static int ice_release_recipe_res(struct ice_hw *hw, + struct ice_sw_recipe *recp) +{ + DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + struct ice_switch_info *sw = hw->switch_info; + u64 recp_assoc; + u32 rid, prof; + int status; + + for_each_set_bit(rid, recp->r_bitmap, ICE_MAX_NUM_RECIPES) { + for_each_set_bit(prof, recipe_to_profile[rid], + ICE_MAX_NUM_PROFILES) { + status = ice_aq_get_recipe_to_profile(hw, prof, + &recp_assoc, + NULL); + if (status) + return status; + + bitmap_from_arr64(r_bitmap, &recp_assoc, + ICE_MAX_NUM_RECIPES); + bitmap_andnot(r_bitmap, r_bitmap, recp->r_bitmap, + ICE_MAX_NUM_RECIPES); + bitmap_to_arr64(&recp_assoc, r_bitmap, + ICE_MAX_NUM_RECIPES); + ice_aq_map_recipe_to_profile(hw, prof, + recp_assoc, NULL); + + clear_bit(rid, profile_to_recipe[prof]); + clear_bit(prof, recipe_to_profile[rid]); + } + + status = ice_free_recipe_res(hw, rid); + if (status) + return status; + + sw->recp_list[rid].recp_created = false; + sw->recp_list[rid].adv_rule = false; + memset(&sw->recp_list[rid].lkup_exts, 0, + sizeof(sw->recp_list[rid].lkup_exts)); + clear_bit(rid, recp->r_bitmap); + } + + return 0; +} + +/** * ice_get_recp_to_prof_map - updates recipe to profile mapping * @hw: pointer to hardware structure * @@ -2108,6 +2262,7 @@ int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) static void ice_get_recp_to_prof_map(struct ice_hw *hw) { DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + u64 recp_assoc; u16 i; for (i = 0; i < hw->switch_info->max_used_prof_index + 1; i++) { @@ -2115,8 +2270,9 @@ static void ice_get_recp_to_prof_map(struct ice_hw *hw) bitmap_zero(profile_to_recipe[i], ICE_MAX_NUM_RECIPES); bitmap_zero(r_bitmap, ICE_MAX_NUM_RECIPES); - if (ice_aq_get_recipe_to_profile(hw, i, (u8 *)r_bitmap, NULL)) + if (ice_aq_get_recipe_to_profile(hw, i, &recp_assoc, NULL)) continue; + bitmap_from_arr64(r_bitmap, &recp_assoc, ICE_MAX_NUM_RECIPES); bitmap_copy(profile_to_recipe[i], r_bitmap, ICE_MAX_NUM_RECIPES); for_each_set_bit(j, r_bitmap, ICE_MAX_NUM_RECIPES) @@ -2144,6 +2300,7 @@ ice_collect_result_idx(struct ice_aqc_recipe_data_elem *buf, * @recps: struct that we need to populate * @rid: recipe ID that we are populating * @refresh_required: true if we should get recipe to profile mapping from FW + * @is_add: flag of adding recipe * * This function is used to populate all the necessary entries into our * bookkeeping so that we have a current list of all the recipes that are @@ -2151,7 +2308,7 @@ ice_collect_result_idx(struct ice_aqc_recipe_data_elem *buf, */ static int ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, - bool *refresh_required) + bool *refresh_required, bool is_add) { DECLARE_BITMAP(result_bm, ICE_MAX_FV_WORDS); struct ice_aqc_recipe_data_elem *tmp; @@ -2268,8 +2425,12 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, recps[idx].chain_idx = ICE_INVAL_CHAIN_IND; } - if (!is_root) + if (!is_root) { + if (hw->recp_reuse && is_add) + recps[idx].recp_created = true; + continue; + } /* Only do the following for root recipes entries */ memcpy(recps[idx].r_bitmap, root_bufs.recipe_bitmap, @@ -2293,7 +2454,8 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, /* Copy result indexes */ bitmap_copy(recps[rid].res_idxs, result_bm, ICE_MAX_FV_WORDS); - recps[rid].recp_created = true; + if (is_add) + recps[rid].recp_created = true; err_unroll: kfree(tmp); @@ -2444,6 +2606,9 @@ static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi) fi->lan_en = true; } } + + if (fi->flag & ICE_FLTR_TX_ONLY) + fi->lan_en = false; } /** @@ -2492,25 +2657,24 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, switch (f_info->fltr_act) { case ICE_FWD_TO_VSI: - act |= (f_info->fwd_id.hw_vsi_id << ICE_SINGLE_ACT_VSI_ID_S) & - ICE_SINGLE_ACT_VSI_ID_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, + f_info->fwd_id.hw_vsi_id); if (f_info->lkup_type != ICE_SW_LKUP_VLAN) act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT; break; case ICE_FWD_TO_VSI_LIST: act |= ICE_SINGLE_ACT_VSI_LIST; - act |= (f_info->fwd_id.vsi_list_id << - ICE_SINGLE_ACT_VSI_LIST_ID_S) & - ICE_SINGLE_ACT_VSI_LIST_ID_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_LIST_ID_M, + f_info->fwd_id.vsi_list_id); if (f_info->lkup_type != ICE_SW_LKUP_VLAN) act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT; break; case ICE_FWD_TO_Q: act |= ICE_SINGLE_ACT_TO_Q; - act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & - ICE_SINGLE_ACT_Q_INDEX_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_Q_INDEX_M, + f_info->fwd_id.q_id); break; case ICE_DROP_PACKET: act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP | @@ -2520,10 +2684,9 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, q_rgn = f_info->qgrp_size > 0 ? (u8)ilog2(f_info->qgrp_size) : 0; act |= ICE_SINGLE_ACT_TO_Q; - act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & - ICE_SINGLE_ACT_Q_INDEX_M; - act |= (q_rgn << ICE_SINGLE_ACT_Q_REGION_S) & - ICE_SINGLE_ACT_Q_REGION_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_Q_INDEX_M, + f_info->fwd_id.q_id); + act |= FIELD_PREP(ICE_SINGLE_ACT_Q_REGION_M, q_rgn); break; default: return; @@ -2649,7 +2812,7 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, m_ent->fltr_info.fwd_id.hw_vsi_id; act = ICE_LG_ACT_VSI_FORWARDING | ICE_LG_ACT_VALID_BIT; - act |= (id << ICE_LG_ACT_VSI_LIST_ID_S) & ICE_LG_ACT_VSI_LIST_ID_M; + act |= FIELD_PREP(ICE_LG_ACT_VSI_LIST_ID_M, id); if (m_ent->vsi_count > 1) act |= ICE_LG_ACT_VSI_LIST; lg_act->act[0] = cpu_to_le32(act); @@ -2657,16 +2820,15 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, /* Second action descriptor type */ act = ICE_LG_ACT_GENERIC; - act |= (1 << ICE_LG_ACT_GENERIC_VALUE_S) & ICE_LG_ACT_GENERIC_VALUE_M; + act |= FIELD_PREP(ICE_LG_ACT_GENERIC_VALUE_M, 1); lg_act->act[1] = cpu_to_le32(act); - act = (ICE_LG_ACT_GENERIC_OFF_RX_DESC_PROF_IDX << - ICE_LG_ACT_GENERIC_OFFSET_S) & ICE_LG_ACT_GENERIC_OFFSET_M; + act = FIELD_PREP(ICE_LG_ACT_GENERIC_OFFSET_M, + ICE_LG_ACT_GENERIC_OFF_RX_DESC_PROF_IDX); /* Third action Marker value */ act |= ICE_LG_ACT_GENERIC; - act |= (sw_marker << ICE_LG_ACT_GENERIC_VALUE_S) & - ICE_LG_ACT_GENERIC_VALUE_M; + act |= FIELD_PREP(ICE_LG_ACT_GENERIC_VALUE_M, sw_marker); lg_act->act[2] = cpu_to_le32(act); @@ -2675,9 +2837,9 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, ice_aqc_opc_update_sw_rules); /* Update the action to point to the large action ID */ - rx_tx->act = cpu_to_le32(ICE_SINGLE_ACT_PTR | - ((l_id << ICE_SINGLE_ACT_PTR_VAL_S) & - ICE_SINGLE_ACT_PTR_VAL_M)); + act = ICE_SINGLE_ACT_PTR; + act |= FIELD_PREP(ICE_SINGLE_ACT_PTR_VAL_M, l_id); + rx_tx->act = cpu_to_le32(act); /* Use the filter rule ID of the previously created rule with single * act. Once the update happens, hardware will treat this as large @@ -3822,6 +3984,7 @@ ice_cfg_dflt_vsi(struct ice_port_info *pi, u16 vsi_handle, bool set, } else if (f_info.flag & ICE_FLTR_TX) { f_info.src_id = ICE_SRC_ID_VSI; f_info.src = hw_vsi_id; + f_info.flag |= ICE_FLTR_TX_ONLY; } f_list_entry.fltr_info = f_info; @@ -4421,13 +4584,13 @@ int ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 *counter_id) { - DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); + DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); u16 buf_len = __struct_size(buf); int status; buf->num_elems = cpu_to_le16(num_items); - buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & - ICE_AQC_RES_TYPE_M) | alloc_shared); + buf->res_type = cpu_to_le16(FIELD_PREP(ICE_AQC_RES_TYPE_M, type) | + alloc_shared); status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_alloc_res); if (status) @@ -4449,13 +4612,13 @@ int ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 counter_id) { - DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); + DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); u16 buf_len = __struct_size(buf); int status; buf->num_elems = cpu_to_le16(num_items); - buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & - ICE_AQC_RES_TYPE_M) | alloc_shared); + buf->res_type = cpu_to_le16(FIELD_PREP(ICE_AQC_RES_TYPE_M, type) | + alloc_shared); buf->elem[0].e.sw_resp = cpu_to_le16(counter_id); status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_free_res); @@ -4479,20 +4642,17 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, */ int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id) { - DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); + DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); u16 buf_len = __struct_size(buf); + u16 res_type; int status; buf->num_elems = cpu_to_le16(1); + res_type = FIELD_PREP(ICE_AQC_RES_TYPE_M, type); if (shared) - buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & - ICE_AQC_RES_TYPE_M) | - ICE_AQC_RES_TYPE_FLAG_SHARED); - else - buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & - ICE_AQC_RES_TYPE_M) & - ~ICE_AQC_RES_TYPE_FLAG_SHARED); + res_type |= ICE_AQC_RES_TYPE_FLAG_SHARED; + buf->res_type = cpu_to_le16(res_type); buf->elem[0].e.sw_resp = cpu_to_le16(res_id); status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_share_res); @@ -4532,6 +4692,7 @@ static const struct ice_prot_ext_tbl_entry ice_prot_ext[ICE_PROTOCOL_LAST] = { ICE_PROTOCOL_ENTRY(ICE_NVGRE, 0, 2, 4, 6), ICE_PROTOCOL_ENTRY(ICE_GTP, 8, 10, 12, 14, 16, 18, 20, 22), ICE_PROTOCOL_ENTRY(ICE_GTP_NO_PAY, 8, 10, 12, 14), + ICE_PROTOCOL_ENTRY(ICE_PFCP, 8, 10, 12, 14, 16, 18, 20, 22), ICE_PROTOCOL_ENTRY(ICE_PPPOE, 0, 2, 4, 6), ICE_PROTOCOL_ENTRY(ICE_L2TPV3, 0, 2, 4, 6, 8, 10), ICE_PROTOCOL_ENTRY(ICE_VLAN_EX, 2, 0), @@ -4565,6 +4726,7 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { { ICE_NVGRE, ICE_GRE_OF_HW }, { ICE_GTP, ICE_UDP_OF_HW }, { ICE_GTP_NO_PAY, ICE_UDP_ILOS_HW }, + { ICE_PFCP, ICE_UDP_ILOS_HW }, { ICE_PPPOE, ICE_PPPOE_HW }, { ICE_L2TPV3, ICE_L2TPV3_HW }, { ICE_VLAN_EX, ICE_VLAN_OF_HW }, @@ -4577,12 +4739,13 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { * @hw: pointer to the hardware structure * @lkup_exts: extension sequence to match * @rinfo: information regarding the rule e.g. priority and action info + * @is_add: flag of adding recipe * * Returns index of matching recipe, or ICE_MAX_NUM_RECIPES if not found. */ static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, - const struct ice_adv_rule_info *rinfo) + const struct ice_adv_rule_info *rinfo, bool is_add) { bool refresh_required = true; struct ice_sw_recipe *recp; @@ -4596,11 +4759,12 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, * entry update it in our SW bookkeeping and continue with the * matching. */ - if (!recp[i].recp_created) + if (hw->recp_reuse) { if (ice_get_recp_frm_fw(hw, hw->switch_info->recp_list, i, - &refresh_required)) + &refresh_required, is_add)) continue; + } /* Skip inverse action recipes */ if (recp[i].root_buf && recp[i].root_buf->content.act_ctrl & @@ -5024,8 +5188,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, entry->chain_idx = chain_idx; content->result_indx = ICE_AQ_RECIPE_RESULT_EN | - ((chain_idx << ICE_AQ_RECIPE_RESULT_DATA_S) & - ICE_AQ_RECIPE_RESULT_DATA_M); + FIELD_PREP(ICE_AQ_RECIPE_RESULT_DATA_M, + chain_idx); clear_bit(chain_idx, result_idx_bm); chain_idx = find_first_bit(result_idx_bm, ICE_MAX_FV_WORDS); @@ -5272,6 +5436,9 @@ ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo, case ICE_SW_TUN_GTPC: prof_type = ICE_PROF_TUN_GTPC; break; + case ICE_SW_TUN_PFCP: + prof_type = ICE_PROF_TUN_PFCP; + break; case ICE_SW_TUN_AND_NON_TUN: default: prof_type = ICE_PROF_ALL; @@ -5282,6 +5449,49 @@ ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo, } /** + * ice_subscribe_recipe - subscribe to an existing recipe + * @hw: pointer to the hardware structure + * @rid: recipe ID to subscribe to + * + * Return: 0 on success, and others on error + */ +static int ice_subscribe_recipe(struct ice_hw *hw, u16 rid) +{ + DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); + u16 buf_len = __struct_size(sw_buf); + u16 res_type; + int status; + + /* Prepare buffer to allocate resource */ + sw_buf->num_elems = cpu_to_le16(1); + res_type = FIELD_PREP(ICE_AQC_RES_TYPE_M, ICE_AQC_RES_TYPE_RECIPE) | + ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_SHARED | + ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_CTL; + sw_buf->res_type = cpu_to_le16(res_type); + + sw_buf->elem[0].e.sw_resp = cpu_to_le16(rid); + + status = ice_aq_alloc_free_res(hw, sw_buf, buf_len, + ice_aqc_opc_alloc_res); + + return status; +} + +/** + * ice_subscribable_recp_shared - share an existing subscribable recipe + * @hw: pointer to the hardware structure + * @rid: recipe ID to subscribe to + */ +static void ice_subscribable_recp_shared(struct ice_hw *hw, u16 rid) +{ + struct ice_sw_recipe *recps = hw->switch_info->recp_list; + u16 sub_rid; + + for_each_set_bit(sub_rid, recps[rid].r_bitmap, ICE_MAX_NUM_RECIPES) + ice_subscribe_recipe(hw, sub_rid); +} + +/** * ice_add_adv_recipe - Add an advanced recipe that is not part of the default * @hw: pointer to hardware structure * @lkups: lookup elements or match criteria for the advanced recipe, one @@ -5303,6 +5513,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, struct ice_sw_fv_list_entry *tmp; struct ice_sw_recipe *rm; int status = 0; + u16 rid_tmp; u8 i; if (!lkups_cnt) @@ -5380,10 +5591,14 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, } /* Look for a recipe which matches our requested fv / mask list */ - *rid = ice_find_recp(hw, lkup_exts, rinfo); - if (*rid < ICE_MAX_NUM_RECIPES) + *rid = ice_find_recp(hw, lkup_exts, rinfo, true); + if (*rid < ICE_MAX_NUM_RECIPES) { /* Success if found a recipe that match the existing criteria */ + if (hw->recp_reuse) + ice_subscribable_recp_shared(hw, *rid); + goto err_unroll; + } rm->tun_type = rinfo->tun_type; /* Recipe we need does not exist, add a recipe */ @@ -5396,26 +5611,28 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, */ list_for_each_entry(fvit, &rm->fv_list, list_entry) { DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + u64 recp_assoc; u16 j; status = ice_aq_get_recipe_to_profile(hw, fvit->profile_id, - (u8 *)r_bitmap, NULL); + &recp_assoc, NULL); if (status) - goto err_unroll; + goto err_free_recipe; + bitmap_from_arr64(r_bitmap, &recp_assoc, ICE_MAX_NUM_RECIPES); bitmap_or(r_bitmap, r_bitmap, rm->r_bitmap, ICE_MAX_NUM_RECIPES); status = ice_acquire_change_lock(hw, ICE_RES_WRITE); if (status) - goto err_unroll; + goto err_free_recipe; + bitmap_to_arr64(&recp_assoc, r_bitmap, ICE_MAX_NUM_RECIPES); status = ice_aq_map_recipe_to_profile(hw, fvit->profile_id, - (u8 *)r_bitmap, - NULL); + recp_assoc, NULL); ice_release_change_lock(hw); if (status) - goto err_unroll; + goto err_free_recipe; /* Update profile to recipe bitmap array */ bitmap_copy(profile_to_recipe[fvit->profile_id], r_bitmap, @@ -5429,6 +5646,16 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, *rid = rm->root_rid; memcpy(&hw->switch_info->recp_list[*rid].lkup_exts, lkup_exts, sizeof(*lkup_exts)); + goto err_unroll; + +err_free_recipe: + if (hw->recp_reuse) { + for_each_set_bit(rid_tmp, rm->r_bitmap, ICE_MAX_NUM_RECIPES) { + if (!ice_free_recipe_res(hw, rid_tmp)) + clear_bit(rid_tmp, rm->r_bitmap); + } + } + err_unroll: list_for_each_entry_safe(r_entry, r_tmp, &rm->rg_list, l_entry) { list_del(&r_entry->l_entry); @@ -5554,6 +5781,9 @@ ice_find_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, case ICE_SW_TUN_VXLAN: match |= ICE_PKT_TUN_UDP; break; + case ICE_SW_TUN_PFCP: + match |= ICE_PKT_PFCP; + break; default: break; } @@ -5694,6 +5924,9 @@ ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, case ICE_GTP: len = sizeof(struct ice_udp_gtp_hdr); break; + case ICE_PFCP: + len = sizeof(struct ice_pfcp_hdr); + break; case ICE_PPPOE: len = sizeof(struct ice_pppoe_hdr); break; @@ -6065,6 +6298,7 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, rinfo->sw_act.fltr_act == ICE_FWD_TO_Q || rinfo->sw_act.fltr_act == ICE_FWD_TO_QGRP || rinfo->sw_act.fltr_act == ICE_DROP_PACKET || + rinfo->sw_act.fltr_act == ICE_MIRROR_PACKET || rinfo->sw_act.fltr_act == ICE_NOP)) { status = -EIO; goto free_pkt_profile; @@ -6077,9 +6311,11 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, } if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI || - rinfo->sw_act.fltr_act == ICE_NOP) + rinfo->sw_act.fltr_act == ICE_MIRROR_PACKET || + rinfo->sw_act.fltr_act == ICE_NOP) { rinfo->sw_act.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); + } if (rinfo->src_vsi) rinfo->sw_act.src = ice_get_hw_vsi_num(hw, rinfo->src_vsi); @@ -6115,38 +6351,45 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, status = -ENOMEM; goto free_pkt_profile; } - if (!rinfo->flags_info.act_valid) { - act |= ICE_SINGLE_ACT_LAN_ENABLE; - act |= ICE_SINGLE_ACT_LB_ENABLE; - } else { - act |= rinfo->flags_info.act & (ICE_SINGLE_ACT_LAN_ENABLE | - ICE_SINGLE_ACT_LB_ENABLE); + + if (rinfo->sw_act.fltr_act != ICE_MIRROR_PACKET) { + if (!rinfo->flags_info.act_valid) { + act |= ICE_SINGLE_ACT_LAN_ENABLE; + act |= ICE_SINGLE_ACT_LB_ENABLE; + } else { + act |= rinfo->flags_info.act & (ICE_SINGLE_ACT_LAN_ENABLE | + ICE_SINGLE_ACT_LB_ENABLE); + } } switch (rinfo->sw_act.fltr_act) { case ICE_FWD_TO_VSI: - act |= (rinfo->sw_act.fwd_id.hw_vsi_id << - ICE_SINGLE_ACT_VSI_ID_S) & ICE_SINGLE_ACT_VSI_ID_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, + rinfo->sw_act.fwd_id.hw_vsi_id); act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT; break; case ICE_FWD_TO_Q: act |= ICE_SINGLE_ACT_TO_Q; - act |= (rinfo->sw_act.fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & - ICE_SINGLE_ACT_Q_INDEX_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_Q_INDEX_M, + rinfo->sw_act.fwd_id.q_id); break; case ICE_FWD_TO_QGRP: q_rgn = rinfo->sw_act.qgrp_size > 0 ? (u8)ilog2(rinfo->sw_act.qgrp_size) : 0; act |= ICE_SINGLE_ACT_TO_Q; - act |= (rinfo->sw_act.fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & - ICE_SINGLE_ACT_Q_INDEX_M; - act |= (q_rgn << ICE_SINGLE_ACT_Q_REGION_S) & - ICE_SINGLE_ACT_Q_REGION_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_Q_INDEX_M, + rinfo->sw_act.fwd_id.q_id); + act |= FIELD_PREP(ICE_SINGLE_ACT_Q_REGION_M, q_rgn); break; case ICE_DROP_PACKET: act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP | ICE_SINGLE_ACT_VALID_BIT; break; + case ICE_MIRROR_PACKET: + act |= ICE_SINGLE_ACT_OTHER_ACTS; + act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, + rinfo->sw_act.fwd_id.hw_vsi_id); + break; case ICE_NOP: act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, rinfo->sw_act.fwd_id.hw_vsi_id); @@ -6432,7 +6675,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, return -EIO; } - rid = ice_find_recp(hw, &lkup_exts, rinfo); + rid = ice_find_recp(hw, &lkup_exts, rinfo, false); /* If did not find a recipe that match the existing criteria */ if (rid == ICE_MAX_NUM_RECIPES) return -EINVAL; @@ -6476,14 +6719,21 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, ice_aqc_opc_remove_sw_rules, NULL); if (!status || status == -ENOENT) { struct ice_switch_info *sw = hw->switch_info; + struct ice_sw_recipe *r_list = sw->recp_list; mutex_lock(rule_lock); list_del(&list_elem->list_entry); devm_kfree(ice_hw_to_dev(hw), list_elem->lkups); devm_kfree(ice_hw_to_dev(hw), list_elem); mutex_unlock(rule_lock); - if (list_empty(&sw->recp_list[rid].filt_rules)) - sw->recp_list[rid].adv_rule = false; + if (list_empty(&r_list[rid].filt_rules)) { + r_list[rid].adv_rule = false; + + /* All rules for this recipe are now removed */ + if (hw->recp_reuse) + ice_release_recipe_res(hw, + &r_list[rid]); + } } kfree(s_rule); } diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index db7e501b7e0a..ad98e98c812d 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -8,8 +8,9 @@ #define ICE_SW_CFG_MAX_BUF_LEN 2048 #define ICE_DFLT_VSI_INVAL 0xff -#define ICE_FLTR_RX BIT(0) -#define ICE_FLTR_TX BIT(1) +#define ICE_FLTR_RX BIT(0) +#define ICE_FLTR_TX BIT(1) +#define ICE_FLTR_TX_ONLY BIT(2) #define ICE_VSI_INVAL_ID 0xffff #define ICE_INVAL_Q_HANDLE 0xFFFF @@ -21,6 +22,8 @@ #define ICE_PROFID_IPV6_GTPC_NO_TEID 45 #define ICE_PROFID_IPV6_GTPU_TEID 46 #define ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER 70 +#define ICE_PROFID_IPV4_PFCP_NODE 79 +#define ICE_PROFID_IPV6_PFCP_SESSION 82 #define ICE_SW_RULE_VSI_LIST_SIZE(s, n) struct_size((s), vsi, (n)) #define ICE_SW_RULE_RX_TX_HDR_SIZE(s, l) struct_size((s), hdr_data, (l)) @@ -424,10 +427,11 @@ int ice_aq_add_recipe(struct ice_hw *hw, struct ice_aqc_recipe_data_elem *s_recipe_list, u16 num_recipes, struct ice_sq_cd *cd); int -ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, +ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 *r_assoc, struct ice_sq_cd *cd); int -ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, +ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 r_assoc, struct ice_sq_cd *cd); +void ice_init_chk_recipe_reuse_support(struct ice_hw *hw); #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index 37b54db91df2..8bd24b33f3a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -28,6 +28,8 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, * - ICE_TC_FLWR_FIELD_VLAN_TPID (present if specified) * - Tunnel flag (present if tunnel) */ + if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS) + lkups_cnt++; if (flags & ICE_TC_FLWR_FIELD_TENANT_ID) lkups_cnt++; @@ -35,7 +37,10 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, if (flags & ICE_TC_FLWR_FIELD_ENC_DST_MAC) lkups_cnt++; - if (flags & ICE_TC_FLWR_FIELD_ENC_OPTS) + if (flags & ICE_TC_FLWR_FIELD_GTP_OPTS) + lkups_cnt++; + + if (flags & ICE_TC_FLWR_FIELD_PFCP_OPTS) lkups_cnt++; if (flags & (ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 | @@ -138,6 +143,8 @@ ice_proto_type_from_tunnel(enum ice_tunnel_type type) return ICE_GTP; case TNL_GTPC: return ICE_GTP_NO_PAY; + case TNL_PFCP: + return ICE_PFCP; default: return 0; } @@ -157,6 +164,8 @@ ice_sw_type_from_tunnel(enum ice_tunnel_type type) return ICE_SW_TUN_GTPU; case TNL_GTPC: return ICE_SW_TUN_GTPC; + case TNL_PFCP: + return ICE_SW_TUN_PFCP; default: return ICE_NON_TUN; } @@ -219,8 +228,7 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, i++; } - if (flags & ICE_TC_FLWR_FIELD_ENC_OPTS && - (fltr->tunnel_type == TNL_GTPU || fltr->tunnel_type == TNL_GTPC)) { + if (flags & ICE_TC_FLWR_FIELD_GTP_OPTS) { list[i].type = ice_proto_type_from_tunnel(fltr->tunnel_type); if (fltr->gtp_pdu_info_masks.pdu_type) { @@ -237,6 +245,22 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, i++; } + if (flags & ICE_TC_FLWR_FIELD_PFCP_OPTS) { + struct ice_pfcp_hdr *hdr_h, *hdr_m; + + hdr_h = &list[i].h_u.pfcp_hdr; + hdr_m = &list[i].m_u.pfcp_hdr; + list[i].type = ICE_PFCP; + + hdr_h->flags = fltr->pfcp_meta_keys.type; + hdr_m->flags = fltr->pfcp_meta_masks.type & 0x01; + + hdr_h->seid = fltr->pfcp_meta_keys.seid; + hdr_m->seid = fltr->pfcp_meta_masks.seid; + + i++; + } + if (flags & (ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 | ICE_TC_FLWR_FIELD_ENC_DEST_IPV4)) { list[i].type = ice_proto_type_from_ipv4(false); @@ -363,12 +387,20 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, /* Always add direction metadata */ ice_rule_add_direction_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); + if (tc_fltr->direction == ICE_ESWITCH_FLTR_EGRESS) { + ice_rule_add_src_vsi_metadata(&list[i]); + i++; + } + rule_info->tun_type = ice_sw_type_from_tunnel(tc_fltr->tunnel_type); if (tc_fltr->tunnel_type != TNL_LAST) { i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list, i); - headers = &tc_fltr->inner_headers; - inner = true; + /* PFCP is considered non-tunneled - don't swap headers. */ + if (tc_fltr->tunnel_type != TNL_PFCP) { + headers = &tc_fltr->inner_headers; + inner = true; + } } if (flags & ICE_TC_FLWR_FIELD_ETH_TYPE_ID) { @@ -622,6 +654,8 @@ static int ice_tc_tun_get_type(struct net_device *tunnel_dev) */ if (netif_is_gtp(tunnel_dev)) return TNL_GTPU; + if (netif_is_pfcp(tunnel_dev)) + return TNL_PFCP; return TNL_LAST; } @@ -630,32 +664,98 @@ bool ice_is_tunnel_supported(struct net_device *dev) return ice_tc_tun_get_type(dev) != TNL_LAST; } -static int -ice_eswitch_tc_parse_action(struct ice_tc_flower_fltr *fltr, - struct flow_action_entry *act) +static bool ice_tc_is_dev_uplink(struct net_device *dev) +{ + return netif_is_ice(dev) || ice_is_tunnel_supported(dev); +} + +static int ice_tc_setup_action(struct net_device *filter_dev, + struct ice_tc_flower_fltr *fltr, + struct net_device *target_dev, + enum ice_sw_fwd_act_type action) { struct ice_repr *repr; + if (action != ICE_FWD_TO_VSI && action != ICE_MIRROR_PACKET) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported action to setup provided"); + return -EINVAL; + } + + fltr->action.fltr_act = action; + + if (ice_is_port_repr_netdev(filter_dev) && + ice_is_port_repr_netdev(target_dev)) { + 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)) { + 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)) { + 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"); + return -EINVAL; + } + + return 0; +} + +static int +ice_tc_setup_drop_action(struct net_device *filter_dev, + struct ice_tc_flower_fltr *fltr) +{ + 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 { + NL_SET_ERR_MSG_MOD(fltr->extack, + "Unsupported netdevice in switchdev mode"); + return -EINVAL; + } + + return 0; +} + +static int ice_eswitch_tc_parse_action(struct net_device *filter_dev, + struct ice_tc_flower_fltr *fltr, + struct flow_action_entry *act) +{ + int err; + switch (act->id) { case FLOW_ACTION_DROP: - fltr->action.fltr_act = ICE_DROP_PACKET; + err = ice_tc_setup_drop_action(filter_dev, fltr); + if (err) + return err; + break; case FLOW_ACTION_REDIRECT: - fltr->action.fltr_act = ICE_FWD_TO_VSI; + err = ice_tc_setup_action(filter_dev, fltr, + act->dev, ICE_FWD_TO_VSI); + if (err) + return err; - if (ice_is_port_repr_netdev(act->dev)) { - repr = ice_netdev_to_repr(act->dev); + break; - fltr->dest_vsi = repr->src_vsi; - fltr->direction = ICE_ESWITCH_FLTR_INGRESS; - } else if (netif_is_ice(act->dev) || - ice_is_tunnel_supported(act->dev)) { - fltr->direction = ICE_ESWITCH_FLTR_EGRESS; - } else { - NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported netdevice in switchdev mode"); - return -EINVAL; - } + case FLOW_ACTION_MIRRED: + err = ice_tc_setup_action(filter_dev, fltr, + act->dev, ICE_MIRROR_PACKET); + if (err) + return err; break; @@ -680,7 +780,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) int ret; int i; - if (!flags || (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT)) { + if (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported encap field(s)"); return -EOPNOTSUPP; } @@ -696,10 +796,6 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) goto exit; } - /* egress traffic is always redirect to uplink */ - if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS) - fltr->dest_vsi = vsi->back->switchdev.uplink_vsi; - rule_info.sw_act.fltr_act = fltr->action.fltr_act; if (fltr->action.fltr_act != ICE_DROP_PACKET) rule_info.sw_act.vsi_handle = fltr->dest_vsi->idx; @@ -713,17 +809,26 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) rule_info.flags_info.act_valid = true; if (fltr->direction == ICE_ESWITCH_FLTR_INGRESS) { + /* Uplink to VF */ rule_info.sw_act.flag |= ICE_FLTR_RX; rule_info.sw_act.src = hw->pf_id; rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE; - } else { + } 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; rule_info.sw_act.src = vsi->idx; rule_info.flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE; + } else { + /* VF to VF */ + rule_info.sw_act.flag |= ICE_FLTR_TX; + rule_info.sw_act.src = vsi->idx; + rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE; } /* specify the cookie as filter_rule_id */ rule_info.fltr_rule_id = fltr->cookie; + rule_info.src_vsi = vsi->idx; ret = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added); if (ret == -EEXIST) { @@ -1305,7 +1410,8 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, } } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS) && + (fltr->tunnel_type == TNL_GTPU || fltr->tunnel_type == TNL_GTPC)) { struct flow_match_enc_opts match; flow_rule_match_enc_opts(rule, &match); @@ -1316,7 +1422,21 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, memcpy(&fltr->gtp_pdu_info_masks, &match.mask->data[0], sizeof(struct gtp_pdu_session_info)); - fltr->flags |= ICE_TC_FLWR_FIELD_ENC_OPTS; + fltr->flags |= ICE_TC_FLWR_FIELD_GTP_OPTS; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS) && + fltr->tunnel_type == TNL_PFCP) { + struct flow_match_enc_opts match; + + flow_rule_match_enc_opts(rule, &match); + + memcpy(&fltr->pfcp_meta_keys, match.key->data, + sizeof(struct pfcp_metadata)); + memcpy(&fltr->pfcp_meta_masks, match.mask->data, + sizeof(struct pfcp_metadata)); + + fltr->flags |= ICE_TC_FLWR_FIELD_PFCP_OPTS; } return 0; @@ -1377,15 +1497,22 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, return err; } - /* header pointers should point to the inner headers, outer - * header were already set by ice_parse_tunnel_attr - */ - headers = &fltr->inner_headers; + /* PFCP is considered non-tunneled - don't swap headers. */ + if (fltr->tunnel_type != TNL_PFCP) { + /* Header pointers should point to the inner headers, + * outer header were already set by + * ice_parse_tunnel_attr(). + */ + headers = &fltr->inner_headers; + } } else if (dissector->used_keys & (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS))) { + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Tunnel key used, but device isn't a tunnel"); return -EOPNOTSUPP; } else { @@ -1531,6 +1658,10 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, flow_rule_match_control(rule, &match); addr_type = match.key->addr_type; + + if (flow_rule_has_control_flags(match.mask->flags, + fltr->extack)) + return -EOPNOTSUPP; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { @@ -1745,16 +1876,17 @@ ice_tc_parse_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr, /** * ice_parse_tc_flower_actions - Parse the actions for a TC filter + * @filter_dev: Pointer to device on which filter is being added * @vsi: Pointer to VSI * @cls_flower: Pointer to TC flower offload structure * @fltr: Pointer to TC flower filter structure * * Parse the actions for a TC filter */ -static int -ice_parse_tc_flower_actions(struct ice_vsi *vsi, - struct flow_cls_offload *cls_flower, - struct ice_tc_flower_fltr *fltr) +static int ice_parse_tc_flower_actions(struct net_device *filter_dev, + struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower, + struct ice_tc_flower_fltr *fltr) { struct flow_rule *rule = flow_cls_offload_flow_rule(cls_flower); struct flow_action *flow_action = &rule->action; @@ -1769,7 +1901,7 @@ ice_parse_tc_flower_actions(struct ice_vsi *vsi, flow_action_for_each(i, act, flow_action) { if (ice_is_eswitch_mode_switchdev(vsi->back)) - err = ice_eswitch_tc_parse_action(fltr, act); + err = ice_eswitch_tc_parse_action(filter_dev, fltr, act); else err = ice_tc_parse_action(vsi, fltr, act); if (err) @@ -1856,7 +1988,7 @@ ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi, if (err < 0) goto err; - err = ice_parse_tc_flower_actions(vsi, f, fltr); + err = ice_parse_tc_flower_actions(netdev, vsi, f, fltr); if (err < 0) goto err; diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h index 65d387163a46..d84f153517ec 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h @@ -4,6 +4,9 @@ #ifndef _ICE_TC_LIB_H_ #define _ICE_TC_LIB_H_ +#include <linux/bits.h> +#include <net/pfcp.h> + #define ICE_TC_FLWR_FIELD_DST_MAC BIT(0) #define ICE_TC_FLWR_FIELD_SRC_MAC BIT(1) #define ICE_TC_FLWR_FIELD_VLAN BIT(2) @@ -22,7 +25,7 @@ #define ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT BIT(15) #define ICE_TC_FLWR_FIELD_ENC_DST_MAC BIT(16) #define ICE_TC_FLWR_FIELD_ETH_TYPE_ID BIT(17) -#define ICE_TC_FLWR_FIELD_ENC_OPTS BIT(18) +#define ICE_TC_FLWR_FIELD_GTP_OPTS BIT(18) #define ICE_TC_FLWR_FIELD_CVLAN BIT(19) #define ICE_TC_FLWR_FIELD_PPPOE_SESSID BIT(20) #define ICE_TC_FLWR_FIELD_PPP_PROTO BIT(21) @@ -34,6 +37,7 @@ #define ICE_TC_FLWR_FIELD_VLAN_PRIO BIT(27) #define ICE_TC_FLWR_FIELD_CVLAN_PRIO BIT(28) #define ICE_TC_FLWR_FIELD_VLAN_TPID BIT(29) +#define ICE_TC_FLWR_FIELD_PFCP_OPTS BIT(30) #define ICE_TC_FLOWER_MASK_32 0xFFFFFFFF @@ -161,6 +165,8 @@ struct ice_tc_flower_fltr { __be32 tenant_id; struct gtp_pdu_session_info gtp_pdu_info_keys; struct gtp_pdu_session_info gtp_pdu_info_masks; + struct pfcp_metadata pfcp_meta_keys; + struct pfcp_metadata pfcp_meta_masks; u32 flags; u8 tunnel_type; struct ice_tc_flower_action action; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 52d0a126eb61..8bb743f78fcb 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -513,11 +513,6 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) if (ice_is_xdp_ena_vsi(rx_ring->vsi)) WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog); - if (rx_ring->vsi->type == ICE_VSI_PF && - !xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) - if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->q_index, rx_ring->q_vector->napi.napi_id)) - goto err; return 0; err: @@ -557,13 +552,14 @@ ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size) * @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 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) + struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc) { unsigned int ret = ICE_XDP_PASS; u32 act; @@ -571,6 +567,8 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, if (!xdp_prog) goto exit; + ice_xdp_meta_set_desc(xdp, eop_desc); + act = bpf_prog_run_xdp(xdp_prog, xdp); switch (act) { case XDP_PASS: @@ -600,9 +598,7 @@ out_failure: ret = ICE_XDP_CONSUMED; } exit: - rx_buf->act = ret; - if (unlikely(xdp_buff_has_frags(xdp))) - ice_set_rx_bufs_act(xdp, rx_ring, ret); + ice_set_rx_bufs_act(xdp, rx_ring, ret); } /** @@ -890,14 +886,17 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, } if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { - if (unlikely(xdp_buff_has_frags(xdp))) - ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED); + ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED); return -ENOMEM; } __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page, rx_buf->page_offset, size); sinfo->xdp_frags_size += size; + /* remember frag count before XDP prog execution; bpf_xdp_adjust_tail() + * can pop off frags but driver has to handle it on its own + */ + rx_ring->nr_frags = sinfo->nr_frags; if (page_is_pfmemalloc(rx_buf->page)) xdp_buff_set_frag_pfmemalloc(xdp); @@ -1052,8 +1051,7 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) } /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE, - GFP_ATOMIC | __GFP_NOWARN); + skb = napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE); if (unlikely(!skb)) return NULL; @@ -1180,8 +1178,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) struct sk_buff *skb; unsigned int size; u16 stat_err_bits; - u16 vlan_tag = 0; - u16 rx_ptype; + u16 vlan_tci; /* get the Rx desc from Rx ring based on 'next_to_clean' */ rx_desc = ICE_RX_DESC(rx_ring, ntc); @@ -1241,7 +1238,7 @@ 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); + ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc); if (rx_buf->act == ICE_XDP_PASS) goto construct_skb; total_rx_bytes += xdp_get_buff_len(xdp); @@ -1249,6 +1246,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) xdp->data = NULL; rx_ring->first_desc = ntc; + rx_ring->nr_frags = 0; continue; construct_skb: if (likely(ice_ring_uses_build_skb(rx_ring))) @@ -1264,10 +1262,12 @@ construct_skb: ICE_XDP_CONSUMED); xdp->data = NULL; rx_ring->first_desc = ntc; + rx_ring->nr_frags = 0; break; } xdp->data = NULL; rx_ring->first_desc = ntc; + rx_ring->nr_frags = 0; stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); if (unlikely(ice_test_staterr(rx_desc->wb.status_error0, @@ -1276,7 +1276,7 @@ construct_skb: continue; } - vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc); + vlan_tci = ice_get_vlan_tci(rx_desc); /* pad the skb if needed, to make a valid ethernet frame */ if (eth_skb_pad(skb)) @@ -1286,14 +1286,11 @@ construct_skb: total_rx_bytes += skb->len; /* populate checksum, VLAN, and protocol */ - rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) & - ICE_RX_FLEX_DESC_PTYPE_M; - - ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); + ice_process_skb_fields(rx_ring, rx_desc, skb); ice_trace(clean_rx_irq_indicate, rx_ring, rx_desc, skb); /* send completed skb up the stack */ - ice_receive_skb(rx_ring, skb, vlan_tag); + ice_receive_skb(rx_ring, skb, vlan_tci); /* update budget accounting */ total_rx_pkts++; @@ -1494,9 +1491,9 @@ static void ice_set_wb_on_itr(struct ice_q_vector *q_vector) * be static in non-adaptive mode (user configured) */ wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx), - ((ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S) & - GLINT_DYN_CTL_ITR_INDX_M) | GLINT_DYN_CTL_INTENA_MSK_M | - GLINT_DYN_CTL_WB_ON_ITR_M); + FIELD_PREP(GLINT_DYN_CTL_ITR_INDX_M, ICE_ITR_NONE) | + FIELD_PREP(GLINT_DYN_CTL_INTENA_MSK_M, 1) | + FIELD_PREP(GLINT_DYN_CTL_WB_ON_ITR_M, 1)); q_vector->wb_on_itr = true; } @@ -2306,9 +2303,6 @@ ice_tstamp(struct ice_tx_ring *tx_ring, struct sk_buff *skb, if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) return; - if (!tx_ring->ptp_tx) - return; - /* Tx timestamps cannot be sampled when doing TSO */ if (first->tx_flags & ICE_TX_FLAGS_TSO) return; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 166413fc33f4..feba314a3fe4 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -257,6 +257,20 @@ enum ice_rx_dtype { ICE_RX_DTYPE_SPLIT_ALWAYS = 2, }; +struct ice_pkt_ctx { + u64 cached_phctime; + __be16 vlan_proto; +}; + +struct ice_xdp_buff { + struct xdp_buff xdp_buff; + const union ice_32b_rx_flex_desc *eop_desc; + const struct ice_pkt_ctx *pkt_ctx; +}; + +/* Required for compatibility with xdp_buffs from xsk_pool */ +static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0); + /* indices into GLINT_ITR registers */ #define ICE_RX_ITR ICE_IDX_ITR0 #define ICE_TX_ITR ICE_IDX_ITR1 @@ -298,7 +312,6 @@ enum ice_dynamic_itr { /* descriptor ring, associated with a VSI */ struct ice_rx_ring { /* CL1 - 1st cacheline starts here */ - struct ice_rx_ring *next; /* pointer to next ring in q_vector */ void *desc; /* Descriptor ring memory */ struct device *dev; /* Used for DMA mapping */ struct net_device *netdev; /* netdev ring maps to */ @@ -310,13 +323,24 @@ struct ice_rx_ring { u16 count; /* Number of descriptors */ u16 reg_idx; /* HW register index of the ring */ u16 next_to_alloc; - /* CL2 - 2nd cacheline starts here */ + union { struct ice_rx_buf *rx_buf; struct xdp_buff **xdp_buf; }; - struct xdp_buff xdp; + /* CL2 - 2nd cacheline starts here */ + union { + struct ice_xdp_buff xdp_ext; + struct xdp_buff xdp; + }; /* CL3 - 3rd cacheline starts here */ + union { + struct ice_pkt_ctx pkt_ctx; + struct { + u64 cached_phctime; + __be16 vlan_proto; + }; + }; struct bpf_prog *xdp_prog; u16 rx_offset; @@ -332,14 +356,16 @@ struct ice_rx_ring { /* CL4 - 4th cacheline starts here */ struct ice_channel *ch; struct ice_tx_ring *xdp_ring; + struct ice_rx_ring *next; /* pointer to next ring in q_vector */ struct xsk_buff_pool *xsk_pool; + u32 nr_frags; dma_addr_t dma; /* physical address of ring */ - u64 cached_phctime; u16 rx_buf_len; u8 dcb_tc; /* Traffic class of ring */ u8 ptp_rx; #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) u8 flags; /* CL5 - 5th cacheline starts here */ struct xdp_rxq_info xdp_rxq; @@ -380,7 +406,6 @@ struct ice_tx_ring { #define ICE_TX_FLAGS_RING_VLAN_L2TAG2 BIT(2) u8 flags; u8 dcb_tc; /* Traffic class of ring */ - u8 ptp_tx; } ____cacheline_internodealigned_in_smp; static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 7e06373e14d9..2719f0e20933 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019, Intel Corporation. */ #include <linux/filter.h> +#include <linux/net/intel/libie/rx.h> #include "ice_txrx_lib.h" #include "ice_eswitch.h" @@ -39,52 +40,44 @@ void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val) } /** - * ice_ptype_to_htype - get a hash type - * @ptype: the ptype value from the descriptor + * ice_get_rx_hash - get RX hash value from descriptor + * @rx_desc: specific descriptor * - * Returns appropriate hash type (such as PKT_HASH_TYPE_L2/L3/L4) to be used by - * skb_set_hash based on PTYPE as parsed by HW Rx pipeline and is part of - * Rx desc. + * Returns hash, if present, 0 otherwise. */ -static enum pkt_hash_types ice_ptype_to_htype(u16 ptype) +static u32 ice_get_rx_hash(const union ice_32b_rx_flex_desc *rx_desc) { - struct ice_rx_ptype_decoded decoded = ice_decode_rx_desc_ptype(ptype); - - if (!decoded.known) - return PKT_HASH_TYPE_NONE; - if (decoded.payload_layer == ICE_RX_PTYPE_PAYLOAD_LAYER_PAY4) - return PKT_HASH_TYPE_L4; - if (decoded.payload_layer == ICE_RX_PTYPE_PAYLOAD_LAYER_PAY3) - return PKT_HASH_TYPE_L3; - if (decoded.outer_ip == ICE_RX_PTYPE_OUTER_L2) - return PKT_HASH_TYPE_L2; - - return PKT_HASH_TYPE_NONE; + const struct ice_32b_rx_flex_desc_nic *nic_mdid; + + if (unlikely(rx_desc->wb.rxdid != ICE_RXDID_FLEX_NIC)) + return 0; + + nic_mdid = (struct ice_32b_rx_flex_desc_nic *)rx_desc; + return le32_to_cpu(nic_mdid->rss_hash); } /** - * ice_rx_hash - set the hash value in the skb + * ice_rx_hash_to_skb - set the hash value in the skb * @rx_ring: descriptor ring * @rx_desc: specific descriptor * @skb: pointer to current skb * @rx_ptype: the ptype value from the descriptor */ static void -ice_rx_hash(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, - struct sk_buff *skb, u16 rx_ptype) +ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring, + const union ice_32b_rx_flex_desc *rx_desc, + struct sk_buff *skb, u16 rx_ptype) { - struct ice_32b_rx_flex_desc_nic *nic_mdid; + struct libeth_rx_pt decoded; u32 hash; - if (!(rx_ring->netdev->features & NETIF_F_RXHASH)) + decoded = libie_rx_pt_parse(rx_ptype); + if (!libeth_rx_pt_has_hash(rx_ring->netdev, decoded)) return; - if (rx_desc->wb.rxdid != ICE_RXDID_FLEX_NIC) - return; - - nic_mdid = (struct ice_32b_rx_flex_desc_nic *)rx_desc; - hash = le32_to_cpu(nic_mdid->rss_hash); - skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype)); + hash = ice_get_rx_hash(rx_desc); + if (likely(hash)) + libeth_rx_pt_set_hash(skb, hash, decoded); } /** @@ -100,37 +93,33 @@ static void ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb, union ice_32b_rx_flex_desc *rx_desc, u16 ptype) { - struct ice_rx_ptype_decoded decoded; + struct libeth_rx_pt decoded; u16 rx_status0, rx_status1; bool ipv4, ipv6; - rx_status0 = le16_to_cpu(rx_desc->wb.status_error0); - rx_status1 = le16_to_cpu(rx_desc->wb.status_error1); - - decoded = ice_decode_rx_desc_ptype(ptype); - /* Start with CHECKSUM_NONE and by default csum_level = 0 */ skb->ip_summed = CHECKSUM_NONE; - skb_checksum_none_assert(skb); - /* check if Rx checksum is enabled */ - if (!(ring->netdev->features & NETIF_F_RXCSUM)) + decoded = libie_rx_pt_parse(ptype); + if (!libeth_rx_pt_has_checksum(ring->netdev, decoded)) return; + rx_status0 = le16_to_cpu(rx_desc->wb.status_error0); + rx_status1 = le16_to_cpu(rx_desc->wb.status_error1); + /* check if HW has decoded the packet and checksum */ if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S))) return; - if (!(decoded.known && decoded.outer_ip)) - return; + ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4; + ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6; - ipv4 = (decoded.outer_ip == ICE_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == ICE_RX_PTYPE_OUTER_IPV4); - ipv6 = (decoded.outer_ip == ICE_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == ICE_RX_PTYPE_OUTER_IPV6); + if (ipv4 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S)))) { + ring->vsi->back->hw_rx_eipe_error++; + return; + } - if (ipv4 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S) | - BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S)))) + if (ipv4 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S)))) goto checksum_fail; if (ipv6 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_IPV6EXADD_S)))) @@ -151,19 +140,10 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb, * we need to bump the checksum level by 1 to reflect the fact that * we are indicating we validated the inner checksum. */ - if (decoded.tunnel_type >= ICE_RX_PTYPE_TUNNEL_IP_GRENAT) + if (decoded.tunnel_type >= LIBETH_RX_PT_TUNNEL_IP_GRENAT) skb->csum_level = 1; - /* Only report checksum unnecessary for TCP, UDP, or SCTP */ - switch (decoded.inner_prot) { - case ICE_RX_PTYPE_INNER_PROT_TCP: - case ICE_RX_PTYPE_INNER_PROT_UDP: - case ICE_RX_PTYPE_INNER_PROT_SCTP: - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; - default: - break; - } + skb->ip_summed = CHECKSUM_UNNECESSARY; return; checksum_fail: @@ -171,11 +151,38 @@ checksum_fail: } /** + * ice_ptp_rx_hwts_to_skb - Put RX timestamp into skb + * @rx_ring: Ring to get the VSI info + * @rx_desc: Receive descriptor + * @skb: Particular skb to send timestamp with + * + * The timestamp is in ns, so we must convert the result first. + */ +static void +ice_ptp_rx_hwts_to_skb(struct ice_rx_ring *rx_ring, + const union ice_32b_rx_flex_desc *rx_desc, + struct sk_buff *skb) +{ + u64 ts_ns = ice_ptp_get_rx_hwts(rx_desc, &rx_ring->pkt_ctx); + + skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(ts_ns); +} + +/** + * ice_get_ptype - Read HW packet type from the descriptor + * @rx_desc: RX descriptor + */ +static u16 ice_get_ptype(const union ice_32b_rx_flex_desc *rx_desc) +{ + return le16_to_cpu(rx_desc->wb.ptype_flex_flags0) & + ICE_RX_FLEX_DESC_PTYPE_M; +} + +/** * ice_process_skb_fields - Populate skb header fields from Rx descriptor * @rx_ring: Rx descriptor ring packet is being transacted on * @rx_desc: pointer to the EOP Rx descriptor * @skb: pointer to current skb being populated - * @ptype: the packet type decoded by hardware * * This function checks the ring, descriptor, and packet information in * order to populate the hash, checksum, VLAN, protocol, and @@ -184,38 +191,45 @@ checksum_fail: void ice_process_skb_fields(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, - struct sk_buff *skb, u16 ptype) + struct sk_buff *skb) { - ice_rx_hash(rx_ring, rx_desc, skb, ptype); + u16 ptype = ice_get_ptype(rx_desc); + + ice_rx_hash_to_skb(rx_ring, rx_desc, skb, ptype); /* modifies the skb - consumes the enet header */ - skb->protocol = eth_type_trans(skb, rx_ring->netdev); + if (unlikely(rx_ring->flags & ICE_RX_FLAGS_MULTIDEV)) { + struct net_device *netdev = ice_eswitch_get_target(rx_ring, + rx_desc); + + if (ice_is_port_repr_netdev(netdev)) + ice_repr_inc_rx_stats(netdev, skb->len); + skb->protocol = eth_type_trans(skb, netdev); + } else { + skb->protocol = eth_type_trans(skb, rx_ring->netdev); + } ice_rx_csum(rx_ring, skb, rx_desc, ptype); if (rx_ring->ptp_rx) - ice_ptp_rx_hwtstamp(rx_ring, rx_desc, skb); + ice_ptp_rx_hwts_to_skb(rx_ring, rx_desc, skb); } /** * ice_receive_skb - Send a completed packet up the stack * @rx_ring: Rx ring in play * @skb: packet to send up - * @vlan_tag: VLAN tag for packet + * @vlan_tci: VLAN TCI for packet * * This function sends the completed packet (via. skb) up the stack using * gro receive functions (with/without VLAN tag) */ void -ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) +ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tci) { - netdev_features_t features = rx_ring->netdev->features; - bool non_zero_vlan = !!(vlan_tag & VLAN_VID_MASK); - - if ((features & NETIF_F_HW_VLAN_CTAG_RX) && non_zero_vlan) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); - else if ((features & NETIF_F_HW_VLAN_STAG_RX) && non_zero_vlan) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021AD), vlan_tag); + if ((vlan_tci & VLAN_VID_MASK) && rx_ring->vlan_proto) + __vlan_hwaccel_put_tag(skb, rx_ring->vlan_proto, + vlan_tci); napi_gro_receive(&rx_ring->q_vector->napi, skb); } @@ -464,3 +478,84 @@ void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res, spin_unlock(&xdp_ring->tx_lock); } } + +/** + * ice_xdp_rx_hw_ts - HW timestamp XDP hint handler + * @ctx: XDP buff pointer + * @ts_ns: destination address + * + * Copy HW timestamp (if available) to the destination address. + */ +static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns) +{ + const struct ice_xdp_buff *xdp_ext = (void *)ctx; + + *ts_ns = ice_ptp_get_rx_hwts(xdp_ext->eop_desc, + xdp_ext->pkt_ctx); + if (!*ts_ns) + return -ENODATA; + + return 0; +} + +/** + * ice_xdp_rx_hash_type - Get XDP-specific hash type from the RX descriptor + * @eop_desc: End of Packet descriptor + */ +static enum xdp_rss_hash_type +ice_xdp_rx_hash_type(const union ice_32b_rx_flex_desc *eop_desc) +{ + return libie_rx_pt_parse(ice_get_ptype(eop_desc)).hash_type; +} + +/** + * ice_xdp_rx_hash - RX hash XDP hint handler + * @ctx: XDP buff pointer + * @hash: hash destination address + * @rss_type: XDP hash type destination address + * + * Copy RX hash (if available) and its type to the destination address. + */ +static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) +{ + const struct ice_xdp_buff *xdp_ext = (void *)ctx; + + *hash = ice_get_rx_hash(xdp_ext->eop_desc); + *rss_type = ice_xdp_rx_hash_type(xdp_ext->eop_desc); + if (!likely(*hash)) + return -ENODATA; + + return 0; +} + +/** + * ice_xdp_rx_vlan_tag - VLAN tag XDP hint handler + * @ctx: XDP buff pointer + * @vlan_proto: destination address for VLAN protocol + * @vlan_tci: destination address for VLAN TCI + * + * Copy VLAN tag (if was stripped) and corresponding protocol + * to the destination address. + */ +static int ice_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, + u16 *vlan_tci) +{ + const struct ice_xdp_buff *xdp_ext = (void *)ctx; + + *vlan_proto = xdp_ext->pkt_ctx->vlan_proto; + if (!*vlan_proto) + return -ENODATA; + + *vlan_tci = ice_get_vlan_tci(xdp_ext->eop_desc); + if (!*vlan_tci) + return -ENODATA; + + return 0; +} + +const struct xdp_metadata_ops ice_xdp_md_ops = { + .xmo_rx_timestamp = ice_xdp_rx_hw_ts, + .xmo_rx_hash = ice_xdp_rx_hash, + .xmo_rx_vlan_tag = ice_xdp_rx_vlan_tag, +}; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index 115969ecdf7b..afcead4baef4 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -12,26 +12,39 @@ * 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 one before last. Last one is handled by caller of this function as it - * is the EOP frag that is currently being processed. This function is - * supposed to be called only when XDP buffer contains frags. + * 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) { - const struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); - u32 first = rx_ring->first_desc; - u32 nr_frags = sinfo->nr_frags; + 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[first]; + buf = &rx_ring->rx_buf[idx]; buf->act = act; - if (++first == cnt) - first = 0; + 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--; + } } } @@ -84,7 +97,7 @@ ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag) } /** - * ice_get_vlan_tag_from_rx_desc - get VLAN from Rx flex descriptor + * ice_get_vlan_tci - get VLAN TCI from Rx flex descriptor * @rx_desc: Rx 32b flex descriptor with RXDID=2 * * The OS and current PF implementation only support stripping a single VLAN tag @@ -92,7 +105,7 @@ ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag) * one is found return the tag, else return 0 to mean no VLAN tag was found. */ static inline u16 -ice_get_vlan_tag_from_rx_desc(union ice_32b_rx_flex_desc *rx_desc) +ice_get_vlan_tci(const union ice_32b_rx_flex_desc *rx_desc) { u16 stat_err_bits; @@ -148,7 +161,17 @@ void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val); void ice_process_skb_fields(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, - struct sk_buff *skb, u16 ptype); + struct sk_buff *skb); void -ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag); +ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tci); + +static inline void +ice_xdp_meta_set_desc(struct xdp_buff *xdp, + union ice_32b_rx_flex_desc *eop_desc) +{ + struct ice_xdp_buff *xdp_ext = container_of(xdp, struct ice_xdp_buff, + xdp_buff); + + xdp_ext->eop_desc = eop_desc; +} #endif /* !_ICE_TXRX_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index a18ca0ff879f..f0796a93f428 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -17,6 +17,7 @@ #include "ice_protocol_type.h" #include "ice_sbq_cmd.h" #include "ice_vlan_mode.h" +#include "ice_fwlog.h" static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc) { @@ -131,6 +132,7 @@ enum ice_mac_type { ICE_MAC_E810, ICE_MAC_E830, ICE_MAC_GENERIC, + ICE_MAC_GENERIC_3K_E825, }; /* Media Types */ @@ -148,7 +150,6 @@ enum ice_vsi_type { ICE_VSI_CTRL = 3, /* equates to ICE_VSI_PF with 1 queue pair */ ICE_VSI_CHNL = 4, ICE_VSI_LB = 6, - ICE_VSI_SWITCHDEV_CTRL = 7, }; struct ice_link_status { @@ -202,6 +203,7 @@ struct ice_phy_info { enum ice_fltr_ptype { /* NONE - used for undef/error */ ICE_FLTR_PTYPE_NONF_NONE = 0, + ICE_FLTR_PTYPE_NONF_ETH, ICE_FLTR_PTYPE_NONF_IPV4_UDP, ICE_FLTR_PTYPE_NONF_IPV4_TCP, ICE_FLTR_PTYPE_NONF_IPV4_SCTP, @@ -246,6 +248,7 @@ struct ice_fd_hw_prof { int cnt; u64 entry_h[ICE_MAX_FDIR_VSI_PER_FILTER][ICE_FD_HW_SEG_MAX]; u16 vsi_h[ICE_MAX_FDIR_VSI_PER_FILTER]; + u64 prof_id[ICE_FD_HW_SEG_MAX]; }; /* Common HW capabilities for SW use */ @@ -293,6 +296,7 @@ struct ice_hw_common_caps { bool pcie_reset_avoidance; /* Post update reset restriction */ bool reset_restrict_support; + bool tx_sched_topo_comp_mode_en; }; /* IEEE 1588 TIME_SYNC specific info */ @@ -351,6 +355,7 @@ struct ice_ts_func_info { #define ICE_TS_TMR0_ENA_M BIT(25) #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) struct ice_ts_dev_info { /* Device specific info */ @@ -364,6 +369,7 @@ struct ice_ts_dev_info { u8 tmr0_ena; u8 tmr1_ena; u8 ts_ll_read; + u8 ts_ll_int_read; }; /* Function specific capabilities */ @@ -377,6 +383,8 @@ struct ice_hw_func_caps { struct ice_ts_func_info ts_func_info; }; +#define ICE_SENSOR_SUPPORT_E810_INT_TEMP_BIT 0 + /* Device wide capabilities */ struct ice_hw_dev_caps { struct ice_hw_common_caps common_cap; @@ -385,6 +393,11 @@ struct ice_hw_dev_caps { u32 num_flow_director_fltr; /* Number of FD filters available */ struct ice_ts_dev_info ts_dev_info; u32 num_funcs; + /* bitmap of supported sensors + * bit 0 - internal temperature sensor + * bit 31:1 - Reserved + */ + u32 supported_sensors; }; /* MAC info */ @@ -730,24 +743,6 @@ struct ice_switch_info { DECLARE_BITMAP(prof_res_bm[ICE_MAX_NUM_PROFILES], ICE_MAX_FV_WORDS); }; -/* FW logging configuration */ -struct ice_fw_log_evnt { - u8 cfg : 4; /* New event enables to configure */ - u8 cur : 4; /* Current/active event enables */ -}; - -struct ice_fw_log_cfg { - u8 cq_en : 1; /* FW logging is enabled via the control queue */ - u8 uart_en : 1; /* FW logging is enabled via UART for all PFs */ - u8 actv_evnts; /* Cumulation of currently enabled log events */ - -#define ICE_FW_LOG_EVNT_INFO (ICE_AQC_FW_LOG_INFO_EN >> ICE_AQC_FW_LOG_EN_S) -#define ICE_FW_LOG_EVNT_INIT (ICE_AQC_FW_LOG_INIT_EN >> ICE_AQC_FW_LOG_EN_S) -#define ICE_FW_LOG_EVNT_FLOW (ICE_AQC_FW_LOG_FLOW_EN >> ICE_AQC_FW_LOG_EN_S) -#define ICE_FW_LOG_EVNT_ERR (ICE_AQC_FW_LOG_ERR_EN >> ICE_AQC_FW_LOG_EN_S) - struct ice_fw_log_evnt evnts[ICE_AQC_FW_LOG_ID_MAX]; -}; - /* Enum defining the different states of the mailbox snapshot in the * PF-VF mailbox overflow detection algorithm. The snapshot can be in * states: @@ -827,7 +822,7 @@ struct ice_mbx_data { enum ice_phy_model { ICE_PHY_UNSUP = -1, ICE_PHY_E810 = 1, - ICE_PHY_E822, + ICE_PHY_E82X, }; /* Port hardware description */ @@ -855,6 +850,8 @@ struct ice_hw { u16 max_burst_size; /* driver sets this value */ + u8 recp_reuse:1; /* indicates whether FW supports recipe reuse */ + /* Tx Scheduler values */ u8 num_tx_sched_layers; u8 num_tx_sched_phys_layers; @@ -889,7 +886,9 @@ struct ice_hw { u8 fw_patch; /* firmware patch version */ u32 fw_build; /* firmware build number */ - struct ice_fw_log_cfg fw_log; + struct ice_fwlog_cfg fwlog_cfg; + bool fwlog_supported; /* does hardware support FW logging? */ + struct ice_fwlog_ring fwlog_ring; /* Device max aggregate bandwidths corresponding to the GL_PWR_MODE_CTL * register. Used for determining the ITR/INTRL granularity during @@ -910,10 +909,9 @@ struct ice_hw { /* INTRL granularity in 1 us */ u8 intrl_gran; -#define ICE_PHY_PER_NAC_E822 1 #define ICE_MAX_QUAD 2 -#define ICE_QUADS_PER_PHY_E822 2 -#define ICE_PORTS_PER_PHY_E822 8 +#define ICE_QUADS_PER_PHY_E82X 2 +#define ICE_PORTS_PER_PHY_E82X 8 #define ICE_PORTS_PER_QUAD 4 #define ICE_PORTS_PER_PHY_E810 4 #define ICE_NUM_EXTERNAL_PORTS (ICE_MAX_QUAD * ICE_PORTS_PER_QUAD) @@ -1009,7 +1007,6 @@ struct ice_hw_port_stats { u64 error_bytes; /* errbc */ u64 mac_local_faults; /* mlfc */ u64 mac_remote_faults; /* mrfc */ - u64 rx_len_errors; /* rlec */ u64 link_xon_rx; /* lxonrxc */ u64 link_xoff_rx; /* lxoffrxc */ u64 link_xon_tx; /* lxontxc */ @@ -1048,6 +1045,7 @@ enum ice_sw_fwd_act_type { ICE_FWD_TO_Q, ICE_FWD_TO_QGRP, ICE_DROP_PACKET, + ICE_MIRROR_PACKET, ICE_NOP, ICE_INVAL_ACT }; @@ -1078,7 +1076,7 @@ struct ice_aq_get_set_rss_lut_params { #define ICE_OROM_VER_BUILD_SHIFT 8 #define ICE_OROM_VER_BUILD_MASK (0xffff << ICE_OROM_VER_BUILD_SHIFT) #define ICE_OROM_VER_SHIFT 24 -#define ICE_OROM_VER_MASK (0xff << ICE_OROM_VER_SHIFT) +#define ICE_OROM_VER_MASK (0xffU << ICE_OROM_VER_SHIFT) #define ICE_SR_PFA_PTR 0x40 #define ICE_SR_1ST_NVM_BANK_PTR 0x42 #define ICE_SR_NVM_BANK_SIZE 0x43 diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index aca1f2ea5034..48a8d462d76a 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -248,25 +248,32 @@ static void ice_vf_pre_vsi_rebuild(struct ice_vf *vf) } /** - * ice_vf_recreate_vsi - Release and re-create the VF's VSI - * @vf: VF to recreate the VSI for + * ice_vf_reconfig_vsi - Reconfigure a VF VSI with the device + * @vf: VF to reconfigure the VSI for * - * This is only called when a single VF is being reset (i.e. VVF, VFLR, host - * VF configuration change, etc) + * This is called when a single VF is being reset (i.e. VVF, VFLR, host VF + * configuration change, etc). * - * It releases and then re-creates a new VSI. + * It brings the VSI down and then reconfigures it with the hardware. */ -static int ice_vf_recreate_vsi(struct ice_vf *vf) +int ice_vf_reconfig_vsi(struct ice_vf *vf) { + struct ice_vsi *vsi = ice_get_vf_vsi(vf); struct ice_pf *pf = vf->pf; int err; - ice_vf_vsi_release(vf); + if (WARN_ON(!vsi)) + return -EINVAL; + + vsi->flags = ICE_VSI_FLAG_NO_INIT; - err = vf->vf_ops->create_vsi(vf); + ice_vsi_decfg(vsi); + ice_fltr_remove_all(vsi); + + err = ice_vsi_cfg(vsi); if (err) { dev_err(ice_pf_to_dev(pf), - "Failed to recreate the VF%u's VSI, error %d\n", + "Failed to reconfigure the VF%u's VSI, error %d\n", vf->vf_id, err); return err; } @@ -300,7 +307,6 @@ static int ice_vf_rebuild_vsi(struct ice_vf *vf) * vf->lan_vsi_idx */ vsi->vsi_num = ice_get_hw_vsi_num(&pf->hw, vsi->idx); - vf->lan_vsi_num = vsi->vsi_num; return 0; } @@ -760,6 +766,7 @@ void ice_reset_all_vfs(struct ice_pf *pf) ice_for_each_vf(pf, bkt, vf) { mutex_lock(&vf->cfg_lock); + ice_eswitch_detach(pf, vf); vf->driver_caps = 0; ice_vc_set_default_allowlist(vf); @@ -775,13 +782,11 @@ void ice_reset_all_vfs(struct ice_pf *pf) ice_vf_rebuild_vsi(vf); ice_vf_post_vsi_rebuild(vf); + ice_eswitch_attach(pf, vf); + mutex_unlock(&vf->cfg_lock); } - if (ice_is_eswitch_mode_switchdev(pf)) - if (ice_eswitch_rebuild(pf)) - dev_warn(dev, "eswitch rebuild failed\n"); - ice_flush(hw); clear_bit(ICE_VF_DIS, pf->state); @@ -829,12 +834,16 @@ static void ice_notify_vf_reset(struct ice_vf *vf) int ice_reset_vf(struct ice_vf *vf, u32 flags) { struct ice_pf *pf = vf->pf; + struct ice_lag *lag; struct ice_vsi *vsi; + u8 act_prt, pri_prt; struct device *dev; int err = 0; bool rsd; dev = ice_pf_to_dev(pf); + act_prt = ICE_LAG_INVALID_PORT; + pri_prt = pf->hw.port_info->lport; if (flags & ICE_VF_RESET_NOTIFY) ice_notify_vf_reset(vf); @@ -850,6 +859,17 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) else lockdep_assert_held(&vf->cfg_lock); + lag = pf->lag; + mutex_lock(&pf->lag_mutex); + if (lag && lag->bonded && lag->primary) { + act_prt = lag->active_port; + if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT && + lag->upper_netdev) + ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt); + else + act_prt = ICE_LAG_INVALID_PORT; + } + if (ice_is_vf_disabled(vf)) { vsi = ice_get_vf_vsi(vf); if (!vsi) { @@ -914,7 +934,7 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) ice_vf_pre_vsi_rebuild(vf); - if (ice_vf_recreate_vsi(vf)) { + if (ice_vf_reconfig_vsi(vf)) { dev_err(dev, "Failed to release and setup the VF%u's VSI\n", vf->vf_id); err = -EFAULT; @@ -928,12 +948,17 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) goto out_unlock; } - ice_eswitch_update_repr(vsi); + ice_eswitch_update_repr(vf->repr_id, vsi); /* if the VF has been reset allow it to come up again */ ice_mbx_clear_malvf(&vf->mbx_info); out_unlock: + if (lag && lag->bonded && lag->primary && + act_prt != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + mutex_unlock(&pf->lag_mutex); + if (flags & ICE_VF_RESET_LOCK) mutex_unlock(&vf->cfg_lock); @@ -965,10 +990,13 @@ void ice_initialize_vf_entry(struct ice_vf *vf) /* assign default capabilities */ vf->spoofchk = true; - vf->num_vf_qs = vfs->num_qps_per; ice_vc_set_default_allowlist(vf); ice_virtchnl_set_dflt_ops(vf); + /* set default number of MSI-X */ + vf->num_msix = vfs->num_msix_per; + vf->num_vf_qs = vfs->num_qps_per; + /* ctrl_vsi_idx will be set to a valid value only when iAVF * creates its first fdir rule. */ @@ -1213,7 +1241,7 @@ struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf) struct ice_vsi *vsi; params.type = ICE_VSI_CTRL; - params.pi = ice_vf_get_port_info(vf); + params.port_info = ice_vf_get_port_info(vf); params.vf = vf; params.flags = ICE_VSI_FLAG_INIT; @@ -1281,13 +1309,12 @@ int ice_vf_init_host_cfg(struct ice_vf *vf, struct ice_vsi *vsi) } /** - * ice_vf_invalidate_vsi - invalidate vsi_idx/vsi_num to remove VSI access + * ice_vf_invalidate_vsi - invalidate vsi_idx to remove VSI access * @vf: VF to remove access to VSI for */ void ice_vf_invalidate_vsi(struct ice_vf *vf) { vf->lan_vsi_idx = ICE_NO_VSI; - vf->lan_vsi_num = ICE_NO_VSI; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index 93c774f2f437..fec16919ec19 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -62,7 +62,6 @@ struct ice_vf_ops { bool (*poll_reset_status)(struct ice_vf *vf); void (*clear_reset_trigger)(struct ice_vf *vf); void (*irq_close)(struct ice_vf *vf); - int (*create_vsi)(struct ice_vf *vf); void (*post_vsi_rebuild)(struct ice_vf *vf); }; @@ -110,11 +109,6 @@ struct ice_vf { u8 spoofchk:1; u8 link_forced:1; u8 link_up:1; /* only valid if VF link is forced */ - /* VSI indices - actual VSI pointers are maintained in the PF structure - * When assigned, these will be non-zero, because VSI 0 is always - * the main LAN VSI for the PF. - */ - u16 lan_vsi_num; /* ID as used by firmware */ 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 */ @@ -130,7 +124,7 @@ struct ice_vf { struct ice_mdd_vf_events mdd_tx_events; DECLARE_BITMAP(opcodes_allowlist, VIRTCHNL_OP_MAX); - struct ice_repr *repr; + unsigned long repr_id; const struct ice_virtchnl_ops *virtchnl_ops; const struct ice_vf_ops *vf_ops; 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..91ba7fe0eaee 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -23,6 +23,7 @@ #warning "Only include ice_vf_lib_private.h in CONFIG_PCI_IOV virtualization files" #endif +int ice_vf_reconfig_vsi(struct ice_vf *vf); void ice_initialize_vf_entry(struct ice_vf *vf); void ice_dis_vf_qs(struct ice_vf *vf); int ice_check_vf_init(struct ice_vf *vf); diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c index d7b10dc67f03..b3e1bdcb80f8 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -26,29 +26,31 @@ static void ice_port_vlan_on(struct ice_vsi *vsi) struct ice_vsi_vlan_ops *vlan_ops; struct ice_pf *pf = vsi->back; - if (ice_is_dvm_ena(&pf->hw)) { - vlan_ops = &vsi->outer_vlan_ops; - - /* setup outer VLAN ops */ - vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; - vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; - vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; + /* setup inner VLAN ops */ + vlan_ops = &vsi->inner_vlan_ops; - /* setup inner VLAN ops */ - vlan_ops = &vsi->inner_vlan_ops; + if (ice_is_dvm_ena(&pf->hw)) { vlan_ops->add_vlan = noop_vlan_arg; vlan_ops->del_vlan = noop_vlan_arg; vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } else { - vlan_ops = &vsi->inner_vlan_ops; + /* setup outer VLAN ops */ + vlan_ops = &vsi->outer_vlan_ops; + vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; + } else { vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; - vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; } + + /* all Rx traffic should be in the domain of the assigned port VLAN, + * so prevent disabling Rx VLAN filtering + */ + vlan_ops->dis_rx_filtering = noop_vlan; + vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; } @@ -77,6 +79,8 @@ static void ice_port_vlan_off(struct ice_vsi *vsi) vlan_ops->del_vlan = ice_vsi_del_vlan; } + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) vlan_ops->ena_rx_filtering = noop_vlan; else @@ -141,7 +145,6 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) &vsi->outer_vlan_ops : &vsi->inner_vlan_ops; vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index cdf17b1e2f25..1c6ce0c4ed4e 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -440,7 +440,6 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vf->driver_caps = *(u32 *)msg; else vf->driver_caps = VIRTCHNL_VF_OFFLOAD_L2 | - VIRTCHNL_VF_OFFLOAD_RSS_REG | VIRTCHNL_VF_OFFLOAD_VLAN; vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2; @@ -453,14 +452,8 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->vf_cap_flags |= ice_vc_get_vlan_caps(hw, vf, vsi, vf->driver_caps); - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; - } else { - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ; - else - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; - } if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC; @@ -506,7 +499,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->rss_lut_size = ICE_LUT_VSI_SIZE; vfres->max_mtu = ice_vc_get_max_frame_size(vf); - vfres->vsi_res[0].vsi_id = vf->lan_vsi_num; + vfres->vsi_res[0].vsi_id = ICE_VF_VSI_ID; vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV; vfres->vsi_res[0].num_queue_pairs = vsi->num_txq; ether_addr_copy(vfres->vsi_res[0].default_mac_addr, @@ -552,27 +545,20 @@ static void ice_vc_reset_vf_msg(struct ice_vf *vf) */ bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) { - struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - - vsi = ice_find_vsi(pf, vsi_id); - - return (vsi && (vsi->vf == vf)); + return vsi_id == ICE_VF_VSI_ID; } /** * ice_vc_isvalid_q_id - * @vf: pointer to the VF info - * @vsi_id: VSI ID + * @vsi: VSI to check queue ID against * @qid: VSI relative queue ID * * check for the valid queue ID */ -static bool ice_vc_isvalid_q_id(struct ice_vf *vf, u16 vsi_id, u8 qid) +static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u8 qid) { - struct ice_vsi *vsi = ice_find_vsi(vf->pf, vsi_id); /* allocated Tx and Rx queues should be always equal for VF VSI */ - return (vsi && (qid < vsi->alloc_txq)); + return qid < vsi->alloc_txq; } /** @@ -689,9 +675,7 @@ out: * a specific virtchnl RSS cfg * @hw: pointer to the hardware * @rss_cfg: pointer to the virtchnl RSS cfg - * @addl_hdrs: pointer to the protocol header fields (ICE_FLOW_SEG_HDR_*) - * to configure - * @hash_flds: pointer to the hash bit fields (ICE_FLOW_HASH_*) to configure + * @hash_cfg: pointer to the HW hash configuration * * Return true if all the protocol header and hash fields in the RSS cfg could * be parsed, else return false @@ -699,13 +683,23 @@ out: * This function parses the virtchnl RSS cfg to be the intended * hash fields and the intended header for RSS configuration */ -static bool -ice_vc_parse_rss_cfg(struct ice_hw *hw, struct virtchnl_rss_cfg *rss_cfg, - u32 *addl_hdrs, u64 *hash_flds) +static bool ice_vc_parse_rss_cfg(struct ice_hw *hw, + struct virtchnl_rss_cfg *rss_cfg, + struct ice_rss_hash_cfg *hash_cfg) { const struct ice_vc_hash_field_match_type *hf_list; const struct ice_vc_hdr_match_type *hdr_list; int i, hf_list_len, hdr_list_len; + u32 *addl_hdrs = &hash_cfg->addl_hdrs; + u64 *hash_flds = &hash_cfg->hash_flds; + + /* set outer layer RSS as default */ + hash_cfg->hdr_type = ICE_RSS_OUTER_HEADERS; + + if (rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC) + hash_cfg->symm = true; + else + hash_cfg->symm = false; hf_list = ice_vc_hash_field_list; hf_list_len = ARRAY_SIZE(ice_vc_hash_field_list); @@ -823,8 +817,8 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) int status; lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; - hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_XOR : - ICE_AQ_VSI_Q_OPT_RSS_TPLZ; + hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_HASH_XOR : + ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) { @@ -832,11 +826,9 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) goto error_param; } - ctx->info.q_opt_rss = ((lut_type << - ICE_AQ_VSI_Q_OPT_RSS_LUT_S) & - ICE_AQ_VSI_Q_OPT_RSS_LUT_M) | - (hash_type & - ICE_AQ_VSI_Q_OPT_RSS_HASH_M); + ctx->info.q_opt_rss = + FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_LUT_M, lut_type) | + FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hash_type); /* Preserve existing queueing option setting */ ctx->info.q_opt_rss |= (vsi->info.q_opt_rss & @@ -858,18 +850,24 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) kfree(ctx); } else { - u32 addl_hdrs = ICE_FLOW_SEG_HDR_NONE; - u64 hash_flds = ICE_HASH_INVALID; + struct ice_rss_hash_cfg cfg; + + /* Only check for none raw pattern case */ + if (!ice_vc_validate_pattern(vf, &rss_cfg->proto_hdrs)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + cfg.addl_hdrs = ICE_FLOW_SEG_HDR_NONE; + cfg.hash_flds = ICE_HASH_INVALID; + cfg.hdr_type = ICE_RSS_ANY_HEADERS; - if (!ice_vc_parse_rss_cfg(hw, rss_cfg, &addl_hdrs, - &hash_flds)) { + if (!ice_vc_parse_rss_cfg(hw, rss_cfg, &cfg)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } if (add) { - if (ice_add_rss_cfg(hw, vsi->idx, hash_flds, - addl_hdrs)) { + if (ice_add_rss_cfg(hw, vsi, &cfg)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; dev_err(dev, "ice_add_rss_cfg failed for vsi = %d, v_ret = %d\n", vsi->vsi_num, v_ret); @@ -877,8 +875,7 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) } else { int status; - status = ice_rem_rss_cfg(hw, vsi->idx, hash_flds, - addl_hdrs); + status = ice_rem_rss_cfg(hw, vsi->idx, &cfg); /* We just ignore -ENOENT, because if two configurations * share the same profile remove one of them actually * removes both, since the profile is deleted. @@ -989,6 +986,51 @@ error_param: } /** + * ice_vc_config_rss_hfunc + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Configure the VF's RSS Hash function + */ +static int ice_vc_config_rss_hfunc(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_rss_hfunc *vrh = (struct virtchnl_rss_hfunc *)msg; + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + u8 hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vrh->vsi_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (vrh->rss_algorithm == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC) + hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ; + + if (ice_set_rss_hfunc(vsi, hfunc)) + v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_HFUNC, v_ret, + NULL, 0); +} + +/** * ice_vc_cfg_promiscuous_mode_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1274,7 +1316,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) */ q_map = vqs->rx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1296,7 +1338,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) q_map = vqs->tx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1401,7 +1443,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) q_map = vqs->tx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1427,7 +1469,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF); } else if (q_map) { for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1463,13 +1505,12 @@ error_param: * ice_cfg_interrupt * @vf: pointer to the VF info * @vsi: the VSI being configured - * @vector_id: vector ID * @map: vector map for mapping vectors to queues * @q_vector: structure for interrupt vector * configure the IRQ to queue map */ -static int -ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, +static enum virtchnl_status_code +ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, struct virtchnl_vector_map *map, struct ice_q_vector *q_vector) { @@ -1483,13 +1524,14 @@ ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) { vsi_q_id = vsi_q_id_idx; - if (!ice_vc_isvalid_q_id(vf, vsi->vsi_num, vsi_q_id)) + if (!ice_vc_isvalid_q_id(vsi, vsi_q_id)) return VIRTCHNL_STATUS_ERR_PARAM; q_vector->num_ring_rx++; q_vector->rx.itr_idx = map->rxitr_idx; vsi->rx_rings[vsi_q_id]->q_vector = q_vector; - ice_cfg_rxq_interrupt(vsi, vsi_q_id, vector_id, + ice_cfg_rxq_interrupt(vsi, vsi_q_id, + q_vector->vf_reg_idx, q_vector->rx.itr_idx); } @@ -1497,13 +1539,14 @@ ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) { vsi_q_id = vsi_q_id_idx; - if (!ice_vc_isvalid_q_id(vf, vsi->vsi_num, vsi_q_id)) + if (!ice_vc_isvalid_q_id(vsi, vsi_q_id)) return VIRTCHNL_STATUS_ERR_PARAM; q_vector->num_ring_tx++; q_vector->tx.itr_idx = map->txitr_idx; vsi->tx_rings[vsi_q_id]->q_vector = q_vector; - ice_cfg_txq_interrupt(vsi, vsi_q_id, vector_id, + ice_cfg_txq_interrupt(vsi, vsi_q_id, + q_vector->vf_reg_idx, q_vector->tx.itr_idx); } @@ -1523,7 +1566,6 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) u16 num_q_vectors_mapped, vsi_id, vector_id; struct virtchnl_irq_map_info *irqmap_info; struct virtchnl_vector_map *map; - struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; int i; @@ -1535,7 +1577,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) * there is actually at least a single VF queue vector mapped */ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || - pf->vfs.num_msix_per < num_q_vectors_mapped || + vf->num_msix < num_q_vectors_mapped || !num_q_vectors_mapped) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -1557,7 +1599,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) /* vector_id is always 0-based for each VF, and can never be * larger than or equal to the max allowed interrupts per VF */ - if (!(vector_id < pf->vfs.num_msix_per) || + if (!(vector_id < vf->num_msix) || !ice_vc_isvalid_vsi_id(vf, vsi_id) || (!vector_id && (map->rxq_map || map->txq_map))) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -1578,8 +1620,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) } /* lookout for the invalid queue index */ - v_ret = (enum virtchnl_status_code) - ice_cfg_interrupt(vf, vsi, vector_id, map, q_vector); + v_ret = ice_cfg_interrupt(vf, vsi, map, q_vector); if (v_ret) goto error_param; } @@ -1603,9 +1644,24 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) (struct virtchnl_vsi_queue_config_info *)msg; struct virtchnl_queue_pair_info *qpi; struct ice_pf *pf = vf->pf; + struct ice_lag *lag; struct ice_vsi *vsi; + u8 act_prt, pri_prt; int i = -1, q_idx; + lag = pf->lag; + mutex_lock(&pf->lag_mutex); + act_prt = ICE_LAG_INVALID_PORT; + pri_prt = pf->hw.port_info->lport; + if (lag && lag->bonded && lag->primary) { + act_prt = lag->active_port; + if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT && + lag->upper_netdev) + ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt); + else + act_prt = ICE_LAG_INVALID_PORT; + } + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) goto error_param; @@ -1640,7 +1696,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) qpi->txq.headwb_enabled || !ice_vc_isvalid_ring_len(qpi->txq.ring_len) || !ice_vc_isvalid_ring_len(qpi->rxq.ring_len) || - !ice_vc_isvalid_q_id(vf, qci->vsi_id, qpi->txq.queue_id)) { + !ice_vc_isvalid_q_id(vsi, qpi->txq.queue_id)) { goto error_param; } @@ -1729,6 +1785,11 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) } } + if (lag && lag->bonded && lag->primary && + act_prt != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + mutex_unlock(&pf->lag_mutex); + /* send the response to the VF */ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, VIRTCHNL_STATUS_SUCCESS, NULL, 0); @@ -1743,6 +1804,11 @@ error_param: vf->vf_id, i); } + if (lag && lag->bonded && lag->primary && + act_prt != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + mutex_unlock(&pf->lag_mutex); + ice_lag_move_new_vf_nodes(vf); /* send the response to the VF */ @@ -2610,7 +2676,7 @@ static int ice_vc_set_rss_hena(struct ice_vf *vf, u8 *msg) } if (vrh->hena) { - status = ice_add_avf_rss_cfg(&pf->hw, vsi->idx, vrh->hena); + status = ice_add_avf_rss_cfg(&pf->hw, vsi, vrh->hena); v_ret = ice_err_to_virt_err(status); } @@ -3022,7 +3088,7 @@ static struct ice_vlan ice_vc_to_vlan(struct virtchnl_vlan *vc_vlan) { struct ice_vlan vlan = { 0 }; - vlan.prio = (vc_vlan->tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + vlan.prio = FIELD_GET(VLAN_PRIO_MASK, vc_vlan->tci); vlan.vid = vc_vlan->tci & VLAN_VID_MASK; vlan.tpid = vc_vlan->tpid; @@ -3731,6 +3797,7 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = { .cfg_irq_map_msg = ice_vc_cfg_irq_map_msg, .config_rss_key = ice_vc_config_rss_key, .config_rss_lut = ice_vc_config_rss_lut, + .config_rss_hfunc = ice_vc_config_rss_hfunc, .get_stats_msg = ice_vc_get_stats_msg, .cfg_promiscuous_mode_msg = ice_vc_cfg_promiscuous_mode_msg, .add_vlan_msg = ice_vc_add_vlan_msg, @@ -3860,6 +3927,7 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = { .cfg_irq_map_msg = ice_vc_cfg_irq_map_msg, .config_rss_key = ice_vc_config_rss_key, .config_rss_lut = ice_vc_config_rss_lut, + .config_rss_hfunc = ice_vc_config_rss_hfunc, .get_stats_msg = ice_vc_get_stats_msg, .cfg_promiscuous_mode_msg = ice_vc_repr_cfg_promiscuous_mode, .add_vlan_msg = ice_vc_add_vlan_msg, @@ -4042,6 +4110,9 @@ error_handler: case VIRTCHNL_OP_CONFIG_RSS_LUT: err = ops->config_rss_lut(vf, msg); break; + case VIRTCHNL_OP_CONFIG_RSS_HFUNC: + err = ops->config_rss_hfunc(vf, msg); + break; case VIRTCHNL_OP_GET_STATS: err = ops->get_stats_msg(vf, msg); break; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h index cd747718de73..3a4115869153 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h @@ -19,6 +19,15 @@ #define ICE_MAX_MACADDR_PER_VF 18 #define ICE_FLEX_DESC_RXDID_MAX_NUM 64 +/* 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. + * + * Since the VF doesn't need this information, report a static value to the VF + * instead of leaking any information about the PF or hardware setup. + */ +#define ICE_VF_VSI_ID 1 + struct ice_virtchnl_ops { int (*get_ver_msg)(struct ice_vf *vf, u8 *msg); int (*get_vf_res_msg)(struct ice_vf *vf, u8 *msg); @@ -32,6 +41,7 @@ struct ice_virtchnl_ops { int (*cfg_irq_map_msg)(struct ice_vf *vf, u8 *msg); int (*config_rss_key)(struct ice_vf *vf, u8 *msg); int (*config_rss_lut)(struct ice_vf *vf, u8 *msg); + int (*config_rss_hfunc)(struct ice_vf *vf, u8 *msg); int (*get_stats_msg)(struct ice_vf *vf, u8 *msg); int (*cfg_promiscuous_mode_msg)(struct ice_vf *vf, u8 *msg); int (*add_vlan_msg)(struct ice_vf *vf, u8 *msg); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c index 7d547fa616fa..d796dbd2a440 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -13,8 +13,6 @@ * - opcodes needed by VF when caps are activated * * Caps that don't use new opcodes (no opcodes should be allowed): - * - VIRTCHNL_VF_OFFLOAD_RSS_AQ - * - VIRTCHNL_VF_OFFLOAD_RSS_REG * - VIRTCHNL_VF_OFFLOAD_WB_ON_ITR * - VIRTCHNL_VF_OFFLOAD_CRC * - VIRTCHNL_VF_OFFLOAD_RX_POLLING @@ -68,6 +66,7 @@ static const u32 vlan_v2_allowlist_opcodes[] = { static const u32 rss_pf_allowlist_opcodes[] = { VIRTCHNL_OP_CONFIG_RSS_KEY, VIRTCHNL_OP_CONFIG_RSS_LUT, VIRTCHNL_OP_GET_RSS_HENA_CAPS, VIRTCHNL_OP_SET_RSS_HENA, + VIRTCHNL_OP_CONFIG_RSS_HFUNC, }; /* VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index 24b23b7ef04a..8e4ff3af86c6 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -10,19 +10,6 @@ #define to_fltr_conf_from_desc(p) \ container_of(p, struct virtchnl_fdir_fltr_conf, input) -#define ICE_FLOW_PROF_TYPE_S 0 -#define ICE_FLOW_PROF_TYPE_M (0xFFFFFFFFULL << ICE_FLOW_PROF_TYPE_S) -#define ICE_FLOW_PROF_VSI_S 32 -#define ICE_FLOW_PROF_VSI_M (0xFFFFFFFFULL << ICE_FLOW_PROF_VSI_S) - -/* Flow profile ID format: - * [0:31] - flow type, flow + tun_offs - * [32:63] - VSI index - */ -#define ICE_FLOW_PROF_FD(vsi, flow, tun_offs) \ - ((u64)(((((flow) + (tun_offs)) & ICE_FLOW_PROF_TYPE_M)) | \ - (((u64)(vsi) << ICE_FLOW_PROF_VSI_S) & ICE_FLOW_PROF_VSI_M))) - #define GTPU_TEID_OFFSET 4 #define GTPU_EH_QFI_OFFSET 1 #define GTPU_EH_QFI_MASK 0x3F @@ -107,9 +94,6 @@ ice_vc_fdir_param_check(struct ice_vf *vf, u16 vsi_id) if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF)) return -EINVAL; - if (vsi_id != vf->lan_vsi_num) - return -EINVAL; - if (!ice_vc_isvalid_vsi_id(vf, vsi_id)) return -EINVAL; @@ -493,6 +477,7 @@ ice_vc_fdir_rem_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, int tun) return; vf_prof = fdir->fdir_prof[flow]; + prof_id = vf_prof->prof_id[tun]; vf_vsi = ice_get_vf_vsi(vf); if (!vf_vsi) { @@ -503,9 +488,6 @@ ice_vc_fdir_rem_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, int tun) if (!fdir->prof_entry_cnt[flow][tun]) return; - prof_id = ICE_FLOW_PROF_FD(vf_vsi->vsi_num, - flow, tun ? ICE_FLTR_PTYPE_MAX : 0); - for (i = 0; i < fdir->prof_entry_cnt[flow][tun]; i++) if (vf_prof->entry_h[i][tun]) { u16 vsi_num = ice_get_hw_vsi_num(hw, vf_prof->vsi_h[i]); @@ -647,7 +629,6 @@ ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, struct ice_hw *hw; u64 entry1_h = 0; u64 entry2_h = 0; - u64 prof_id; int ret; pf = vf->pf; @@ -681,18 +662,15 @@ ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, ice_vc_fdir_rem_prof(vf, flow, tun); } - prof_id = ICE_FLOW_PROF_FD(vf_vsi->vsi_num, flow, - tun ? ICE_FLTR_PTYPE_MAX : 0); - - ret = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof_id, seg, - tun + 1, &prof); + ret = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, seg, + tun + 1, false, &prof); if (ret) { dev_dbg(dev, "Could not add VSI flow 0x%x for VF %d\n", flow, vf->vf_id); goto err_exit; } - ret = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, vf_vsi->idx, + ret = ice_flow_add_entry(hw, ICE_BLK_FD, prof->id, vf_vsi->idx, vf_vsi->idx, ICE_FLOW_PRIO_NORMAL, seg, &entry1_h); if (ret) { @@ -701,7 +679,7 @@ ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, goto err_prof; } - ret = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, vf_vsi->idx, + ret = ice_flow_add_entry(hw, ICE_BLK_FD, prof->id, vf_vsi->idx, ctrl_vsi->idx, ICE_FLOW_PRIO_NORMAL, seg, &entry2_h); if (ret) { @@ -725,14 +703,16 @@ ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, vf_prof->cnt++; fdir->prof_entry_cnt[flow][tun]++; + vf_prof->prof_id[tun] = prof->id; + return 0; err_entry_1: ice_rem_prof_id_flow(hw, ICE_BLK_FD, - ice_get_hw_vsi_num(hw, vf_vsi->idx), prof_id); + ice_get_hw_vsi_num(hw, vf_vsi->idx), prof->id); ice_flow_rem_entry(hw, ICE_BLK_FD, entry1_h); err_prof: - ice_flow_rem_prof(hw, ICE_BLK_FD, prof_id); + ice_flow_rem_prof(hw, ICE_BLK_FD, prof->id); err_exit: return ret; } @@ -1480,16 +1460,15 @@ ice_vf_verify_rx_desc(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx, int ret; stat_err = le16_to_cpu(ctx->rx_desc.wb.status_error0); - if (((stat_err & ICE_FXD_FLTR_WB_QW1_DD_M) >> - ICE_FXD_FLTR_WB_QW1_DD_S) != ICE_FXD_FLTR_WB_QW1_DD_YES) { + if (FIELD_GET(ICE_FXD_FLTR_WB_QW1_DD_M, stat_err) != + ICE_FXD_FLTR_WB_QW1_DD_YES) { *status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; dev_err(dev, "VF %d: Desc Done not set\n", vf->vf_id); ret = -EINVAL; goto err_exit; } - prog_id = (stat_err & ICE_FXD_FLTR_WB_QW1_PROG_ID_M) >> - ICE_FXD_FLTR_WB_QW1_PROG_ID_S; + prog_id = FIELD_GET(ICE_FXD_FLTR_WB_QW1_PROG_ID_M, stat_err); if (prog_id == ICE_FXD_FLTR_WB_QW1_PROG_ADD && ctx->v_opcode != VIRTCHNL_OP_ADD_FDIR_FILTER) { dev_err(dev, "VF %d: Desc show add, but ctx not", @@ -1508,8 +1487,7 @@ ice_vf_verify_rx_desc(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx, goto err_exit; } - error = (stat_err & ICE_FXD_FLTR_WB_QW1_FAIL_M) >> - ICE_FXD_FLTR_WB_QW1_FAIL_S; + error = FIELD_GET(ICE_FXD_FLTR_WB_QW1_FAIL_M, stat_err); if (error == ICE_FXD_FLTR_WB_QW1_FAIL_YES) { if (prog_id == ICE_FXD_FLTR_WB_QW1_PROG_ADD) { dev_err(dev, "VF %d, Failed to add FDIR rule due to no space in the table", @@ -1524,8 +1502,7 @@ ice_vf_verify_rx_desc(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx, goto err_exit; } - error = (stat_err & ICE_FXD_FLTR_WB_QW1_FAIL_PROF_M) >> - ICE_FXD_FLTR_WB_QW1_FAIL_PROF_S; + error = FIELD_GET(ICE_FXD_FLTR_WB_QW1_FAIL_PROF_M, stat_err); if (error == ICE_FXD_FLTR_WB_QW1_FAIL_PROF_YES) { dev_err(dev, "VF %d: Profile matching error", vf->vf_id); *status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c index 76266e709a39..2e9ad27cb9d1 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c @@ -131,6 +131,7 @@ static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) { struct ice_hw *hw = &vsi->back->hw; struct ice_vsi_ctx *ctxt; + u8 *ivf; int err; /* do not allow modifying VLAN stripping when a port VLAN is configured @@ -143,19 +144,24 @@ static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) if (!ctxt) return -ENOMEM; + ivf = &ctxt->info.inner_vlan_flags; + /* Here we are configuring what the VSI should do with the VLAN tag in * the Rx packet. We can either leave the tag in the packet or put it in * the Rx descriptor. */ - if (ena) + if (ena) { /* Strip VLAN tag from Rx packet and put it in the desc */ - ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH; - else + *ivf = FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M, + ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH); + } else { /* Disable stripping. Leave tag in packet */ - ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING; + *ivf = FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M, + ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING); + } /* Allow all packets untagged/tagged */ - ctxt->info.inner_vlan_flags |= ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL; + *ivf |= ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL; ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); @@ -481,10 +487,11 @@ int ice_vsi_ena_outer_stripping(struct ice_vsi *vsi, u16 tpid) ctxt->info.outer_vlan_flags = vsi->info.outer_vlan_flags & ~(ICE_AQ_VSI_OUTER_VLAN_EMODE_M | ICE_AQ_VSI_OUTER_TAG_TYPE_M); ctxt->info.outer_vlan_flags |= - ((ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW_BOTH << - ICE_AQ_VSI_OUTER_VLAN_EMODE_S) | - ((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) & - ICE_AQ_VSI_OUTER_TAG_TYPE_M)); + /* we want EMODE_SHOW_BOTH, but that value is zero, so the line + * above clears it well enough that we don't need to try to set + * zero here, so just do the tag type + */ + FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M, tag_type); err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (err) @@ -589,11 +596,9 @@ int ice_vsi_ena_outer_insertion(struct ice_vsi *vsi, u16 tpid) ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M | ICE_AQ_VSI_OUTER_TAG_TYPE_M); ctxt->info.outer_vlan_flags |= - ((ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M) | - ((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) & - ICE_AQ_VSI_OUTER_TAG_TYPE_M); + FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M, + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL) | + FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M, tag_type); err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (err) @@ -642,9 +647,8 @@ int ice_vsi_dis_outer_insertion(struct ice_vsi *vsi) ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M); ctxt->info.outer_vlan_flags |= ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC | - ((ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M); + FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M, + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL); err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (err) @@ -702,8 +706,7 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid) ctxt->info.outer_vlan_flags = (ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW << ICE_AQ_VSI_OUTER_VLAN_EMODE_S) | - ((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) & - ICE_AQ_VSI_OUTER_TAG_TYPE_M) | + FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M, tag_type) | ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC | (ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ACCEPTUNTAGGED << ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) | diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c index 4a6c850d83ac..7aae7fdcfcdb 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c @@ -72,7 +72,6 @@ void ice_vsi_init_vlan_ops(struct ice_vsi *vsi) switch (vsi->type) { case ICE_VSI_PF: - case ICE_VSI_SWITCHDEV_CTRL: ice_pf_vsi_init_vlan_ops(vsi); break; case ICE_VSI_VF: diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 99954508184f..aa81d1162b81 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -179,6 +179,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) return -EBUSY; usleep_range(1000, 2000); } + + ice_qvec_dis_irq(vsi, rx_ring, q_vector); + ice_qvec_toggle_napi(vsi, q_vector, false); + netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); ice_fill_txq_meta(vsi, tx_ring, &txq_meta); @@ -195,13 +199,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) if (err) return err; } - ice_qvec_dis_irq(vsi, rx_ring, q_vector); - err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); if (err) return err; - ice_qvec_toggle_napi(vsi, q_vector, false); ice_qp_clean_rings(vsi, q_idx); ice_qp_reset_stats(vsi, q_idx); @@ -217,53 +218,39 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) */ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) { - DEFINE_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); - u16 size = __struct_size(qg_buf); struct ice_q_vector *q_vector; - struct ice_tx_ring *tx_ring; - struct ice_rx_ring *rx_ring; int err; - if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq) - return -EINVAL; - - qg_buf->num_txqs = 1; - - tx_ring = vsi->tx_rings[q_idx]; - rx_ring = vsi->rx_rings[q_idx]; - q_vector = rx_ring->q_vector; - - err = ice_vsi_cfg_txq(vsi, tx_ring, qg_buf); + err = ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx); if (err) return err; if (ice_is_xdp_ena_vsi(vsi)) { struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; - memset(qg_buf, 0, size); - qg_buf->num_txqs = 1; - err = ice_vsi_cfg_txq(vsi, xdp_ring, qg_buf); + err = ice_vsi_cfg_single_txq(vsi, vsi->xdp_rings, q_idx); if (err) return err; ice_set_ring_xdp(xdp_ring); ice_tx_xsk_pool(vsi, q_idx); } - err = ice_vsi_cfg_rxq(rx_ring); + err = ice_vsi_cfg_single_rxq(vsi, q_idx); if (err) return err; + q_vector = vsi->rx_rings[q_idx]->q_vector; ice_qvec_cfg_msix(vsi, q_vector); err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true); if (err) return err; - clear_bit(ICE_CFG_BUSY, vsi->state); ice_qvec_toggle_napi(vsi, q_vector, true); ice_qvec_ena_irq(vsi, q_vector); netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); + clear_bit(ICE_CFG_BUSY, vsi->state); return 0; } @@ -458,6 +445,11 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, rx_desc->read.pkt_addr = cpu_to_le64(dma); rx_desc->wb.status_error0 = 0; + /* Put private info that changes on a per-packet basis + * into xdp_buff_xsk->cb. + */ + ice_xdp_meta_set_desc(*xdp, rx_desc); + rx_desc++; xdp++; } @@ -563,8 +555,7 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) } net_prefetch(xdp->data_meta); - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, - GFP_ATOMIC | __GFP_NOWARN); + skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize); if (unlikely(!skb)) return NULL; @@ -820,7 +811,8 @@ ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first, } __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, - virt_to_page(xdp->data_hard_start), 0, size); + virt_to_page(xdp->data_hard_start), + XDP_PACKET_HEADROOM, size); sinfo->xdp_frags_size += size; xsk_buff_add_frag(xdp); @@ -863,8 +855,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) struct xdp_buff *xdp; struct sk_buff *skb; u16 stat_err_bits; - u16 vlan_tag = 0; - u16 rx_ptype; + u16 vlan_tci; rx_desc = ICE_RX_DESC(rx_ring, ntc); @@ -891,7 +882,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) if (!first) { first = xdp; - xdp_buff_clear_frags_flag(first); } else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) { break; } @@ -942,13 +932,10 @@ construct_skb: total_rx_bytes += skb->len; total_rx_packets++; - vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc); - - rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) & - ICE_RX_FLEX_DESC_PTYPE_M; + vlan_tci = ice_get_vlan_tci(rx_desc); - ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); - ice_receive_skb(rx_ring, skb, vlan_tag); + ice_process_skb_fields(rx_ring, rx_desc, skb); + ice_receive_skb(rx_ring, skb, vlan_tci); } rx_ring->next_to_clean = ntc; |