diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 9109006336f0..5ac0ad12f9f1 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -200,6 +200,8 @@ enum ice_feature { ICE_F_PTP_EXTTS, ICE_F_SMA_CTRL, ICE_F_GNSS, + ICE_F_ROCE_LAG, + ICE_F_SRIOV_LAG, ICE_F_MAX }; @@ -569,6 +571,7 @@ struct ice_pf { struct mutex sw_mutex; /* lock for protecting VSI alloc flow */ struct mutex tc_mutex; /* lock to protect TC changes */ struct mutex adev_mutex; /* lock to protect aux device access */ + struct mutex lag_mutex; /* protect ice_lag struct in PF */ u32 msg_enable; struct ice_ptp ptp; struct gnss_serial *gnss_serial; @@ -639,6 +642,8 @@ struct ice_pf { struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES]; }; +extern struct workqueue_struct *ice_lag_wq; + struct ice_netdev_priv { struct ice_vsi *vsi; struct ice_repr *repr; diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 63d3e1dcbba5..c0ad34b42531 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -120,6 +120,9 @@ struct ice_aqc_list_caps_elem { #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_FW_LAG_SUPPORT 0x0092 +#define ICE_AQC_BIT_ROCEV2_LAG 0x01 +#define ICE_AQC_BIT_SRIOV_LAG 0x02 u8 major_ver; u8 minor_ver; @@ -232,6 +235,8 @@ struct ice_aqc_set_port_params { #define ICE_AQC_SET_P_PARAMS_DOUBLE_VLAN_ENA BIT(2) __le16 bad_frame_vsi; __le16 swid; +#define ICE_AQC_PORT_SWID_VALID BIT(15) +#define ICE_AQC_PORT_SWID_M 0xFF u8 reserved[10]; }; @@ -241,10 +246,12 @@ struct ice_aqc_set_port_params { * Allocate Resources command (indirect 0x0208) * Free Resources command (indirect 0x0209) * Get Allocated Resource Descriptors Command (indirect 0x020A) + * Share Resource command (indirect 0x020B) */ #define ICE_AQC_RES_TYPE_VSI_LIST_REP 0x03 #define ICE_AQC_RES_TYPE_VSI_LIST_PRUNE 0x04 #define ICE_AQC_RES_TYPE_RECIPE 0x05 +#define ICE_AQC_RES_TYPE_SWID 0x07 #define ICE_AQC_RES_TYPE_FDIR_COUNTER_BLOCK 0x21 #define ICE_AQC_RES_TYPE_FDIR_GUARANTEED_ENTRIES 0x22 #define ICE_AQC_RES_TYPE_FDIR_SHARED_ENTRIES 0x23 @@ -264,6 +271,7 @@ struct ice_aqc_set_port_params { /* Allocate Resources command (indirect 0x0208) * Free Resources command (indirect 0x0209) + * Share Resource command (indirect 0x020B) */ struct ice_aqc_alloc_free_res_cmd { __le16 num_entries; /* Number of Resource entries */ @@ -818,7 +826,11 @@ struct ice_aqc_txsched_move_grp_info_hdr { __le32 src_parent_teid; __le32 dest_parent_teid; __le16 num_elems; - __le16 reserved; + u8 mode; +#define ICE_AQC_MOVE_ELEM_MODE_SAME_PF 0x0 +#define ICE_AQC_MOVE_ELEM_MODE_GIVE_OWN 0x1 +#define ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN 0x2 + u8 reserved; }; struct ice_aqc_move_elem { @@ -1923,6 +1935,42 @@ struct ice_aqc_dis_txq_item { __le16 q_id[]; } __packed; +/* Move/Reconfigure Tx queue (indirect 0x0C32) */ +struct ice_aqc_cfg_txqs { + u8 cmd_type; +#define ICE_AQC_Q_CFG_MOVE_NODE 0x1 +#define ICE_AQC_Q_CFG_TC_CHNG 0x2 +#define ICE_AQC_Q_CFG_MOVE_TC_CHNG 0x3 +#define ICE_AQC_Q_CFG_SUBSEQ_CALL BIT(2) +#define ICE_AQC_Q_CFG_FLUSH BIT(3) + u8 num_qs; + u8 port_num_chng; +#define ICE_AQC_Q_CFG_SRC_PRT_M 0x7 +#define ICE_AQC_Q_CFG_DST_PRT_S 3 +#define ICE_AQC_Q_CFG_DST_PRT_M (0x7 << ICE_AQC_Q_CFG_DST_PRT_S) + u8 time_out; +#define ICE_AQC_Q_CFG_TIMEOUT_S 2 +#define ICE_AQC_Q_CFG_TIMEOUT_M (0x1F << ICE_AQC_Q_CFG_TIMEOUT_S) + __le32 blocked_cgds; + __le32 addr_high; + __le32 addr_low; +}; + +/* Per Q struct for Move/Reconfigure Tx LAN Queues (indirect 0x0C32) */ +struct ice_aqc_cfg_txq_perq { + __le16 q_handle; + u8 tc; + u8 rsvd; + __le32 q_teid; +}; + +/* The buffer for Move/Reconfigure Tx LAN Queues (indirect 0x0C32) */ +struct ice_aqc_cfg_txqs_buf { + __le32 src_parent_teid; + __le32 dst_parent_teid; + struct ice_aqc_cfg_txq_perq queue_info[]; +}; + /* Add Tx RDMA Queue Set (indirect 0x0C33) */ struct ice_aqc_add_rdma_qset { u8 num_qset_grps; @@ -2181,6 +2229,7 @@ struct ice_aq_desc { struct ice_aqc_neigh_dev_req neigh_dev; struct ice_aqc_add_txqs add_txqs; struct ice_aqc_dis_txqs dis_txqs; + struct ice_aqc_cfg_txqs cfg_txqs; 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; @@ -2263,6 +2312,7 @@ enum ice_adminq_opc { /* Alloc/Free/Get Resources */ ice_aqc_opc_alloc_res = 0x0208, ice_aqc_opc_free_res = 0x0209, + ice_aqc_opc_share_res = 0x020B, ice_aqc_opc_set_vlan_mode_parameters = 0x020C, ice_aqc_opc_get_vlan_mode_parameters = 0x020D, @@ -2356,6 +2406,7 @@ enum ice_adminq_opc { /* Tx queue handling commands/events */ ice_aqc_opc_add_txqs = 0x0C30, ice_aqc_opc_dis_txqs = 0x0C31, + ice_aqc_opc_cfg_txqs = 0x0C32, ice_aqc_opc_add_rdma_qset = 0x0C33, /* package commands */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index e16d4c83ed5f..dade0a50299c 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -2241,6 +2241,14 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, "%s: reset_restrict_support = %d\n", prefix, caps->reset_restrict_support); break; + case ICE_AQC_CAPS_FW_LAG_SUPPORT: + caps->roce_lag = !!(number & ICE_AQC_BIT_ROCEV2_LAG); + ice_debug(hw, ICE_DBG_INIT, "%s: roce_lag = %u\n", + prefix, caps->roce_lag); + caps->sriov_lag = !!(number & ICE_AQC_BIT_SRIOV_LAG); + ice_debug(hw, ICE_DBG_INIT, "%s: sriov_lag = %u\n", + prefix, caps->sriov_lag); + break; default: /* Not one of the recognized common capabilities */ found = false; @@ -4221,6 +4229,53 @@ do_aq: return status; } +/** + * ice_aq_cfg_lan_txq + * @hw: pointer to the hardware structure + * @buf: buffer for command + * @buf_size: size of buffer in bytes + * @num_qs: number of queues being configured + * @oldport: origination lport + * @newport: destination lport + * @cd: pointer to command details structure or NULL + * + * Move/Configure LAN Tx queue (0x0C32) + * + * There is a better AQ command to use for moving nodes, so only coding + * this one for configuring the node. + */ +int +ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf, + u16 buf_size, u16 num_qs, u8 oldport, u8 newport, + struct ice_sq_cd *cd) +{ + struct ice_aqc_cfg_txqs *cmd; + struct ice_aq_desc desc; + int status; + + cmd = &desc.params.cfg_txqs; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_cfg_txqs); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + if (!buf) + return -EINVAL; + + 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->blocked_cgds = 0; + + status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); + if (status) + ice_debug(hw, ICE_DBG_SCHED, "Failed to reconfigure nodes %d\n", + hw->adminq.sq_last_status); + return status; +} + /** * ice_aq_add_rdma_qsets * @hw: pointer to the hardware structure @@ -4700,6 +4755,7 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, break; ice_free_sched_node(pi, node); q_ctx->q_handle = ICE_INVAL_Q_HANDLE; + q_ctx->q_teid = ICE_INVAL_TEID; } mutex_unlock(&pi->sched_lock); kfree(qg_list); diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 81961a7d6598..df12a9d8d28c 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -186,6 +186,10 @@ int ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size, struct ice_sq_cd *cd); +int +ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf, + u16 buf_size, u16 num_qs, u8 oldport, u8 newport, + 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); diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index 3eb01731e496..e1fbc6de452d 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -70,6 +70,11 @@ static int ice_dcbnl_setets(struct net_device *netdev, struct ieee_ets *ets) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) return -EINVAL; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; mutex_lock(&pf->tc_mutex); @@ -170,6 +175,11 @@ static u8 ice_dcbnl_setdcbx(struct net_device *netdev, u8 mode) if (mode == pf->dcbx_cap) return ICE_DCB_NO_HW_CHG; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return ICE_DCB_NO_HW_CHG; + } + qos_cfg = &pf->hw.port_info->qos_cfg; /* DSCP configuration is not DCBx negotiated */ @@ -261,6 +271,11 @@ static int ice_dcbnl_setpfc(struct net_device *netdev, struct ieee_pfc *pfc) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) return -EINVAL; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + mutex_lock(&pf->tc_mutex); new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; @@ -323,6 +338,11 @@ static void ice_dcbnl_set_pfc_cfg(struct net_device *netdev, int prio, u8 set) if (prio >= ICE_MAX_USER_PRIORITY) return; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; new_cfg->pfc.pfccap = pf->hw.func_caps.common_cap.maxtc; @@ -379,6 +399,11 @@ static u8 ice_dcbnl_setstate(struct net_device *netdev, u8 state) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) return ICE_DCB_NO_HW_CHG; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return ICE_DCB_NO_HW_CHG; + } + /* Nothing to do */ if (!!state == test_bit(ICE_FLAG_DCB_ENA, pf->flags)) return ICE_DCB_NO_HW_CHG; @@ -451,6 +476,11 @@ ice_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc, if (tc >= ICE_MAX_TRAFFIC_CLASS) return; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; /* prio_type, bwg_id and bw_pct per UP are not supported */ @@ -505,6 +535,11 @@ ice_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int pgid, u8 bw_pct) if (pgid >= ICE_MAX_TRAFFIC_CLASS) return; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; new_cfg->etscfg.tcbwtable[pgid] = bw_pct; @@ -725,6 +760,11 @@ static int ice_dcbnl_setapp(struct net_device *netdev, struct dcb_app *app) return -EINVAL; } + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + max_tc = pf->hw.func_caps.common_cap.maxtc; if (app->priority >= max_tc) { netdev_err(netdev, "TC %d out of range, max TC %d\n", @@ -836,6 +876,11 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app) return -EINVAL; } + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + mutex_lock(&pf->tc_mutex); old_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; @@ -937,6 +982,11 @@ static u8 ice_dcbnl_cee_set_all(struct net_device *netdev) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) return ICE_DCB_NO_HW_CHG; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return ICE_DCB_NO_HW_CHG; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; mutex_lock(&pf->tc_mutex); diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 5a7753bda324..36b7044717e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -4,8 +4,24 @@ /* Link Aggregation code */ #include "ice.h" +#include "ice_lib.h" #include "ice_lag.h" +#define ICE_LAG_RES_SHARED BIT(14) +#define ICE_LAG_RES_VALID BIT(15) + +#define LACP_TRAIN_PKT_LEN 16 +static const u8 lacp_train_pkt[LACP_TRAIN_PKT_LEN] = { 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, + 0x88, 0x09, 0, 0 }; + +#define ICE_RECIPE_LEN 64 +static const u8 ice_dflt_vsi_rcp[ICE_RECIPE_LEN] = { + 0x05, 0, 0, 0, 0x20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0x85, 0, 0x01, 0, 0, 0, 0xff, 0xff, 0x08, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0x30, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; + /** * ice_lag_set_primary - set PF LAG state as Primary * @lag: LAG info struct @@ -46,17 +62,222 @@ static void ice_lag_set_backup(struct ice_lag *lag) lag->role = ICE_LAG_BACKUP; } +/** + * netif_is_same_ice - determine if netdev is on the same ice NIC as local PF + * @pf: local PF struct + * @netdev: netdev we are evaluating + */ +static bool netif_is_same_ice(struct ice_pf *pf, struct net_device *netdev) +{ + struct ice_netdev_priv *np; + struct ice_pf *test_pf; + struct ice_vsi *vsi; + + if (!netif_is_ice(netdev)) + return false; + + np = netdev_priv(netdev); + if (!np) + return false; + + vsi = np->vsi; + if (!vsi) + return false; + + test_pf = vsi->back; + if (!test_pf) + return false; + + if (pf->pdev->bus != test_pf->pdev->bus || + pf->pdev->slot != test_pf->pdev->slot) + return false; + + return true; +} + +/** + * ice_netdev_to_lag - return pointer to associated lag struct from netdev + * @netdev: pointer to net_device struct to query + */ +static struct ice_lag *ice_netdev_to_lag(struct net_device *netdev) +{ + struct ice_netdev_priv *np; + struct ice_vsi *vsi; + + if (!netif_is_ice(netdev)) + return NULL; + + np = netdev_priv(netdev); + if (!np) + return NULL; + + vsi = np->vsi; + if (!vsi) + return NULL; + + return vsi->back->lag; +} + +/** + * ice_lag_find_hw_by_lport - return an hw struct from bond members lport + * @lag: lag struct + * @lport: lport value to search for + */ +static struct ice_hw * +ice_lag_find_hw_by_lport(struct ice_lag *lag, u8 lport) +{ + struct ice_lag_netdev_list *entry; + struct net_device *tmp_netdev; + struct ice_netdev_priv *np; + struct list_head *tmp; + struct ice_hw *hw; + + list_for_each(tmp, lag->netdev_head) { + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + tmp_netdev = entry->netdev; + if (!tmp_netdev || !netif_is_ice(tmp_netdev)) + continue; + + np = netdev_priv(tmp_netdev); + if (!np || !np->vsi) + continue; + + hw = &np->vsi->back->hw; + if (hw->port_info->lport == lport) + return hw; + } + + return NULL; +} + +/** + * ice_lag_find_primary - returns pointer to primary interfaces lag struct + * @lag: local interfaces lag struct + */ +static struct ice_lag *ice_lag_find_primary(struct ice_lag *lag) +{ + struct ice_lag *primary_lag = NULL; + struct list_head *tmp; + + list_for_each(tmp, lag->netdev_head) { + struct ice_lag_netdev_list *entry; + struct ice_lag *tmp_lag; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + tmp_lag = ice_netdev_to_lag(entry->netdev); + if (tmp_lag && tmp_lag->primary) { + primary_lag = tmp_lag; + break; + } + } + + return primary_lag; +} + +/** + * ice_lag_cfg_dflt_fltr - Add/Remove default VSI rule for LAG + * @lag: lag struct for local interface + * @add: boolean on whether we are adding filters + */ +static int +ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add) +{ + struct ice_sw_rule_lkup_rx_tx *s_rule; + u16 s_rule_sz, vsi_num; + struct ice_hw *hw; + u32 act, opc; + u8 *eth_hdr; + int err; + + hw = &lag->pf->hw; + vsi_num = ice_get_hw_vsi_num(hw, 0); + + s_rule_sz = ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s_rule); + s_rule = kzalloc(s_rule_sz, GFP_KERNEL); + if (!s_rule) { + dev_err(ice_pf_to_dev(lag->pf), "error allocating rule for LAG default VSI\n"); + return -ENOMEM; + } + + if (add) { + 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 |= ICE_SINGLE_ACT_VSI_FORWARDING | + ICE_SINGLE_ACT_VALID_BIT | ICE_SINGLE_ACT_LAN_ENABLE; + + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->recipe_id = cpu_to_le16(lag->pf_recipe); + s_rule->src = cpu_to_le16(hw->port_info->lport); + 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; + } else { + s_rule->index = cpu_to_le16(lag->pf_rule_id); + opc = ice_aqc_opc_remove_sw_rules; + } + + err = ice_aq_sw_rules(&lag->pf->hw, s_rule, s_rule_sz, 1, opc, NULL); + if (err) + goto dflt_fltr_free; + + if (add) + lag->pf_rule_id = le16_to_cpu(s_rule->index); + else + lag->pf_rule_id = 0; + +dflt_fltr_free: + kfree(s_rule); + return err; +} + +/** + * ice_lag_cfg_pf_fltrs - set filters up for new active port + * @lag: local interfaces lag struct + * @ptr: opaque data containing notifier event + */ +static void +ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr) +{ + struct netdev_notifier_bonding_info *info; + struct netdev_bonding_info *bonding_info; + struct net_device *event_netdev; + struct device *dev; + + event_netdev = netdev_notifier_info_to_dev(ptr); + /* not for this netdev */ + if (event_netdev != lag->netdev) + return; + + info = (struct netdev_notifier_bonding_info *)ptr; + bonding_info = &info->bonding_info; + 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 (ice_lag_cfg_dflt_fltr(lag, false)) + dev_err(dev, "Error removing old default VSI filter\n"); + return; + } + + /* interface becoming active - add new default VSI rule */ + if (!bonding_info->slave.state && !lag->pf_rule_id) + if (ice_lag_cfg_dflt_fltr(lag, true)) + dev_err(dev, "Error adding new default VSI filter\n"); +} + /** * ice_display_lag_info - print LAG info * @lag: LAG info struct */ static void ice_display_lag_info(struct ice_lag *lag) { - const char *name, *peer, *upper, *role, *bonded, *primary; + const char *name, *upper, *role, *bonded, *primary; struct device *dev = &lag->pf->pdev->dev; name = lag->netdev ? netdev_name(lag->netdev) : "unset"; - peer = lag->peer_netdev ? netdev_name(lag->peer_netdev) : "unset"; upper = lag->upper_netdev ? netdev_name(lag->upper_netdev) : "unset"; primary = lag->primary ? "TRUE" : "FALSE"; bonded = lag->bonded ? "BONDED" : "UNBONDED"; @@ -78,8 +299,410 @@ static void ice_display_lag_info(struct ice_lag *lag) role = "ERROR"; } - dev_dbg(dev, "%s %s, peer:%s, upper:%s, role:%s, primary:%s\n", name, - bonded, peer, upper, role, primary); + dev_dbg(dev, "%s %s, upper:%s, role:%s, primary:%s\n", name, bonded, + upper, role, primary); +} + +/** + * ice_lag_qbuf_recfg - generate a buffer of queues for a reconfigure command + * @hw: HW struct that contains the queue contexts + * @qbuf: pointer to buffer to populate + * @vsi_num: index of the VSI in PF space + * @numq: number of queues to search for + * @tc: traffic class that contains the queues + * + * function returns the number of valid queues in buffer + */ +static u16 +ice_lag_qbuf_recfg(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *qbuf, + u16 vsi_num, u16 numq, u8 tc) +{ + struct ice_q_ctx *q_ctx; + u16 qid, count = 0; + struct ice_pf *pf; + int i; + + pf = hw->back; + for (i = 0; i < numq; i++) { + q_ctx = ice_get_lan_q_ctx(hw, vsi_num, tc, i); + if (!q_ctx) { + dev_dbg(ice_hw_to_dev(hw), "%s queue %d NO Q CONTEXT\n", + __func__, i); + continue; + } + if (q_ctx->q_teid == ICE_INVAL_TEID) { + dev_dbg(ice_hw_to_dev(hw), "%s queue %d INVAL TEID\n", + __func__, i); + continue; + } + if (q_ctx->q_handle == ICE_INVAL_Q_HANDLE) { + dev_dbg(ice_hw_to_dev(hw), "%s queue %d INVAL Q HANDLE\n", + __func__, i); + continue; + } + + qid = pf->vsi[vsi_num]->txq_map[q_ctx->q_handle]; + qbuf->queue_info[count].q_handle = cpu_to_le16(qid); + qbuf->queue_info[count].tc = tc; + qbuf->queue_info[count].q_teid = cpu_to_le32(q_ctx->q_teid); + count++; + } + + return count; +} + +/** + * ice_lag_get_sched_parent - locate or create a sched node parent + * @hw: HW struct for getting parent in + * @tc: traffic class on parent/node + */ +static struct ice_sched_node * +ice_lag_get_sched_parent(struct ice_hw *hw, u8 tc) +{ + struct ice_sched_node *tc_node, *aggnode, *parent = NULL; + u16 num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 }; + struct ice_port_info *pi = hw->port_info; + struct device *dev; + u8 aggl, vsil; + int n; + + dev = ice_hw_to_dev(hw); + + tc_node = ice_sched_get_tc_node(pi, tc); + if (!tc_node) { + dev_warn(dev, "Failure to find TC node for LAG move\n"); + return parent; + } + + aggnode = ice_sched_get_agg_node(pi, tc_node, ICE_DFLT_AGG_ID); + if (!aggnode) { + dev_warn(dev, "Failure to find aggregate node for LAG move\n"); + return parent; + } + + aggl = ice_sched_get_agg_layer(hw); + vsil = ice_sched_get_vsi_layer(hw); + + for (n = aggl + 1; n < vsil; n++) + num_nodes[n] = 1; + + for (n = 0; n < aggnode->num_children; n++) { + parent = ice_sched_get_free_vsi_parent(hw, aggnode->children[n], + num_nodes); + if (parent) + return parent; + } + + /* if free parent not found - add one */ + parent = aggnode; + for (n = aggl + 1; n < vsil; n++) { + u16 num_nodes_added; + u32 first_teid; + int err; + + err = ice_sched_add_nodes_to_layer(pi, tc_node, parent, n, + num_nodes[n], &first_teid, + &num_nodes_added); + if (err || num_nodes[n] != num_nodes_added) + return NULL; + + if (num_nodes_added) + parent = ice_sched_find_node_by_teid(tc_node, + first_teid); + else + parent = parent->children[0]; + if (!parent) { + dev_warn(dev, "Failure to add new parent for LAG move\n"); + return parent; + } + } + + return parent; +} + +/** + * ice_lag_move_vf_node_tc - move scheduling nodes for one VF on one TC + * @lag: lag info struct + * @oldport: lport of previous nodes location + * @newport: lport of destination nodes location + * @vsi_num: array index of VSI in PF space + * @tc: traffic class to move + */ +static void +ice_lag_move_vf_node_tc(struct ice_lag *lag, u8 oldport, u8 newport, + u16 vsi_num, u8 tc) +{ + u16 numq, valq, buf_size, num_moved, qbuf_size; + struct device *dev = ice_pf_to_dev(lag->pf); + struct ice_aqc_cfg_txqs_buf *qbuf; + struct ice_aqc_move_elem *buf; + struct ice_sched_node *n_prt; + struct ice_hw *new_hw = NULL; + __le32 teid, parent_teid; + struct ice_vsi_ctx *ctx; + u32 tmp_teid; + + ctx = ice_get_vsi_ctx(&lag->pf->hw, vsi_num); + if (!ctx) { + dev_warn(dev, "Unable to locate VSI context for LAG failover\n"); + return; + } + + /* check to see if this VF is enabled on this TC */ + if (!ctx->sched.vsi_node[tc]) + return; + + /* locate HW struct for destination port */ + new_hw = ice_lag_find_hw_by_lport(lag, newport); + if (!new_hw) { + dev_warn(dev, "Unable to locate HW struct for LAG node destination\n"); + return; + } + + numq = ctx->num_lan_q_entries[tc]; + teid = ctx->sched.vsi_node[tc]->info.node_teid; + tmp_teid = le32_to_cpu(teid); + parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid; + /* if no teid assigned or numq == 0, then this TC is not active */ + if (!tmp_teid || !numq) + return; + + /* suspend VSI subtree for Traffic Class "tc" on + * this VF's VSI + */ + if (ice_sched_suspend_resume_elems(&lag->pf->hw, 1, &tmp_teid, true)) + dev_dbg(dev, "Problem suspending traffic for LAG node move\n"); + + /* reconfigure all VF's queues on this Traffic Class + * to new port + */ + qbuf_size = struct_size(qbuf, queue_info, numq); + qbuf = kzalloc(qbuf_size, GFP_KERNEL); + if (!qbuf) { + dev_warn(dev, "Failure allocating memory for VF queue recfg buffer\n"); + goto resume_traffic; + } + + /* add the per queue info for the reconfigure command buffer */ + valq = ice_lag_qbuf_recfg(&lag->pf->hw, qbuf, vsi_num, numq, tc); + if (!valq) { + dev_dbg(dev, "No valid queues found for LAG failover\n"); + goto qbuf_none; + } + + if (ice_aq_cfg_lan_txq(&lag->pf->hw, qbuf, qbuf_size, valq, oldport, + newport, NULL)) { + dev_warn(dev, "Failure to configure queues for LAG failover\n"); + goto qbuf_err; + } + +qbuf_none: + kfree(qbuf); + + /* find new parent in destination port's tree for VF VSI node on this + * Traffic Class + */ + n_prt = ice_lag_get_sched_parent(new_hw, tc); + if (!n_prt) + goto resume_traffic; + + /* Move Vf's VSI node for this TC to newport's scheduler tree */ + buf_size = struct_size(buf, teid, 1); + buf = kzalloc(buf_size, GFP_KERNEL); + if (!buf) { + dev_warn(dev, "Failure to alloc memory for VF node failover\n"); + goto resume_traffic; + } + + buf->hdr.src_parent_teid = parent_teid; + buf->hdr.dest_parent_teid = n_prt->info.node_teid; + buf->hdr.num_elems = cpu_to_le16(1); + buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN; + buf->teid[0] = teid; + + if (ice_aq_move_sched_elems(&lag->pf->hw, 1, buf, buf_size, &num_moved, + NULL)) + dev_warn(dev, "Failure to move VF nodes for failover\n"); + else + ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]); + + kfree(buf); + goto resume_traffic; + +qbuf_err: + kfree(qbuf); + +resume_traffic: + /* restart traffic for VSI node */ + if (ice_sched_suspend_resume_elems(&lag->pf->hw, 1, &tmp_teid, false)) + dev_dbg(dev, "Problem restarting traffic for LAG node move\n"); +} + +/** + * ice_lag_move_single_vf_nodes - Move Tx scheduling nodes for single VF + * @lag: primary interface LAG struct + * @oldport: lport of previous interface + * @newport: lport of destination interface + * @vsi_num: SW index of VF's VSI + */ +static void +ice_lag_move_single_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport, + u16 vsi_num) +{ + u8 tc; + + ice_for_each_traffic_class(tc) + ice_lag_move_vf_node_tc(lag, oldport, newport, vsi_num, tc); +} + +/** + * ice_lag_move_new_vf_nodes - Move Tx scheduling nodes for a VF if required + * @vf: the VF to move Tx nodes for + * + * Called just after configuring new VF queues. Check whether the VF Tx + * scheduling nodes need to be updated to fail over to the active port. If so, + * move them now. + */ +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; + struct ice_pf *pf; + + vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + return; + + if (WARN_ON(vsi->type != ICE_VSI_VF)) + return; + + pf = vf->pf; + lag = pf->lag; + + mutex_lock(&pf->lag_mutex); + if (!lag->bonded) + goto new_vf_unlock; + + 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 (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; + +new_vf_unlock: + mutex_unlock(&pf->lag_mutex); +} + +/** + * ice_lag_move_vf_nodes - move Tx scheduling nodes for all VFs to new port + * @lag: lag info struct + * @oldport: lport of previous interface + * @newport: lport of destination interface + */ +static void ice_lag_move_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport) +{ + struct ice_pf *pf; + int i; + + if (!lag->primary) + return; + + 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)) + ice_lag_move_single_vf_nodes(lag, oldport, newport, i); +} + +#define ICE_LAG_SRIOV_CP_RECIPE 10 +#define ICE_LAG_SRIOV_TRAIN_PKT_LEN 16 + +/** + * ice_lag_cfg_cp_fltr - configure filter for control packets + * @lag: local interface's lag struct + * @add: add or remove rule + */ +static void +ice_lag_cfg_cp_fltr(struct ice_lag *lag, bool add) +{ + struct ice_sw_rule_lkup_rx_tx *s_rule = NULL; + struct ice_vsi *vsi; + u16 buf_len, opc; + + vsi = lag->pf->vsi[0]; + + buf_len = ICE_SW_RULE_RX_TX_HDR_SIZE(s_rule, + ICE_LAG_SRIOV_TRAIN_PKT_LEN); + s_rule = kzalloc(buf_len, GFP_KERNEL); + if (!s_rule) { + netdev_warn(lag->netdev, "-ENOMEM error configuring CP filter\n"); + return; + } + + if (add) { + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->recipe_id = cpu_to_le16(ICE_LAG_SRIOV_CP_RECIPE); + s_rule->src = cpu_to_le16(vsi->port_info->lport); + 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)); + 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; + } else { + opc = ice_aqc_opc_remove_sw_rules; + s_rule->index = cpu_to_le16(lag->cp_rule_idx); + } + if (ice_aq_sw_rules(&lag->pf->hw, s_rule, buf_len, 1, opc, NULL)) { + netdev_warn(lag->netdev, "Error %s CP rule for fail-over\n", + add ? "ADDING" : "REMOVING"); + goto cp_free; + } + + if (add) + lag->cp_rule_idx = le16_to_cpu(s_rule->index); + else + lag->cp_rule_idx = 0; + +cp_free: + kfree(s_rule); } /** @@ -124,117 +747,431 @@ lag_out: } /** - * ice_lag_link - handle LAG link event - * @lag: LAG info struct - * @info: info from the netdev notifier + * ice_lag_reclaim_vf_tc - move scheduling nodes back to primary interface + * @lag: primary interface lag struct + * @src_hw: HW struct current node location + * @vsi_num: VSI index in PF space + * @tc: traffic class to move */ static void -ice_lag_link(struct ice_lag *lag, struct netdev_notifier_changeupper_info *info) +ice_lag_reclaim_vf_tc(struct ice_lag *lag, struct ice_hw *src_hw, u16 vsi_num, + u8 tc) +{ + u16 numq, valq, buf_size, num_moved, qbuf_size; + struct device *dev = ice_pf_to_dev(lag->pf); + struct ice_aqc_cfg_txqs_buf *qbuf; + struct ice_aqc_move_elem *buf; + struct ice_sched_node *n_prt; + __le32 teid, parent_teid; + struct ice_vsi_ctx *ctx; + struct ice_hw *hw; + u32 tmp_teid; + + hw = &lag->pf->hw; + ctx = ice_get_vsi_ctx(hw, vsi_num); + if (!ctx) { + dev_warn(dev, "Unable to locate VSI context for LAG reclaim\n"); + return; + } + + /* check to see if this VF is enabled on this TC */ + if (!ctx->sched.vsi_node[tc]) + return; + + numq = ctx->num_lan_q_entries[tc]; + teid = ctx->sched.vsi_node[tc]->info.node_teid; + tmp_teid = le32_to_cpu(teid); + parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid; + + /* if !teid or !numq, then this TC is not active */ + if (!tmp_teid || !numq) + return; + + /* suspend traffic */ + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, true)) + dev_dbg(dev, "Problem suspending traffic for LAG node move\n"); + + /* reconfig queues for new port */ + qbuf_size = struct_size(qbuf, queue_info, numq); + qbuf = kzalloc(qbuf_size, GFP_KERNEL); + if (!qbuf) { + dev_warn(dev, "Failure allocating memory for VF queue recfg buffer\n"); + goto resume_reclaim; + } + + /* add the per queue info for the reconfigure command buffer */ + valq = ice_lag_qbuf_recfg(hw, qbuf, vsi_num, numq, tc); + if (!valq) { + dev_dbg(dev, "No valid queues found for LAG reclaim\n"); + goto reclaim_none; + } + + if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq, + src_hw->port_info->lport, hw->port_info->lport, + NULL)) { + dev_warn(dev, "Failure to configure queues for LAG failover\n"); + goto reclaim_qerr; + } + +reclaim_none: + kfree(qbuf); + + /* find parent in primary tree */ + n_prt = ice_lag_get_sched_parent(hw, tc); + if (!n_prt) + goto resume_reclaim; + + /* Move node to new parent */ + buf_size = struct_size(buf, teid, 1); + buf = kzalloc(buf_size, GFP_KERNEL); + if (!buf) { + dev_warn(dev, "Failure to alloc memory for VF node failover\n"); + goto resume_reclaim; + } + + buf->hdr.src_parent_teid = parent_teid; + buf->hdr.dest_parent_teid = n_prt->info.node_teid; + buf->hdr.num_elems = cpu_to_le16(1); + buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN; + buf->teid[0] = teid; + + if (ice_aq_move_sched_elems(&lag->pf->hw, 1, buf, buf_size, &num_moved, + NULL)) + dev_warn(dev, "Failure to move VF nodes for LAG reclaim\n"); + else + ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]); + + kfree(buf); + goto resume_reclaim; + +reclaim_qerr: + kfree(qbuf); + +resume_reclaim: + /* restart traffic */ + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, false)) + dev_warn(dev, "Problem restarting traffic for LAG node reclaim\n"); +} + +/** + * ice_lag_reclaim_vf_nodes - When interface leaving bond primary reclaims nodes + * @lag: primary interface lag struct + * @src_hw: HW struct for current node location + */ +static void +ice_lag_reclaim_vf_nodes(struct ice_lag *lag, struct ice_hw *src_hw) +{ + struct ice_pf *pf; + int i, tc; + + if (!lag->primary || !src_hw) + return; + + 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)) + ice_for_each_traffic_class(tc) + ice_lag_reclaim_vf_tc(lag, src_hw, i, tc); +} + +/** + * ice_lag_link - handle LAG link event + * @lag: LAG info struct + */ +static void ice_lag_link(struct ice_lag *lag) { - struct net_device *netdev_tmp, *upper = info->upper_dev; struct ice_pf *pf = lag->pf; - int peers = 0; if (lag->bonded) dev_warn(ice_pf_to_dev(pf), "%s Already part of a bond\n", netdev_name(lag->netdev)); - rcu_read_lock(); - for_each_netdev_in_bond_rcu(upper, netdev_tmp) - peers++; - rcu_read_unlock(); - - if (lag->upper_netdev != upper) { - dev_hold(upper); - lag->upper_netdev = upper; - } - - ice_clear_rdma_cap(pf); - lag->bonded = true; lag->role = ICE_LAG_UNSET; - - /* if this is the first element in an LAG mark as primary */ - lag->primary = !!(peers == 1); + netdev_info(lag->netdev, "Shared SR-IOV resources in bond are active\n"); } /** * ice_lag_unlink - handle unlink event * @lag: LAG info struct - * @info: info from netdev notification */ -static void -ice_lag_unlink(struct ice_lag *lag, - struct netdev_notifier_changeupper_info *info) +static void ice_lag_unlink(struct ice_lag *lag) { - struct net_device *netdev_tmp, *upper = info->upper_dev; + u8 pri_port, act_port, loc_port; struct ice_pf *pf = lag->pf; - bool found = false; if (!lag->bonded) { netdev_dbg(lag->netdev, "bonding unlink event on non-LAG netdev\n"); return; } - /* determine if we are in the new LAG config or not */ - rcu_read_lock(); - for_each_netdev_in_bond_rcu(upper, netdev_tmp) { - if (netdev_tmp == lag->netdev) { - found = true; - break; + if (lag->primary) { + act_port = lag->active_port; + pri_port = lag->pf->hw.port_info->lport; + if (act_port != pri_port && act_port != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes(lag, act_port, pri_port); + lag->primary = false; + lag->active_port = ICE_LAG_INVALID_PORT; + } else { + struct ice_lag *primary_lag; + + primary_lag = ice_lag_find_primary(lag); + if (primary_lag) { + act_port = primary_lag->active_port; + pri_port = primary_lag->pf->hw.port_info->lport; + loc_port = pf->hw.port_info->lport; + if (act_port == loc_port && + act_port != ICE_LAG_INVALID_PORT) { + ice_lag_reclaim_vf_nodes(primary_lag, + &lag->pf->hw); + primary_lag->active_port = ICE_LAG_INVALID_PORT; + } } } - rcu_read_unlock(); - if (found) - return; - - if (lag->upper_netdev) { - dev_put(lag->upper_netdev); - lag->upper_netdev = NULL; - } - - lag->peer_netdev = NULL; - ice_set_rdma_cap(pf); lag->bonded = false; lag->role = ICE_LAG_NONE; + lag->upper_netdev = NULL; } /** - * ice_lag_unregister - handle netdev unregister events - * @lag: LAG info struct - * @netdev: netdev reporting the event + * ice_lag_link_unlink - helper function to call lag_link/unlink + * @lag: lag info struct + * @ptr: opaque pointer data */ -static void ice_lag_unregister(struct ice_lag *lag, struct net_device *netdev) +static void ice_lag_link_unlink(struct ice_lag *lag, void *ptr) { - struct ice_pf *pf = lag->pf; + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; - /* check to see if this event is for this netdev - * check that we are in an aggregate - */ - if (netdev != lag->netdev || !lag->bonded) + if (netdev != lag->netdev) return; - if (lag->upper_netdev) { - dev_put(lag->upper_netdev); - lag->upper_netdev = NULL; - ice_set_rdma_cap(pf); + if (info->linking) + ice_lag_link(lag); + else + ice_lag_unlink(lag); +} + +/** + * ice_lag_set_swid - set the SWID on secondary interface + * @primary_swid: primary interface's SWID + * @local_lag: local interfaces LAG struct + * @link: Is this a linking activity + * + * If link is false, then primary_swid should be expected to not be valid + * This function should never be called in interrupt context. + */ +static void +ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag, + bool link) +{ + struct ice_aqc_alloc_free_res_elem *buf; + struct ice_aqc_set_port_params *cmd; + struct ice_aq_desc desc; + u16 buf_len, swid; + int status, i; + + buf_len = struct_size(buf, elem, 1); + buf = kzalloc(buf_len, GFP_KERNEL); + if (!buf) { + dev_err(ice_pf_to_dev(local_lag->pf), "-ENOMEM error setting SWID\n"); + return; } - /* perform some cleanup in case we come back */ - lag->bonded = false; - lag->role = ICE_LAG_NONE; + + buf->num_elems = cpu_to_le16(1); + buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_SWID); + /* if unlinnking need to free the shared resource */ + if (!link && local_lag->bond_swid) { + buf->elem[0].e.sw_resp = cpu_to_le16(local_lag->bond_swid); + status = ice_aq_alloc_free_res(&local_lag->pf->hw, 1, buf, + buf_len, ice_aqc_opc_free_res, + NULL); + if (status) + dev_err(ice_pf_to_dev(local_lag->pf), "Error freeing SWID during LAG unlink\n"); + local_lag->bond_swid = 0; + } + + if (link) { + buf->res_type |= cpu_to_le16(ICE_LAG_RES_SHARED | + ICE_LAG_RES_VALID); + /* store the primary's SWID in case it leaves bond first */ + local_lag->bond_swid = primary_swid; + buf->elem[0].e.sw_resp = cpu_to_le16(local_lag->bond_swid); + } else { + buf->elem[0].e.sw_resp = + cpu_to_le16(local_lag->pf->hw.port_info->sw_id); + } + + status = ice_aq_alloc_free_res(&local_lag->pf->hw, 1, buf, buf_len, + ice_aqc_opc_alloc_res, NULL); + if (status) + dev_err(ice_pf_to_dev(local_lag->pf), "Error subscribing to SWID 0x%04X\n", + local_lag->bond_swid); + + kfree(buf); + + /* Configure port param SWID to correct value */ + if (link) + swid = primary_swid; + else + swid = local_lag->pf->hw.port_info->sw_id; + + cmd = &desc.params.set_port_params; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_params); + + cmd->swid = cpu_to_le16(ICE_AQC_PORT_SWID_VALID | swid); + /* If this is happening in reset context, it is possible that the + * primary interface has not finished setting its SWID to SHARED + * yet. Allow retries to account for this timing issue between + * interfaces. + */ + for (i = 0; i < ICE_LAG_RESET_RETRIES; i++) { + status = ice_aq_send_cmd(&local_lag->pf->hw, &desc, NULL, 0, + NULL); + if (!status) + break; + + usleep_range(1000, 2000); + } + + if (status) + dev_err(ice_pf_to_dev(local_lag->pf), "Error setting SWID in port params %d\n", + status); +} + +/** + * ice_lag_primary_swid - set/clear the SHARED attrib of primary's SWID + * @lag: primary interface's lag struct + * @link: is this a linking activity + * + * Implement setting primary SWID as shared using 0x020B + */ +static void ice_lag_primary_swid(struct ice_lag *lag, bool link) +{ + struct ice_hw *hw; + u16 swid; + + hw = &lag->pf->hw; + swid = hw->port_info->sw_id; + + if (ice_share_res(hw, ICE_AQC_RES_TYPE_SWID, link, swid)) + dev_warn(ice_pf_to_dev(lag->pf), "Failure to set primary interface shared status\n"); +} + +/** + * ice_lag_add_prune_list - Adds event_pf's VSI to primary's prune list + * @lag: lag info struct + * @event_pf: PF struct for VSI we are adding to primary's prune list + */ +static void ice_lag_add_prune_list(struct ice_lag *lag, struct ice_pf *event_pf) +{ + u16 num_vsi, rule_buf_sz, vsi_list_id, event_vsi_num, prim_vsi_idx; + struct ice_sw_rule_vsi_list *s_rule = NULL; + struct device *dev; + + num_vsi = 1; + + dev = ice_pf_to_dev(lag->pf); + event_vsi_num = event_pf->vsi[0]->vsi_num; + prim_vsi_idx = lag->pf->vsi[0]->idx; + + if (!ice_find_vsi_list_entry(&lag->pf->hw, ICE_SW_LKUP_VLAN, + prim_vsi_idx, &vsi_list_id)) { + dev_warn(dev, "Could not locate prune list when setting up SRIOV LAG\n"); + return; + } + + rule_buf_sz = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, num_vsi); + s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); + if (!s_rule) { + dev_warn(dev, "Error allocating space for prune list when configuring SRIOV LAG\n"); + return; + } + + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_PRUNE_LIST_SET); + s_rule->index = cpu_to_le16(vsi_list_id); + s_rule->number_vsi = cpu_to_le16(num_vsi); + s_rule->vsi[0] = cpu_to_le16(event_vsi_num); + + if (ice_aq_sw_rules(&event_pf->hw, s_rule, rule_buf_sz, 1, + ice_aqc_opc_update_sw_rules, NULL)) + dev_warn(dev, "Error adding VSI prune list\n"); + kfree(s_rule); +} + +/** + * ice_lag_del_prune_list - Remove secondary's vsi from primary's prune list + * @lag: primary interface's ice_lag struct + * @event_pf: PF struct for unlinking interface + */ +static void ice_lag_del_prune_list(struct ice_lag *lag, struct ice_pf *event_pf) +{ + u16 num_vsi, vsi_num, vsi_idx, rule_buf_sz, vsi_list_id; + struct ice_sw_rule_vsi_list *s_rule = NULL; + struct device *dev; + + num_vsi = 1; + + dev = ice_pf_to_dev(lag->pf); + vsi_num = event_pf->vsi[0]->vsi_num; + vsi_idx = lag->pf->vsi[0]->idx; + + if (!ice_find_vsi_list_entry(&lag->pf->hw, ICE_SW_LKUP_VLAN, + vsi_idx, &vsi_list_id)) { + dev_warn(dev, "Could not locate prune list when unwinding SRIOV LAG\n"); + return; + } + + rule_buf_sz = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, num_vsi); + s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); + if (!s_rule) { + dev_warn(dev, "Error allocating prune list when unwinding SRIOV LAG\n"); + return; + } + + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_PRUNE_LIST_CLEAR); + s_rule->index = cpu_to_le16(vsi_list_id); + s_rule->number_vsi = cpu_to_le16(num_vsi); + s_rule->vsi[0] = cpu_to_le16(vsi_num); + + if (ice_aq_sw_rules(&event_pf->hw, (struct ice_aqc_sw_rules *)s_rule, + rule_buf_sz, 1, ice_aqc_opc_update_sw_rules, NULL)) + dev_warn(dev, "Error clearing VSI prune list\n"); + + kfree(s_rule); +} + +/** + * ice_lag_init_feature_support_flag - Check for NVM support for LAG + * @pf: PF struct + */ +static void ice_lag_init_feature_support_flag(struct ice_pf *pf) +{ + struct ice_hw_common_caps *caps; + + caps = &pf->hw.dev_caps.common_cap; + if (caps->roce_lag) + ice_set_feature_support(pf, ICE_F_ROCE_LAG); + else + ice_clear_feature_support(pf, ICE_F_ROCE_LAG); + + if (caps->sriov_lag) + ice_set_feature_support(pf, ICE_F_SRIOV_LAG); + else + ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); } /** * ice_lag_changeupper_event - handle LAG changeupper event * @lag: LAG info struct * @ptr: opaque pointer data - * - * ptr is to be cast into netdev_notifier_changeupper_info */ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr) { struct netdev_notifier_changeupper_info *info; + struct ice_lag *primary_lag; struct net_device *netdev; info = ptr; @@ -244,44 +1181,444 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr) if (netdev != lag->netdev) return; - if (!info->upper_dev) { - netdev_dbg(netdev, "changeupper rcvd, but no upper defined\n"); - return; + primary_lag = ice_lag_find_primary(lag); + if (info->linking) { + lag->upper_netdev = info->upper_dev; + /* If there is not already a primary interface in the LAG, + * then mark this one as primary. + */ + if (!primary_lag) { + lag->primary = true; + /* Configure primary's SWID to be shared */ + ice_lag_primary_swid(lag, true); + primary_lag = lag; + } else { + u16 swid; + + swid = primary_lag->pf->hw.port_info->sw_id; + ice_lag_set_swid(swid, lag, true); + ice_lag_add_prune_list(primary_lag, lag->pf); + } + /* add filter for primary control packets */ + ice_lag_cfg_cp_fltr(lag, true); + } else { + if (!primary_lag && lag->primary) + primary_lag = lag; + + if (!lag->primary) { + ice_lag_set_swid(0, lag, false); + } else { + if (primary_lag && lag->primary) { + ice_lag_primary_swid(lag, false); + ice_lag_del_prune_list(primary_lag, lag->pf); + } + } + /* remove filter for control packets */ + ice_lag_cfg_cp_fltr(lag, false); } - - netdev_dbg(netdev, "bonding %s\n", info->linking ? "LINK" : "UNLINK"); - - if (!netif_is_lag_master(info->upper_dev)) { - netdev_dbg(netdev, "changeupper rcvd, but not primary. bail\n"); - return; - } - - if (info->linking) - ice_lag_link(lag, info); - else - ice_lag_unlink(lag, info); - - ice_display_lag_info(lag); } /** - * ice_lag_changelower_event - handle LAG changelower event - * @lag: LAG info struct - * @ptr: opaque data pointer + * ice_lag_monitor_link - monitor interfaces entering/leaving the aggregate + * @lag: lag info struct + * @ptr: opaque data containing notifier event * - * ptr to be cast to netdev_notifier_changelowerstate_info + * This function only operates after a primary has been set. */ -static void ice_lag_changelower_event(struct ice_lag *lag, void *ptr) +static void ice_lag_monitor_link(struct ice_lag *lag, void *ptr) { - struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info; + struct ice_hw *prim_hw, *active_hw; + struct net_device *event_netdev; + struct ice_pf *pf; + u8 prim_port; + + if (!lag->primary) + return; + + event_netdev = netdev_notifier_info_to_dev(ptr); + if (!netif_is_same_ice(lag->pf, event_netdev)) + return; + + pf = lag->pf; + prim_hw = &pf->hw; + prim_port = prim_hw->port_info->lport; + + info = (struct netdev_notifier_changeupper_info *)ptr; + if (info->upper_dev != lag->upper_netdev) + return; + + if (!info->linking) { + /* Since there are only two interfaces allowed in SRIOV+LAG, if + * one port is leaving, then nodes need to be on primary + * interface. + */ + if (prim_port != lag->active_port && + lag->active_port != ICE_LAG_INVALID_PORT) { + active_hw = ice_lag_find_hw_by_lport(lag, + lag->active_port); + ice_lag_reclaim_vf_nodes(lag, active_hw); + lag->active_port = ICE_LAG_INVALID_PORT; + } + } +} + +/** + * ice_lag_monitor_active - main PF keep track of which port is active + * @lag: lag info struct + * @ptr: opaque data containing notifier event + * + * This function is for the primary PF to monitor changes in which port is + * active and handle changes for SRIOV VF functionality + */ +static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr) +{ + struct net_device *event_netdev, *event_upper; + struct netdev_notifier_bonding_info *info; + struct netdev_bonding_info *bonding_info; + struct ice_netdev_priv *event_np; + struct ice_pf *pf, *event_pf; + u8 prim_port, event_port; + + if (!lag->primary) + return; + + pf = lag->pf; + if (!pf) + return; + + event_netdev = netdev_notifier_info_to_dev(ptr); + rcu_read_lock(); + event_upper = netdev_master_upper_dev_get_rcu(event_netdev); + rcu_read_unlock(); + if (!netif_is_ice(event_netdev) || event_upper != lag->upper_netdev) + return; + + event_np = netdev_priv(event_netdev); + event_pf = event_np->vsi->back; + event_port = event_pf->hw.port_info->lport; + prim_port = pf->hw.port_info->lport; + + info = (struct netdev_notifier_bonding_info *)ptr; + bonding_info = &info->bonding_info; + + if (!bonding_info->slave.state) { + /* if no port is currently active, then nodes and filters exist + * on primary port, check if we need to move them + */ + if (lag->active_port == ICE_LAG_INVALID_PORT) { + if (event_port != prim_port) + ice_lag_move_vf_nodes(lag, prim_port, + event_port); + lag->active_port = event_port; + return; + } + + /* active port is already set and is current event port */ + if (lag->active_port == event_port) + return; + /* new active port */ + ice_lag_move_vf_nodes(lag, lag->active_port, event_port); + lag->active_port = event_port; + } else { + /* port not set as currently active (e.g. new active port + * has already claimed the nodes and filters + */ + if (lag->active_port != event_port) + return; + /* This is the case when neither port is active (both link down) + * Link down on the bond - set active port to invalid and move + * nodes and filters back to primary if not already there + */ + if (event_port != prim_port) + ice_lag_move_vf_nodes(lag, event_port, prim_port); + lag->active_port = ICE_LAG_INVALID_PORT; + } +} + +/** + * ice_lag_chk_comp - evaluate bonded interface for feature support + * @lag: lag info struct + * @ptr: opaque data for netdev event info + */ +static bool +ice_lag_chk_comp(struct ice_lag *lag, void *ptr) +{ + struct net_device *event_netdev, *event_upper; + struct netdev_notifier_bonding_info *info; + struct netdev_bonding_info *bonding_info; + struct list_head *tmp; + struct device *dev; + int count = 0; + + if (!lag->primary) + return true; + + event_netdev = netdev_notifier_info_to_dev(ptr); + rcu_read_lock(); + event_upper = netdev_master_upper_dev_get_rcu(event_netdev); + rcu_read_unlock(); + if (event_upper != lag->upper_netdev) + return true; + + dev = ice_pf_to_dev(lag->pf); + + /* only supporting switchdev mode for SRIOV VF LAG. + * primary interface has to be in switchdev mode + */ + if (!ice_is_switchdev_running(lag->pf)) { + dev_info(dev, "Primary interface not in switchdev mode - VF LAG disabled\n"); + return false; + } + + info = (struct netdev_notifier_bonding_info *)ptr; + bonding_info = &info->bonding_info; + lag->bond_mode = bonding_info->master.bond_mode; + if (lag->bond_mode != BOND_MODE_ACTIVEBACKUP) { + dev_info(dev, "Bond Mode not ACTIVE-BACKUP - VF LAG disabled\n"); + return false; + } + + list_for_each(tmp, lag->netdev_head) { + struct ice_dcbx_cfg *dcb_cfg, *peer_dcb_cfg; + struct ice_lag_netdev_list *entry; + struct ice_netdev_priv *peer_np; + struct net_device *peer_netdev; + struct ice_vsi *vsi, *peer_vsi; + struct ice_pf *peer_pf; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + peer_netdev = entry->netdev; + if (!netif_is_ice(peer_netdev)) { + dev_info(dev, "Found %s non-ice netdev in LAG - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + + count++; + if (count > 2) { + dev_info(dev, "Found more than two netdevs in LAG - VF LAG disabled\n"); + return false; + } + + peer_np = netdev_priv(peer_netdev); + vsi = ice_get_main_vsi(lag->pf); + peer_vsi = peer_np->vsi; + if (lag->pf->pdev->bus != peer_vsi->back->pdev->bus || + lag->pf->pdev->slot != peer_vsi->back->pdev->slot) { + dev_info(dev, "Found %s on different device in LAG - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + + dcb_cfg = &vsi->port_info->qos_cfg.local_dcbx_cfg; + peer_dcb_cfg = &peer_vsi->port_info->qos_cfg.local_dcbx_cfg; + if (memcmp(dcb_cfg, peer_dcb_cfg, + sizeof(struct ice_dcbx_cfg))) { + dev_info(dev, "Found %s with different DCB in LAG - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + + peer_pf = peer_vsi->back; + if (test_bit(ICE_FLAG_FW_LLDP_AGENT, peer_pf->flags)) { + dev_warn(dev, "Found %s with FW LLDP agent active - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + } + + return true; +} + +/** + * ice_lag_unregister - handle netdev unregister events + * @lag: LAG info struct + * @event_netdev: netdev struct for target of notifier event + */ +static void +ice_lag_unregister(struct ice_lag *lag, struct net_device *event_netdev) +{ + struct ice_netdev_priv *np; + struct ice_pf *event_pf; + struct ice_lag *p_lag; + + p_lag = ice_lag_find_primary(lag); + np = netdev_priv(event_netdev); + event_pf = np->vsi->back; + + if (p_lag) { + if (p_lag->active_port != p_lag->pf->hw.port_info->lport && + p_lag->active_port != ICE_LAG_INVALID_PORT) { + struct ice_hw *active_hw; + + active_hw = ice_lag_find_hw_by_lport(lag, + p_lag->active_port); + if (active_hw) + ice_lag_reclaim_vf_nodes(p_lag, active_hw); + lag->active_port = ICE_LAG_INVALID_PORT; + } + } + + /* primary processing for primary */ + if (lag->primary && lag->netdev == event_netdev) + ice_lag_primary_swid(lag, false); + + /* primary processing for secondary */ + if (lag->primary && lag->netdev != event_netdev) + ice_lag_del_prune_list(lag, event_pf); + + /* secondary processing for secondary */ + if (!lag->primary && lag->netdev == event_netdev) + ice_lag_set_swid(0, lag, false); +} + +/** + * ice_lag_monitor_rdma - set and clear rdma functionality + * @lag: pointer to lag struct + * @ptr: opaque data for netdev event info + */ +static void +ice_lag_monitor_rdma(struct ice_lag *lag, void *ptr) +{ + struct netdev_notifier_changeupper_info *info; + struct net_device *netdev; + + info = ptr; + netdev = netdev_notifier_info_to_dev(ptr); if (netdev != lag->netdev) return; - netdev_dbg(netdev, "bonding info\n"); + if (info->linking) + ice_clear_rdma_cap(lag->pf); + else + ice_set_rdma_cap(lag->pf); +} - if (!netif_is_lag_port(netdev)) - netdev_dbg(netdev, "CHANGELOWER rcvd, but netdev not in LAG. Bail\n"); +/** + * ice_lag_chk_disabled_bond - monitor interfaces entering/leaving disabled bond + * @lag: lag info struct + * @ptr: opaque data containing event + * + * as interfaces enter a bond - determine if the bond is currently + * SRIOV LAG compliant and flag if not. As interfaces leave the + * bond, reset their compliant status. + */ +static void ice_lag_chk_disabled_bond(struct ice_lag *lag, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + struct ice_lag *prim_lag; + + if (netdev != lag->netdev) + return; + + if (info->linking) { + prim_lag = ice_lag_find_primary(lag); + if (prim_lag && + !ice_is_feature_supported(prim_lag->pf, ICE_F_SRIOV_LAG)) { + ice_clear_feature_support(lag->pf, ICE_F_SRIOV_LAG); + netdev_info(netdev, "Interface added to non-compliant SRIOV LAG aggregate\n"); + } + } else { + ice_lag_init_feature_support_flag(lag->pf); + } +} + +/** + * ice_lag_disable_sriov_bond - set members of bond as not supporting SRIOV LAG + * @lag: primary interfaces lag struct + */ +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 list_head *tmp; + struct ice_pf *pf; + + list_for_each(tmp, lag->netdev_head) { + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + netdev = entry->netdev; + np = netdev_priv(netdev); + pf = np->vsi->back; + + ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); + } +} + +/** + * ice_lag_process_event - process a task assigned to the lag_wq + * @work: pointer to work_struct + */ +static void ice_lag_process_event(struct work_struct *work) +{ + struct netdev_notifier_changeupper_info *info; + struct ice_lag_work *lag_work; + struct net_device *netdev; + struct list_head *tmp, *n; + struct ice_pf *pf; + + lag_work = container_of(work, struct ice_lag_work, lag_task); + pf = lag_work->lag->pf; + + mutex_lock(&pf->lag_mutex); + lag_work->lag->netdev_head = &lag_work->netdev_list.node; + + switch (lag_work->event) { + case NETDEV_CHANGEUPPER: + info = &lag_work->info.changeupper_info; + ice_lag_chk_disabled_bond(lag_work->lag, info); + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) { + ice_lag_monitor_link(lag_work->lag, info); + ice_lag_changeupper_event(lag_work->lag, info); + ice_lag_link_unlink(lag_work->lag, info); + } + ice_lag_monitor_rdma(lag_work->lag, info); + break; + case NETDEV_BONDING_INFO: + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) { + if (!ice_lag_chk_comp(lag_work->lag, + &lag_work->info.bonding_info)) { + netdev = lag_work->info.bonding_info.info.dev; + ice_lag_disable_sriov_bond(lag_work->lag); + ice_lag_unregister(lag_work->lag, netdev); + goto lag_cleanup; + } + ice_lag_monitor_active(lag_work->lag, + &lag_work->info.bonding_info); + ice_lag_cfg_pf_fltrs(lag_work->lag, + &lag_work->info.bonding_info); + } + ice_lag_info_event(lag_work->lag, &lag_work->info.bonding_info); + break; + case NETDEV_UNREGISTER: + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) { + netdev = lag_work->info.bonding_info.info.dev; + if ((netdev == lag_work->lag->netdev || + lag_work->lag->primary) && lag_work->lag->bonded) + ice_lag_unregister(lag_work->lag, netdev); + } + break; + default: + break; + } + +lag_cleanup: + /* cleanup resources allocated for this work item */ + list_for_each_safe(tmp, n, &lag_work->netdev_list.node) { + struct ice_lag_netdev_list *entry; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + list_del(&entry->node); + kfree(entry); + } + lag_work->lag->netdev_head = NULL; + + mutex_unlock(&pf->lag_mutex); + + kfree(lag_work); } /** @@ -295,34 +1632,79 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct net_device *upper_netdev; + struct ice_lag_work *lag_work; struct ice_lag *lag; - lag = container_of(notif_blk, struct ice_lag, notif_block); + if (!netif_is_ice(netdev)) + return NOTIFY_DONE; + if (event != NETDEV_CHANGEUPPER && event != NETDEV_BONDING_INFO && + event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + + if (!(netdev->priv_flags & IFF_BONDING)) + return NOTIFY_DONE; + + lag = container_of(notif_blk, struct ice_lag, notif_block); if (!lag->netdev) return NOTIFY_DONE; - /* Check that the netdev is in the working namespace */ if (!net_eq(dev_net(netdev), &init_net)) return NOTIFY_DONE; + /* This memory will be freed at the end of ice_lag_process_event */ + lag_work = kzalloc(sizeof(*lag_work), GFP_KERNEL); + if (!lag_work) + return -ENOMEM; + + lag_work->event_netdev = netdev; + lag_work->lag = lag; + lag_work->event = event; + if (event == NETDEV_CHANGEUPPER) { + struct netdev_notifier_changeupper_info *info; + + info = ptr; + upper_netdev = info->upper_dev; + } else { + upper_netdev = netdev_master_upper_dev_get(netdev); + } + + INIT_LIST_HEAD(&lag_work->netdev_list.node); + if (upper_netdev) { + struct ice_lag_netdev_list *nd_list; + struct net_device *tmp_nd; + + rcu_read_lock(); + for_each_netdev_in_bond_rcu(upper_netdev, tmp_nd) { + nd_list = kzalloc(sizeof(*nd_list), GFP_KERNEL); + if (!nd_list) + break; + + nd_list->netdev = tmp_nd; + list_add(&nd_list->node, &lag_work->netdev_list.node); + } + rcu_read_unlock(); + } + switch (event) { case NETDEV_CHANGEUPPER: - ice_lag_changeupper_event(lag, ptr); - break; - case NETDEV_CHANGELOWERSTATE: - ice_lag_changelower_event(lag, ptr); + lag_work->info.changeupper_info = + *((struct netdev_notifier_changeupper_info *)ptr); break; case NETDEV_BONDING_INFO: - ice_lag_info_event(lag, ptr); - break; - case NETDEV_UNREGISTER: - ice_lag_unregister(lag, netdev); + lag_work->info.bonding_info = + *((struct netdev_notifier_bonding_info *)ptr); break; default: + lag_work->info.notifier_info = + *((struct netdev_notifier_info *)ptr); break; } + INIT_WORK(&lag_work->lag_task, ice_lag_process_event); + queue_work(ice_lag_wq, &lag_work->lag_task); + return NOTIFY_DONE; } @@ -365,6 +1747,174 @@ static void ice_unregister_lag_handler(struct ice_lag *lag) } } +/** + * ice_create_lag_recipe + * @hw: pointer to HW struct + * @rid: pointer to u16 to pass back recipe index + * @base_recipe: recipe to base the new recipe on + * @prio: priority for new recipe + * + * function returns 0 on error + */ +static int ice_create_lag_recipe(struct ice_hw *hw, u16 *rid, + const u8 *base_recipe, u8 prio) +{ + struct ice_aqc_recipe_data_elem *new_rcp; + int err; + + err = ice_alloc_recipe(hw, rid); + if (err) + return err; + + new_rcp = kzalloc(ICE_RECIPE_LEN * ICE_MAX_NUM_RECIPES, GFP_KERNEL); + if (!new_rcp) + return -ENOMEM; + + memcpy(new_rcp, base_recipe, ICE_RECIPE_LEN); + new_rcp->content.act_ctrl_fwd_priority = prio; + new_rcp->content.rid = *rid | ICE_AQ_RECIPE_ID_IS_ROOT; + new_rcp->recipe_indx = *rid; + bitmap_zero((unsigned long *)new_rcp->recipe_bitmap, + ICE_MAX_NUM_RECIPES); + set_bit(*rid, (unsigned long *)new_rcp->recipe_bitmap); + + err = ice_aq_add_recipe(hw, new_rcp, 1, NULL); + if (err) + *rid = 0; + + kfree(new_rcp); + return err; +} + +/** + * ice_lag_move_vf_nodes_tc_sync - move a VF's nodes for a tc during reset + * @lag: primary interfaces lag struct + * @dest_hw: HW struct for destination's interface + * @vsi_num: VSI index in PF space + * @tc: traffic class to move + */ +static void +ice_lag_move_vf_nodes_tc_sync(struct ice_lag *lag, struct ice_hw *dest_hw, + u16 vsi_num, u8 tc) +{ + u16 numq, valq, buf_size, num_moved, qbuf_size; + struct device *dev = ice_pf_to_dev(lag->pf); + struct ice_aqc_cfg_txqs_buf *qbuf; + struct ice_aqc_move_elem *buf; + struct ice_sched_node *n_prt; + __le32 teid, parent_teid; + struct ice_vsi_ctx *ctx; + struct ice_hw *hw; + u32 tmp_teid; + + hw = &lag->pf->hw; + ctx = ice_get_vsi_ctx(hw, vsi_num); + if (!ctx) { + dev_warn(dev, "LAG rebuild failed after reset due to VSI Context failure\n"); + return; + } + + if (!ctx->sched.vsi_node[tc]) + return; + + numq = ctx->num_lan_q_entries[tc]; + teid = ctx->sched.vsi_node[tc]->info.node_teid; + tmp_teid = le32_to_cpu(teid); + parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid; + + if (!tmp_teid || !numq) + return; + + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, true)) + dev_dbg(dev, "Problem suspending traffic during reset rebuild\n"); + + /* reconfig queues for new port */ + qbuf_size = struct_size(qbuf, queue_info, numq); + qbuf = kzalloc(qbuf_size, GFP_KERNEL); + if (!qbuf) { + dev_warn(dev, "Failure allocating VF queue recfg buffer for reset rebuild\n"); + goto resume_sync; + } + + /* add the per queue info for the reconfigure command buffer */ + valq = ice_lag_qbuf_recfg(hw, qbuf, vsi_num, numq, tc); + if (!valq) { + dev_warn(dev, "Failure to reconfig queues for LAG reset rebuild\n"); + goto sync_none; + } + + if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq, hw->port_info->lport, + dest_hw->port_info->lport, NULL)) { + dev_warn(dev, "Failure to configure queues for LAG reset rebuild\n"); + goto sync_qerr; + } + +sync_none: + kfree(qbuf); + + /* find parent in destination tree */ + n_prt = ice_lag_get_sched_parent(dest_hw, tc); + if (!n_prt) + goto resume_sync; + + /* Move node to new parent */ + buf_size = struct_size(buf, teid, 1); + buf = kzalloc(buf_size, GFP_KERNEL); + if (!buf) { + dev_warn(dev, "Failure to alloc for VF node move in reset rebuild\n"); + goto resume_sync; + } + + buf->hdr.src_parent_teid = parent_teid; + buf->hdr.dest_parent_teid = n_prt->info.node_teid; + buf->hdr.num_elems = cpu_to_le16(1); + buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN; + buf->teid[0] = teid; + + if (ice_aq_move_sched_elems(&lag->pf->hw, 1, buf, buf_size, &num_moved, + NULL)) + dev_warn(dev, "Failure to move VF nodes for LAG reset rebuild\n"); + else + ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]); + + kfree(buf); + goto resume_sync; + +sync_qerr: + kfree(qbuf); + +resume_sync: + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, false)) + dev_warn(dev, "Problem restarting traffic for LAG node reset rebuild\n"); +} + +/** + * ice_lag_move_vf_nodes_sync - move vf nodes to active interface + * @lag: primary interfaces lag struct + * @dest_hw: lport value for currently active port + * + * This function is used in a reset context, outside of event handling, + * to move the VF nodes to the secondary interface when that interface + * is the active interface during a reset rebuild + */ +static void +ice_lag_move_vf_nodes_sync(struct ice_lag *lag, struct ice_hw *dest_hw) +{ + struct ice_pf *pf; + int i, tc; + + if (!lag->primary || !dest_hw) + return; + + 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)) + ice_for_each_traffic_class(tc) + ice_lag_move_vf_nodes_tc_sync(lag, dest_hw, i, + tc); +} + /** * ice_init_lag - initialize support for LAG * @pf: PF struct @@ -377,7 +1927,10 @@ int ice_init_lag(struct ice_pf *pf) struct device *dev = ice_pf_to_dev(pf); struct ice_lag *lag; struct ice_vsi *vsi; - int err; + u64 recipe_bits = 0; + int n, err; + + ice_lag_init_feature_support_flag(pf); pf->lag = kzalloc(sizeof(*lag), GFP_KERNEL); if (!pf->lag) @@ -394,8 +1947,8 @@ int ice_init_lag(struct ice_pf *pf) lag->pf = pf; lag->netdev = vsi->netdev; lag->role = ICE_LAG_NONE; + lag->active_port = ICE_LAG_INVALID_PORT; lag->bonded = false; - lag->peer_netdev = NULL; lag->upper_netdev = NULL; lag->notif_block.notifier_call = NULL; @@ -405,6 +1958,25 @@ int ice_init_lag(struct ice_pf *pf) goto lag_error; } + err = ice_create_lag_recipe(&pf->hw, &lag->pf_recipe, ice_dflt_vsi_rcp, + 1); + if (err) + goto lag_error; + + /* 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); + if (err) + continue; + + if (recipe_bits & BIT(ICE_SW_LKUP_DFLT)) { + recipe_bits |= BIT(lag->pf_recipe); + ice_aq_map_recipe_to_profile(&pf->hw, n, + (u8 *)&recipe_bits, NULL); + } + } + ice_display_lag_info(lag); dev_dbg(dev, "INIT LAG complete\n"); @@ -435,11 +2007,94 @@ void ice_deinit_lag(struct ice_pf *pf) if (lag->pf) ice_unregister_lag_handler(lag); - dev_put(lag->upper_netdev); + flush_workqueue(ice_lag_wq); - dev_put(lag->peer_netdev); + ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1, + &pf->lag->pf_recipe); kfree(lag); pf->lag = NULL; } + +/** + * ice_lag_rebuild - rebuild lag resources after reset + * @pf: pointer to local pf struct + * + * PF resets are promoted to CORER resets when interface in an aggregate. This + * means that we need to rebuild the PF resources for the interface. Since + * this will happen outside the normal event processing, need to acquire the lag + * lock. + * + * This function will also evaluate the VF resources if this is the primary + * interface. + */ +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) + return; + + mutex_lock(&pf->lag_mutex); + + lag = pf->lag; + 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; + prim_lag = ice_lag_find_primary(lag); + } + + if (!prim_lag) { + dev_dbg(ice_pf_to_dev(pf), "No primary interface in aggregate, can't rebuild\n"); + goto lag_rebuild_out; + } + + act_port = prim_lag->active_port; + loc_port = lag->pf->hw.port_info->lport; + + /* configure SWID for this port */ + if (lag->primary) { + ice_lag_primary_swid(lag, true); + } else { + ice_lag_set_swid(prim_lag->pf->hw.port_info->sw_id, lag, true); + ice_lag_add_prune_list(prim_lag, pf); + if (act_port == loc_port) + ice_lag_move_vf_nodes_sync(prim_lag, &pf->hw); + } + + ice_lag_cfg_cp_fltr(lag, true); + + if (lag->pf_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); + } + 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 2c373676c42f..18075b82485a 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.h +++ b/drivers/net/ethernet/intel/ice/ice_lag.h @@ -14,20 +14,52 @@ enum ice_lag_role { ICE_LAG_UNSET }; +#define ICE_LAG_INVALID_PORT 0xFF + +#define ICE_LAG_RESET_RETRIES 5 + struct ice_pf; +struct ice_vf; + +struct ice_lag_netdev_list { + struct list_head node; + struct net_device *netdev; +}; /* LAG info struct */ struct ice_lag { struct ice_pf *pf; /* backlink to PF struct */ struct net_device *netdev; /* this PF's netdev */ - struct net_device *peer_netdev; struct net_device *upper_netdev; /* upper bonding netdev */ + struct list_head *netdev_head; struct notifier_block notif_block; + s32 bond_mode; + u16 bond_swid; /* swid for primary interface */ + u8 active_port; /* lport value for the current active port */ u8 bonded:1; /* currently bonded */ u8 primary:1; /* this is primary */ + u16 pf_recipe; + u16 pf_rule_id; + u16 cp_rule_idx; u8 role; }; +/* LAG workqueue struct */ +struct ice_lag_work { + struct work_struct lag_task; + struct ice_lag_netdev_list netdev_list; + struct ice_lag *lag; + unsigned long event; + struct net_device *event_netdev; + union { + struct netdev_notifier_changeupper_info changeupper_info; + struct netdev_notifier_bonding_info bonding_info; + struct netdev_notifier_info notifier_info; + } info; +}; + +void ice_lag_move_new_vf_nodes(struct ice_vf *vf); int ice_init_lag(struct ice_pf *pf); void ice_deinit_lag(struct ice_pf *pf); +void ice_lag_rebuild(struct ice_pf *pf); #endif /* _ICE_LAG_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index a43c23c80565..077f2e91ae1a 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -3970,7 +3970,7 @@ bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f) * @pf: pointer to the struct ice_pf instance * @f: feature enum to set */ -static void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f) +void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f) { if (f < 0 || f >= ICE_F_MAX) return; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 1628385a9672..dd53fe968ad8 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -163,6 +163,7 @@ int ice_vsi_del_vlan_zero(struct ice_vsi *vsi); bool ice_vsi_has_non_zero_vlans(struct ice_vsi *vsi); u16 ice_vsi_num_non_zero_vlans(struct ice_vsi *vsi); bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f); +void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f); void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f); void ice_init_feature_support(struct ice_pf *pf); bool ice_vsi_is_rx_queue_active(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 9b36cce306b8..20d5ed572a8c 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -64,6 +64,7 @@ struct device *ice_hw_to_dev(struct ice_hw *hw) } static struct workqueue_struct *ice_wq; +struct workqueue_struct *ice_lag_wq; static const struct net_device_ops ice_netdev_safe_mode_ops; static const struct net_device_ops ice_netdev_ops; @@ -635,6 +636,11 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) dev_dbg(dev, "reset_type 0x%x requested\n", reset_type); + if (pf->lag && pf->lag->bonded && reset_type == ICE_RESET_PFR) { + dev_dbg(dev, "PFR on a bonded interface, promoting to CORER\n"); + reset_type = ICE_RESET_CORER; + } + ice_prepare_for_reset(pf, reset_type); /* trigger the reset */ @@ -718,8 +724,13 @@ static void ice_reset_subtask(struct ice_pf *pf) } /* No pending resets to finish processing. Check for new resets */ - if (test_bit(ICE_PFR_REQ, pf->state)) + if (test_bit(ICE_PFR_REQ, pf->state)) { reset_type = ICE_RESET_PFR; + if (pf->lag && pf->lag->bonded) { + dev_dbg(ice_pf_to_dev(pf), "PFR on a bonded interface, promoting to CORER\n"); + reset_type = ICE_RESET_CORER; + } + } if (test_bit(ICE_CORER_REQ, pf->state)) reset_type = ICE_RESET_CORER; if (test_bit(ICE_GLOBR_REQ, pf->state)) @@ -3795,6 +3806,7 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf) static void ice_deinit_pf(struct ice_pf *pf) { ice_service_task_stop(pf); + mutex_destroy(&pf->lag_mutex); mutex_destroy(&pf->adev_mutex); mutex_destroy(&pf->sw_mutex); mutex_destroy(&pf->tc_mutex); @@ -3875,6 +3887,7 @@ static int ice_init_pf(struct ice_pf *pf) mutex_init(&pf->sw_mutex); mutex_init(&pf->tc_mutex); mutex_init(&pf->adev_mutex); + mutex_init(&pf->lag_mutex); INIT_HLIST_HEAD(&pf->aq_wait_list); spin_lock_init(&pf->aq_wait_lock); @@ -5571,7 +5584,7 @@ static struct pci_driver ice_driver = { */ static int __init ice_module_init(void) { - int status; + int status = -ENOMEM; pr_info("%s\n", ice_driver_string); pr_info("%s\n", ice_copyright); @@ -5579,15 +5592,27 @@ static int __init ice_module_init(void) ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); - return -ENOMEM; + return status; + } + + ice_lag_wq = alloc_ordered_workqueue("ice_lag_wq", 0); + if (!ice_lag_wq) { + pr_err("Failed to create LAG workqueue\n"); + goto err_dest_wq; } status = pci_register_driver(&ice_driver); if (status) { pr_err("failed to register PCI driver, err %d\n", status); - destroy_workqueue(ice_wq); + goto err_dest_lag_wq; } + return 0; + +err_dest_lag_wq: + destroy_workqueue(ice_lag_wq); +err_dest_wq: + destroy_workqueue(ice_wq); return status; } module_init(ice_module_init); @@ -5602,6 +5627,7 @@ static void __exit ice_module_exit(void) { pci_unregister_driver(&ice_driver); destroy_workqueue(ice_wq); + destroy_workqueue(ice_lag_wq); pr_info("module unloaded\n"); } module_exit(ice_module_exit); @@ -7357,6 +7383,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) clear_bit(ICE_RESET_FAILED, pf->state); ice_plug_aux_dev(pf); + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) + ice_lag_rebuild(pf); return; err_vsi_rebuild: diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index b664d60fd037..f4677704b95e 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -447,7 +447,7 @@ ice_aq_cfg_sched_elems(struct ice_hw *hw, u16 elems_req, * * Move scheduling elements (0x0408) */ -static int +int ice_aq_move_sched_elems(struct ice_hw *hw, u16 grps_req, struct ice_aqc_move_elem *buf, u16 buf_size, u16 *grps_movd, struct ice_sq_cd *cd) @@ -526,7 +526,7 @@ ice_aq_query_sched_res(struct ice_hw *hw, u16 buf_size, * * This function suspends or resumes HW nodes */ -static int +int ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids, bool suspend) { @@ -569,18 +569,24 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) { struct ice_vsi_ctx *vsi_ctx; struct ice_q_ctx *q_ctx; + u16 idx; vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); if (!vsi_ctx) return -EINVAL; /* allocate LAN queue contexts */ if (!vsi_ctx->lan_q_ctx[tc]) { - vsi_ctx->lan_q_ctx[tc] = devm_kcalloc(ice_hw_to_dev(hw), - new_numqs, - sizeof(*q_ctx), - GFP_KERNEL); - if (!vsi_ctx->lan_q_ctx[tc]) + q_ctx = devm_kcalloc(ice_hw_to_dev(hw), new_numqs, + sizeof(*q_ctx), GFP_KERNEL); + if (!q_ctx) return -ENOMEM; + + for (idx = 0; idx < new_numqs; idx++) { + q_ctx[idx].q_handle = ICE_INVAL_Q_HANDLE; + q_ctx[idx].q_teid = ICE_INVAL_TEID; + } + + vsi_ctx->lan_q_ctx[tc] = q_ctx; vsi_ctx->num_lan_q_entries[tc] = new_numqs; return 0; } @@ -592,9 +598,16 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) sizeof(*q_ctx), GFP_KERNEL); if (!q_ctx) return -ENOMEM; + memcpy(q_ctx, vsi_ctx->lan_q_ctx[tc], prev_num * sizeof(*q_ctx)); devm_kfree(ice_hw_to_dev(hw), vsi_ctx->lan_q_ctx[tc]); + + for (idx = prev_num; idx < new_numqs; idx++) { + q_ctx[idx].q_handle = ICE_INVAL_Q_HANDLE; + q_ctx[idx].q_teid = ICE_INVAL_TEID; + } + vsi_ctx->lan_q_ctx[tc] = q_ctx; vsi_ctx->num_lan_q_entries[tc] = new_numqs; } @@ -1044,7 +1057,7 @@ ice_sched_add_nodes_to_hw_layer(struct ice_port_info *pi, * * This function add nodes to a given layer. */ -static int +int ice_sched_add_nodes_to_layer(struct ice_port_info *pi, struct ice_sched_node *tc_node, struct ice_sched_node *parent, u8 layer, @@ -1119,7 +1132,7 @@ static u8 ice_sched_get_qgrp_layer(struct ice_hw *hw) * * This function returns the current VSI layer number */ -static u8 ice_sched_get_vsi_layer(struct ice_hw *hw) +u8 ice_sched_get_vsi_layer(struct ice_hw *hw) { /* Num Layers VSI layer * 9 6 @@ -1142,7 +1155,7 @@ static u8 ice_sched_get_vsi_layer(struct ice_hw *hw) * * This function returns the current aggregator layer number */ -static u8 ice_sched_get_agg_layer(struct ice_hw *hw) +u8 ice_sched_get_agg_layer(struct ice_hw *hw) { /* Num Layers aggregator layer * 9 4 @@ -1577,7 +1590,7 @@ ice_sched_get_vsi_node(struct ice_port_info *pi, struct ice_sched_node *tc_node, * This function retrieves an aggregator node for a given aggregator ID from * a given TC branch */ -static struct ice_sched_node * +struct ice_sched_node * ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node, u32 agg_id) { @@ -2139,7 +2152,7 @@ ice_get_agg_info(struct ice_hw *hw, u32 agg_id) * This function walks through the aggregator subtree to find a free parent * node */ -static struct ice_sched_node * +struct ice_sched_node * ice_sched_get_free_vsi_parent(struct ice_hw *hw, struct ice_sched_node *node, u16 *num_nodes) { diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h index 9c100747445a..8bd26353d76a 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.h +++ b/drivers/net/ethernet/intel/ice/ice_sched.h @@ -146,8 +146,29 @@ ice_sched_set_node_bw_lmt_per_tc(struct ice_port_info *pi, u32 id, enum ice_agg_type agg_type, u8 tc, enum ice_rl_type rl_type, u32 bw); int ice_cfg_rl_burst_size(struct ice_hw *hw, u32 bytes); +int +ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids, + bool suspend); +struct ice_sched_node * +ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node, + u32 agg_id); +u8 ice_sched_get_agg_layer(struct ice_hw *hw); +u8 ice_sched_get_vsi_layer(struct ice_hw *hw); +struct ice_sched_node * +ice_sched_get_free_vsi_parent(struct ice_hw *hw, struct ice_sched_node *node, + u16 *num_nodes); +int +ice_sched_add_nodes_to_layer(struct ice_port_info *pi, + struct ice_sched_node *tc_node, + struct ice_sched_node *parent, u8 layer, + u16 num_nodes, u32 *first_node_teid, + u16 *num_nodes_added); void ice_sched_replay_agg_vsi_preinit(struct ice_hw *hw); void ice_sched_replay_agg(struct ice_hw *hw); +int +ice_aq_move_sched_elems(struct ice_hw *hw, u16 grps_req, + struct ice_aqc_move_elem *buf, u16 buf_size, + u16 *grps_movd, struct ice_sq_cd *cd); int ice_replay_vsi_agg(struct ice_hw *hw, u16 vsi_handle); int ice_sched_replay_q_bw(struct ice_port_info *pi, struct ice_q_ctx *q_ctx); #endif /* _ICE_SCHED_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 813fef5fd748..91bc92f5059b 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -20,12 +20,11 @@ * byte 0 = 0x2: to identify it as locally administered DA MAC * byte 6 = 0x2: to identify it as locally administered SA MAC * byte 12 = 0x81 & byte 13 = 0x00: - * In case of VLAN filter first two bytes defines ether type (0x8100) - * and remaining two bytes are placeholder for programming a given VLAN ID - * In case of Ether type filter it is treated as header without VLAN tag - * and byte 12 and 13 is used to program a given Ether type instead + * In case of VLAN filter first two bytes defines ether type (0x8100) + * and remaining two bytes are placeholder for programming a given VLAN ID + * In case of Ether type filter it is treated as header without VLAN tag + * and byte 12 and 13 is used to program a given Ether type instead */ -#define DUMMY_ETH_HDR_LEN 16 static const u8 dummy_eth_header[DUMMY_ETH_HDR_LEN] = { 0x2, 0, 0, 0, 0, 0, 0x2, 0, 0, 0, 0, 0, 0x81, 0, 0, 0}; @@ -1369,14 +1368,6 @@ static const struct ice_dummy_pkt_profile ice_dummy_pkt_profiles[] = { ICE_PKT_PROFILE(tcp, 0), }; -#define ICE_SW_RULE_RX_TX_HDR_SIZE(s, l) struct_size((s), hdr_data, (l)) -#define ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s) \ - ICE_SW_RULE_RX_TX_HDR_SIZE((s), DUMMY_ETH_HDR_LEN) -#define ICE_SW_RULE_RX_TX_NO_HDR_SIZE(s) \ - ICE_SW_RULE_RX_TX_HDR_SIZE((s), 0) -#define ICE_SW_RULE_LG_ACT_SIZE(s, n) struct_size((s), act, (n)) -#define ICE_SW_RULE_VSI_LIST_SIZE(s, n) struct_size((s), vsi, (n)) - /* this is a recipe to profile association bitmap */ static DECLARE_BITMAP(recipe_to_profile[ICE_MAX_NUM_RECIPES], ICE_MAX_NUM_PROFILES); @@ -1841,8 +1832,13 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, lkup_type == ICE_SW_LKUP_DFLT) { sw_buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_REP); } else if (lkup_type == ICE_SW_LKUP_VLAN) { - sw_buf->res_type = - cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE); + if (opc == ice_aqc_opc_alloc_res) + sw_buf->res_type = + cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE | + ICE_AQC_RES_TYPE_FLAG_SHARED); + else + sw_buf->res_type = + cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE); } else { status = -EINVAL; goto ice_aq_alloc_free_vsi_list_exit; @@ -1910,7 +1906,7 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, * * Add(0x0290) */ -static int +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) @@ -1947,7 +1943,7 @@ ice_aq_add_recipe(struct ice_hw *hw, * The caller must supply enough space in s_recipe_list to hold all possible * recipes and *num_recipes must equal ICE_MAX_NUM_RECIPES. */ -static int +int ice_aq_get_recipe(struct ice_hw *hw, struct ice_aqc_recipe_data_elem *s_recipe_list, u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd) @@ -2040,7 +2036,7 @@ error_out: * @cd: pointer to command details structure or NULL * Recipe to profile association (0x0291) */ -static int +int ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, struct ice_sq_cd *cd) { @@ -2066,7 +2062,7 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, * @cd: pointer to command details structure or NULL * Associate profile ID with given recipe (0x0293) */ -static int +int ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, struct ice_sq_cd *cd) { @@ -2090,7 +2086,7 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, * @hw: pointer to the hardware structure * @rid: recipe ID returned as response to AQ call */ -static int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) +int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) { struct ice_aqc_alloc_free_res_elem *sw_buf; u16 buf_len; @@ -2463,6 +2459,15 @@ static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi) } } +/** + * ice_fill_eth_hdr - helper to copy dummy_eth_hdr into supplied buffer + * @eth_hdr: pointer to buffer to populate + */ +void ice_fill_eth_hdr(u8 *eth_hdr) +{ + memcpy(eth_hdr, dummy_eth_header, DUMMY_ETH_HDR_LEN); +} + /** * ice_fill_sw_rule - Helper function to fill switch rule structure * @hw: pointer to the hardware structure @@ -3122,7 +3127,7 @@ ice_find_rule_entry(struct ice_hw *hw, u8 recp_id, struct ice_fltr_info *f_info) * handle element. This can be extended further to search VSI list with more * than 1 vsi_count. Returns pointer to VSI list entry if found. */ -static struct ice_vsi_list_map_info * +struct ice_vsi_list_map_info * ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, u16 *vsi_list_id) { @@ -3133,7 +3138,7 @@ ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, list_head = &sw->recp_list[recp_id].filt_rules; list_for_each_entry(list_itr, list_head, list_entry) { - if (list_itr->vsi_count == 1 && list_itr->vsi_list_info) { + if (list_itr->vsi_list_info) { map_info = list_itr->vsi_list_info; if (test_bit(vsi_handle, map_info->vsi_map)) { *vsi_list_id = map_info->vsi_list_id; @@ -4544,6 +4549,45 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, .offs = {__VA_ARGS__}, \ } +/** + * ice_share_res - set a resource as shared or dedicated + * @hw: hw struct of original owner of resource + * @type: resource type + * @shared: is the resource being set to shared + * @res_id: resource id (descriptor) + */ +int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id) +{ + struct ice_aqc_alloc_free_res_elem *buf; + u16 buf_len; + int status; + + buf_len = struct_size(buf, elem, 1); + buf = kzalloc(buf_len, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + buf->num_elems = cpu_to_le16(1); + 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); + + buf->elem[0].e.sw_resp = cpu_to_le16(res_id); + status = ice_aq_alloc_free_res(hw, 1, buf, buf_len, + ice_aqc_opc_share_res, NULL); + if (status) + ice_debug(hw, ICE_DBG_SW, "Could not set resource type %u id %u to %s\n", + type, res_id, shared ? "SHARED" : "DEDICATED"); + + kfree(buf); + return status; +} + /* This is mapping table entry that maps every word within a given protocol * structure to the real byte offset as per the specification of that * protocol header. diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index 10f5a0ae199e..250823ac173a 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -22,6 +22,16 @@ #define ICE_PROFID_IPV6_GTPU_TEID 46 #define ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER 70 +#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)) +#define ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s) \ + ICE_SW_RULE_RX_TX_HDR_SIZE((s), DUMMY_ETH_HDR_LEN) +#define ICE_SW_RULE_RX_TX_NO_HDR_SIZE(s) \ + ICE_SW_RULE_RX_TX_HDR_SIZE((s), 0) +#define ICE_SW_RULE_LG_ACT_SIZE(s, n) struct_size((s), act, (n)) + +#define DUMMY_ETH_HDR_LEN 16 + /* VSI context structure for add/get/update/free operations */ struct ice_vsi_ctx { u16 vsi_num; @@ -345,6 +355,7 @@ ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, int ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 counter_id); +int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id); /* Switch/bridge related commands */ void ice_rule_add_tunnel_metadata(struct ice_adv_lkup_elem *lkup); @@ -393,6 +404,7 @@ u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle); int ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle); void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw); +void ice_fill_eth_hdr(u8 *eth_hdr); int ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, @@ -401,4 +413,21 @@ int ice_update_recipe_lkup_idx(struct ice_hw *hw, struct ice_update_recipe_lkup_idx_params *params); void ice_change_proto_id_to_dvm(void); +struct ice_vsi_list_map_info * +ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, + u16 *vsi_list_id); +int ice_alloc_recipe(struct ice_hw *hw, u16 *rid); +int ice_aq_get_recipe(struct ice_hw *hw, + struct ice_aqc_recipe_data_elem *s_recipe_list, + u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd); +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, + struct ice_sq_cd *cd); +int +ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, + struct ice_sq_cd *cd); + #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index df9171a1a34f..e82f38c2a940 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -277,6 +277,8 @@ struct ice_hw_common_caps { u8 dcb; u8 ieee_1588; u8 rdma; + u8 roce_lag; + u8 sriov_lag; bool nvm_update_pending_nvm; bool nvm_update_pending_orom; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index efbc2968a7bf..625da88e7965 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -1724,6 +1724,8 @@ error_param: vf->vf_id, i); } + ice_lag_move_new_vf_nodes(vf); + /* send the response to the VF */ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, VIRTCHNL_STATUS_ERR_PARAM, NULL, 0);