diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ice/ice_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/ice/ice_main.c | 3253 |
1 files changed, 1939 insertions, 1314 deletions
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 237ede2cffb0..4bb68e7a00f5 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1,18 +1,22 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2018, Intel Corporation. */ +/* Copyright (c) 2018-2023, Intel Corporation. */ /* Intel(R) Ethernet Connection E800 Series Linux Driver */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <generated/utsrelease.h> +#include <linux/crash_dump.h> #include "ice.h" #include "ice_base.h" #include "ice_lib.h" #include "ice_fltr.h" #include "ice_dcb_lib.h" #include "ice_dcb_nl.h" -#include "ice_devlink.h" +#include "devlink/devlink.h" +#include "devlink/port.h" +#include "ice_sf_eth.h" +#include "ice_hwmon.h" /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the * ice tracepoint functions. This must be done exactly once across the * ice driver. @@ -22,6 +26,7 @@ #include "ice_eswitch.h" #include "ice_tc_lib.h" #include "ice_vsi_vlan_ops.h" +#include <net/xdp_sock_drv.h> #define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver" static const char ice_driver_string[] = DRV_SUMMARY; @@ -31,8 +36,12 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation."; #define ICE_DDP_PKG_PATH "intel/ice/ddp/" #define ICE_DDP_PKG_FILE ICE_DDP_PKG_PATH "ice.pkg" -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); +MODULE_IMPORT_NS("LIBETH"); +MODULE_IMPORT_NS("LIBETH_XDP"); +MODULE_IMPORT_NS("LIBIE"); +MODULE_IMPORT_NS("LIBIE_ADMINQ"); +MODULE_IMPORT_NS("LIBIE_FWLOG"); MODULE_LICENSE("GPL v2"); MODULE_FIRMWARE(ICE_DDP_PKG_FILE); @@ -44,7 +53,6 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all), hw debug_mask (0x8XXXX MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)"); #endif /* !CONFIG_DYNAMIC_DEBUG */ -static DEFINE_IDA(ice_aux_ida); DEFINE_STATIC_KEY_FALSE(ice_xdp_locking_key); EXPORT_SYMBOL(ice_xdp_locking_key); @@ -64,6 +72,7 @@ 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; @@ -80,9 +89,10 @@ ice_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, void *data, void (*cleanup)(struct flow_block_cb *block_cb)); -bool netif_is_ice(struct net_device *dev) +bool netif_is_ice(const struct net_device *dev) { - return dev && (dev->netdev_ops == &ice_netdev_ops); + return dev && (dev->netdev_ops == &ice_netdev_ops || + dev->netdev_ops == &ice_netdev_safe_mode_ops); } /** @@ -275,6 +285,8 @@ static int ice_set_promisc(struct ice_vsi *vsi, u8 promisc_m) if (status && status != -EEXIST) return status; + netdev_dbg(vsi->netdev, "set promisc filter bits for VSI %i: 0x%x\n", + vsi->vsi_num, promisc_m); return 0; } @@ -300,6 +312,8 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) promisc_m, 0); } + netdev_dbg(vsi->netdev, "clear promisc filter bits for VSI %i: 0x%x\n", + vsi->vsi_num, promisc_m); return status; } @@ -369,7 +383,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) * should go into promiscuous mode. There should be some * space reserved for promiscuous filters. */ - if (hw->adminq.sq_last_status == ICE_AQ_RC_ENOSPC && + if (hw->adminq.sq_last_status == LIBIE_AQ_RC_ENOSPC && !test_and_set_bit(ICE_FLTR_OVERFLOW_PROMISC, vsi->state)) { promisc_forced_on = true; @@ -414,6 +428,16 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) } err = 0; vlan_ops->dis_rx_filtering(vsi); + + /* promiscuous mode implies allmulticast so + * that VSIs that are in promiscuous mode are + * subscribed to multicast packets coming to + * the port + */ + err = ice_set_promisc(vsi, + ICE_MCAST_PROMISC_BITS); + if (err) + goto out_promisc; } } else { /* Clear Rx filter to remove traffic from wire */ @@ -430,6 +454,18 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) NETIF_F_HW_VLAN_CTAG_FILTER) vlan_ops->ena_rx_filtering(vsi); } + + /* disable allmulti here, but only if allmulti is not + * still enabled for the netdev + */ + if (!(vsi->current_netdev_flags & IFF_ALLMULTI)) { + err = ice_clear_promisc(vsi, + ICE_MCAST_PROMISC_BITS); + if (err) { + netdev_err(netdev, "Error %d clearing multicast promiscuous on VSI %i\n", + err, vsi->vsi_num); + } + } } } goto exit; @@ -490,25 +526,6 @@ static void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked) } /** - * ice_clear_sw_switch_recipes - clear switch recipes - * @pf: board private structure - * - * Mark switch recipes as not created in sw structures. There are cases where - * rules (especially advanced rules) need to be restored, either re-read from - * hardware or added again. For example after the reset. 'recp_created' flag - * prevents from doing that and need to be cleared upfront. - */ -static void ice_clear_sw_switch_recipes(struct ice_pf *pf) -{ - struct ice_sw_recipe *recp; - u8 i; - - recp = pf->hw.switch_info->recp_list; - for (i = 0; i < ICE_MAX_NUM_RECIPES; i++) - recp[i].recp_created = false; -} - -/** * ice_prepare_for_reset - prep for reset * @pf: board private structure * @reset_type: reset type requested @@ -529,6 +546,8 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) if (test_bit(ICE_PREPARED_FOR_RESET, pf->state)) return; + synchronize_irq(pf->oicr_irq.virq); + ice_unplug_aux_dev(pf); /* Notify VFs of impending reset */ @@ -538,12 +557,13 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) /* Disable VFs until reset is completed */ mutex_lock(&pf->vfs.table_lock); ice_for_each_vf(pf, bkt, vf) - ice_set_vf_state_qs_dis(vf); + ice_set_vf_state_dis(vf); mutex_unlock(&pf->vfs.table_lock); if (ice_is_eswitch_mode_switchdev(pf)) { - if (reset_type != ICE_RESET_PFR) - ice_clear_sw_switch_recipes(pf); + rtnl_lock(); + ice_eswitch_br_fdb_flush(pf->eswitch.br_offloads->bridge); + rtnl_unlock(); } /* release ADQ specific HW and SW resources */ @@ -576,15 +596,19 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) memset(&vsi->mqprio_qopt, 0, sizeof(vsi->mqprio_qopt)); } } + + if (vsi->netdev) + netif_device_detach(vsi->netdev); skip: /* clear SW filtering DB */ ice_clear_hw_tbls(hw); /* disable the VSIs and their queues that are not already DOWN */ + set_bit(ICE_VSI_REBUILD_PENDING, ice_get_main_vsi(pf)->state); 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); @@ -592,7 +616,7 @@ skip: if (hw->port_info) ice_sched_clear_port(hw->port_info); - ice_shutdown_all_ctrlq(hw); + ice_shutdown_all_ctrlq(hw, false); set_bit(ICE_PREPARED_FOR_RESET, pf->state); } @@ -609,6 +633,11 @@ 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 */ @@ -692,8 +721,13 @@ 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)) @@ -764,6 +798,9 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) } switch (vsi->port_info->phy.link_info.link_speed) { + case ICE_AQ_LINK_SPEED_200GB: + speed = "200 G"; + break; case ICE_AQ_LINK_SPEED_100GB: speed = "100 G"; break; @@ -941,7 +978,7 @@ 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); @@ -975,7 +1012,7 @@ 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)) @@ -1086,7 +1123,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, if (status) dev_dbg(dev, "Failed to update link status on port %d, err %d aq_err %s\n", pi->lport, status, - ice_aq_str(pi->hw->adminq.sq_last_status)); + libie_aq_str(pi->hw->adminq.sq_last_status)); ice_check_link_cfg_err(pf, pi->phy.link_info.link_cfg_err); @@ -1111,7 +1148,10 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, if (link_up == old_link && link_speed == old_link_speed) return 0; - ice_ptp_link_change(pf, pf->hw.pf_id, link_up); + if (!link_up && old_link) + pf->link_down_events++; + + ice_ptp_link_change(pf, link_up); if (ice_is_dcb_active(pf)) { if (test_bit(ICE_FLAG_DCB_ENA, pf->flags)) @@ -1213,64 +1253,63 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event) return status; } -enum ice_aq_task_state { - ICE_AQ_TASK_WAITING = 0, - ICE_AQ_TASK_COMPLETE, - ICE_AQ_TASK_CANCELED, -}; - -struct ice_aq_task { - struct hlist_node entry; +/** + * 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 + * @opcode: the opcode to wait for + * + * Prepares to wait for a specific AdminQ completion event on the ARQ for + * a given PF. Actual wait would be done by a call to ice_aq_wait_for_event(). + * + * Calls are separated to allow caller registering for event before sending + * the command, which mitigates a race between registering and FW responding. + * + * To obtain only the descriptor contents, pass an task->event with null + * msg_buf. If the complete data buffer is desired, allocate the + * task->event.msg_buf with enough space ahead of time. + */ +void ice_aq_prep_for_event(struct ice_pf *pf, struct ice_aq_task *task, + u16 opcode) +{ + INIT_HLIST_NODE(&task->entry); + task->opcode = opcode; + task->state = ICE_AQ_TASK_WAITING; - u16 opcode; - struct ice_rq_event_info *event; - enum ice_aq_task_state state; -}; + spin_lock_bh(&pf->aq_wait_lock); + hlist_add_head(&task->entry, &pf->aq_wait_list); + spin_unlock_bh(&pf->aq_wait_lock); +} /** * ice_aq_wait_for_event - Wait for an AdminQ event from firmware * @pf: pointer to the PF private structure - * @opcode: the opcode to wait for + * @task: ptr prepared by ice_aq_prep_for_event() * @timeout: how long to wait, in jiffies - * @event: storage for the event info * * Waits for a specific AdminQ completion event on the ARQ for a given PF. The * current thread will be put to sleep until the specified event occurs or * until the given timeout is reached. * - * To obtain only the descriptor contents, pass an event without an allocated - * msg_buf. If the complete data buffer is desired, allocate the - * event->msg_buf with enough space ahead of time. - * * Returns: zero on success, or a negative error code on failure. */ -int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, - struct ice_rq_event_info *event) +int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task, + unsigned long timeout) { + enum ice_aq_task_state *state = &task->state; struct device *dev = ice_pf_to_dev(pf); - struct ice_aq_task *task; - unsigned long start; + unsigned long start = jiffies; long ret; int err; - task = kzalloc(sizeof(*task), GFP_KERNEL); - if (!task) - return -ENOMEM; - - INIT_HLIST_NODE(&task->entry); - task->opcode = opcode; - task->event = event; - task->state = ICE_AQ_TASK_WAITING; - - spin_lock_bh(&pf->aq_wait_lock); - hlist_add_head(&task->entry, &pf->aq_wait_list); - spin_unlock_bh(&pf->aq_wait_lock); - - start = jiffies; - - ret = wait_event_interruptible_timeout(pf->aq_wait_queue, task->state, + ret = wait_event_interruptible_timeout(pf->aq_wait_queue, + *state != ICE_AQ_TASK_WAITING, timeout); - switch (task->state) { + switch (*state) { + case ICE_AQ_TASK_NOT_PREPARED: + WARN(1, "call to %s without ice_aq_prep_for_event()", __func__); + err = -EINVAL; + break; case ICE_AQ_TASK_WAITING: err = ret < 0 ? ret : -ETIMEDOUT; break; @@ -1281,7 +1320,7 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, err = ret < 0 ? ret : 0; break; default: - WARN(1, "Unexpected AdminQ wait task state %u", task->state); + WARN(1, "Unexpected AdminQ wait task state %u", *state); err = -EINVAL; break; } @@ -1289,12 +1328,11 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, dev_dbg(dev, "Waited %u msecs (max %u msecs) for firmware response to op 0x%04x\n", jiffies_to_msecs(jiffies - start), jiffies_to_msecs(timeout), - opcode); + task->opcode); spin_lock_bh(&pf->aq_wait_lock); hlist_del(&task->entry); spin_unlock_bh(&pf->aq_wait_lock); - kfree(task); return err; } @@ -1320,23 +1358,26 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, static void ice_aq_check_events(struct ice_pf *pf, u16 opcode, struct ice_rq_event_info *event) { + struct ice_rq_event_info *task_ev; struct ice_aq_task *task; bool found = false; spin_lock_bh(&pf->aq_wait_lock); hlist_for_each_entry(task, &pf->aq_wait_list, entry) { - if (task->state || task->opcode != opcode) + if (task->state != ICE_AQ_TASK_WAITING) + continue; + if (task->opcode != opcode) continue; - memcpy(&task->event->desc, &event->desc, sizeof(event->desc)); - task->event->msg_len = event->msg_len; + task_ev = &task->event; + memcpy(&task_ev->desc, &event->desc, sizeof(event->desc)); + task_ev->msg_len = event->msg_len; /* Only copy the data buffer if a destination was set */ - if (task->event->msg_buf && - task->event->buf_len > event->buf_len) { - memcpy(task->event->msg_buf, event->msg_buf, + if (task_ev->msg_buf && task_ev->buf_len >= event->buf_len) { + memcpy(task_ev->msg_buf, event->msg_buf, event->buf_len); - task->event->buf_len = event->buf_len; + task_ev->buf_len = event->buf_len; } task->state = ICE_AQ_TASK_COMPLETE; @@ -1367,6 +1408,8 @@ static void ice_aq_cancel_waiting_tasks(struct ice_pf *pf) wake_up(&pf->aq_wait_queue); } +#define ICE_MBX_OVERFLOW_WATERMARK 64 + /** * __ice_clean_ctrlq - helper function to clean controlq rings * @pf: ptr to struct ice_pf @@ -1457,6 +1500,7 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) return 0; do { + struct ice_mbx_data data = {}; u16 opcode; int ret; @@ -1483,15 +1527,31 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) ice_vf_lan_overflow_event(pf, &event); break; case ice_mbx_opc_send_msg_to_pf: - if (!ice_is_malicious_vf(pf, &event, i, pending)) - ice_vc_process_vf_msg(pf, &event); + if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) { + ice_vc_process_vf_msg(pf, &event, NULL); + ice_mbx_vf_dec_trig_e830(hw, &event); + } else { + u16 val = hw->mailboxq.num_rq_entries; + + data.max_num_msgs_mbx = val; + val = ICE_MBX_OVERFLOW_WATERMARK; + data.async_watermark_val = val; + data.num_msg_proc = i; + data.num_pending_arq = pending; + + 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: + libie_get_fwlog_data(&hw->fwlog, event.msg_buf, + le16_to_cpu(event.desc.datalen)); break; case ice_aqc_opc_lldp_set_mib_change: ice_dcb_process_lldp_set_mib_change(pf, &event); break; + case ice_aqc_opc_get_health_status: + ice_process_health_status_event(pf, &event); + break; default: dev_dbg(dev, "%s Receive Queue unknown event 0x%04x ignored\n", qtype, opcode); @@ -1576,8 +1636,10 @@ 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; } @@ -1637,7 +1699,7 @@ static int ice_service_task_stop(struct ice_pf *pf) ret = test_and_set_bit(ICE_SERVICE_DIS, pf->state); if (pf->serv_tmr.function) - del_timer_sync(&pf->serv_tmr); + timer_delete_sync(&pf->serv_tmr); if (pf->serv_task.func) cancel_work_sync(&pf->serv_task); @@ -1663,13 +1725,46 @@ static void ice_service_task_restart(struct ice_pf *pf) */ static void ice_service_timer(struct timer_list *t) { - struct ice_pf *pf = from_timer(pf, t, serv_tmr); + struct ice_pf *pf = timer_container_of(pf, t, serv_tmr); mod_timer(&pf->serv_tmr, round_jiffies(pf->serv_tmr_period + jiffies)); ice_service_task_schedule(pf); } /** + * 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 * @@ -1698,52 +1793,46 @@ 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", event, queue, pf_num, vf_num); + ice_report_mdd_event(pf, ICE_MDD_SRC_TX_PQM, pf_num, vf_num, + event, queue); wr32(hw, GL_MDET_TX_PQM, 0xffffffff); } - reg = rd32(hw, GL_MDET_TX_TCLAN); + 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", event, queue, pf_num, vf_num); - wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff); + ice_report_mdd_event(pf, ICE_MDD_SRC_TX_TCLAN, pf_num, vf_num, + event, queue); + wr32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw), U32_MAX); } 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", event, queue, pf_num, vf_num); + ice_report_mdd_event(pf, ICE_MDD_SRC_RX, pf_num, vf_num, event, + queue); wr32(hw, GL_MDET_RX, 0xffffffff); } @@ -1755,9 +1844,9 @@ static void ice_handle_mdd_event(struct ice_pf *pf) dev_info(dev, "Malicious Driver Detection event TX_PQM detected on PF\n"); } - reg = rd32(hw, PF_MDET_TX_TCLAN); + reg = rd32(hw, PF_MDET_TX_TCLAN_BY_MAC(hw)); if (reg & PF_MDET_TX_TCLAN_VALID_M) { - wr32(hw, PF_MDET_TX_TCLAN, 0xFFFF); + wr32(hw, PF_MDET_TX_TCLAN_BY_MAC(hw), 0xffff); if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_TCLAN detected on PF\n"); } @@ -1774,6 +1863,8 @@ 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); @@ -1782,6 +1873,8 @@ 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)); @@ -1792,6 +1885,8 @@ 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)); @@ -1802,6 +1897,8 @@ 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)); @@ -1813,18 +1910,12 @@ 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); @@ -2100,7 +2191,7 @@ 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); @@ -2255,6 +2346,18 @@ static void ice_check_media_subtask(struct ice_pf *pf) } } +static void ice_service_task_recovery_mode(struct work_struct *work) +{ + struct ice_pf *pf = container_of(work, struct ice_pf, serv_task); + + set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state); + ice_clean_adminq_subtask(pf); + + ice_service_task_complete(pf); + + mod_timer(&pf->serv_tmr, jiffies + msecs_to_jiffies(100)); +} + /** * ice_service_task - manage and run subtasks * @work: pointer to work_struct contained by the PF struct @@ -2264,9 +2367,11 @@ static void ice_service_task(struct work_struct *work) struct ice_pf *pf = container_of(work, struct ice_pf, serv_task); unsigned long start_time = jiffies; - /* subtasks */ + if (pf->health_reporters.tx_hang_buf.tx_ring) { + ice_report_tx_hang(pf); + pf->health_reporters.tx_hang_buf.tx_ring = NULL; + } - /* process reset requests first */ ice_reset_subtask(pf); /* bail if a reset/recovery cycle is pending or rebuild failed */ @@ -2278,11 +2383,11 @@ static void ice_service_task(struct work_struct *work) } if (test_and_clear_bit(ICE_AUX_ERR_PENDING, pf->state)) { - struct iidc_event *event; + struct iidc_rdma_event *event; event = kzalloc(sizeof(*event), GFP_KERNEL); if (event) { - set_bit(IIDC_EVENT_CRIT_ERR, event->type); + set_bit(IIDC_RDMA_EVENT_CRIT_ERR, event->type); /* report the entire OICR value to AUX driver */ swap(event->reg, pf->oicr_err_reg); ice_send_event_to_aux(pf, event); @@ -2290,25 +2395,22 @@ static void ice_service_task(struct work_struct *work) } } - if (test_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) { - /* Plug aux device per request */ - ice_plug_aux_dev(pf); + /* unplug aux dev per request, if an unplug request came in + * while processing a plug request, this will handle it + */ + if (test_and_clear_bit(ICE_FLAG_UNPLUG_AUX_DEV, pf->flags)) + ice_unplug_aux_dev(pf); - /* Mark plugging as done but check whether unplug was - * requested during ice_plug_aux_dev() call - * (e.g. from ice_clear_rdma_cap()) and if so then - * plug aux device. - */ - if (!test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) - ice_unplug_aux_dev(pf); - } + /* Plug aux device per request */ + if (test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + ice_plug_aux_dev(pf); if (test_and_clear_bit(ICE_FLAG_MTU_CHANGED, pf->flags)) { - struct iidc_event *event; + struct iidc_rdma_event *event; event = kzalloc(sizeof(*event), GFP_KERNEL); if (event) { - set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type); + set_bit(IIDC_RDMA_EVENT_AFTER_MTU_CHANGE, event->type); ice_send_event_to_aux(pf, event); kfree(event); } @@ -2408,34 +2510,6 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset) } /** - * ice_irq_affinity_notify - Callback for affinity changes - * @notify: context as to what irq was changed - * @mask: the new affinity mask - * - * This is a callback function used by the irq_set_affinity_notifier function - * so that we may register to receive changes to the irq affinity masks. - */ -static void -ice_irq_affinity_notify(struct irq_affinity_notify *notify, - const cpumask_t *mask) -{ - struct ice_q_vector *q_vector = - container_of(notify, struct ice_q_vector, affinity_notify); - - cpumask_copy(&q_vector->affinity_mask, mask); -} - -/** - * ice_irq_affinity_release - Callback for affinity notifier release - * @ref: internal core kernel usage - * - * This is a callback function used by the irq_set_affinity_notifier function - * to inform the current notification subscriber that they will no longer - * receive notifications. - */ -static void ice_irq_affinity_release(struct kref __always_unused *ref) {} - -/** * ice_vsi_ena_irq - Enable IRQ for the given VSI * @vsi: the VSI being configured */ @@ -2460,7 +2534,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) { int q_vectors = vsi->num_q_vectors; struct ice_pf *pf = vsi->back; - int base = vsi->base_vector; struct device *dev; int rx_int_idx = 0; int tx_int_idx = 0; @@ -2471,7 +2544,7 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) for (vector = 0; vector < q_vectors; vector++) { struct ice_q_vector *q_vector = vsi->q_vectors[vector]; - irq_num = pf->msix_entries[base + vector].vector; + irq_num = q_vector->irq.virq; if (q_vector->tx.tx_ring && q_vector->rx.rx_ring) { snprintf(q_vector->name, sizeof(q_vector->name) - 1, @@ -2499,19 +2572,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) err); goto free_q_irqs; } - - /* register for affinity change notifications */ - if (!IS_ENABLED(CONFIG_RFS_ACCEL)) { - struct irq_affinity_notify *affinity_notify; - - affinity_notify = &q_vector->affinity_notify; - affinity_notify->notify = ice_irq_affinity_notify; - affinity_notify->release = ice_irq_affinity_release; - irq_set_affinity_notifier(irq_num, affinity_notify); - } - - /* assign the mask for this irq */ - irq_set_affinity_hint(irq_num, &q_vector->affinity_mask); } err = ice_set_cpu_rx_rmap(vsi); @@ -2525,12 +2585,8 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) return 0; free_q_irqs: - while (vector) { - vector--; - irq_num = pf->msix_entries[base + vector].vector; - if (!IS_ENABLED(CONFIG_RFS_ACCEL)) - irq_set_affinity_notifier(irq_num, NULL); - irq_set_affinity_hint(irq_num, NULL); + while (vector--) { + irq_num = vsi->q_vectors[vector]->irq.virq; devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]); } return err; @@ -2570,8 +2626,6 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) xdp_ring->netdev = NULL; xdp_ring->dev = dev; xdp_ring->count = vsi->num_tx_desc; - xdp_ring->next_dd = ICE_RING_QUARTER(xdp_ring) - 1; - xdp_ring->next_rs = ICE_RING_QUARTER(xdp_ring) - 1; WRITE_ONCE(vsi->xdp_rings[i], xdp_ring); if (ice_setup_tx_ring(xdp_ring)) goto free_xdp_rings; @@ -2607,24 +2661,100 @@ static void ice_vsi_assign_bpf_prog(struct ice_vsi *vsi, struct bpf_prog *prog) int i; old_prog = xchg(&vsi->xdp_prog, prog); + ice_for_each_rxq(vsi, i) + WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog); + if (old_prog) bpf_prog_put(old_prog); +} - ice_for_each_rxq(vsi, i) - WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog); +static struct ice_tx_ring *ice_xdp_ring_from_qid(struct ice_vsi *vsi, int qid) +{ + struct ice_q_vector *q_vector; + struct ice_tx_ring *ring; + + if (static_key_enabled(&ice_xdp_locking_key)) + return vsi->xdp_rings[qid % vsi->num_xdp_txq]; + + q_vector = vsi->rx_rings[qid]->q_vector; + ice_for_each_tx_ring(ring, q_vector->tx) + if (ice_ring_is_xdp(ring)) + return ring; + + return NULL; +} + +/** + * ice_map_xdp_rings - Map XDP rings to interrupt vectors + * @vsi: the VSI with XDP rings being configured + * + * Map XDP rings to interrupt vectors and perform the configuration steps + * dependent on the mapping. + */ +void ice_map_xdp_rings(struct ice_vsi *vsi) +{ + int xdp_rings_rem = vsi->num_xdp_txq; + int v_idx, q_idx; + + /* follow the logic from ice_vsi_map_rings_to_vectors */ + ice_for_each_q_vector(vsi, v_idx) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; + int xdp_rings_per_v, q_id, q_base; + + xdp_rings_per_v = DIV_ROUND_UP(xdp_rings_rem, + vsi->num_q_vectors - v_idx); + q_base = vsi->num_xdp_txq - xdp_rings_rem; + + for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) { + struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_id]; + + xdp_ring->q_vector = q_vector; + xdp_ring->next = q_vector->tx.tx_ring; + q_vector->tx.tx_ring = xdp_ring; + } + xdp_rings_rem -= xdp_rings_per_v; + } + + ice_for_each_rxq(vsi, q_idx) { + vsi->rx_rings[q_idx]->xdp_ring = ice_xdp_ring_from_qid(vsi, + q_idx); + ice_tx_xsk_pool(vsi, q_idx); + } +} + +/** + * ice_unmap_xdp_rings - Unmap XDP rings from interrupt vectors + * @vsi: the VSI with XDP rings being unmapped + */ +static void ice_unmap_xdp_rings(struct ice_vsi *vsi) +{ + int v_idx; + + ice_for_each_q_vector(vsi, v_idx) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; + struct ice_tx_ring *ring; + + ice_for_each_tx_ring(ring, q_vector->tx) + if (!ring->tx_buf || !ice_ring_is_xdp(ring)) + break; + + /* restore the value of last node prior to XDP setup */ + q_vector->tx.tx_ring = ring; + } } /** * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP * @vsi: VSI to bring up Tx rings used by XDP * @prog: bpf program that will be assigned to VSI + * @cfg_type: create from scratch or restore the existing configuration * * Return 0 on success and negative value on error */ -int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) +int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog, + enum ice_xdp_cfg cfg_type) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; - int xdp_rings_rem = vsi->num_xdp_txq; struct ice_pf *pf = vsi->back; struct ice_qs_cfg xdp_qs_cfg = { .qs_mutex = &pf->avail_q_mutex, @@ -2637,8 +2767,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) .mapping_mode = ICE_VSI_MAP_CONTIG }; struct device *dev; - int i, v_idx; - int status; + int status, i; dev = ice_pf_to_dev(pf); vsi->xdp_rings = devm_kcalloc(dev, vsi->num_xdp_txq, @@ -2657,49 +2786,15 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) if (ice_xdp_alloc_setup_rings(vsi)) goto clear_xdp_rings; - /* follow the logic from ice_vsi_map_rings_to_vectors */ - ice_for_each_q_vector(vsi, v_idx) { - struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; - int xdp_rings_per_v, q_id, q_base; - - xdp_rings_per_v = DIV_ROUND_UP(xdp_rings_rem, - vsi->num_q_vectors - v_idx); - q_base = vsi->num_xdp_txq - xdp_rings_rem; - - for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) { - struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_id]; - - xdp_ring->q_vector = q_vector; - xdp_ring->next = q_vector->tx.tx_ring; - q_vector->tx.tx_ring = xdp_ring; - } - xdp_rings_rem -= xdp_rings_per_v; - } - - ice_for_each_rxq(vsi, i) { - if (static_key_enabled(&ice_xdp_locking_key)) { - vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq]; - } else { - struct ice_q_vector *q_vector = vsi->rx_rings[i]->q_vector; - struct ice_tx_ring *ring; - - ice_for_each_tx_ring(ring, q_vector->tx) { - if (ice_ring_is_xdp(ring)) { - vsi->rx_rings[i]->xdp_ring = ring; - break; - } - } - } - ice_tx_xsk_pool(vsi, i); - } - /* omit the scheduler update if in reset path; XDP queues will be * taken into account at the end of ice_vsi_rebuild, where * ice_cfg_vsi_lan is being called */ - if (ice_is_reset_in_progress(pf->state)) + if (cfg_type == ICE_XDP_CFG_PART) return 0; + ice_map_xdp_rings(vsi); + /* tell the Tx scheduler that right now we have * additional queues */ @@ -2711,7 +2806,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) if (status) { dev_err(dev, "Failed VSI LAN queue config for XDP, error: %d\n", status); - goto clear_xdp_rings; + goto unmap_xdp_rings; } /* assign the prog only when it's not already present on VSI; @@ -2727,6 +2822,8 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) ice_vsi_assign_bpf_prog(vsi, prog); return 0; +unmap_xdp_rings: + ice_unmap_xdp_rings(vsi); clear_xdp_rings: ice_for_each_xdp_txq(vsi, i) if (vsi->xdp_rings[i]) { @@ -2743,41 +2840,32 @@ err_map_xdp: mutex_unlock(&pf->avail_q_mutex); devm_kfree(dev, vsi->xdp_rings); + vsi->xdp_rings = NULL; + return -ENOMEM; } /** * ice_destroy_xdp_rings - undo the configuration made by ice_prepare_xdp_rings * @vsi: VSI to remove XDP rings + * @cfg_type: disable XDP permanently or allow it to be restored later * * Detach XDP rings from irq vectors, clean up the PF bitmap and free * resources */ -int ice_destroy_xdp_rings(struct ice_vsi *vsi) +int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct ice_pf *pf = vsi->back; - int i, v_idx; + int i; /* q_vectors are freed in reset path so there's no point in detaching - * rings; in case of rebuild being triggered not from reset bits - * in pf->state won't be set, so additionally check first q_vector - * against NULL + * rings */ - if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0]) + if (cfg_type == ICE_XDP_CFG_PART) goto free_qmap; - ice_for_each_q_vector(vsi, v_idx) { - struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; - struct ice_tx_ring *ring; - - ice_for_each_tx_ring(ring, q_vector->tx) - if (!ring->tx_buf || !ice_ring_is_xdp(ring)) - break; - - /* restore the value of last node prior to XDP setup */ - q_vector->tx.tx_ring = ring; - } + ice_unmap_xdp_rings(vsi); free_qmap: mutex_lock(&pf->avail_q_mutex); @@ -2805,7 +2893,7 @@ free_qmap: if (static_key_enabled(&ice_xdp_locking_key)) static_branch_dec(&ice_xdp_locking_key); - if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0]) + if (cfg_type == ICE_XDP_CFG_PART) return 0; ice_vsi_assign_bpf_prog(vsi, NULL); @@ -2834,7 +2922,7 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi) ice_for_each_rxq(vsi, i) { struct ice_rx_ring *rx_ring = vsi->rx_rings[i]; - if (rx_ring->xsk_pool) + if (READ_ONCE(rx_ring->xsk_pool)) napi_schedule(&rx_ring->q_vector->napi); } } @@ -2854,6 +2942,9 @@ int ice_vsi_determine_xdp_res(struct ice_vsi *vsi) if (avail < cpus / 2) return -ENOMEM; + if (vsi->type == ICE_VSI_SF) + avail = vsi->alloc_txq; + vsi->num_xdp_txq = min_t(u16, avail, cpus); if (vsi->num_xdp_txq < cpus) @@ -2863,6 +2954,15 @@ int ice_vsi_determine_xdp_res(struct ice_vsi *vsi) } /** + * ice_max_xdp_frame_size - returns the maximum allowed frame size for XDP + * @vsi: Pointer to VSI structure + */ +static int ice_max_xdp_frame_size(struct ice_vsi *vsi) +{ + return ICE_RXBUF_3072; +} + +/** * ice_xdp_setup_prog - Add or remove XDP eBPF program * @vsi: VSI to setup XDP for * @prog: XDP program @@ -2872,17 +2972,30 @@ static int ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, struct netlink_ext_ack *extack) { - int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD; - bool if_running = netif_running(vsi->netdev); + unsigned int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD; int ret = 0, xdp_ring_err = 0; + bool if_running; - if (frame_size > vsi->rx_buf_len) { - NL_SET_ERR_MSG_MOD(extack, "MTU too large for loading XDP"); - return -EOPNOTSUPP; + if (prog && !prog->aux->xdp_has_frags) { + if (frame_size > ice_max_xdp_frame_size(vsi)) { + NL_SET_ERR_MSG_MOD(extack, + "MTU is too large for linear frames and XDP prog does not support frags"); + return -EOPNOTSUPP; + } + } + + /* hot swap progs and avoid toggling link */ + if (ice_is_xdp_ena_vsi(vsi) == !!prog || + test_bit(ICE_VSI_REBUILD_PENDING, vsi->state)) { + ice_vsi_assign_bpf_prog(vsi, prog); + return 0; } + if_running = netif_running(vsi->netdev) && + !test_and_set_bit(ICE_VSI_DOWN, vsi->state); + /* need to stop netdev while setting up the program for Rx rings */ - if (if_running && !test_and_set_bit(ICE_VSI_DOWN, vsi->state)) { + if (if_running) { ret = ice_down(vsi); if (ret) { NL_SET_ERR_MSG_MOD(extack, "Preparing device for XDP attach failed"); @@ -2894,32 +3007,24 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, xdp_ring_err = ice_vsi_determine_xdp_res(vsi); if (xdp_ring_err) { NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP"); + goto resume_if; } else { - xdp_ring_err = ice_prepare_xdp_rings(vsi, prog); - if (xdp_ring_err) + xdp_ring_err = ice_prepare_xdp_rings(vsi, prog, + ICE_XDP_CFG_FULL); + if (xdp_ring_err) { NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); + goto resume_if; + } } - /* reallocate Rx queues that are used for zero-copy */ - xdp_ring_err = ice_realloc_zc_buf(vsi, true); - if (xdp_ring_err) - NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed"); + xdp_features_set_redirect_target(vsi->netdev, true); } else if (ice_is_xdp_ena_vsi(vsi) && !prog) { - xdp_ring_err = ice_destroy_xdp_rings(vsi); + xdp_features_clear_redirect_target(vsi->netdev); + xdp_ring_err = ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_FULL); if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); - /* reallocate Rx queues that were used for zero-copy */ - xdp_ring_err = ice_realloc_zc_buf(vsi, false); - if (xdp_ring_err) - NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Rx resources failed"); - } else { - /* safe to call even when prog == vsi->xdp_prog as - * dev_xdp_install in net/core/dev.c incremented prog's - * refcount so corresponding bpf_prog_put won't cause - * underflow - */ - ice_vsi_assign_bpf_prog(vsi, prog); } +resume_if: if (if_running) ret = ice_up(vsi); @@ -2948,25 +3053,32 @@ static int ice_xdp_safe_mode(struct net_device __always_unused *dev, * @dev: netdevice * @xdp: XDP command */ -static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp) +int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp) { struct ice_netdev_priv *np = netdev_priv(dev); struct ice_vsi *vsi = np->vsi; + int ret; - if (vsi->type != ICE_VSI_PF) { - NL_SET_ERR_MSG_MOD(xdp->extack, "XDP can be loaded only on PF VSI"); + if (vsi->type != ICE_VSI_PF && vsi->type != ICE_VSI_SF) { + NL_SET_ERR_MSG_MOD(xdp->extack, "XDP can be loaded only on PF or SF VSI"); return -EINVAL; } + mutex_lock(&vsi->xdp_state_lock); + switch (xdp->command) { case XDP_SETUP_PROG: - return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack); + ret = ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack); + break; case XDP_SETUP_XSK_POOL: - return ice_xsk_pool_setup(vsi, xdp->xsk.pool, - xdp->xsk.queue_id); + ret = ice_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id); + break; default: - return -EINVAL; + ret = -EINVAL; } + + mutex_unlock(&vsi->xdp_state_lock); + return ret; } /** @@ -2976,6 +3088,7 @@ 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 @@ -3002,11 +3115,54 @@ static void ice_ena_misc_vector(struct ice_pf *pf) wr32(hw, PFINT_OICR_ENA, val); /* SW_ITR_IDX = 0, but don't change INTENA */ - wr32(hw, GLINT_DYN_CTL(pf->oicr_idx), + 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); + if (tx->init) { + 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; +} + +/** * ice_misc_intr - misc interrupt handler * @irq: interrupt number * @data: pointer to a q_vector @@ -3014,8 +3170,8 @@ 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; - irqreturn_t ret = IRQ_NONE; struct device *dev; u32 oicr, ena_mask; @@ -3054,8 +3210,8 @@ 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++; @@ -3096,20 +3252,25 @@ 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) - ret = IRQ_WAKE_THREAD; + + ret = ice_ptp_ts_irq(pf); } if (oicr & PFINT_OICR_TSYN_EVNT_M) { u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; u32 gltsyn_stat = rd32(hw, GLTSYN_STAT(tmr_idx)); - /* Save EVENTs from GTSYN register */ - pf->ptp.ext_ts_irq |= gltsyn_stat & (GLTSYN_STAT_EVENT0_M | - GLTSYN_STAT_EVENT1_M | - GLTSYN_STAT_EVENT2_M); ena_mask &= ~PFINT_OICR_TSYN_EVNT_M; - kthread_queue_work(pf->ptp.kworker, &pf->ptp.extts_work); + + if (ice_pf_src_tmr_owned(pf)) { + /* Save EVENTs from GLTSYN register */ + pf->ptp.ext_ts_irq |= gltsyn_stat & + (GLTSYN_STAT_EVENT0_M | + GLTSYN_STAT_EVENT1_M | + GLTSYN_STAT_EVENT2_M); + + ice_ptp_extts_event(pf); + } } #define ICE_AUX_CRIT_ERR (PFINT_OICR_PE_CRITERR_M | PFINT_OICR_HMC_ERR_M | PFINT_OICR_PE_PUSH_M) @@ -3129,14 +3290,11 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) if (oicr & (PFINT_OICR_PCI_EXCEPTION_M | PFINT_OICR_ECC_ERR_M)) { set_bit(ICE_PFR_REQ, pf->state); - ice_service_task_schedule(pf); } } - if (!ret) - ret = IRQ_HANDLED; - ice_service_task_schedule(pf); - ice_irq_dynamic_ena(hw, NULL, NULL); + if (ret == IRQ_HANDLED) + ice_irq_dynamic_ena(hw, NULL, NULL); return ret; } @@ -3149,12 +3307,25 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data) { struct ice_pf *pf = data; + struct ice_hw *hw; + + hw = &pf->hw; if (ice_is_reset_in_progress(pf->state)) - return IRQ_HANDLED; + 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, + * re-arm the interrupt to trigger again. + */ + if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) { + wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); + ice_flush(hw); + } + } - while (!ice_ptp_process_ts(pf)) - usleep_range(50, 100); +skip_irq: + ice_irq_dynamic_ena(hw, NULL, NULL); return IRQ_HANDLED; } @@ -3184,11 +3355,26 @@ 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 */ static void ice_free_irq_msix_misc(struct ice_pf *pf) { + int misc_irq_num = pf->oicr_irq.virq; struct ice_hw *hw = &pf->hw; ice_dis_ctrlq_interrupts(hw); @@ -3197,14 +3383,12 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf) wr32(hw, PFINT_OICR_ENA, 0); ice_flush(hw); - if (pf->msix_entries) { - synchronize_irq(pf->msix_entries[pf->oicr_idx].vector); - devm_free_irq(ice_pf_to_dev(pf), - pf->msix_entries[pf->oicr_idx].vector, pf); - } + synchronize_irq(misc_irq_num); + devm_free_irq(ice_pf_to_dev(pf), misc_irq_num, pf); - pf->num_avail_sw_msix += 1; - ice_free_res(pf->irq_tracker, pf->oicr_idx, ICE_RES_MISC_VEC_ID); + 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); } /** @@ -3230,10 +3414,12 @@ 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); } @@ -3250,12 +3436,17 @@ 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; - int oicr_idx, err = 0; + 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. @@ -3264,30 +3455,50 @@ 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_idx = ice_get_res(pf, pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID); - if (oicr_idx < 0) - return oicr_idx; - - pf->num_avail_sw_msix -= 1; - pf->oicr_idx = (u16)oicr_idx; - - err = devm_request_threaded_irq(dev, - pf->msix_entries[pf->oicr_idx].vector, - ice_misc_intr, ice_misc_intr_thread_fn, - 0, pf->int_name, pf); + irq = ice_alloc_irq(pf, false); + if (irq.index < 0) + return irq.index; + + 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); if (err) { dev_err(dev, "devm_request_threaded_irq for %s failed: %d\n", pf->int_name, err); - ice_free_res(pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID); - pf->num_avail_sw_msix += 1; + ice_free_irq(pf, pf->oicr_irq); + 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_idx); - wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_idx), + 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); ice_flush(hw); @@ -3297,31 +3508,12 @@ skip_req_irq: } /** - * ice_napi_add - register NAPI handler for the VSI - * @vsi: VSI for which NAPI handler is to be registered - * - * This function is only called in the driver's load path. Registering the NAPI - * handler is done in ice_vsi_alloc_q_vector() for all other cases (i.e. resume, - * reset/rebuild, etc.) - */ -static void ice_napi_add(struct ice_vsi *vsi) -{ - int v_idx; - - if (!vsi->netdev) - return; - - ice_for_each_q_vector(vsi, v_idx) - netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi, - ice_napi_poll); -} - -/** * ice_set_ops - set netdev and ethtools ops for the given netdev - * @netdev: netdev instance + * @vsi: the VSI associated with the new netdev */ -static void ice_set_ops(struct net_device *netdev) +static void ice_set_ops(struct ice_vsi *vsi) { + struct net_device *netdev = vsi->netdev; struct ice_pf *pf = ice_netdev_to_pf(netdev); if (ice_is_safe_mode(pf)) { @@ -3332,14 +3524,23 @@ static void ice_set_ops(struct net_device *netdev) 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) + return; + + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_XSK_ZEROCOPY | + NETDEV_XDP_ACT_RX_SG; + netdev->xdp_zc_max_segs = ICE_MAX_BUF_TXD; } /** * ice_set_netdev_features - set features for the given netdev * @netdev: netdev instance */ -static void ice_set_netdev_features(struct net_device *netdev) +void ice_set_netdev_features(struct net_device *netdev) { struct ice_pf *pf = ice_netdev_to_pf(netdev); bool is_dvm_ena = ice_is_dvm_ena(&pf->hw); @@ -3421,53 +3622,17 @@ static void ice_set_netdev_features(struct net_device *netdev) * be changed at runtime */ netdev->hw_features |= NETIF_F_RXFCS; -} - -/** - * ice_cfg_netdev - Allocate, configure and register a netdev - * @vsi: the VSI associated with the new netdev - * - * Returns 0 on success, negative value on failure - */ -static int ice_cfg_netdev(struct ice_vsi *vsi) -{ - struct ice_netdev_priv *np; - struct net_device *netdev; - u8 mac_addr[ETH_ALEN]; - netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq, - vsi->alloc_rxq); - if (!netdev) - return -ENOMEM; + /* Allow core to manage IRQs affinity */ + netif_set_affinity_auto(netdev); - set_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - vsi->netdev = netdev; - np = netdev_priv(netdev); - np->vsi = vsi; - - ice_set_netdev_features(netdev); - - ice_set_ops(netdev); - - if (vsi->type == ICE_VSI_PF) { - SET_NETDEV_DEV(netdev, ice_pf_to_dev(vsi->back)); - ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr); - eth_hw_addr_set(netdev, mac_addr); - ether_addr_copy(netdev->perm_addr, mac_addr); - } - - netdev->priv_flags |= IFF_UNICAST_FLT; - - /* Setup netdev TC information */ - ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc); - - /* setup watchdog timeout value to be 5 second */ - netdev->watchdog_timeo = 5 * HZ; - - netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = ICE_MAX_MTU; + /* Mutual exclusivity for TSO and GCS is enforced by the set features + * ndo callback. + */ + if (ice_is_feature_supported(pf, ICE_F_GCS)) + netdev->hw_features |= NETIF_F_HW_CSUM; - return 0; + netif_set_tso_max_size(netdev, ICE_MAX_TSO_SIZE); } /** @@ -3495,14 +3660,27 @@ void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size) static struct ice_vsi * ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_PF, NULL, NULL); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_PF; + params.port_info = pi; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } static struct ice_vsi * ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, struct ice_channel *ch) { - return ice_vsi_setup(pf, pi, ICE_VSI_CHNL, NULL, ch); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_CHNL; + params.port_info = pi; + params.ch = ch; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } /** @@ -3516,7 +3694,13 @@ ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, static struct ice_vsi * ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_CTRL, NULL, NULL); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_CTRL; + params.port_info = pi; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } /** @@ -3530,7 +3714,13 @@ ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) struct ice_vsi * ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_LB, NULL, NULL); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_LB; + params.port_info = pi; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } /** @@ -3541,8 +3731,7 @@ ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) * * net_device_ops implementation for adding VLAN IDs */ -static int -ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) +int ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi_vlan_ops *vlan_ops; @@ -3604,8 +3793,7 @@ finish: * * net_device_ops implementation for removing VLAN IDs */ -static int -ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) +int ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi_vlan_ops *vlan_ops; @@ -3690,20 +3878,6 @@ static void ice_tc_indir_block_unregister(struct ice_vsi *vsi) } /** - * ice_tc_indir_block_remove - clean indirect TC block notifications - * @pf: PF structure - */ -static void ice_tc_indir_block_remove(struct ice_pf *pf) -{ - struct ice_vsi *pf_vsi = ice_get_main_vsi(pf); - - if (!pf_vsi) - return; - - ice_tc_indir_block_unregister(pf_vsi); -} - -/** * ice_tc_indir_block_register - Register TC indirect block notifications * @vsi: VSI struct which has the netdev * @@ -3723,78 +3897,6 @@ static int ice_tc_indir_block_register(struct ice_vsi *vsi) } /** - * ice_setup_pf_sw - Setup the HW switch on startup or after reset - * @pf: board private structure - * - * Returns 0 on success, negative value on failure - */ -static int ice_setup_pf_sw(struct ice_pf *pf) -{ - struct device *dev = ice_pf_to_dev(pf); - bool dvm = ice_is_dvm_ena(&pf->hw); - struct ice_vsi *vsi; - int status; - - if (ice_is_reset_in_progress(pf->state)) - return -EBUSY; - - status = ice_aq_set_port_params(pf->hw.port_info, dvm, NULL); - if (status) - return -EIO; - - vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); - if (!vsi) - return -ENOMEM; - - /* init channel list */ - INIT_LIST_HEAD(&vsi->ch_list); - - status = ice_cfg_netdev(vsi); - if (status) - goto unroll_vsi_setup; - /* netdev has to be configured before setting frame size */ - ice_vsi_cfg_frame_size(vsi); - - /* init indirect block notifications */ - status = ice_tc_indir_block_register(vsi); - if (status) { - dev_err(dev, "Failed to register netdev notifier\n"); - goto unroll_cfg_netdev; - } - - /* Setup DCB netlink interface */ - ice_dcbnl_setup(vsi); - - /* registering the NAPI handler requires both the queues and - * netdev to be created, which are done in ice_pf_vsi_setup() - * and ice_cfg_netdev() respectively - */ - ice_napi_add(vsi); - - status = ice_init_mac_fltr(pf); - if (status) - goto unroll_napi_add; - - return 0; - -unroll_napi_add: - ice_tc_indir_block_unregister(vsi); -unroll_cfg_netdev: - if (vsi) { - ice_napi_del(vsi); - if (vsi->netdev) { - clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - free_netdev(vsi->netdev); - vsi->netdev = NULL; - } - } - -unroll_vsi_setup: - ice_vsi_release(vsi); - return status; -} - -/** * ice_get_avail_q_count - Get count of queues in use * @pf_qmap: bitmap to get queue use count from * @lock: pointer to a mutex that protects access to pf_qmap @@ -3838,9 +3940,11 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf) * ice_deinit_pf - Unrolls initialziations done by ice_init_pf * @pf: board private structure to initialize */ -static void ice_deinit_pf(struct ice_pf *pf) +void ice_deinit_pf(struct ice_pf *pf) { - ice_service_task_stop(pf); + /* note that we unroll also on ice_init_pf() failure here */ + + mutex_destroy(&pf->lag_mutex); mutex_destroy(&pf->adev_mutex); mutex_destroy(&pf->sw_mutex); mutex_destroy(&pf->tc_mutex); @@ -3857,8 +3961,19 @@ static void ice_deinit_pf(struct ice_pf *pf) pf->avail_rxqs = NULL; } + if (pf->txtime_txqs) { + bitmap_free(pf->txtime_txqs); + pf->txtime_txqs = NULL; + } + if (pf->ptp.clock) ptp_clock_unregister(pf->ptp.clock); + + if (!xa_empty(&pf->irq_tracker.entries)) + ice_free_irq_msix_misc(pf); + + xa_destroy(&pf->dyn_ports); + xa_destroy(&pf->sf_nums); } /** @@ -3910,17 +4025,30 @@ static void ice_set_pf_caps(struct ice_pf *pf) pf->max_pf_rxqs = func_caps->common_cap.num_rxq; } +void ice_start_service_task(struct ice_pf *pf) +{ + timer_setup(&pf->serv_tmr, ice_service_timer, 0); + pf->serv_tmr_period = HZ; + INIT_WORK(&pf->serv_task, ice_service_task); + clear_bit(ICE_SERVICE_SCHED, pf->state); +} + /** * ice_init_pf - Initialize general software structures (struct ice_pf) * @pf: board private structure to initialize + * Return: 0 on success, negative errno otherwise. */ -static int ice_init_pf(struct ice_pf *pf) +int ice_init_pf(struct ice_pf *pf) { - ice_set_pf_caps(pf); + struct udp_tunnel_nic_info *udp_tunnel_nic = &pf->hw.udp_tunnel_nic; + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + int err = -ENOMEM; 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); @@ -3928,246 +4056,49 @@ static int ice_init_pf(struct ice_pf *pf) init_waitqueue_head(&pf->reset_wait_queue); - /* setup service timer and periodic service task */ - timer_setup(&pf->serv_tmr, ice_service_timer, 0); - pf->serv_tmr_period = HZ; - INIT_WORK(&pf->serv_task, ice_service_task); - clear_bit(ICE_SERVICE_SCHED, pf->state); - mutex_init(&pf->avail_q_mutex); - pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); - if (!pf->avail_txqs) - return -ENOMEM; - - pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL); - if (!pf->avail_rxqs) { - bitmap_free(pf->avail_txqs); - pf->avail_txqs = NULL; - return -ENOMEM; - } mutex_init(&pf->vfs.table_lock); hash_init(pf->vfs.table); + if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) + wr32(&pf->hw, E830_MBX_PF_IN_FLIGHT_VF_MSGS_THRESH, + ICE_MBX_OVERFLOW_WATERMARK); + else + ice_mbx_init_snapshot(&pf->hw); - return 0; -} - -/** - * ice_reduce_msix_usage - Reduce usage of MSI-X vectors - * @pf: board private structure - * @v_remain: number of remaining MSI-X vectors to be distributed - * - * Reduce the usage of MSI-X vectors when entire request cannot be fulfilled. - * pf->num_lan_msix and pf->num_rdma_msix values are set based on number of - * remaining vectors. - */ -static void ice_reduce_msix_usage(struct ice_pf *pf, int v_remain) -{ - int v_rdma; - - if (!ice_is_rdma_ena(pf)) { - pf->num_lan_msix = v_remain; - return; - } - - /* RDMA needs at least 1 interrupt in addition to AEQ MSIX */ - v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1; - - if (v_remain < ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_RDMA_MSIX) { - dev_warn(ice_pf_to_dev(pf), "Not enough MSI-X vectors to support RDMA.\n"); - clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); - - pf->num_rdma_msix = 0; - pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX; - } else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) || - (v_remain - v_rdma < v_rdma)) { - /* Support minimum RDMA and give remaining vectors to LAN MSIX */ - pf->num_rdma_msix = ICE_MIN_RDMA_MSIX; - pf->num_lan_msix = v_remain - ICE_MIN_RDMA_MSIX; - } else { - /* Split remaining MSIX with RDMA after accounting for AEQ MSIX - */ - pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 + - ICE_RDMA_NUM_AEQ_MSIX; - pf->num_lan_msix = v_remain - pf->num_rdma_msix; - } -} - -/** - * ice_ena_msix_range - Request a range of MSIX vectors from the OS - * @pf: board private structure - * - * Compute the number of MSIX vectors wanted and request from the OS. Adjust - * device usage if there are not enough vectors. Return the number of vectors - * reserved or negative on failure. - */ -static int ice_ena_msix_range(struct ice_pf *pf) -{ - int num_cpus, hw_num_msix, v_other, v_wanted, v_actual; - struct device *dev = ice_pf_to_dev(pf); - int err, i; - - hw_num_msix = pf->hw.func_caps.common_cap.num_msix_vectors; - num_cpus = num_online_cpus(); - - /* LAN miscellaneous handler */ - v_other = ICE_MIN_LAN_OICR_MSIX; - - /* Flow Director */ - if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) - v_other += ICE_FDIR_MSIX; - - /* switchdev */ - v_other += ICE_ESWITCH_MSIX; - - v_wanted = v_other; - - /* LAN traffic */ - pf->num_lan_msix = num_cpus; - v_wanted += pf->num_lan_msix; - - /* RDMA auxiliary driver */ - if (ice_is_rdma_ena(pf)) { - pf->num_rdma_msix = num_cpus + ICE_RDMA_NUM_AEQ_MSIX; - v_wanted += pf->num_rdma_msix; - } - - if (v_wanted > hw_num_msix) { - int v_remain; - - dev_warn(dev, "not enough device MSI-X vectors. wanted = %d, available = %d\n", - v_wanted, hw_num_msix); - - if (hw_num_msix < ICE_MIN_MSIX) { - err = -ERANGE; - goto exit_err; - } - - v_remain = hw_num_msix - v_other; - if (v_remain < ICE_MIN_LAN_TXRX_MSIX) { - v_other = ICE_MIN_MSIX - ICE_MIN_LAN_TXRX_MSIX; - v_remain = ICE_MIN_LAN_TXRX_MSIX; - } - - ice_reduce_msix_usage(pf, v_remain); - v_wanted = pf->num_lan_msix + pf->num_rdma_msix + v_other; - - dev_notice(dev, "Reducing request to %d MSI-X vectors for LAN traffic.\n", - pf->num_lan_msix); - if (ice_is_rdma_ena(pf)) - dev_notice(dev, "Reducing request to %d MSI-X vectors for RDMA.\n", - pf->num_rdma_msix); - } - - pf->msix_entries = devm_kcalloc(dev, v_wanted, - sizeof(*pf->msix_entries), GFP_KERNEL); - if (!pf->msix_entries) { - err = -ENOMEM; - goto exit_err; - } - - for (i = 0; i < v_wanted; i++) - pf->msix_entries[i].entry = i; - - /* actually reserve the vectors */ - v_actual = pci_enable_msix_range(pf->pdev, pf->msix_entries, - ICE_MIN_MSIX, v_wanted); - if (v_actual < 0) { - dev_err(dev, "unable to reserve MSI-X vectors\n"); - err = v_actual; - goto msix_err; - } - - if (v_actual < v_wanted) { - dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n", - v_wanted, v_actual); - - if (v_actual < ICE_MIN_MSIX) { - /* error if we can't get minimum vectors */ - pci_disable_msix(pf->pdev); - err = -ERANGE; - goto msix_err; - } else { - int v_remain = v_actual - v_other; - - if (v_remain < ICE_MIN_LAN_TXRX_MSIX) - v_remain = ICE_MIN_LAN_TXRX_MSIX; - - ice_reduce_msix_usage(pf, v_remain); - - dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n", - pf->num_lan_msix); - - if (ice_is_rdma_ena(pf)) - dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n", - pf->num_rdma_msix); - } - } - - return v_actual; - -msix_err: - devm_kfree(dev, pf->msix_entries); - -exit_err: - pf->num_rdma_msix = 0; - pf->num_lan_msix = 0; - return err; -} - -/** - * ice_dis_msix - Disable MSI-X interrupt setup in OS - * @pf: board private structure - */ -static void ice_dis_msix(struct ice_pf *pf) -{ - pci_disable_msix(pf->pdev); - devm_kfree(ice_pf_to_dev(pf), pf->msix_entries); - pf->msix_entries = NULL; -} - -/** - * ice_clear_interrupt_scheme - Undo things done by ice_init_interrupt_scheme - * @pf: board private structure - */ -static void ice_clear_interrupt_scheme(struct ice_pf *pf) -{ - ice_dis_msix(pf); - - if (pf->irq_tracker) { - devm_kfree(ice_pf_to_dev(pf), pf->irq_tracker); - pf->irq_tracker = NULL; - } -} - -/** - * ice_init_interrupt_scheme - Determine proper interrupt scheme - * @pf: board private structure to initialize - */ -static int ice_init_interrupt_scheme(struct ice_pf *pf) -{ - int vectors; - - vectors = ice_ena_msix_range(pf); + xa_init(&pf->dyn_ports); + xa_init(&pf->sf_nums); - if (vectors < 0) - return vectors; + pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); + pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL); + pf->txtime_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); + if (!pf->avail_txqs || !pf->avail_rxqs || !pf->txtime_txqs) + goto undo_init; + + udp_tunnel_nic->set_port = ice_udp_tunnel_set_port; + udp_tunnel_nic->unset_port = ice_udp_tunnel_unset_port; + udp_tunnel_nic->shared = &hw->udp_tunnel_shared; + udp_tunnel_nic->tables[0].n_entries = hw->tnl.valid_count[TNL_VXLAN]; + udp_tunnel_nic->tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN; + udp_tunnel_nic->tables[1].n_entries = hw->tnl.valid_count[TNL_GENEVE]; + udp_tunnel_nic->tables[1].tunnel_types = UDP_TUNNEL_TYPE_GENEVE; - /* set up vector assignment tracking */ - pf->irq_tracker = devm_kzalloc(ice_pf_to_dev(pf), - struct_size(pf->irq_tracker, list, vectors), - GFP_KERNEL); - if (!pf->irq_tracker) { - ice_dis_msix(pf); - return -ENOMEM; + /* In case of MSIX we are going to setup the misc vector right here + * to handle admin queue events etc. In case of legacy and MSI + * the misc functionality and queue processing is combined in + * the same vector and that gets setup at open. + */ + err = ice_req_irq_msix_misc(pf); + if (err) { + dev_err(dev, "setup of misc vector failed: %d\n", err); + goto undo_init; } - /* populate SW interrupts pool with number of OS granted IRQs. */ - pf->num_avail_sw_msix = (u16)vectors; - pf->irq_tracker->num_entries = (u16)vectors; - pf->irq_tracker->end = pf->irq_tracker->num_entries; - return 0; +undo_init: + /* deinit handles half-initialized pf just fine */ + ice_deinit_pf(pf); + return err; } /** @@ -4195,15 +4126,16 @@ bool ice_is_wol_supported(struct ice_hw *hw) * @vsi: VSI being changed * @new_rx: new number of Rx queues * @new_tx: new number of Tx queues + * @locked: is adev device_lock held * * Only change the number of queues if new_tx, or new_rx is non-0. * * Returns 0 on success. */ -int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx) +int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked) { struct ice_pf *pf = vsi->back; - int err = 0, timeout = 50; + int i, err = 0, timeout = 50; if (!new_rx && !new_tx) return -EINVAL; @@ -4222,15 +4154,32 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx) /* set for the next time the netdev is started */ if (!netif_running(vsi->netdev)) { - ice_vsi_rebuild(vsi, false); + err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); + if (err) + goto rebuild_err; dev_dbg(ice_pf_to_dev(pf), "Link is down, queue count change happens when link is brought up\n"); goto done; } ice_vsi_close(vsi); - ice_vsi_rebuild(vsi, false); - ice_pf_dcb_recfg(pf); + err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); + if (err) + goto rebuild_err; + + ice_for_each_traffic_class(i) { + if (vsi->tc_cfg.ena_tc & BIT(i)) + netdev_set_tc_queue(vsi->netdev, + vsi->tc_cfg.tc_info[i].netdev_tc, + vsi->tc_cfg.tc_info[i].qcount_tx, + vsi->tc_cfg.tc_info[i].qoffset); + } + ice_pf_dcb_recfg(pf, locked); ice_vsi_open(vsi); + goto done; + +rebuild_err: + dev_err(ice_pf_to_dev(pf), "Error during VSI rebuild: %d. Unload and reload the driver.\n", + err); done: clear_bit(ICE_CFG_BUSY, pf->state); return err; @@ -4279,7 +4228,7 @@ static void ice_set_safe_mode_vlan_cfg(struct ice_pf *pf) status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (status) { dev_err(ice_pf_to_dev(vsi->back), "Failed to update VSI for safe mode VLANs, err %d aq_err %s\n", - status, ice_aq_str(hw->adminq.sq_last_status)); + status, libie_aq_str(hw->adminq.sq_last_status)); } else { vsi->info.sec_flags = ctxt->info.sec_flags; vsi->info.sw_flags2 = ctxt->info.sw_flags2; @@ -4491,6 +4440,23 @@ err_vsi_open: return err; } +static void ice_deinit_fdir(struct ice_pf *pf) +{ + struct ice_vsi *vsi = ice_get_ctrl_vsi(pf); + + if (!vsi) + return; + + ice_vsi_manage_fdir(vsi, false); + ice_vsi_release(vsi); + if (pf->ctrl_vsi_idx != ICE_NO_VSI) { + pf->vsi[pf->ctrl_vsi_idx] = NULL; + pf->ctrl_vsi_idx = ICE_NO_VSI; + } + + mutex_destroy(&(&pf->hw)->fdir_fltr_lock); +} + /** * ice_get_opt_fw_name - return optional firmware file name or NULL * @pf: pointer to the PF instance @@ -4524,11 +4490,13 @@ 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; @@ -4537,29 +4505,126 @@ 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; + int err; -dflt_pkg_load: - err = request_firmware(&firmware, ICE_DDP_PKG_FILE, dev); + dev = ice_pf_to_dev(pf); + err = ice_cfg_tx_topo(hw, firmware->data, 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"); + return 0; + } else if (err == -ENODEV) { + /* If we failed to re-initialize the device, we can no longer + * continue loading. + */ + dev_warn(dev, "Failed to initialize hardware after applying Tx scheduling configuration.\n"); + 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"); + return 0; + } else if (err == -EEXIST) { + return 0; + } + + /* Do not treat this as a fatal error. */ + dev_info(dev, "Failed to apply Tx scheduling configuration, err %pe\n", + ERR_PTR(err)); + return 0; +} + +/** + * ice_init_supported_rxdids - Initialize supported Rx descriptor IDs + * @hw: pointer to the hardware structure + * @pf: pointer to pf structure + * + * The pf->supported_rxdids bitmap is used to indicate to VFs which descriptor + * formats the PF hardware supports. The exact list of supported RXDIDs + * depends on the loaded DDP package. The IDs can be determined by reading the + * GLFLXP_RXDID_FLAGS register after the DDP package is loaded. + * + * Note that the legacy 32-byte RXDID 0 is always supported but is not listed + * in the DDP package. The 16-byte legacy descriptor is never supported by + * VFs. + */ +static void ice_init_supported_rxdids(struct ice_hw *hw, struct ice_pf *pf) +{ + pf->supported_rxdids = BIT(ICE_RXDID_LEGACY_1); + + for (int i = ICE_RXDID_FLEX_NIC; i < ICE_FLEX_DESC_RXDID_MAX_NUM; i++) { + u32 regval; + + regval = rd32(hw, GLFLXP_RXDID_FLAGS(i, 0)); + if ((regval >> GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) + & GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M) + pf->supported_rxdids |= BIT(i); + } +} + +/** + * 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; + } + + 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; } - /* request for firmware was successful. Download to device */ + /* Download firmware to device */ ice_load_pkg(firmware, pf); release_firmware(firmware); + + /* Initialize the supported Rx descriptor IDs after loading DDP */ + ice_init_supported_rxdids(hw, pf); + + return 0; } /** @@ -4591,127 +4656,97 @@ static void ice_print_wake_reason(struct ice_pf *pf) /** * ice_register_netdev - register netdev - * @pf: pointer to the PF struct + * @vsi: pointer to the VSI struct */ -static int ice_register_netdev(struct ice_pf *pf) +static int ice_register_netdev(struct ice_vsi *vsi) { - struct ice_vsi *vsi; - int err = 0; + int err; - vsi = ice_get_main_vsi(pf); if (!vsi || !vsi->netdev) return -EIO; err = register_netdev(vsi->netdev); if (err) - goto err_register_netdev; + return err; set_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); netif_carrier_off(vsi->netdev); netif_tx_stop_all_queues(vsi->netdev); return 0; -err_register_netdev: - free_netdev(vsi->netdev); - vsi->netdev = NULL; - clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - return err; +} + +static void ice_unregister_netdev(struct ice_vsi *vsi) +{ + if (!vsi || !vsi->netdev) + return; + + unregister_netdev(vsi->netdev); + clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); } /** - * ice_probe - Device initialization routine - * @pdev: PCI device information struct - * @ent: entry in ice_pci_tbl + * ice_cfg_netdev - Allocate, configure and register a netdev + * @vsi: the VSI associated with the new netdev * - * Returns 0 on success, negative on failure + * Returns 0 on success, negative value on failure */ -static int -ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) +static int ice_cfg_netdev(struct ice_vsi *vsi) { - struct device *dev = &pdev->dev; - struct ice_vsi *vsi; - struct ice_pf *pf; - struct ice_hw *hw; - int i, err; - - if (pdev->is_virtfn) { - dev_err(dev, "can't probe a virtual function\n"); - return -EINVAL; - } - - /* this driver uses devres, see - * Documentation/driver-api/driver-model/devres.rst - */ - err = pcim_enable_device(pdev); - if (err) - return err; - - err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), dev_driver_string(dev)); - if (err) { - dev_err(dev, "BAR0 I/O map error %d\n", err); - return err; - } + struct ice_netdev_priv *np; + struct net_device *netdev; + u8 mac_addr[ETH_ALEN]; - pf = ice_allocate_pf(dev); - if (!pf) + netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq, + vsi->alloc_rxq); + if (!netdev) return -ENOMEM; - /* initialize Auxiliary index to invalid value */ - pf->aux_idx = -1; + set_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); + vsi->netdev = netdev; + np = netdev_priv(netdev); + np->vsi = vsi; - /* set up for high or low DMA */ - err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); - if (err) { - dev_err(dev, "DMA configuration failed: 0x%x\n", err); - return err; - } + ice_set_netdev_features(netdev); + ice_set_ops(vsi); - pci_enable_pcie_error_reporting(pdev); - pci_set_master(pdev); + if (vsi->type == ICE_VSI_PF) { + SET_NETDEV_DEV(netdev, ice_pf_to_dev(vsi->back)); + ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr); + eth_hw_addr_set(netdev, mac_addr); + } - pf->pdev = pdev; - pci_set_drvdata(pdev, pf); - set_bit(ICE_DOWN, pf->state); - /* Disable service task until DOWN bit is cleared */ - set_bit(ICE_SERVICE_DIS, pf->state); + netdev->priv_flags |= IFF_UNICAST_FLT; - hw = &pf->hw; - hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0]; - pci_save_state(pdev); + /* Setup netdev TC information */ + ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc); - hw->back = pf; - hw->vendor_id = pdev->vendor; - hw->device_id = pdev->device; - pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id); - hw->subsystem_vendor_id = pdev->subsystem_vendor; - hw->subsystem_device_id = pdev->subsystem_device; - hw->bus.device = PCI_SLOT(pdev->devfn); - hw->bus.func = PCI_FUNC(pdev->devfn); - ice_set_ctrlq_len(hw); + netdev->max_mtu = ICE_MAX_MTU; - pf->msg_enable = netif_msg_init(debug, ICE_DFLT_NETIF_M); + return 0; +} -#ifndef CONFIG_DYNAMIC_DEBUG - if (debug < -1) - hw->debug_mask = debug; -#endif +static void ice_decfg_netdev(struct ice_vsi *vsi) +{ + clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); + free_netdev(vsi->netdev); + vsi->netdev = NULL; +} - err = ice_init_hw(hw); - if (err) { - dev_err(dev, "ice_init_hw failed: %d\n", err); - err = -EIO; - goto err_exit_unroll; - } +void ice_init_dev_hw(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + int err; ice_init_feature_support(pf); - ice_request_fw(pf); + err = ice_init_ddp_config(hw, pf); - /* 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 */ - if (ice_is_safe_mode(pf)) { + if (err || ice_is_safe_mode(pf)) { /* we already got function/device capabilities but these don't * reflect what the driver needs to do in safe mode. Instead of * adding conditional logic everywhere to ignore these @@ -4719,119 +4754,114 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) */ ice_set_safe_mode_caps(hw); } +} - err = ice_init_pf(pf); +int ice_init_dev(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + ice_set_pf_caps(pf); + err = ice_init_interrupt_scheme(pf); if (err) { - dev_err(dev, "ice_init_pf failed: %d\n", err); - goto err_init_pf_unroll; + dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err); + return -EIO; } - ice_devlink_init_regions(pf); + ice_start_service_task(pf); - pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port; - pf->hw.udp_tunnel_nic.unset_port = ice_udp_tunnel_unset_port; - pf->hw.udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP; - pf->hw.udp_tunnel_nic.shared = &pf->hw.udp_tunnel_shared; - i = 0; - if (pf->hw.tnl.valid_count[TNL_VXLAN]) { - pf->hw.udp_tunnel_nic.tables[i].n_entries = - pf->hw.tnl.valid_count[TNL_VXLAN]; - pf->hw.udp_tunnel_nic.tables[i].tunnel_types = - UDP_TUNNEL_TYPE_VXLAN; - i++; - } - if (pf->hw.tnl.valid_count[TNL_GENEVE]) { - pf->hw.udp_tunnel_nic.tables[i].n_entries = - pf->hw.tnl.valid_count[TNL_GENEVE]; - pf->hw.udp_tunnel_nic.tables[i].tunnel_types = - UDP_TUNNEL_TYPE_GENEVE; - i++; - } - - pf->num_alloc_vsi = hw->func_caps.guar_num_vsi; - if (!pf->num_alloc_vsi) { - err = -EIO; - goto err_init_pf_unroll; - } - if (pf->num_alloc_vsi > UDP_TUNNEL_NIC_MAX_SHARING_DEVICES) { - dev_warn(&pf->pdev->dev, - "limiting the VSI count due to UDP tunnel limitation %d > %d\n", - pf->num_alloc_vsi, UDP_TUNNEL_NIC_MAX_SHARING_DEVICES); - pf->num_alloc_vsi = UDP_TUNNEL_NIC_MAX_SHARING_DEVICES; - } + return 0; +} - pf->vsi = devm_kcalloc(dev, pf->num_alloc_vsi, sizeof(*pf->vsi), - GFP_KERNEL); - if (!pf->vsi) { - err = -ENOMEM; - goto err_init_pf_unroll; - } +void ice_deinit_dev(struct ice_pf *pf) +{ + ice_service_task_stop(pf); - pf->vsi_stats = devm_kcalloc(dev, pf->num_alloc_vsi, - sizeof(*pf->vsi_stats), GFP_KERNEL); - if (!pf->vsi_stats) { - err = -ENOMEM; - goto err_init_vsi_unroll; - } + /* Service task is already stopped, so call reset directly. */ + ice_reset(&pf->hw, ICE_RESET_PFR); + pci_wait_for_pending_transaction(pf->pdev); + ice_clear_interrupt_scheme(pf); +} - err = ice_init_interrupt_scheme(pf); - if (err) { - dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err); - err = -EIO; - goto err_init_vsi_stats_unroll; - } +static void ice_init_features(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); - /* In case of MSIX we are going to setup the misc vector right here - * to handle admin queue events etc. In case of legacy and MSI - * the misc functionality and queue processing is combined in - * the same vector and that gets setup at open. - */ - err = ice_req_irq_msix_misc(pf); - if (err) { - dev_err(dev, "setup of misc vector failed: %d\n", err); - goto err_init_interrupt_unroll; - } + if (ice_is_safe_mode(pf)) + return; - /* create switch struct for the switch element created by FW on boot */ - pf->first_sw = devm_kzalloc(dev, sizeof(*pf->first_sw), GFP_KERNEL); - if (!pf->first_sw) { - err = -ENOMEM; - goto err_msix_misc_unroll; - } + /* initialize DDP driven features */ + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) + ice_ptp_init(pf); - if (hw->evb_veb) - pf->first_sw->bridge_mode = BRIDGE_MODE_VEB; - else - pf->first_sw->bridge_mode = BRIDGE_MODE_VEPA; + if (ice_is_feature_supported(pf, ICE_F_GNSS)) + ice_gnss_init(pf); - pf->first_sw->pf = pf; + if (ice_is_feature_supported(pf, ICE_F_CGU) || + ice_is_feature_supported(pf, ICE_F_PHY_RCLK)) + ice_dpll_init(pf); - /* record the sw_id available for later use */ - pf->first_sw->sw_id = hw->port_info->sw_id; + /* Note: Flow director init failure is non-fatal to load */ + if (ice_init_fdir(pf)) + dev_err(dev, "could not initialize flow director\n"); - err = ice_setup_pf_sw(pf); - if (err) { - dev_err(dev, "probe failed due to setup PF switch: %d\n", err); - goto err_alloc_sw_unroll; + /* Note: DCB init failure is non-fatal to load */ + if (ice_init_pf_dcb(pf, false)) { + clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); + clear_bit(ICE_FLAG_DCB_ENA, pf->flags); + } else { + ice_cfg_lldp_mib_change(&pf->hw, true); } - clear_bit(ICE_SERVICE_DIS, pf->state); + if (ice_init_lag(pf)) + dev_warn(dev, "Failed to init link aggregation support\n"); - /* tell the firmware we are up */ - err = ice_send_version(pf); - if (err) { - dev_err(dev, "probe failed sending driver version %s. error: %d\n", - UTS_RELEASE, err); - goto err_send_version_unroll; - } + ice_hwmon_init(pf); +} - /* since everything is good, start the service timer */ - mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); +static void ice_deinit_features(struct ice_pf *pf) +{ + if (ice_is_safe_mode(pf)) + return; + + ice_deinit_lag(pf); + if (test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags)) + ice_cfg_lldp_mib_change(&pf->hw, false); + ice_deinit_fdir(pf); + if (ice_is_feature_supported(pf, ICE_F_GNSS)) + ice_gnss_exit(pf); + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) + 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) +{ + /* Save wakeup reason register for later use */ + pf->wakeup_reason = rd32(&pf->hw, PFPM_WUS); + + /* check for a power management event */ + ice_print_wake_reason(pf); + + /* clear wake status, all bits */ + wr32(&pf->hw, PFPM_WUS, U32_MAX); + + /* Disable WoL at init, wait for user to enable */ + device_set_wakeup_enable(ice_pf_to_dev(pf), false); +} + +static int ice_init_link(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; err = ice_init_link_events(pf->hw.port_info); if (err) { dev_err(dev, "ice_init_link_events failed: %d\n", err); - goto err_send_version_unroll; + return err; } /* not a fatal error if this fails */ @@ -4867,124 +4897,454 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) set_bit(ICE_FLAG_NO_MEDIA, pf->flags); } - ice_verify_cacheline_size(pf); + return err; +} - /* Save wakeup reason register for later use */ - pf->wakeup_reason = rd32(hw, PFPM_WUS); +static int ice_init_pf_sw(struct ice_pf *pf) +{ + bool dvm = ice_is_dvm_ena(&pf->hw); + struct ice_vsi *vsi; + int err; - /* check for a power management event */ - ice_print_wake_reason(pf); + /* create switch struct for the switch element created by FW on boot */ + pf->first_sw = kzalloc(sizeof(*pf->first_sw), GFP_KERNEL); + if (!pf->first_sw) + return -ENOMEM; - /* clear wake status, all bits */ - wr32(hw, PFPM_WUS, U32_MAX); + if (pf->hw.evb_veb) + pf->first_sw->bridge_mode = BRIDGE_MODE_VEB; + else + pf->first_sw->bridge_mode = BRIDGE_MODE_VEPA; - /* Disable WoL at init, wait for user to enable */ - device_set_wakeup_enable(dev, false); + pf->first_sw->pf = pf; - if (ice_is_safe_mode(pf)) { - ice_set_safe_mode_vlan_cfg(pf); - goto probe_done; + /* record the sw_id available for later use */ + pf->first_sw->sw_id = pf->hw.port_info->sw_id; + + err = ice_aq_set_port_params(pf->hw.port_info, dvm, NULL); + if (err) + goto err_aq_set_port_params; + + vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); + if (!vsi) { + err = -ENOMEM; + goto err_pf_vsi_setup; } - /* initialize DDP driven features */ - if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) - ice_ptp_init(pf); + return 0; - if (ice_is_feature_supported(pf, ICE_F_GNSS)) - ice_gnss_init(pf); +err_pf_vsi_setup: +err_aq_set_port_params: + kfree(pf->first_sw); + return err; +} - /* Note: Flow director init failure is non-fatal to load */ - if (ice_init_fdir(pf)) - dev_err(dev, "could not initialize flow director\n"); +static void ice_deinit_pf_sw(struct ice_pf *pf) +{ + struct ice_vsi *vsi = ice_get_main_vsi(pf); - /* Note: DCB init failure is non-fatal to load */ - if (ice_init_pf_dcb(pf, false)) { - clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); - clear_bit(ICE_FLAG_DCB_ENA, pf->flags); - } else { - ice_cfg_lldp_mib_change(&pf->hw, true); + if (!vsi) + return; + + ice_vsi_release(vsi); + kfree(pf->first_sw); +} + +static int ice_alloc_vsis(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + + pf->num_alloc_vsi = pf->hw.func_caps.guar_num_vsi; + if (!pf->num_alloc_vsi) + return -EIO; + + if (pf->num_alloc_vsi > UDP_TUNNEL_NIC_MAX_SHARING_DEVICES) { + dev_warn(dev, + "limiting the VSI count due to UDP tunnel limitation %d > %d\n", + pf->num_alloc_vsi, UDP_TUNNEL_NIC_MAX_SHARING_DEVICES); + pf->num_alloc_vsi = UDP_TUNNEL_NIC_MAX_SHARING_DEVICES; } - if (ice_init_lag(pf)) - dev_warn(dev, "Failed to init link aggregation support\n"); + pf->vsi = devm_kcalloc(dev, pf->num_alloc_vsi, sizeof(*pf->vsi), + GFP_KERNEL); + if (!pf->vsi) + return -ENOMEM; - /* print PCI link speed and width */ - pcie_print_link_status(pf->pdev); + pf->vsi_stats = devm_kcalloc(dev, pf->num_alloc_vsi, + sizeof(*pf->vsi_stats), GFP_KERNEL); + if (!pf->vsi_stats) { + devm_kfree(dev, pf->vsi); + return -ENOMEM; + } -probe_done: - err = ice_devlink_create_pf_port(pf); + return 0; +} + +static void ice_dealloc_vsis(struct ice_pf *pf) +{ + devm_kfree(ice_pf_to_dev(pf), pf->vsi_stats); + pf->vsi_stats = NULL; + + pf->num_alloc_vsi = 0; + devm_kfree(ice_pf_to_dev(pf), pf->vsi); + pf->vsi = NULL; +} + +static int ice_init_devlink(struct ice_pf *pf) +{ + int err; + + err = ice_devlink_register_params(pf); if (err) - goto err_create_pf_port; + return err; - vsi = ice_get_main_vsi(pf); - if (!vsi || !vsi->netdev) { - err = -EINVAL; - goto err_netdev_reg; + ice_devlink_init_regions(pf); + ice_devlink_register(pf); + ice_health_init(pf); + + return 0; +} + +static void ice_deinit_devlink(struct ice_pf *pf) +{ + ice_health_deinit(pf); + ice_devlink_unregister(pf); + ice_devlink_destroy_regions(pf); + ice_devlink_unregister_params(pf); +} + +static int ice_init(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + err = ice_init_pf(pf); + if (err) { + dev_err(dev, "ice_init_pf failed: %d\n", err); + return err; } - SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port); + if (pf->hw.mac_type == ICE_MAC_E830) { + err = pci_enable_ptm(pf->pdev, NULL); + if (err) + dev_dbg(dev, "PCIe PTM not supported by PCIe bus/controller\n"); + } - err = ice_register_netdev(pf); + err = ice_alloc_vsis(pf); if (err) - goto err_netdev_reg; + goto unroll_pf_init; - err = ice_devlink_register_params(pf); + err = ice_init_pf_sw(pf); + if (err) + goto err_init_pf_sw; + + ice_init_wakeup(pf); + + err = ice_init_link(pf); if (err) - goto err_netdev_reg; + goto err_init_link; + + err = ice_send_version(pf); + if (err) + goto err_init_link; + + ice_verify_cacheline_size(pf); + + if (ice_is_safe_mode(pf)) + ice_set_safe_mode_vlan_cfg(pf); + else + /* print PCI link speed and width */ + pcie_print_link_status(pf->pdev); /* ready to go, so clear down state bit */ clear_bit(ICE_DOWN, pf->state); - if (ice_is_rdma_ena(pf)) { - pf->aux_idx = ida_alloc(&ice_aux_ida, GFP_KERNEL); - if (pf->aux_idx < 0) { - dev_err(dev, "Failed to allocate device ID for AUX driver\n"); - err = -ENOMEM; - goto err_devlink_reg_param; - } + clear_bit(ICE_SERVICE_DIS, pf->state); - err = ice_init_rdma(pf); - if (err) { - dev_err(dev, "Failed to initialize RDMA: %d\n", err); - err = -EIO; - goto err_init_aux_unroll; - } - } else { - dev_warn(dev, "RDMA is not supported on this device\n"); - } + /* since everything is good, start the service timer */ + mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); - ice_devlink_register(pf); return 0; -err_init_aux_unroll: - pf->adev = NULL; - ida_free(&ice_aux_ida, pf->aux_idx); -err_devlink_reg_param: - ice_devlink_unregister_params(pf); -err_netdev_reg: - ice_devlink_destroy_pf_port(pf); -err_create_pf_port: -err_send_version_unroll: - ice_vsi_release_all(pf); -err_alloc_sw_unroll: +err_init_link: + ice_deinit_pf_sw(pf); +err_init_pf_sw: + ice_dealloc_vsis(pf); +unroll_pf_init: + ice_deinit_pf(pf); + return err; +} + +static void ice_deinit(struct ice_pf *pf) +{ set_bit(ICE_SERVICE_DIS, pf->state); set_bit(ICE_DOWN, pf->state); - devm_kfree(dev, pf->first_sw); -err_msix_misc_unroll: - ice_free_irq_msix_misc(pf); -err_init_interrupt_unroll: - ice_clear_interrupt_scheme(pf); -err_init_vsi_stats_unroll: - devm_kfree(dev, pf->vsi_stats); - pf->vsi_stats = NULL; -err_init_vsi_unroll: - devm_kfree(dev, pf->vsi); -err_init_pf_unroll: + + ice_deinit_pf_sw(pf); + ice_dealloc_vsis(pf); ice_deinit_pf(pf); - ice_devlink_destroy_regions(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 *vsi; + int err; + + 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; + + /* 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); + + ice_init_features(pf); + + err = ice_init_rdma(pf); + if (err) + goto err_init_rdma; + + ice_service_task_restart(pf); + + clear_bit(ICE_DOWN, pf->state); + + return 0; + +err_init_rdma: + ice_deinit_features(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_rdma(pf); + ice_deinit_features(pf); + ice_tc_indir_block_unregister(vsi); + ice_unregister_netdev(vsi); + ice_devlink_destroy_pf_port(pf); + ice_decfg_netdev(vsi); +} + +static int ice_probe_recovery_mode(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + dev_err(dev, "Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode\n"); + + INIT_HLIST_HEAD(&pf->aq_wait_list); + spin_lock_init(&pf->aq_wait_lock); + init_waitqueue_head(&pf->aq_wait_queue); + + timer_setup(&pf->serv_tmr, ice_service_timer, 0); + pf->serv_tmr_period = HZ; + INIT_WORK(&pf->serv_task, ice_service_task_recovery_mode); + clear_bit(ICE_SERVICE_SCHED, pf->state); + err = ice_create_all_ctrlq(&pf->hw); + if (err) + return err; + + scoped_guard(devl, priv_to_devlink(pf)) { + err = ice_init_devlink(pf); + if (err) + return err; + } + + ice_service_task_restart(pf); + + return 0; +} + +/** + * ice_probe - Device initialization routine + * @pdev: PCI device information struct + * @ent: entry in ice_pci_tbl + * + * Returns 0 on success, negative on failure + */ +static int +ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) +{ + struct device *dev = &pdev->dev; + bool need_dev_deinit = false; + struct ice_adapter *adapter; + struct ice_pf *pf; + struct ice_hw *hw; + int err; + + if (pdev->is_virtfn) { + dev_err(dev, "can't probe a virtual function\n"); + return -EINVAL; + } + + /* when under a kdump kernel initiate a reset before enabling the + * device in order to clear out any pending DMA transactions. These + * transactions can cause some systems to machine check when doing + * the pcim_enable_device() below. + */ + if (is_kdump_kernel()) { + pci_save_state(pdev); + pci_clear_master(pdev); + err = pcie_flr(pdev); + if (err) + return err; + pci_restore_state(pdev); + } + + /* this driver uses devres, see + * Documentation/driver-api/driver-model/devres.rst + */ + err = pcim_enable_device(pdev); + if (err) + return err; + + err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), dev_driver_string(dev)); + if (err) { + dev_err(dev, "BAR0 I/O map error %d\n", err); + return err; + } + + pf = ice_allocate_pf(dev); + if (!pf) + return -ENOMEM; + + /* initialize Auxiliary index to invalid value */ + pf->aux_idx = -1; + + /* set up for high or low DMA */ + err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(dev, "DMA configuration failed: 0x%x\n", err); + return err; + } + + pci_set_master(pdev); + pf->pdev = pdev; + pci_set_drvdata(pdev, pf); + set_bit(ICE_DOWN, pf->state); + /* Disable service task until DOWN bit is cleared */ + set_bit(ICE_SERVICE_DIS, pf->state); + + hw = &pf->hw; + hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0]; + pci_save_state(pdev); + + hw->back = pf; + hw->port_info = NULL; + hw->vendor_id = pdev->vendor; + hw->device_id = pdev->device; + pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id); + hw->subsystem_vendor_id = pdev->subsystem_vendor; + hw->subsystem_device_id = pdev->subsystem_device; + hw->bus.device = PCI_SLOT(pdev->devfn); + hw->bus.func = PCI_FUNC(pdev->devfn); + ice_set_ctrlq_len(hw); + + pf->msg_enable = netif_msg_init(debug, ICE_DFLT_NETIF_M); + +#ifndef CONFIG_DYNAMIC_DEBUG + if (debug < -1) + hw->debug_mask = debug; +#endif + + if (ice_is_recovery_mode(hw)) + return ice_probe_recovery_mode(pf); + + err = ice_init_hw(hw); + if (err) { + dev_err(dev, "ice_init_hw failed: %d\n", err); + return err; + } + + adapter = ice_adapter_get(pdev); + if (IS_ERR(adapter)) { + err = PTR_ERR(adapter); + goto unroll_hw_init; + } + pf->adapter = adapter; + + err = ice_init_dev(pf); + if (err) + goto unroll_adapter; + + err = ice_init(pf); + if (err) + goto unroll_dev_init; + + devl_lock(priv_to_devlink(pf)); + err = ice_load(pf); + if (err) + goto unroll_init; + + err = ice_init_devlink(pf); + if (err) + goto unroll_load; + devl_unlock(priv_to_devlink(pf)); + + return 0; + +unroll_load: + ice_unload(pf); +unroll_init: + devl_unlock(priv_to_devlink(pf)); + ice_deinit(pf); +unroll_dev_init: + need_dev_deinit = true; +unroll_adapter: + ice_adapter_put(pdev); +unroll_hw_init: ice_deinit_hw(hw); -err_exit_unroll: - pci_disable_pcie_error_reporting(pdev); - pci_disable_device(pdev); + if (need_dev_deinit) + ice_deinit_dev(pf); return err; } @@ -5046,7 +5406,7 @@ static void ice_setup_mc_magic_wake(struct ice_pf *pf) status = ice_aq_manage_mac_write(hw, mac_addr, flags, NULL); if (status) dev_err(dev, "Failed to enable Multicast Magic Packet wake, err %d aq_err %s\n", - status, ice_aq_str(hw->adminq.sq_last_status)); + status, libie_aq_str(hw->adminq.sq_last_status)); } /** @@ -5058,62 +5418,49 @@ static void ice_remove(struct pci_dev *pdev) struct ice_pf *pf = pci_get_drvdata(pdev); int i; - ice_devlink_unregister(pf); for (i = 0; i < ICE_MAX_RESET_WAIT; i++) { if (!ice_is_reset_in_progress(pf->state)) break; msleep(100); } - ice_tc_indir_block_remove(pf); + if (ice_is_recovery_mode(&pf->hw)) { + ice_service_task_stop(pf); + scoped_guard(devl, priv_to_devlink(pf)) { + ice_deinit_devlink(pf); + } + return; + } if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) { set_bit(ICE_VF_RESETS_DISABLED, pf->state); ice_free_vfs(pf); } - ice_service_task_stop(pf); + ice_hwmon_exit(pf); - ice_aq_cancel_waiting_tasks(pf); - ice_unplug_aux_dev(pf); - if (pf->aux_idx >= 0) - ida_free(&ice_aux_ida, pf->aux_idx); - ice_devlink_unregister_params(pf); - set_bit(ICE_DOWN, pf->state); - - ice_deinit_lag(pf); - if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) - ice_ptp_release(pf); - if (ice_is_feature_supported(pf, ICE_F_GNSS)) - ice_gnss_exit(pf); if (!ice_is_safe_mode(pf)) ice_remove_arfs(pf); - ice_setup_mc_magic_wake(pf); + + devl_lock(priv_to_devlink(pf)); + ice_dealloc_all_dynamic_ports(pf); + ice_deinit_devlink(pf); + + ice_unload(pf); + devl_unlock(priv_to_devlink(pf)); + + ice_deinit(pf); ice_vsi_release_all(pf); - mutex_destroy(&(&pf->hw)->fdir_fltr_lock); - ice_devlink_destroy_pf_port(pf); + + ice_setup_mc_magic_wake(pf); ice_set_wake(pf); - ice_free_irq_msix_misc(pf); - ice_for_each_vsi(pf, i) { - if (!pf->vsi[i]) - continue; - ice_vsi_free_q_vectors(pf->vsi[i]); - } - devm_kfree(&pdev->dev, pf->vsi_stats); - pf->vsi_stats = NULL; - ice_deinit_pf(pf); - ice_devlink_destroy_regions(pf); + + ice_adapter_put(pdev); ice_deinit_hw(&pf->hw); - /* Issue a PFR as part of the prescribed driver unload flow. Do not - * do it via ice_schedule_reset() since there is no need to rebuild - * and the service task is already stopped. - */ - ice_reset(&pf->hw, ICE_RESET_PFR); - pci_wait_for_pending_transaction(pdev); - ice_clear_interrupt_scheme(pf); - pci_disable_pcie_error_reporting(pdev); - pci_disable_device(pdev); + ice_deinit_dev(pf); + ice_aq_cancel_waiting_tasks(pf); + set_bit(ICE_DOWN, pf->state); } /** @@ -5132,7 +5479,6 @@ static void ice_shutdown(struct pci_dev *pdev) } } -#ifdef CONFIG_PM /** * ice_prepare_for_shutdown - prep for PCI shutdown * @pf: board private structure @@ -5157,7 +5503,7 @@ static void ice_prepare_for_shutdown(struct ice_pf *pf) if (pf->vsi[v]) pf->vsi[v]->vsi_num = 0; - ice_shutdown_all_ctrlq(hw); + ice_shutdown_all_ctrlq(hw, true); } /** @@ -5194,6 +5540,9 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf) if (ret) goto err_reinit; ice_vsi_map_rings_to_vectors(pf->vsi[v]); + rtnl_lock(); + ice_vsi_set_napi_queues(pf->vsi[v]); + rtnl_unlock(); } ret = ice_req_irq_msix_misc(pf); @@ -5207,8 +5556,12 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf) err_reinit: while (v--) - if (pf->vsi[v]) + if (pf->vsi[v]) { + rtnl_lock(); + ice_vsi_clear_napi_queues(pf->vsi[v]); + rtnl_unlock(); ice_vsi_free_q_vectors(pf->vsi[v]); + } return ret; } @@ -5220,7 +5573,7 @@ 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; @@ -5241,7 +5594,7 @@ static int __maybe_unused ice_suspend(struct device *dev) */ disabled = ice_service_task_stop(pf); - ice_unplug_aux_dev(pf); + ice_deinit_rdma(pf); /* Already suspended?, then there is nothing to do */ if (test_and_set_bit(ICE_SUSPENDED, pf->state)) { @@ -5273,6 +5626,9 @@ static int __maybe_unused ice_suspend(struct device *dev) ice_for_each_vsi(pf, v) { if (!pf->vsi[v]) continue; + rtnl_lock(); + ice_vsi_clear_napi_queues(pf->vsi[v]); + rtnl_unlock(); ice_vsi_free_q_vectors(pf->vsi[v]); } ice_clear_interrupt_scheme(pf); @@ -5287,7 +5643,7 @@ 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; @@ -5297,7 +5653,6 @@ static int __maybe_unused ice_resume(struct device *dev) pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); - pci_save_state(pdev); if (!pci_device_is_present(pdev)) return -ENODEV; @@ -5321,6 +5676,11 @@ static int __maybe_unused ice_resume(struct device *dev) if (ret) dev_err(dev, "Cannot restore interrupt scheme: %d\n", ret); + ret = ice_init_rdma(pf); + if (ret) + dev_err(dev, "Reinitialize RDMA during resume failed: %d\n", + ret); + clear_bit(ICE_DOWN, pf->state); /* Now perform PF reset and rebuild */ reset_type = ICE_RESET_PFR; @@ -5338,7 +5698,6 @@ 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 @@ -5393,7 +5752,6 @@ static pci_ers_result_t ice_pci_err_slot_reset(struct pci_dev *pdev) } else { pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); pci_wake_from_d3(pdev, false); /* Check for life */ @@ -5430,7 +5788,7 @@ static void ice_pci_err_resume(struct pci_dev *pdev) return; } - ice_restore_all_vfs_msi_state(pdev); + ice_restore_all_vfs_msi_state(pf); ice_do_reset(pf, ICE_RESET_PFR); ice_service_task_restart(pf); @@ -5473,38 +5831,61 @@ static void ice_pci_err_reset_done(struct pci_dev *pdev) * Class, Class Mask, private data (not used) } */ static const struct pci_device_id ice_pci_tbl[] = { - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SGMII), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SGMII), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SGMII), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_1GBE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822_SI_DFLT), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_10G_BASE_T) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SGMII) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_10G_BASE_T) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SGMII) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_10G_BASE_T) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SGMII) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_10G_BASE_T) }, + { 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_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), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835CC_BACKPLANE), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835CC_QSFP56), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835CC_SFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835C_BACKPLANE), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835C_QSFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835C_SFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835_L_BACKPLANE), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835_L_QSFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835_L_SFP), }, /* required last entry */ - { 0, } + {} }; 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, @@ -5519,11 +5900,11 @@ 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, + .sriov_set_msix_vec_count = ice_sriov_set_msix_vec_count, .err_handler = &ice_pci_err_handler }; @@ -5535,23 +5916,48 @@ 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); - ice_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, KBUILD_MODNAME); + ice_adv_lnk_speed_maps_init(); + + ice_wq = alloc_workqueue("%s", WQ_UNBOUND, 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; + } + + ice_debugfs_init(); + 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; + } + + status = ice_sf_driver_register(); + if (status) { + pr_err("Failed to register SF driver, err %d\n", status); + goto err_sf_driver; } + return 0; + +err_sf_driver: + pci_unregister_driver(&ice_driver); +err_dest_lag_wq: + destroy_workqueue(ice_lag_wq); + ice_debugfs_exit(); +err_dest_wq: + destroy_workqueue(ice_wq); return status; } module_init(ice_module_init); @@ -5564,8 +5970,11 @@ module_init(ice_module_init); */ static void __exit ice_module_exit(void) { + ice_sf_driver_unregister(); pci_unregister_driver(&ice_driver); + ice_debugfs_exit(); destroy_workqueue(ice_wq); + destroy_workqueue(ice_lag_wq); pr_info("module unloaded\n"); } module_exit(ice_module_exit); @@ -5594,11 +6003,6 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) if (!is_valid_ether_addr(mac)) return -EADDRNOTAVAIL; - if (ether_addr_equal(netdev->dev_addr, mac)) { - netdev_dbg(netdev, "already using mac %pM\n", mac); - return 0; - } - if (test_bit(ICE_DOWN, pf->state) || ice_is_reset_in_progress(pf->state)) { netdev_err(netdev, "can't set mac %pM. device not ready\n", @@ -5673,7 +6077,7 @@ static void ice_set_rx_mode(struct net_device *netdev) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - if (!vsi) + if (!vsi || ice_is_switchdev_running(vsi->back)) return; /* Set the flags to synchronize filters @@ -5715,6 +6119,13 @@ ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate) q_handle = vsi->tx_rings[queue_index]->q_handle; tc = ice_dcb_get_tc(vsi, queue_index); + vsi = ice_locate_vsi_using_queue(vsi, queue_index); + if (!vsi) { + netdev_err(netdev, "Invalid VSI for given queue %d\n", + queue_index); + return -EINVAL; + } + /* Set BW back to default, when user set maxrate to 0 */ if (!maxrate) status = ice_cfg_q_bw_dflt_lmt(vsi->port_info, vsi->idx, tc, @@ -5737,12 +6148,14 @@ ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate) * @addr: the MAC address entry being added * @vid: VLAN ID * @flags: instructions from stack about fdb operation + * @notified: whether notification was emitted * @extack: netlink extended ack */ static int ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags, struct netlink_ext_ack __always_unused *extack) + u16 flags, bool *notified, + struct netlink_ext_ack __always_unused *extack) { int err; @@ -5776,12 +6189,14 @@ ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[], * @dev: the net device pointer * @addr: the MAC address entry being added * @vid: VLAN ID + * @notified: whether notification was emitted * @extack: netlink extended ack */ static int ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, - __always_unused u16 vid, struct netlink_ext_ack *extack) + __always_unused u16 vid, bool *notified, + struct netlink_ext_ack *extack) { int err; @@ -5906,6 +6321,23 @@ 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 @@ -5947,6 +6379,9 @@ 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; } @@ -5965,10 +6400,12 @@ ice_set_vlan_filtering_features(struct ice_vsi *vsi, netdev_features_t features) int err = 0; /* support Single VLAN Mode (SVM) and Double VLAN Mode (DVM) by checking - * if either bit is set + * if either bit is set. In switchdev mode Rx filtering should never be + * enabled. */ - if (features & - (NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)) + if ((features & + (NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)) && + !ice_is_eswitch_mode_switchdev(vsi->back)) err = vlan_ops->ena_rx_filtering(vsi); else err = vlan_ops->dis_rx_filtering(vsi); @@ -6116,13 +6553,24 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) if (changed & NETIF_F_HW_TC) { bool ena = !!(features & NETIF_F_HW_TC); - ena ? set_bit(ICE_FLAG_CLS_FLOWER, pf->flags) : - clear_bit(ICE_FLAG_CLS_FLOWER, pf->flags); + assign_bit(ICE_FLAG_CLS_FLOWER, pf->flags, ena); } if (changed & NETIF_F_LOOPBACK) ret = ice_set_loopback(vsi, !!(features & NETIF_F_LOOPBACK)); + /* Due to E830 hardware limitations, TSO (NETIF_F_ALL_TSO) with GCS + * (NETIF_F_HW_CSUM) is not supported. + */ + if (ice_is_feature_supported(pf, ICE_F_GCS) && + ((features & NETIF_F_HW_CSUM) && (features & NETIF_F_ALL_TSO))) { + if (netdev->features & NETIF_F_HW_CSUM) + dev_err(ice_pf_to_dev(pf), "To enable TSO, you must first disable HW checksum.\n"); + else + dev_err(ice_pf_to_dev(pf), "To enable HW checksum, you must first disable TSO.\n"); + return -EIO; + } + return ret; } @@ -6146,24 +6594,21 @@ static int ice_vsi_vlan_setup(struct ice_vsi *vsi) } /** - * ice_vsi_cfg - Setup the VSI + * ice_vsi_cfg_lan - Setup the VSI lan related config * @vsi: the VSI being configured * * Return 0 on success and negative value on error */ -int ice_vsi_cfg(struct ice_vsi *vsi) +int ice_vsi_cfg_lan(struct ice_vsi *vsi) { int err; - if (vsi->netdev) { + if (vsi->netdev && vsi->type == ICE_VSI_PF) { ice_set_rx_mode(vsi->netdev); - if (vsi->type != ICE_VSI_LB) { - err = ice_vsi_vlan_setup(vsi); - - if (err) - return err; - } + err = ice_vsi_vlan_setup(vsi); + if (err) + return err; } ice_vsi_cfg_dcb_rings(vsi); @@ -6221,7 +6666,7 @@ static void ice_tx_dim_work(struct work_struct *work) u16 itr; dim = container_of(work, struct dim, work); - rc = (struct ice_ring_container *)dim->priv; + rc = dim->priv; WARN_ON(dim->profile_ix >= ARRAY_SIZE(tx_profile)); @@ -6241,7 +6686,7 @@ static void ice_rx_dim_work(struct work_struct *work) u16 itr; dim = container_of(work, struct dim, work); - rc = (struct ice_ring_container *)dim->priv; + rc = dim->priv; WARN_ON(dim->profile_ix >= ARRAY_SIZE(rx_profile)); @@ -6344,18 +6789,21 @@ static int ice_up_complete(struct ice_vsi *vsi) if (vsi->port_info && (vsi->port_info->phy.link_info.link_info & ICE_AQ_LINK_UP) && - vsi->netdev) { + ((vsi->netdev && (vsi->type == ICE_VSI_PF || + vsi->type == ICE_VSI_SF)))) { ice_print_link_msg(vsi, true); netif_tx_start_all_queues(vsi->netdev); netif_carrier_on(vsi->netdev); - ice_ptp_link_change(pf, pf->hw.pf_id, true); + ice_ptp_link_change(pf, true); } /* Perform an initial read of the statistics registers now to * set the baseline so counters are ready when interface is up */ ice_update_eth_stats(vsi); - ice_service_task_schedule(pf); + + if (vsi->type == ICE_VSI_PF) + ice_service_task_schedule(pf); return 0; } @@ -6368,7 +6816,7 @@ int ice_up(struct ice_vsi *vsi) { int err; - err = ice_vsi_cfg(vsi); + err = ice_vsi_cfg_lan(vsi); if (!err) err = ice_up_complete(vsi); @@ -6438,6 +6886,7 @@ 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; @@ -6483,21 +6932,18 @@ 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; @@ -6536,13 +6982,11 @@ 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; } @@ -6707,7 +7151,6 @@ void ice_update_pf_stats(struct ice_pf *pf) * @netdev: network interface device structure * @stats: main device statistics structure */ -static void ice_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { struct ice_netdev_priv *np = netdev_priv(netdev); @@ -6767,6 +7210,50 @@ 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 * @@ -6778,13 +7265,11 @@ 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); + ice_ptp_link_change(vsi->back, 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); @@ -6793,7 +7278,7 @@ int ice_down(struct ice_vsi *vsi) if (tx_err) netdev_err(vsi->netdev, "Failed stop Tx rings, VSI %d error %d\n", vsi->vsi_num, tx_err); - if (!tx_err && ice_is_xdp_ena_vsi(vsi)) { + if (!tx_err && vsi->xdp_rings) { tx_err = ice_vsi_stop_xdp_tx_rings(vsi); if (tx_err) netdev_err(vsi->netdev, "Failed stop XDP rings, VSI %d error %d\n", @@ -6810,6 +7295,10 @@ int ice_down(struct ice_vsi *vsi) ice_for_each_txq(vsi, i) ice_clean_tx_ring(vsi->tx_rings[i]); + if (vsi->xdp_rings) + ice_for_each_xdp_txq(vsi, i) + ice_clean_tx_ring(vsi->xdp_rings[i]); + ice_for_each_rxq(vsi, i) ice_clean_rx_ring(vsi->rx_rings[i]); @@ -6936,7 +7425,7 @@ int ice_vsi_open_ctrl(struct ice_vsi *vsi) if (err) goto err_setup_rx; - err = ice_vsi_cfg(vsi); + err = ice_vsi_cfg_lan(vsi); if (err) goto err_setup_rx; @@ -6990,7 +7479,7 @@ int ice_vsi_open(struct ice_vsi *vsi) if (err) goto err_setup_rx; - err = ice_vsi_cfg(vsi); + err = ice_vsi_cfg_lan(vsi); if (err) goto err_setup_rx; @@ -7000,9 +7489,10 @@ int ice_vsi_open(struct ice_vsi *vsi) if (err) goto err_setup_rx; - ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc); + if (bitmap_empty(pf->txtime_txqs, pf->max_pf_txqs)) + ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc); - if (vsi->type == ICE_VSI_PF) { + if (vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_SF) { /* Notify the stack of the actual queue counts. */ err = netif_set_real_num_tx_queues(vsi->netdev, vsi->num_txq); if (err) @@ -7011,6 +7501,8 @@ int ice_vsi_open(struct ice_vsi *vsi) err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_rxq); if (err) goto err_set_qs; + + ice_vsi_set_napi_queues(vsi); } err = ice_up_complete(vsi); @@ -7075,7 +7567,7 @@ static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type) continue; /* rebuild the VSI */ - err = ice_vsi_rebuild(vsi, true); + err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_INIT); if (err) { dev_err(dev, "rebuild VSI failed, err %d, VSI index %d, type %s\n", err, vsi->idx, ice_vsi_type_str(type)); @@ -7148,6 +7640,7 @@ static void ice_update_pf_netdev_link(struct ice_pf *pf) */ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) { + struct ice_vsi *vsi = ice_get_main_vsi(pf); struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; bool dvm; @@ -7251,7 +7744,7 @@ 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); @@ -7263,16 +7756,6 @@ 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)) - ice_ptp_cfg_timestamp(pf, false); - - 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; - } - if (reset_type == ICE_RESET_PFR) { err = ice_rebuild_channels(pf); if (err) { @@ -7300,6 +7783,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ice_rebuild_arfs(pf); } + if (vsi && vsi->netdev) + netif_device_attach(vsi->netdev); + ice_update_pf_netdev_link(pf); /* tell the firmware we are up */ @@ -7315,14 +7801,21 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) /* if we get here, reset flow is successful */ clear_bit(ICE_RESET_FAILED, pf->state); + ice_health_clear(pf); + ice_plug_aux_dev(pf); + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) + ice_lag_rebuild(pf); + + /* Restore timestamp mode settings after VSI rebuild */ + ice_ptp_restore_timestamp_mode(pf); return; err_vsi_rebuild: err_sched_init_port: ice_sched_cleanup_all(hw); err_init_ctrlq: - ice_shutdown_all_ctrlq(hw); + ice_shutdown_all_ctrlq(hw, false); set_bit(ICE_RESET_FAILED, pf->state); clear_recovery: /* set this bit in PF state to control service task scheduling */ @@ -7331,29 +7824,18 @@ clear_recovery: } /** - * ice_max_xdp_frame_size - returns the maximum allowed frame size for XDP - * @vsi: Pointer to VSI structure - */ -static int ice_max_xdp_frame_size(struct ice_vsi *vsi) -{ - if (PAGE_SIZE >= 8192 || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) - return ICE_RXBUF_2048 - XDP_PACKET_HEADROOM; - else - return ICE_RXBUF_3072; -} - -/** * ice_change_mtu - NDO callback to change the MTU * @netdev: network interface device structure * @new_mtu: new value for maximum frame size * * Returns 0 on success, negative on failure */ -static int ice_change_mtu(struct net_device *netdev, int new_mtu) +int ice_change_mtu(struct net_device *netdev, int new_mtu) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; + struct bpf_prog *prog; u8 count = 0; int err = 0; @@ -7362,7 +7844,8 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) return 0; } - if (ice_is_xdp_ena_vsi(vsi)) { + prog = vsi->xdp_prog; + if (prog && !prog->aux->xdp_has_frags) { int frame_size = ice_max_xdp_frame_size(vsi); if (new_mtu + ICE_ETH_PKT_HDR_PAD > frame_size) { @@ -7388,22 +7871,10 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) return -EBUSY; } - netdev->mtu = (unsigned int)new_mtu; - - /* if VSI is up, bring it down and then back up */ - if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) { - err = ice_down(vsi); - if (err) { - netdev_err(netdev, "change MTU if_down err %d\n", err); - return err; - } - - err = ice_up(vsi); - if (err) { - netdev_err(netdev, "change MTU if_up err %d\n", err); - return err; - } - } + WRITE_ONCE(netdev->mtu, (unsigned int)new_mtu); + err = ice_down_up(vsi); + if (err) + return err; netdev_dbg(netdev, "changed MTU to %d\n", new_mtu); set_bit(ICE_FLAG_MTU_CHANGED, pf->flags); @@ -7412,69 +7883,6 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) } /** - * ice_eth_ioctl - Access the hwtstamp interface - * @netdev: network interface device structure - * @ifr: interface request data - * @cmd: ioctl command - */ -static int ice_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) -{ - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; - - switch (cmd) { - case SIOCGHWTSTAMP: - return ice_ptp_get_ts_config(pf, ifr); - case SIOCSHWTSTAMP: - return ice_ptp_set_ts_config(pf, ifr); - default: - return -EOPNOTSUPP; - } -} - -/** - * ice_aq_str - convert AQ err code to a string - * @aq_err: the AQ error code to convert - */ -const char *ice_aq_str(enum ice_aq_err aq_err) -{ - switch (aq_err) { - case ICE_AQ_RC_OK: - return "OK"; - case ICE_AQ_RC_EPERM: - return "ICE_AQ_RC_EPERM"; - case ICE_AQ_RC_ENOENT: - return "ICE_AQ_RC_ENOENT"; - case ICE_AQ_RC_ENOMEM: - return "ICE_AQ_RC_ENOMEM"; - case ICE_AQ_RC_EBUSY: - return "ICE_AQ_RC_EBUSY"; - case ICE_AQ_RC_EEXIST: - return "ICE_AQ_RC_EEXIST"; - case ICE_AQ_RC_EINVAL: - return "ICE_AQ_RC_EINVAL"; - case ICE_AQ_RC_ENOSPC: - return "ICE_AQ_RC_ENOSPC"; - case ICE_AQ_RC_ENOSYS: - return "ICE_AQ_RC_ENOSYS"; - case ICE_AQ_RC_EMODE: - return "ICE_AQ_RC_EMODE"; - case ICE_AQ_RC_ENOSEC: - return "ICE_AQ_RC_ENOSEC"; - case ICE_AQ_RC_EBADSIG: - return "ICE_AQ_RC_EBADSIG"; - case ICE_AQ_RC_ESVN: - return "ICE_AQ_RC_ESVN"; - case ICE_AQ_RC_EBADMAN: - return "ICE_AQ_RC_EBADMAN"; - case ICE_AQ_RC_EBADBUF: - return "ICE_AQ_RC_EBADBUF"; - } - - return "ICE_AQ_RC_UNKNOWN"; -} - -/** * ice_set_rss_lut - Set RSS LUT * @vsi: Pointer to VSI structure * @lut: Lookup table @@ -7499,7 +7907,7 @@ int ice_set_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size) status = ice_aq_set_rss_lut(hw, ¶ms); if (status) dev_err(ice_pf_to_dev(vsi->back), "Cannot set RSS lut, err %d aq_err %s\n", - status, ice_aq_str(hw->adminq.sq_last_status)); + status, libie_aq_str(hw->adminq.sq_last_status)); return status; } @@ -7522,7 +7930,7 @@ int ice_set_rss_key(struct ice_vsi *vsi, u8 *seed) status = ice_aq_set_rss_key(hw, vsi->idx, (struct ice_aqc_get_set_rss_keys *)seed); if (status) dev_err(ice_pf_to_dev(vsi->back), "Cannot set RSS key, err %d aq_err %s\n", - status, ice_aq_str(hw->adminq.sq_last_status)); + status, libie_aq_str(hw->adminq.sq_last_status)); return status; } @@ -7552,7 +7960,7 @@ int ice_get_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size) status = ice_aq_get_rss_lut(hw, ¶ms); if (status) dev_err(ice_pf_to_dev(vsi->back), "Cannot get RSS lut, err %d aq_err %s\n", - status, ice_aq_str(hw->adminq.sq_last_status)); + status, libie_aq_str(hw->adminq.sq_last_status)); return status; } @@ -7575,12 +7983,65 @@ int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed) status = ice_aq_get_rss_key(hw, vsi->idx, (struct ice_aqc_get_set_rss_keys *)seed); if (status) dev_err(ice_pf_to_dev(vsi->back), "Cannot get RSS key, err %d aq_err %s\n", - status, ice_aq_str(hw->adminq.sq_last_status)); + status, libie_aq_str(hw->adminq.sq_last_status)); return status; } /** + * 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 @@ -7595,9 +8056,7 @@ static int ice_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags) { - struct ice_netdev_priv *np = netdev_priv(dev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(dev); u16 bmode; bmode = pf->first_sw->bridge_mode; @@ -7639,7 +8098,7 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode) ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (ret) { dev_err(ice_pf_to_dev(vsi->back), "update VSI for bridge mode failed, bmode = %d err %d aq_err %s\n", - bmode, ret, ice_aq_str(hw->adminq.sq_last_status)); + bmode, ret, libie_aq_str(hw->adminq.sq_last_status)); goto out; } /* Update sw flags for book keeping */ @@ -7667,8 +8126,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 __always_unused flags, struct netlink_ext_ack __always_unused *extack) { - struct ice_netdev_priv *np = netdev_priv(dev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(dev); struct nlattr *attr, *br_spec; struct ice_hw *hw = &pf->hw; struct ice_sw *pf_sw; @@ -7677,13 +8135,12 @@ 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 */ @@ -7708,7 +8165,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, if (err) { netdev_err(dev, "switch rule update failed, mode = %d err %d aq_err %s\n", mode, err, - ice_aq_str(hw->adminq.sq_last_status)); + libie_aq_str(hw->adminq.sq_last_status)); /* revert hw->evb_veb */ hw->evb_veb = (pf_sw->bridge_mode == BRIDGE_MODE_VEB); return err; @@ -7725,7 +8182,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, * @netdev: network interface device structure * @txqueue: Tx queue */ -static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) +void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_tx_ring *tx_ring = NULL; @@ -7764,16 +8221,18 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) if (tx_ring) { struct ice_hw *hw = &pf->hw; - u32 head, val = 0; + u32 head, intr = 0; - head = (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)); + intr = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx)); netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %u, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n", vsi->vsi_num, txqueue, tx_ring->next_to_clean, - head, tx_ring->next_to_use, val); + head, tx_ring->next_to_use, intr); + + ice_prep_tx_hang_report(pf, tx_ring, vsi->vsi_num, head, intr); } pf->tx_timeout_last_recovery = jiffies; @@ -7807,11 +8266,16 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) * @np: net device to configure * @filter_dev: device on which filter is added * @cls_flower: offload data + * @ingress: if the rule is added to an ingress block + * + * Return: 0 if the flower was successfully added or deleted, + * negative error code otherwise. */ static int ice_setup_tc_cls_flower(struct ice_netdev_priv *np, struct net_device *filter_dev, - struct flow_cls_offload *cls_flower) + struct flow_cls_offload *cls_flower, + bool ingress) { struct ice_vsi *vsi = np->vsi; @@ -7820,7 +8284,7 @@ ice_setup_tc_cls_flower(struct ice_netdev_priv *np, switch (cls_flower->command) { case FLOW_CLS_REPLACE: - return ice_add_cls_flower(filter_dev, vsi, cls_flower); + return ice_add_cls_flower(filter_dev, vsi, cls_flower, ingress); case FLOW_CLS_DESTROY: return ice_del_cls_flower(vsi, cls_flower); default: @@ -7829,20 +8293,46 @@ ice_setup_tc_cls_flower(struct ice_netdev_priv *np, } /** - * ice_setup_tc_block_cb - callback handler registered for TC block + * ice_setup_tc_block_cb_ingress - callback handler for ingress TC block * @type: TC SETUP type * @type_data: TC flower offload data that contains user input * @cb_priv: netdev private data + * + * Return: 0 if the setup was successful, negative error code otherwise. */ static int -ice_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) +ice_setup_tc_block_cb_ingress(enum tc_setup_type type, void *type_data, + void *cb_priv) { struct ice_netdev_priv *np = cb_priv; switch (type) { case TC_SETUP_CLSFLOWER: return ice_setup_tc_cls_flower(np, np->vsi->netdev, - type_data); + type_data, true); + default: + return -EOPNOTSUPP; + } +} + +/** + * ice_setup_tc_block_cb_egress - callback handler for egress TC block + * @type: TC SETUP type + * @type_data: TC flower offload data that contains user input + * @cb_priv: netdev private data + * + * Return: 0 if the setup was successful, negative error code otherwise. + */ +static int +ice_setup_tc_block_cb_egress(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct ice_netdev_priv *np = cb_priv; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return ice_setup_tc_cls_flower(np, np->vsi->netdev, + type_data, false); default: return -EOPNOTSUPP; } @@ -7861,10 +8351,10 @@ static int ice_validate_mqprio_qopt(struct ice_vsi *vsi, struct tc_mqprio_qopt_offload *mqprio_qopt) { - u64 sum_max_rate = 0, sum_min_rate = 0; int non_power_of_2_qcount = 0; struct ice_pf *pf = vsi->back; int max_rss_q_cnt = 0; + u64 sum_min_rate = 0; struct device *dev; int i, speed; u8 num_tc; @@ -7880,6 +8370,7 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi, dev = ice_pf_to_dev(pf); vsi->ch_rss_size = 0; num_tc = mqprio_qopt->qopt.num_tc; + speed = ice_get_link_speed_kbps(vsi); for (i = 0; num_tc; i++) { int qcount = mqprio_qopt->qopt.count[i]; @@ -7920,7 +8411,6 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi, */ max_rate = mqprio_qopt->max_rate[i]; max_rate = div_u64(max_rate, ICE_BW_KBPS_DIVISOR); - sum_max_rate += max_rate; /* min_rate is minimum guaranteed rate and it can't be zero */ min_rate = mqprio_qopt->min_rate[i]; @@ -7933,6 +8423,12 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi, return -EINVAL; } + if (max_rate && max_rate > speed) { + dev_err(dev, "TC%d: max_rate(%llu Kbps) > link speed of %u Kbps\n", + i, max_rate, speed); + return -EINVAL; + } + iter_div_u64_rem(min_rate, ICE_MIN_BW_LIMIT, &rem); if (rem) { dev_err(dev, "TC%d: Min Rate not multiple of %u Kbps", @@ -7970,12 +8466,6 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi, (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) return -EINVAL; - speed = ice_get_link_speed_kbps(vsi); - if (sum_max_rate && sum_max_rate > (u64)speed) { - dev_err(dev, "Invalid max Tx rate(%llu) Kbps > speed(%u) Kbps specified\n", - sum_max_rate, speed); - return -EINVAL; - } if (sum_min_rate && sum_min_rate > (u64)speed) { dev_err(dev, "Invalid min Tx rate(%llu) Kbps > speed (%u) Kbps specified\n", sum_min_rate, speed); @@ -8015,13 +8505,12 @@ 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); @@ -8420,12 +8909,9 @@ static void ice_remove_q_channels(struct ice_vsi *vsi, bool rem_fltr) /* clear the VSI from scheduler tree */ ice_rm_vsi_lan_cfg(ch->ch_vsi->port_info, ch->ch_vsi->idx); - /* Delete VSI from FW */ + /* Delete VSI from FW, PF and HW VSI arrays */ ice_vsi_delete(ch->ch_vsi); - /* Delete VSI from PF and HW VSI arrays */ - ice_vsi_clear(ch->ch_vsi); - /* free the channel */ kfree(ch); } @@ -8484,7 +8970,7 @@ static int ice_rebuild_channels(struct ice_pf *pf) type = vsi->type; /* rebuild ADQ VSI */ - err = ice_vsi_rebuild(vsi, true); + err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_INIT); if (err) { dev_err(dev, "VSI (type:%s) at index %d rebuild failed, err %d\n", ice_vsi_type_str(type), vsi->idx, err); @@ -8599,7 +9085,7 @@ static int ice_create_q_channels(struct ice_vsi *vsi) list_add_tail(&ch->list, &vsi->ch_list); vsi->tc_map_vsi[i] = ch->ch_vsi; dev_dbg(ice_pf_to_dev(pf), - "successfully created channel: VSI %pK\n", ch->ch_vsi); + "successfully created channel: VSI %p\n", ch->ch_vsi); } return 0; @@ -8716,14 +9202,14 @@ config_tcf: cur_rxq = vsi->num_rxq; /* proceed with rebuild main VSI using correct number of queues */ - ret = ice_vsi_rebuild(vsi, false); + ret = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); if (ret) { /* fallback to current number of queues */ dev_info(dev, "Rebuild failed with new queues, try with current number of queues\n"); vsi->req_txq = cur_txq; vsi->req_rxq = cur_rxq; clear_bit(ICE_RESET_FAILED, pf->state); - if (ice_vsi_rebuild(vsi, false)) { + if (ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT)) { dev_err(dev, "Rebuild of main VSI failed again\n"); return ret; } @@ -8784,6 +9270,96 @@ exit: return ret; } +/** + * ice_cfg_txtime - configure Tx Time for the Tx ring + * @tx_ring: pointer to the Tx ring structure + * + * Return: 0 on success, negative value on failure. + */ +static int ice_cfg_txtime(struct ice_tx_ring *tx_ring) +{ + int err, timeout = 50; + struct ice_vsi *vsi; + struct device *dev; + struct ice_pf *pf; + u32 queue; + + if (!tx_ring) + return -EINVAL; + + vsi = tx_ring->vsi; + pf = vsi->back; + while (test_and_set_bit(ICE_CFG_BUSY, pf->state)) { + timeout--; + if (!timeout) + return -EBUSY; + usleep_range(1000, 2000); + } + + queue = tx_ring->q_index; + dev = ice_pf_to_dev(pf); + + /* Ignore return value, and always attempt to enable queue. */ + ice_qp_dis(vsi, queue); + + err = ice_qp_ena(vsi, queue); + if (err) + dev_err(dev, "Failed to enable Tx queue %d for TxTime configuration\n", + queue); + + clear_bit(ICE_CFG_BUSY, pf->state); + return err; +} + +/** + * ice_offload_txtime - set earliest TxTime first + * @netdev: network interface device structure + * @qopt_off: etf queue option offload from the skb to set + * + * Return: 0 on success, negative value on failure. + */ +static int ice_offload_txtime(struct net_device *netdev, + void *qopt_off) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; + struct tc_etf_qopt_offload *qopt; + struct ice_vsi *vsi = np->vsi; + struct ice_tx_ring *tx_ring; + int ret = 0; + + if (!ice_is_feature_supported(pf, ICE_F_TXTIME)) + return -EOPNOTSUPP; + + qopt = qopt_off; + if (!qopt_off || qopt->queue < 0 || qopt->queue >= vsi->num_txq) + return -EINVAL; + + if (qopt->enable) + set_bit(qopt->queue, pf->txtime_txqs); + else + clear_bit(qopt->queue, pf->txtime_txqs); + + if (netif_running(vsi->netdev)) { + tx_ring = vsi->tx_rings[qopt->queue]; + ret = ice_cfg_txtime(tx_ring); + if (ret) + goto err; + } + + netdev_info(netdev, "%s TxTime on queue: %i\n", + str_enable_disable(qopt->enable), qopt->queue); + return 0; + +err: + netdev_err(netdev, "Failed to %s TxTime on queue: %i\n", + str_enable_disable(qopt->enable), qopt->queue); + + if (qopt->enable) + clear_bit(qopt->queue, pf->txtime_txqs); + return ret; +} + static LIST_HEAD(ice_block_cb_list); static int @@ -8791,21 +9367,64 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, void *type_data) { struct ice_netdev_priv *np = netdev_priv(netdev); + enum flow_block_binder_type binder_type; + struct iidc_rdma_core_dev_info *cdev; struct ice_pf *pf = np->vsi->back; + flow_setup_cb_t *flower_handler; + bool locked = false; int err; switch (type) { case TC_SETUP_BLOCK: + binder_type = + ((struct flow_block_offload *)type_data)->binder_type; + + switch (binder_type) { + case FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS: + flower_handler = ice_setup_tc_block_cb_ingress; + break; + case FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS: + flower_handler = ice_setup_tc_block_cb_egress; + break; + default: + return -EOPNOTSUPP; + } + return flow_block_cb_setup_simple(type_data, &ice_block_cb_list, - ice_setup_tc_block_cb, - np, np, true); + flower_handler, + np, np, false); case TC_SETUP_QDISC_MQPRIO: + if (ice_is_eswitch_mode_switchdev(pf)) { + netdev_err(netdev, "TC MQPRIO offload not supported, switchdev is enabled\n"); + return -EOPNOTSUPP; + } + + cdev = pf->cdev_info; + if (cdev && cdev->adev) { + mutex_lock(&pf->adev_mutex); + device_lock(&cdev->adev->dev); + locked = true; + if (cdev->adev->dev.driver) { + netdev_err(netdev, "Cannot change qdisc when RDMA is active\n"); + err = -EBUSY; + goto adev_unlock; + } + } + /* setup traffic classifier for receive side */ mutex_lock(&pf->tc_mutex); err = ice_setup_tc_mqprio_qdisc(netdev, type_data); mutex_unlock(&pf->tc_mutex); + +adev_unlock: + if (locked) { + device_unlock(&cdev->adev->dev); + mutex_unlock(&pf->adev_mutex); + } return err; + case TC_SETUP_QDISC_ETF: + return ice_offload_txtime(netdev, type_data); default: return -EOPNOTSUPP; } @@ -8838,7 +9457,7 @@ ice_indr_setup_block_cb(enum tc_setup_type type, void *type_data, case TC_SETUP_CLSFLOWER: return ice_setup_tc_cls_flower(np, priv->netdev, (struct flow_cls_offload *) - type_data); + type_data, false); default: return -EOPNOTSUPP; } @@ -8941,8 +9560,7 @@ ice_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, */ int ice_open(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); if (ice_is_reset_in_progress(pf->state)) { netdev_err(netdev, "can't open net device while reset is in progress"); @@ -9044,8 +9662,14 @@ 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; } } @@ -9139,7 +9763,6 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_change_mtu = ice_change_mtu, .ndo_get_stats64 = ice_get_stats64, .ndo_set_tx_maxrate = ice_set_tx_maxrate, - .ndo_eth_ioctl = ice_eth_ioctl, .ndo_set_vf_spoofchk = ice_set_vf_spoofchk, .ndo_set_vf_mac = ice_set_vf_mac, .ndo_get_vf_config = ice_get_vf_cfg, @@ -9163,4 +9786,6 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_bpf = ice_xdp, .ndo_xdp_xmit = ice_xdp_xmit, .ndo_xsk_wakeup = ice_xsk_wakeup, + .ndo_hwtstamp_get = ice_ptp_hwtstamp_get, + .ndo_hwtstamp_set = ice_ptp_hwtstamp_set, }; |