diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
33 files changed, 736 insertions, 364 deletions
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 5039a2536951..0bf3d47bb90d 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -3003,9 +3003,10 @@ static void __e100_shutdown(struct pci_dev *pdev, bool *enable_wake) struct net_device *netdev = pci_get_drvdata(pdev); struct nic *nic = netdev_priv(netdev); + netif_device_detach(netdev); + if (netif_running(netdev)) e100_down(nic); - netif_device_detach(netdev); if ((nic->flags & wol_magic) | e100_asf(nic)) { /* enable reverse auto-negotiation */ @@ -3022,7 +3023,7 @@ static void __e100_shutdown(struct pci_dev *pdev, bool *enable_wake) *enable_wake = false; } - pci_clear_master(pdev); + pci_disable_device(pdev); } static int __e100_power_off(struct pci_dev *pdev, bool wake) @@ -3042,8 +3043,6 @@ static int __maybe_unused e100_suspend(struct device *dev_d) __e100_shutdown(to_pci_dev(dev_d), &wake); - device_wakeup_disable(dev_d); - return 0; } @@ -3051,6 +3050,14 @@ static int __maybe_unused e100_resume(struct device *dev_d) { struct net_device *netdev = dev_get_drvdata(dev_d); struct nic *nic = netdev_priv(netdev); + int err; + + err = pci_enable_device(to_pci_dev(dev_d)); + if (err) { + netdev_err(netdev, "Resume cannot enable PCI device, aborting\n"); + return err; + } + pci_set_master(to_pci_dev(dev_d)); /* disable reverse auto-negotiation */ if (nic->phy == phy_82552_v) { @@ -3062,10 +3069,11 @@ static int __maybe_unused e100_resume(struct device *dev_d) smartspeed & ~(E100_82552_REV_ANEG)); } - netif_device_attach(netdev); if (netif_running(netdev)) e100_up(nic); + netif_device_attach(netdev); + return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 3d528fba754b..4d939af0a626 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -161,6 +161,7 @@ enum i40e_vsi_state_t { __I40E_VSI_OVERFLOW_PROMISC, __I40E_VSI_REINIT_REQUESTED, __I40E_VSI_DOWN_REQUESTED, + __I40E_VSI_RELEASING, /* This must be last as it determines the size of the BITMAP */ __I40E_VSI_STATE_SIZE__, }; @@ -1247,6 +1248,7 @@ void i40e_ptp_restore_hw_time(struct i40e_pf *pf); void i40e_ptp_init(struct i40e_pf *pf); void i40e_ptp_stop(struct i40e_pf *pf); int i40e_ptp_alloc_pins(struct i40e_pf *pf); +int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset); int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi); i40e_status i40e_get_partition_bw_setting(struct i40e_pf *pf); i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf); diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 291e61ac3e44..2c1b1da1220e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -553,6 +553,14 @@ static void i40e_dbg_dump_desc(int cnt, int vsi_seid, int ring_id, int desc_n, dev_info(&pf->pdev->dev, "vsi %d not found\n", vsi_seid); return; } + if (vsi->type != I40E_VSI_MAIN && + vsi->type != I40E_VSI_FDIR && + vsi->type != I40E_VSI_VMDQ2) { + dev_info(&pf->pdev->dev, + "vsi %d type %d descriptor rings not available\n", + vsi_seid, vsi->type); + return; + } if (type == RING_TYPE_XDP && !i40e_enabled_xdp_vsi(vsi)) { dev_info(&pf->pdev->dev, "XDP not enabled on VSI %d\n", vsi_seid); return; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index ba862131b9bd..61afc220fc6c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -99,6 +99,24 @@ MODULE_LICENSE("GPL v2"); static struct workqueue_struct *i40e_wq; +static void netdev_hw_addr_refcnt(struct i40e_mac_filter *f, + struct net_device *netdev, int delta) +{ + struct netdev_hw_addr *ha; + + if (!f || !netdev) + return; + + netdev_for_each_mc_addr(ha, netdev) { + if (ether_addr_equal(ha->addr, f->macaddr)) { + ha->refcount += delta; + if (ha->refcount <= 0) + ha->refcount = 1; + break; + } + } +} + /** * i40e_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure @@ -1790,6 +1808,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, bool is_add) { struct i40e_pf *pf = vsi->back; + u16 num_tc_qps = 0; u16 sections = 0; u8 netdev_tc = 0; u16 numtc = 1; @@ -1797,13 +1816,33 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, u8 offset; u16 qmap; int i; - u16 num_tc_qps = 0; sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID; offset = 0; + /* zero out queue mapping, it will get updated on the end of the function */ + memset(ctxt->info.queue_mapping, 0, sizeof(ctxt->info.queue_mapping)); + + if (vsi->type == I40E_VSI_MAIN) { + /* This code helps add more queue to the VSI if we have + * more cores than RSS can support, the higher cores will + * be served by ATR or other filters. Furthermore, the + * non-zero req_queue_pairs says that user requested a new + * queue count via ethtool's set_channels, so use this + * value for queues distribution across traffic classes + */ + if (vsi->req_queue_pairs > 0) + vsi->num_queue_pairs = vsi->req_queue_pairs; + else if (pf->flags & I40E_FLAG_MSIX_ENABLED) + vsi->num_queue_pairs = pf->num_lan_msix; + } /* Number of queues per enabled TC */ - num_tc_qps = vsi->alloc_queue_pairs; + if (vsi->type == I40E_VSI_MAIN || + (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs != 0)) + num_tc_qps = vsi->num_queue_pairs; + else + num_tc_qps = vsi->alloc_queue_pairs; + if (enabled_tc && (vsi->back->flags & I40E_FLAG_DCB_ENABLED)) { /* Find numtc from enabled TC bitmap */ for (i = 0, numtc = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { @@ -1881,15 +1920,11 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, } ctxt->info.tc_mapping[i] = cpu_to_le16(qmap); } - - /* Set actual Tx/Rx queue pairs */ - vsi->num_queue_pairs = offset; - if ((vsi->type == I40E_VSI_MAIN) && (numtc == 1)) { - if (vsi->req_queue_pairs > 0) - vsi->num_queue_pairs = vsi->req_queue_pairs; - else if (pf->flags & I40E_FLAG_MSIX_ENABLED) - vsi->num_queue_pairs = pf->num_lan_msix; - } + /* Do not change previously set num_queue_pairs for PFs and VFs*/ + if ((vsi->type == I40E_VSI_MAIN && numtc != 1) || + (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs == 0) || + (vsi->type != I40E_VSI_MAIN && vsi->type != I40E_VSI_SRIOV)) + vsi->num_queue_pairs = offset; /* Scheduler section valid can only be set for ADD VSI */ if (is_add) { @@ -2019,6 +2054,7 @@ static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi, hlist_for_each_entry_safe(new, h, from, hlist) { /* We can simply free the wrapper structure */ hlist_del(&new->hlist); + netdev_hw_addr_refcnt(new->f, vsi->netdev, -1); kfree(new); } } @@ -2366,6 +2402,10 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) &tmp_add_list, &tmp_del_list, vlan_filters); + + hlist_for_each_entry(new, &tmp_add_list, hlist) + netdev_hw_addr_refcnt(new->f, vsi->netdev, 1); + if (retval) goto err_no_memory_locked; @@ -2498,6 +2538,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) if (new->f->state == I40E_FILTER_NEW) new->f->state = new->state; hlist_del(&new->hlist); + netdev_hw_addr_refcnt(new->f, vsi->netdev, -1); kfree(new); } spin_unlock_bh(&vsi->mac_filter_hash_lock); @@ -2623,7 +2664,8 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v] && - (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED)) { + (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED) && + !test_bit(__I40E_VSI_RELEASING, pf->vsi[v]->state)) { int ret = i40e_sync_vsi_filters(pf->vsi[v]); if (ret) { @@ -5427,6 +5469,58 @@ static void i40e_vsi_update_queue_map(struct i40e_vsi *vsi, } /** + * i40e_update_adq_vsi_queues - update queue mapping for ADq VSI + * @vsi: the VSI being reconfigured + * @vsi_offset: offset from main VF VSI + */ +int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset) +{ + struct i40e_vsi_context ctxt = {}; + struct i40e_pf *pf; + struct i40e_hw *hw; + int ret; + + if (!vsi) + return I40E_ERR_PARAM; + pf = vsi->back; + hw = &pf->hw; + + ctxt.seid = vsi->seid; + ctxt.pf_num = hw->pf_id; + ctxt.vf_num = vsi->vf_id + hw->func_caps.vf_base_id + vsi_offset; + ctxt.uplink_seid = vsi->uplink_seid; + ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL; + ctxt.flags = I40E_AQ_VSI_TYPE_VF; + ctxt.info = vsi->info; + + i40e_vsi_setup_queue_map(vsi, &ctxt, vsi->tc_config.enabled_tc, + false); + if (vsi->reconfig_rss) { + vsi->rss_size = min_t(int, pf->alloc_rss_size, + vsi->num_queue_pairs); + ret = i40e_vsi_config_rss(vsi); + if (ret) { + dev_info(&pf->pdev->dev, "Failed to reconfig rss for num_queues\n"); + return ret; + } + vsi->reconfig_rss = false; + } + + ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL); + if (ret) { + dev_info(&pf->pdev->dev, "Update vsi config failed, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return ret; + } + /* update the local VSI info with updated queue map */ + i40e_vsi_update_queue_map(vsi, &ctxt); + vsi->info.valid_sections = 0; + + return ret; +} + +/** * i40e_vsi_config_tc - Configure VSI Tx Scheduler for given TC map * @vsi: VSI to be configured * @enabled_tc: TC bitmap @@ -5717,24 +5811,6 @@ static void i40e_remove_queue_channels(struct i40e_vsi *vsi) } /** - * i40e_is_any_channel - channel exist or not - * @vsi: ptr to VSI to which channels are associated with - * - * Returns true or false if channel(s) exist for associated VSI or not - **/ -static bool i40e_is_any_channel(struct i40e_vsi *vsi) -{ - struct i40e_channel *ch, *ch_tmp; - - list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { - if (ch->initialized) - return true; - } - - return false; -} - -/** * i40e_get_max_queues_for_channel * @vsi: ptr to VSI to which channels are associated with * @@ -6240,26 +6316,15 @@ int i40e_create_queue_channel(struct i40e_vsi *vsi, /* By default we are in VEPA mode, if this is the first VF/VMDq * VSI to be added switch to VEB mode. */ - if ((!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) || - (!i40e_is_any_channel(vsi))) { - if (!is_power_of_2(vsi->tc_config.tc_info[0].qcount)) { - dev_dbg(&pf->pdev->dev, - "Failed to create channel. Override queues (%u) not power of 2\n", - vsi->tc_config.tc_info[0].qcount); - return -EINVAL; - } - if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { - pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; + if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { + pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; - if (vsi->type == I40E_VSI_MAIN) { - if (pf->flags & I40E_FLAG_TC_MQPRIO) - i40e_do_reset(pf, I40E_PF_RESET_FLAG, - true); - else - i40e_do_reset_safe(pf, - I40E_PF_RESET_FLAG); - } + if (vsi->type == I40E_VSI_MAIN) { + if (pf->flags & I40E_FLAG_TC_MQPRIO) + i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); + else + i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } /* now onwards for main VSI, number of queues will be value * of TC0's queue count @@ -7912,12 +7977,20 @@ config_tc: vsi->seid); need_reset = true; goto exit; - } else { - dev_info(&vsi->back->pdev->dev, - "Setup channel (id:%u) utilizing num_queues %d\n", - vsi->seid, vsi->tc_config.tc_info[0].qcount); + } else if (enabled_tc && + (!is_power_of_2(vsi->tc_config.tc_info[0].qcount))) { + netdev_info(netdev, + "Failed to create channel. Override queues (%u) not power of 2\n", + vsi->tc_config.tc_info[0].qcount); + ret = -EINVAL; + need_reset = true; + goto exit; } + dev_info(&vsi->back->pdev->dev, + "Setup channel (id:%u) utilizing num_queues %d\n", + vsi->seid, vsi->tc_config.tc_info[0].qcount); + if (pf->flags & I40E_FLAG_TC_MQPRIO) { if (vsi->mqprio_qopt.max_rate[0]) { u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; @@ -8482,9 +8555,8 @@ static int i40e_configure_clsflower(struct i40e_vsi *vsi, err = i40e_add_del_cloud_filter(vsi, filter, true); if (err) { - dev_err(&pf->pdev->dev, - "Failed to add cloud filter, err %s\n", - i40e_stat_str(&pf->hw, err)); + dev_err(&pf->pdev->dev, "Failed to add cloud filter, err %d\n", + err); goto err; } @@ -8669,6 +8741,27 @@ int i40e_open(struct net_device *netdev) } /** + * i40e_netif_set_realnum_tx_rx_queues - Update number of tx/rx queues + * @vsi: vsi structure + * + * This updates netdev's number of tx/rx queues + * + * Returns status of setting tx/rx queues + **/ +static int i40e_netif_set_realnum_tx_rx_queues(struct i40e_vsi *vsi) +{ + int ret; + + ret = netif_set_real_num_rx_queues(vsi->netdev, + vsi->num_queue_pairs); + if (ret) + return ret; + + return netif_set_real_num_tx_queues(vsi->netdev, + vsi->num_queue_pairs); +} + +/** * i40e_vsi_open - * @vsi: the VSI to open * @@ -8704,13 +8797,7 @@ int i40e_vsi_open(struct i40e_vsi *vsi) goto err_setup_rx; /* Notify the stack of the actual queue counts. */ - err = netif_set_real_num_tx_queues(vsi->netdev, - vsi->num_queue_pairs); - if (err) - goto err_set_queues; - - err = netif_set_real_num_rx_queues(vsi->netdev, - vsi->num_queue_pairs); + err = i40e_netif_set_realnum_tx_rx_queues(vsi); if (err) goto err_set_queues; @@ -13771,7 +13858,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi) dev_info(&pf->pdev->dev, "Can't remove PF VSI\n"); return -ENODEV; } - + set_bit(__I40E_VSI_RELEASING, vsi->state); uplink_seid = vsi->uplink_seid; if (vsi->type != I40E_VSI_SRIOV) { if (vsi->netdev_registered) { @@ -14103,6 +14190,9 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, ret = i40e_config_netdev(vsi); if (ret) goto err_netdev; + ret = i40e_netif_set_realnum_tx_rx_queues(vsi); + if (ret) + goto err_netdev; ret = register_netdev(vsi->netdev); if (ret) goto err_netdev; @@ -15403,8 +15493,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw)) - dev_info(&pdev->dev, - "The driver for the device detected a newer version of the NVM image v%u.%u than expected v%u.%u. Please install the most recent version of the network driver.\n", + dev_dbg(&pdev->dev, + "The driver for the device detected a newer version of the NVM image v%u.%u than v%u.%u.\n", hw->aq.api_maj_ver, hw->aq.api_min_ver, I40E_FW_API_VERSION_MAJOR, diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 472f56b360b8..048f1678ab8a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -183,17 +183,18 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf) /***********************misc routines*****************************/ /** - * i40e_vc_disable_vf + * i40e_vc_reset_vf * @vf: pointer to the VF info - * - * Disable the VF through a SW reset. + * @notify_vf: notify vf about reset or not + * Reset VF handler. **/ -static inline void i40e_vc_disable_vf(struct i40e_vf *vf) +static void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf) { struct i40e_pf *pf = vf->pf; int i; - i40e_vc_notify_vf_reset(vf); + if (notify_vf) + i40e_vc_notify_vf_reset(vf); /* We want to ensure that an actual reset occurs initiated after this * function was called. However, we do not want to wait forever, so @@ -211,9 +212,14 @@ static inline void i40e_vc_disable_vf(struct i40e_vf *vf) usleep_range(10000, 20000); } - dev_warn(&vf->pf->pdev->dev, - "Failed to initiate reset for VF %d after 200 milliseconds\n", - vf->vf_id); + if (notify_vf) + dev_warn(&vf->pf->pdev->dev, + "Failed to initiate reset for VF %d after 200 milliseconds\n", + vf->vf_id); + else + dev_dbg(&vf->pf->pdev->dev, + "Failed to initiate reset for VF %d after 200 milliseconds\n", + vf->vf_id); } /** @@ -674,14 +680,13 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id, u16 vsi_queue_id, struct virtchnl_rxq_info *info) { + u16 pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id); struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = pf->vsi[vf->lan_vsi_idx]; struct i40e_hw *hw = &pf->hw; struct i40e_hmc_obj_rxq rx_ctx; - u16 pf_queue_id; int ret = 0; - pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id); - /* clear the context structure first */ memset(&rx_ctx, 0, sizeof(struct i40e_hmc_obj_rxq)); @@ -719,6 +724,10 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id, } rx_ctx.rxmax = info->max_pkt_size; + /* if port VLAN is configured increase the max packet size */ + if (vsi->info.pvid) + rx_ctx.rxmax += VLAN_HLEN; + /* enable 32bytes desc always */ rx_ctx.dsize = 1; @@ -1868,17 +1877,19 @@ sriov_configure_out: /***********************virtual channel routines******************/ /** - * i40e_vc_send_msg_to_vf + * i40e_vc_send_msg_to_vf_ex * @vf: pointer to the VF info * @v_opcode: virtual channel opcode * @v_retval: virtual channel return value * @msg: pointer to the msg buffer * @msglen: msg length + * @is_quiet: true for not printing unsuccessful return values, false otherwise * * send msg to VF **/ -static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, - u32 v_retval, u8 *msg, u16 msglen) +static int i40e_vc_send_msg_to_vf_ex(struct i40e_vf *vf, u32 v_opcode, + u32 v_retval, u8 *msg, u16 msglen, + bool is_quiet) { struct i40e_pf *pf; struct i40e_hw *hw; @@ -1894,7 +1905,7 @@ static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id; /* single place to detect unsuccessful return values */ - if (v_retval) { + if (v_retval && !is_quiet) { vf->num_invalid_msgs++; dev_info(&pf->pdev->dev, "VF %d failed opcode %d, retval: %d\n", vf->vf_id, v_opcode, v_retval); @@ -1925,6 +1936,23 @@ static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, } /** + * i40e_vc_send_msg_to_vf + * @vf: pointer to the VF info + * @v_opcode: virtual channel opcode + * @v_retval: virtual channel return value + * @msg: pointer to the msg buffer + * @msglen: msg length + * + * send msg to VF + **/ +static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, + u32 v_retval, u8 *msg, u16 msglen) +{ + return i40e_vc_send_msg_to_vf_ex(vf, v_opcode, v_retval, + msg, msglen, false); +} + +/** * i40e_vc_send_resp_to_vf * @vf: pointer to the VF info * @opcode: operation code @@ -1940,6 +1968,32 @@ static int i40e_vc_send_resp_to_vf(struct i40e_vf *vf, } /** + * i40e_sync_vf_state + * @vf: pointer to the VF info + * @state: VF state + * + * Called from a VF message to synchronize the service with a potential + * VF reset state + **/ +static bool i40e_sync_vf_state(struct i40e_vf *vf, enum i40e_vf_states state) +{ + int i; + + /* When handling some messages, it needs VF state to be set. + * It is possible that this flag is cleared during VF reset, + * so there is a need to wait until the end of the reset to + * handle the request message correctly. + */ + for (i = 0; i < I40E_VF_STATE_WAIT_COUNT; i++) { + if (test_bit(state, &vf->vf_states)) + return true; + usleep_range(10000, 20000); + } + + return test_bit(state, &vf->vf_states); +} + +/** * i40e_vc_get_version_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1999,7 +2053,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) size_t len = 0; int ret; - if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_INIT)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -2106,20 +2160,6 @@ err: } /** - * i40e_vc_reset_vf_msg - * @vf: pointer to the VF info - * - * called from the VF to reset itself, - * unlike other virtchnl messages, PF driver - * doesn't send the response back to the VF - **/ -static void i40e_vc_reset_vf_msg(struct i40e_vf *vf) -{ - if (test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) - i40e_reset_vf(vf, false); -} - -/** * i40e_vc_config_promiscuous_mode_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -2136,7 +2176,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg) bool allmulti = false; bool alluni = false; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err_out; } @@ -2217,13 +2257,14 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) struct virtchnl_vsi_queue_config_info *qci = (struct virtchnl_vsi_queue_config_info *)msg; struct virtchnl_queue_pair_info *qpi; - struct i40e_pf *pf = vf->pf; u16 vsi_id, vsi_queue_id = 0; - u16 num_qps_all = 0; + struct i40e_pf *pf = vf->pf; i40e_status aq_ret = 0; int i, j = 0, idx = 0; + struct i40e_vsi *vsi; + u16 num_qps_all = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -2310,9 +2351,15 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) pf->vsi[vf->lan_vsi_idx]->num_queue_pairs = qci->num_queue_pairs; } else { - for (i = 0; i < vf->num_tc; i++) - pf->vsi[vf->ch[i].vsi_idx]->num_queue_pairs = - vf->ch[i].num_qps; + for (i = 0; i < vf->num_tc; i++) { + vsi = pf->vsi[vf->ch[i].vsi_idx]; + vsi->num_queue_pairs = vf->ch[i].num_qps; + + if (i40e_update_adq_vsi_queues(vsi, i)) { + aq_ret = I40E_ERR_CONFIG; + goto error_param; + } + } } error_param: @@ -2366,7 +2413,7 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; int i; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -2538,7 +2585,7 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg) struct i40e_pf *pf = vf->pf; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -2588,7 +2635,7 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg) u8 cur_pairs = vf->num_queue_pairs; struct i40e_pf *pf = vf->pf; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) return -EINVAL; if (req_pairs > I40E_MAX_VF_QUEUES) { @@ -2607,8 +2654,7 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg) } else { /* successful request */ vf->num_req_queues = req_pairs; - i40e_vc_notify_vf_reset(vf); - i40e_reset_vf(vf, false); + i40e_vc_reset_vf(vf, true); return 0; } @@ -2634,7 +2680,7 @@ static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg) memset(&stats, 0, sizeof(struct i40e_eth_stats)); - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -2668,6 +2714,7 @@ error_param: * i40e_check_vf_permission * @vf: pointer to the VF info * @al: MAC address list from virtchnl + * @is_quiet: set true for printing msg without opcode info, false otherwise * * Check that the given list of MAC addresses is allowed. Will return -EPERM * if any address in the list is not valid. Checks the following conditions: @@ -2682,13 +2729,15 @@ error_param: * addresses might not be accurate. **/ static inline int i40e_check_vf_permission(struct i40e_vf *vf, - struct virtchnl_ether_addr_list *al) + struct virtchnl_ether_addr_list *al, + bool *is_quiet) { struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = pf->vsi[vf->lan_vsi_idx]; int mac2add_cnt = 0; int i; + *is_quiet = false; for (i = 0; i < al->num_elements; i++) { struct i40e_mac_filter *f; u8 *addr = al->list[i].addr; @@ -2712,6 +2761,7 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, !ether_addr_equal(addr, vf->default_lan_addr.addr)) { dev_err(&pf->pdev->dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); + *is_quiet = true; return -EPERM; } @@ -2748,10 +2798,11 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) (struct virtchnl_ether_addr_list *)msg; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; + bool is_quiet = false; i40e_status ret = 0; int i; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) { ret = I40E_ERR_PARAM; goto error_param; @@ -2764,7 +2815,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) */ spin_lock_bh(&vsi->mac_filter_hash_lock); - ret = i40e_check_vf_permission(vf, al); + ret = i40e_check_vf_permission(vf, al, &is_quiet); if (ret) { spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; @@ -2802,8 +2853,8 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) error_param: /* send the response to the VF */ - return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ADD_ETH_ADDR, - ret); + return i40e_vc_send_msg_to_vf_ex(vf, VIRTCHNL_OP_ADD_ETH_ADDR, + ret, NULL, 0, is_quiet); } /** @@ -2823,7 +2874,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) i40e_status ret = 0; int i; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) { ret = I40E_ERR_PARAM; goto error_param; @@ -2967,7 +3018,7 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; int i; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, vfl->vsi_id)) { aq_ret = I40E_ERR_PARAM; goto error_param; @@ -3087,9 +3138,9 @@ static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg) struct i40e_vsi *vsi = NULL; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, vrk->vsi_id) || - (vrk->key_len != I40E_HKEY_ARRAY_SIZE)) { + vrk->key_len != I40E_HKEY_ARRAY_SIZE) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3118,9 +3169,9 @@ static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; u16 i; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, vrl->vsi_id) || - (vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE)) { + vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3153,7 +3204,7 @@ static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; int len = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3189,7 +3240,7 @@ static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg) struct i40e_hw *hw = &pf->hw; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3214,7 +3265,7 @@ static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; struct i40e_vsi *vsi; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3240,7 +3291,7 @@ static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; struct i40e_vsi *vsi; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3467,7 +3518,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; int i, ret; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3598,7 +3649,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; int i, ret; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err_out; } @@ -3707,7 +3758,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; u64 speed = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3796,15 +3847,9 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) /* set this flag only after making sure all inputs are sane */ vf->adq_enabled = true; - /* num_req_queues is set when user changes number of queues via ethtool - * and this causes issue for default VSI(which depends on this variable) - * when ADq is enabled, hence reset it. - */ - vf->num_req_queues = 0; /* reset the VF in order to allocate resources */ - i40e_vc_notify_vf_reset(vf); - i40e_reset_vf(vf, false); + i40e_vc_reset_vf(vf, true); return I40E_SUCCESS; @@ -3824,7 +3869,7 @@ static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg) struct i40e_pf *pf = vf->pf; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3844,8 +3889,7 @@ static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg) } /* reset the VF in order to allocate resources */ - i40e_vc_notify_vf_reset(vf); - i40e_reset_vf(vf, false); + i40e_vc_reset_vf(vf, true); return I40E_SUCCESS; @@ -3907,7 +3951,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, i40e_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: - i40e_vc_reset_vf_msg(vf); + i40e_vc_reset_vf(vf, false); ret = 0; break; case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE: @@ -4161,7 +4205,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) /* Force the VF interface down so it has to bring up with new MAC * address */ - i40e_vc_disable_vf(vf); + i40e_vc_reset_vf(vf, true); dev_info(&pf->pdev->dev, "Bring down and up the VF interface to make this change effective.\n"); error_param: @@ -4170,34 +4214,6 @@ error_param: } /** - * i40e_vsi_has_vlans - True if VSI has configured VLANs - * @vsi: pointer to the vsi - * - * Check if a VSI has configured any VLANs. False if we have a port VLAN or if - * we have no configured VLANs. Do not call while holding the - * mac_filter_hash_lock. - */ -static bool i40e_vsi_has_vlans(struct i40e_vsi *vsi) -{ - bool have_vlans; - - /* If we have a port VLAN, then the VSI cannot have any VLANs - * configured, as all MAC/VLAN filters will be assigned to the PVID. - */ - if (vsi->info.pvid) - return false; - - /* Since we don't have a PVID, we know that if the device is in VLAN - * mode it must be because of a VLAN filter configured on this VSI. - */ - spin_lock_bh(&vsi->mac_filter_hash_lock); - have_vlans = i40e_is_vsi_in_vlan(vsi); - spin_unlock_bh(&vsi->mac_filter_hash_lock); - - return have_vlans; -} - -/** * i40e_ndo_set_vf_port_vlan * @netdev: network interface device structure * @vf_id: VF identifier @@ -4253,19 +4269,9 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, /* duplicate request, so just return success */ goto error_pvid; - if (i40e_vsi_has_vlans(vsi)) { - dev_err(&pf->pdev->dev, - "VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n", - vf_id); - /* Administrator Error - knock the VF offline until he does - * the right thing by reconfiguring his network correctly - * and then reloading the VF driver. - */ - i40e_vc_disable_vf(vf); - /* During reset the VF got a new VSI, so refresh the pointer. */ - vsi = pf->vsi[vf->lan_vsi_idx]; - } - + i40e_vc_reset_vf(vf, true); + /* During reset the VF got a new VSI, so refresh a pointer. */ + vsi = pf->vsi[vf->lan_vsi_idx]; /* Locked once because multiple functions below iterate list */ spin_lock_bh(&vsi->mac_filter_hash_lock); @@ -4641,7 +4647,7 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting) goto out; vf->trusted = setting; - i40e_vc_disable_vf(vf); + i40e_vc_reset_vf(vf, true); dev_info(&pf->pdev->dev, "VF %u is now %strusted\n", vf_id, setting ? "" : "un"); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 091e32c1bb46..49575a640a84 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -18,6 +18,8 @@ #define I40E_MAX_VF_PROMISC_FLAGS 3 +#define I40E_VF_STATE_WAIT_COUNT 20 + /* Various queue ctrls */ enum i40e_queue_ctrl { I40E_QUEUE_CTRL_UNKNOWN = 0, diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index e6e7c1da47fb..3789269ce741 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -39,6 +39,7 @@ #include "iavf_txrx.h" #include "iavf_fdir.h" #include "iavf_adv_rss.h" +#include <linux/bitmap.h> #define DEFAULT_DEBUG_LEVEL_SHIFT 3 #define PFX "iavf: " @@ -304,6 +305,7 @@ struct iavf_adapter { #define IAVF_FLAG_AQ_DEL_FDIR_FILTER BIT(26) #define IAVF_FLAG_AQ_ADD_ADV_RSS_CFG BIT(27) #define IAVF_FLAG_AQ_DEL_ADV_RSS_CFG BIT(28) +#define IAVF_FLAG_AQ_REQUEST_STATS BIT(29) /* OS defined structs */ struct net_device *netdev; @@ -443,6 +445,7 @@ int iavf_up(struct iavf_adapter *adapter); void iavf_down(struct iavf_adapter *adapter); int iavf_process_config(struct iavf_adapter *adapter); void iavf_schedule_reset(struct iavf_adapter *adapter); +void iavf_schedule_request_stats(struct iavf_adapter *adapter); void iavf_reset(struct iavf_adapter *adapter); void iavf_set_ethtool_ops(struct net_device *netdev); void iavf_update_stats(struct iavf_adapter *adapter); @@ -500,4 +503,5 @@ void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter); void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter); struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, const u8 *macaddr); +int iavf_lock_timeout(struct mutex *lock, unsigned int msecs); #endif /* _IAVF_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 5a359a0a20ec..461f5237a2f8 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -354,6 +354,9 @@ static void iavf_get_ethtool_stats(struct net_device *netdev, struct iavf_adapter *adapter = netdev_priv(netdev); unsigned int i; + /* Explicitly request stats refresh */ + iavf_schedule_request_stats(adapter); + iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats); rcu_read_lock(); @@ -612,23 +615,44 @@ static int iavf_set_ringparam(struct net_device *netdev, if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) return -EINVAL; - new_tx_count = clamp_t(u32, ring->tx_pending, - IAVF_MIN_TXD, - IAVF_MAX_TXD); - new_tx_count = ALIGN(new_tx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE); + if (ring->tx_pending > IAVF_MAX_TXD || + ring->tx_pending < IAVF_MIN_TXD || + ring->rx_pending > IAVF_MAX_RXD || + ring->rx_pending < IAVF_MIN_RXD) { + netdev_err(netdev, "Descriptors requested (Tx: %d / Rx: %d) out of range [%d-%d] (increment %d)\n", + ring->tx_pending, ring->rx_pending, IAVF_MIN_TXD, + IAVF_MAX_RXD, IAVF_REQ_DESCRIPTOR_MULTIPLE); + return -EINVAL; + } + + new_tx_count = ALIGN(ring->tx_pending, IAVF_REQ_DESCRIPTOR_MULTIPLE); + if (new_tx_count != ring->tx_pending) + netdev_info(netdev, "Requested Tx descriptor count rounded up to %d\n", + new_tx_count); - new_rx_count = clamp_t(u32, ring->rx_pending, - IAVF_MIN_RXD, - IAVF_MAX_RXD); - new_rx_count = ALIGN(new_rx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE); + new_rx_count = ALIGN(ring->rx_pending, IAVF_REQ_DESCRIPTOR_MULTIPLE); + if (new_rx_count != ring->rx_pending) + netdev_info(netdev, "Requested Rx descriptor count rounded up to %d\n", + new_rx_count); /* if nothing to do return success */ if ((new_tx_count == adapter->tx_desc_count) && - (new_rx_count == adapter->rx_desc_count)) + (new_rx_count == adapter->rx_desc_count)) { + netdev_dbg(netdev, "Nothing to change, descriptor count is same as requested\n"); return 0; + } + + if (new_tx_count != adapter->tx_desc_count) { + netdev_dbg(netdev, "Changing Tx descriptor count from %d to %d\n", + adapter->tx_desc_count, new_tx_count); + adapter->tx_desc_count = new_tx_count; + } - adapter->tx_desc_count = new_tx_count; - adapter->rx_desc_count = new_rx_count; + if (new_rx_count != adapter->rx_desc_count) { + netdev_dbg(netdev, "Changing Rx descriptor count from %d to %d\n", + adapter->rx_desc_count, new_rx_count); + adapter->rx_desc_count = new_rx_count; + } if (netif_running(netdev)) { adapter->flags |= IAVF_FLAG_RESET_NEEDED; @@ -723,12 +747,31 @@ static int iavf_get_per_queue_coalesce(struct net_device *netdev, u32 queue, * * Change the ITR settings for a specific queue. **/ -static void iavf_set_itr_per_queue(struct iavf_adapter *adapter, - struct ethtool_coalesce *ec, int queue) +static int iavf_set_itr_per_queue(struct iavf_adapter *adapter, + struct ethtool_coalesce *ec, int queue) { struct iavf_ring *rx_ring = &adapter->rx_rings[queue]; struct iavf_ring *tx_ring = &adapter->tx_rings[queue]; struct iavf_q_vector *q_vector; + u16 itr_setting; + + itr_setting = rx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + + if (ec->rx_coalesce_usecs != itr_setting && + ec->use_adaptive_rx_coalesce) { + netif_info(adapter, drv, adapter->netdev, + "Rx interrupt throttling cannot be changed if adaptive-rx is enabled\n"); + return -EINVAL; + } + + itr_setting = tx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + + if (ec->tx_coalesce_usecs != itr_setting && + ec->use_adaptive_tx_coalesce) { + netif_info(adapter, drv, adapter->netdev, + "Tx interrupt throttling cannot be changed if adaptive-tx is enabled\n"); + return -EINVAL; + } rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); @@ -751,6 +794,7 @@ static void iavf_set_itr_per_queue(struct iavf_adapter *adapter, * the Tx and Rx ITR values based on the values we have entered * into the q_vector, no need to write the values now. */ + return 0; } /** @@ -792,9 +836,11 @@ static int __iavf_set_coalesce(struct net_device *netdev, */ if (queue < 0) { for (i = 0; i < adapter->num_active_queues; i++) - iavf_set_itr_per_queue(adapter, ec, i); + if (iavf_set_itr_per_queue(adapter, ec, i)) + return -EINVAL; } else if (queue < adapter->num_active_queues) { - iavf_set_itr_per_queue(adapter, ec, queue); + if (iavf_set_itr_per_queue(adapter, ec, queue)) + return -EINVAL; } else { netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", adapter->num_active_queues - 1); @@ -1776,6 +1822,7 @@ static int iavf_set_channels(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); u32 num_req = ch->combined_count; + int i; if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && adapter->num_tc) { @@ -1786,7 +1833,7 @@ static int iavf_set_channels(struct net_device *netdev, /* All of these should have already been checked by ethtool before this * even gets to us, but just to be sure. */ - if (num_req > adapter->vsi_res->num_queue_pairs) + if (num_req == 0 || num_req > adapter->vsi_res->num_queue_pairs) return -EINVAL; if (num_req == adapter->num_active_queues) @@ -1798,6 +1845,20 @@ static int iavf_set_channels(struct net_device *netdev, adapter->num_req_queues = num_req; adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; iavf_schedule_reset(adapter); + + /* wait for the reset is done */ + for (i = 0; i < IAVF_RESET_WAIT_COMPLETE_COUNT; i++) { + msleep(IAVF_RESET_WAIT_MS); + if (adapter->flags & IAVF_FLAG_RESET_PENDING) + continue; + break; + } + if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) { + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->num_active_queues = num_req; + return -EOPNOTSUPP; + } + return 0; } @@ -1844,14 +1905,13 @@ static int iavf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, if (hfunc) *hfunc = ETH_RSS_HASH_TOP; - if (!indir) - return 0; - - memcpy(key, adapter->rss_key, adapter->rss_key_size); + if (key) + memcpy(key, adapter->rss_key, adapter->rss_key_size); - /* Each 32 bits pointed by 'indir' is stored with a lut entry */ - for (i = 0; i < adapter->rss_lut_size; i++) - indir[i] = (u32)adapter->rss_lut[i]; + if (indir) + /* Each 32 bits pointed by 'indir' is stored with a lut entry */ + for (i = 0; i < adapter->rss_lut_size; i++) + indir[i] = (u32)adapter->rss_lut[i]; return 0; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 847d67e32a54..e4439b095533 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -147,7 +147,7 @@ enum iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw, * * Returns 0 on success, negative on failure **/ -static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) +int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) { unsigned int wait, delay = 10; @@ -175,6 +175,19 @@ void iavf_schedule_reset(struct iavf_adapter *adapter) } /** + * iavf_schedule_request_stats - Set the flags and schedule statistics request + * @adapter: board private structure + * + * Sets IAVF_FLAG_AQ_REQUEST_STATS flag so iavf_watchdog_task() will explicitly + * request and refresh ethtool stats + **/ +void iavf_schedule_request_stats(struct iavf_adapter *adapter) +{ + adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_STATS; + mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); +} + +/** * iavf_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure * @txqueue: queue number that is timing out @@ -697,6 +710,21 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, u16 vlan) } /** + * iavf_restore_filters + * @adapter: board private structure + * + * Restore existing non MAC filters when VF netdev comes back up + **/ +static void iavf_restore_filters(struct iavf_adapter *adapter) +{ + u16 vid; + + /* re-add all VLAN filters */ + for_each_set_bit(vid, adapter->vsi.active_vlans, VLAN_N_VID) + iavf_add_vlan(adapter, vid); +} + +/** * iavf_vlan_rx_add_vid - Add a VLAN filter to a device * @netdev: network device struct * @proto: unused protocol data @@ -709,8 +737,11 @@ static int iavf_vlan_rx_add_vid(struct net_device *netdev, if (!VLAN_ALLOWED(adapter)) return -EIO; + if (iavf_add_vlan(adapter, vid) == NULL) return -ENOMEM; + + set_bit(vid, adapter->vsi.active_vlans); return 0; } @@ -725,11 +756,10 @@ static int iavf_vlan_rx_kill_vid(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - if (VLAN_ALLOWED(adapter)) { - iavf_del_vlan(adapter, vid); - return 0; - } - return -EIO; + iavf_del_vlan(adapter, vid); + clear_bit(vid, adapter->vsi.active_vlans); + + return 0; } /** @@ -1639,8 +1669,7 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) iavf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC); return 0; } - - if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) && + if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) || (adapter->aq_required & IAVF_FLAG_AQ_RELEASE_ALLMULTI)) { iavf_set_promiscuous(adapter, 0); return 0; @@ -1688,6 +1717,11 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) iavf_del_adv_rss_cfg(adapter); return 0; } + if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_STATS) { + iavf_request_stats(adapter); + return 0; + } + return -EAGAIN; } @@ -2012,6 +2046,7 @@ static void iavf_watchdog_task(struct work_struct *work) } adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; + mutex_unlock(&adapter->crit_lock); queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(10)); @@ -2042,16 +2077,14 @@ static void iavf_watchdog_task(struct work_struct *work) iavf_detect_recover_hung(&adapter->vsi); break; case __IAVF_REMOVE: - mutex_unlock(&adapter->crit_lock); - return; default: + mutex_unlock(&adapter->crit_lock); return; } /* check for hw reset */ reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; if (!reg_val) { - iavf_change_state(adapter, __IAVF_RESETTING); adapter->flags |= IAVF_FLAG_RESET_PENDING; adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; @@ -2123,8 +2156,8 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) iavf_free_misc_irq(adapter); iavf_reset_interrupt_capability(adapter); - iavf_free_queues(adapter); iavf_free_q_vectors(adapter); + iavf_free_queues(adapter); memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE); iavf_shutdown_adminq(&adapter->hw); adapter->netdev->flags &= ~IFF_UP; @@ -2152,7 +2185,6 @@ static void iavf_reset_task(struct work_struct *work) struct net_device *netdev = adapter->netdev; struct iavf_hw *hw = &adapter->hw; struct iavf_mac_filter *f, *ftmp; - struct iavf_vlan_filter *vlf; struct iavf_cloud_filter *cf; u32 reg_val; int i = 0, err; @@ -2215,6 +2247,7 @@ static void iavf_reset_task(struct work_struct *work) } pci_set_master(adapter->pdev); + pci_restore_msi_state(adapter->pdev); if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) { dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n", @@ -2233,6 +2266,7 @@ continue_reset: (adapter->state == __IAVF_RESETTING)); if (running) { + netdev->flags &= ~IFF_UP; netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); adapter->link_up = false; @@ -2292,11 +2326,6 @@ continue_reset: list_for_each_entry(f, &adapter->mac_filter_list, list) { f->add = true; } - /* re-add all VLAN filters */ - list_for_each_entry(vlf, &adapter->vlan_filter_list, list) { - vlf->add = true; - } - spin_unlock_bh(&adapter->mac_vlan_list_lock); /* check if TCs are running and re-add all cloud filters */ @@ -2310,7 +2339,6 @@ continue_reset: spin_unlock_bh(&adapter->cloud_filter_list_lock); adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; - adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; iavf_misc_irq_enable(adapter); @@ -2344,7 +2372,7 @@ continue_reset: * to __IAVF_RUNNING */ iavf_up_complete(adapter); - + netdev->flags |= IFF_UP; iavf_irq_enable(adapter, true); } else { iavf_change_state(adapter, __IAVF_DOWN); @@ -2357,8 +2385,10 @@ continue_reset: reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); - if (running) + if (running) { iavf_change_state(adapter, __IAVF_RUNNING); + netdev->flags |= IFF_UP; + } dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); iavf_close(netdev); } @@ -2410,7 +2440,7 @@ static void iavf_adminq_task(struct work_struct *work) /* check for error indications */ val = rd32(hw, hw->aq.arq.len); - if (val == 0xdeadbeef) /* indicates device in reset */ + if (val == 0xdeadbeef || val == 0xffffffff) /* device in reset */ goto freedom; oldval = val; if (val & IAVF_VF_ARQLEN1_ARQVFE_MASK) { @@ -2678,8 +2708,11 @@ static int iavf_validate_ch_config(struct iavf_adapter *adapter, total_max_rate += tx_rate; num_qps += mqprio_qopt->qopt.count[i]; } - if (num_qps > IAVF_MAX_REQ_QUEUES) + if (num_qps > adapter->num_active_queues) { + dev_err(&adapter->pdev->dev, + "Cannot support requested number of queues\n"); return -EINVAL; + } ret = iavf_validate_tx_bandwidth(adapter, total_max_rate); return ret; @@ -3095,8 +3128,10 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter, return -ENOMEM; while (!mutex_trylock(&adapter->crit_lock)) { - if (--count == 0) - goto err; + if (--count == 0) { + kfree(filter); + return err; + } udelay(1); } @@ -3107,11 +3142,11 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter, /* start out with flow type and eth type IPv4 to begin with */ filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW; err = iavf_parse_cls_flower(adapter, cls_flower, filter); - if (err < 0) + if (err) goto err; err = iavf_handle_tclass(adapter, tc, filter); - if (err < 0) + if (err) goto err; /* add filter to the list */ @@ -3308,6 +3343,9 @@ static int iavf_open(struct net_device *netdev) spin_unlock_bh(&adapter->mac_vlan_list_lock); + /* Restore VLAN filters that were removed with IFF_DOWN */ + iavf_restore_filters(adapter); + iavf_configure(adapter); iavf_up_complete(adapter); @@ -3415,11 +3453,16 @@ static int iavf_set_features(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - /* Don't allow changing VLAN_RX flag when adapter is not capable - * of VLAN offload + /* Don't allow enabling VLAN features when adapter is not capable + * of VLAN offload/filtering */ if (!VLAN_ALLOWED(adapter)) { - if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) + netdev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_FILTER); + if (features & (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_FILTER)) return -EINVAL; } else if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) { if (features & NETIF_F_HW_VLAN_CTAG_RX) @@ -3503,7 +3546,8 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)) + if (adapter->vf_res && + !(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)) features &= ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 8c3f0f77cb57..d60bf7c21200 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -607,7 +607,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) if (f->add) count++; } - if (!count) { + if (!count || !VLAN_ALLOWED(adapter)) { adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_VLAN_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -673,9 +673,19 @@ void iavf_del_vlans(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); - list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->remove) + list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { + /* since VLAN capabilities are not allowed, we dont want to send + * a VLAN delete request because it will most likely fail and + * create unnecessary errors/noise, so just free the VLAN + * filters marked for removal to enable bailing out before + * sending a virtchnl message + */ + if (f->remove && !VLAN_ALLOWED(adapter)) { + list_del(&f->list); + kfree(f); + } else if (f->remove) { count++; + } } if (!count) { adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_VLAN_FILTER; @@ -784,6 +794,8 @@ void iavf_request_stats(struct iavf_adapter *adapter) /* no error message, this isn't crucial */ return; } + + adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_STATS; adapter->current_op = VIRTCHNL_OP_GET_STATS; vqs.vsi_id = adapter->vsi_res->vsi_id; /* queue maps are ignored for this message - only the vsi is used */ @@ -1722,8 +1734,37 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, } spin_lock_bh(&adapter->mac_vlan_list_lock); iavf_add_filter(adapter, adapter->hw.mac.addr); + + if (VLAN_ALLOWED(adapter)) { + if (!list_empty(&adapter->vlan_filter_list)) { + struct iavf_vlan_filter *vlf; + + /* re-add all VLAN filters over virtchnl */ + list_for_each_entry(vlf, + &adapter->vlan_filter_list, + list) + vlf->add = true; + + adapter->aq_required |= + IAVF_FLAG_AQ_ADD_VLAN_FILTER; + } + } + spin_unlock_bh(&adapter->mac_vlan_list_lock); iavf_process_config(adapter); + + /* unlock crit_lock before acquiring rtnl_lock as other + * processes holding rtnl_lock could be waiting for the same + * crit_lock + */ + mutex_unlock(&adapter->crit_lock); + rtnl_lock(); + netdev_update_features(adapter->netdev); + rtnl_unlock(); + if (iavf_lock_timeout(&adapter->crit_lock, 10000)) + dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", + __FUNCTION__); + } break; case VIRTCHNL_OP_ENABLE_QUEUES: diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 1efc635cc0f5..fafe020e46ee 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -6,6 +6,18 @@ #include "ice_lib.h" #include "ice_dcb_lib.h" +static bool ice_alloc_rx_buf_zc(struct ice_rx_ring *rx_ring) +{ + rx_ring->xdp_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->xdp_buf), GFP_KERNEL); + return !!rx_ring->xdp_buf; +} + +static bool ice_alloc_rx_buf(struct ice_rx_ring *rx_ring) +{ + rx_ring->rx_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL); + return !!rx_ring->rx_buf; +} + /** * __ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI * @qs_cfg: gathered variables needed for PF->VSI queues assignment @@ -492,8 +504,11 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index, ring->q_vector->napi.napi_id); + kfree(ring->rx_buf); ring->xsk_pool = ice_xsk_pool(ring); if (ring->xsk_pool) { + if (!ice_alloc_rx_buf_zc(ring)) + return -ENOMEM; xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); ring->rx_buf_len = @@ -508,6 +523,8 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->q_index); } else { + if (!ice_alloc_rx_buf(ring)) + return -ENOMEM; if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) /* coverity[check_return] */ xdp_rxq_info_reg(&ring->xdp_rxq, diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index 7fdeb411b6df..3eb01731e496 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -97,6 +97,9 @@ static int ice_dcbnl_setets(struct net_device *netdev, struct ieee_ets *ets) new_cfg->etscfg.maxtcs = pf->hw.func_caps.common_cap.maxtc; + if (!bwcfg) + new_cfg->etscfg.tcbwtable[0] = 100; + if (!bwrec) new_cfg->etsrec.tcbwtable[0] = 100; @@ -167,15 +170,18 @@ static u8 ice_dcbnl_setdcbx(struct net_device *netdev, u8 mode) if (mode == pf->dcbx_cap) return ICE_DCB_NO_HW_CHG; - pf->dcbx_cap = mode; qos_cfg = &pf->hw.port_info->qos_cfg; - if (mode & DCB_CAP_DCBX_VER_CEE) { - if (qos_cfg->local_dcbx_cfg.pfc_mode == ICE_QOS_MODE_DSCP) - return ICE_DCB_NO_HW_CHG; + + /* DSCP configuration is not DCBx negotiated */ + if (qos_cfg->local_dcbx_cfg.pfc_mode == ICE_QOS_MODE_DSCP) + return ICE_DCB_NO_HW_CHG; + + pf->dcbx_cap = mode; + + if (mode & DCB_CAP_DCBX_VER_CEE) qos_cfg->local_dcbx_cfg.dcbx_mode = ICE_DCBX_MODE_CEE; - } else { + else qos_cfg->local_dcbx_cfg.dcbx_mode = ICE_DCBX_MODE_IEEE; - } dev_info(ice_pf_to_dev(pf), "DCBx mode = 0x%x\n", mode); return ICE_DCB_HW_CHG_RST; diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index 38960bcc384c..b6e7f47c8c78 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -1268,7 +1268,7 @@ ice_fdir_write_all_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input, bool is_tun = tun == ICE_FD_HW_SEG_TUN; int err; - if (is_tun && !ice_get_open_tunnel_port(&pf->hw, &port_num)) + if (is_tun && !ice_get_open_tunnel_port(&pf->hw, &port_num, TNL_ALL)) continue; err = ice_fdir_write_fltr(pf, input, add, is_tun); if (err) @@ -1652,7 +1652,7 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd) } /* return error if not an update and no available filters */ - fltrs_needed = ice_get_open_tunnel_port(hw, &tunnel_port) ? 2 : 1; + fltrs_needed = ice_get_open_tunnel_port(hw, &tunnel_port, TNL_ALL) ? 2 : 1; if (!ice_fdir_find_fltr_by_idx(hw, fsp->location) && ice_fdir_num_avail_fltr(hw, pf->vsi[vsi->idx]) < fltrs_needed) { dev_err(dev, "Failed to add filter. The maximum number of flow director filters has been reached.\n"); diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c index cbd8424631e3..4dca009bdd50 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_fdir.c @@ -924,7 +924,7 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, memcpy(pkt, ice_fdir_pkt[idx].pkt, ice_fdir_pkt[idx].pkt_len); loc = pkt; } else { - if (!ice_get_open_tunnel_port(hw, &tnl_port)) + if (!ice_get_open_tunnel_port(hw, &tnl_port, TNL_ALL)) return ICE_ERR_DOES_NOT_EXIST; if (!ice_fdir_pkt[idx].tun_pkt) return ICE_ERR_PARAM; diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 23cfcceb1536..6ad1c2559724 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -1899,9 +1899,11 @@ static struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld) * ice_get_open_tunnel_port - retrieve an open tunnel port * @hw: pointer to the HW structure * @port: returns open port + * @type: type of tunnel, can be TNL_LAST if it doesn't matter */ bool -ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port) +ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port, + enum ice_tunnel_type type) { bool res = false; u16 i; @@ -1909,7 +1911,8 @@ ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port) mutex_lock(&hw->tnl_lock); for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++) - if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].port) { + if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].port && + (type == TNL_LAST || type == hw->tnl.tbl[i].type)) { *port = hw->tnl.tbl[i].port; res = true; break; diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index 344c2637facd..a2863f38fd1f 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -33,7 +33,8 @@ enum ice_status ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, unsigned long *bm, struct list_head *fv_list); bool -ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port); +ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port, + enum ice_tunnel_type type); int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table, diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 40562600a8cf..09a3297cd63c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -89,8 +89,13 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->rx_rings) goto err_rings; - /* XDP will have vsi->alloc_txq Tx queues as well, so double the size */ - vsi->txq_map = devm_kcalloc(dev, (2 * vsi->alloc_txq), + /* txq_map needs to have enough space to track both Tx (stack) rings + * and XDP rings; at this point vsi->num_xdp_txq might not be set, + * so use num_possible_cpus() as we want to always provide XDP ring + * per CPU, regardless of queue count settings from user that might + * have come from ethtool's set_channels() callback; + */ + vsi->txq_map = devm_kcalloc(dev, (vsi->alloc_txq + num_possible_cpus()), sizeof(*vsi->txq_map), GFP_KERNEL); if (!vsi->txq_map) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f099797f35e3..73c61cdb036f 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2609,7 +2609,18 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) ice_stat_str(status)); goto clear_xdp_rings; } - ice_vsi_assign_bpf_prog(vsi, prog); + + /* assign the prog only when it's not already present on VSI; + * this flow is a subject of both ethtool -L and ndo_bpf flows; + * VSI rebuild that happens under ethtool -L can expose us to + * the bpf_prog refcount issues as we would be swapping same + * bpf_prog pointers from vsi->xdp_prog and calling bpf_prog_put + * on it as it would be treated as an 'old_prog'; for ndo_bpf + * this is not harmful as dev_xdp_install bumps the refcount + * before calling the op exposed by the driver; + */ + if (!ice_is_xdp_ena_vsi(vsi)) + ice_vsi_assign_bpf_prog(vsi, prog); return 0; clear_xdp_rings: @@ -2785,6 +2796,11 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx 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); } @@ -5865,6 +5881,9 @@ static int ice_up_complete(struct ice_vsi *vsi) netif_carrier_on(vsi->netdev); } + /* clear this now, and the first stats read will be used as baseline */ + vsi->stat_offsets_loaded = false; + ice_service_task_schedule(pf); return 0; @@ -5911,14 +5930,15 @@ ice_fetch_u64_stats_per_ring(struct u64_stats_sync *syncp, struct ice_q_stats st /** * ice_update_vsi_tx_ring_stats - Update VSI Tx ring stats counters * @vsi: the VSI to be updated + * @vsi_stats: the stats struct to be updated * @rings: rings to work on * @count: number of rings */ static void -ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_tx_ring **rings, - u16 count) +ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, + struct rtnl_link_stats64 *vsi_stats, + struct ice_tx_ring **rings, u16 count) { - struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats; u16 i; for (i = 0; i < count; i++) { @@ -5942,15 +5962,13 @@ ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_tx_ring **rings, */ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) { - struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats; + struct rtnl_link_stats64 *vsi_stats; u64 pkts, bytes; int i; - /* reset netdev stats */ - vsi_stats->tx_packets = 0; - vsi_stats->tx_bytes = 0; - vsi_stats->rx_packets = 0; - vsi_stats->rx_bytes = 0; + vsi_stats = kzalloc(sizeof(*vsi_stats), GFP_ATOMIC); + if (!vsi_stats) + return; /* reset non-netdev (extended) stats */ vsi->tx_restart = 0; @@ -5962,7 +5980,8 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) rcu_read_lock(); /* update Tx rings counters */ - ice_update_vsi_tx_ring_stats(vsi, vsi->tx_rings, vsi->num_txq); + ice_update_vsi_tx_ring_stats(vsi, vsi_stats, vsi->tx_rings, + vsi->num_txq); /* update Rx rings counters */ ice_for_each_rxq(vsi, i) { @@ -5977,10 +5996,17 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) /* update XDP Tx rings counters */ if (ice_is_xdp_ena_vsi(vsi)) - ice_update_vsi_tx_ring_stats(vsi, vsi->xdp_rings, + ice_update_vsi_tx_ring_stats(vsi, vsi_stats, vsi->xdp_rings, vsi->num_xdp_txq); rcu_read_unlock(); + + vsi->net_stats.tx_packets = vsi_stats->tx_packets; + vsi->net_stats.tx_bytes = vsi_stats->tx_bytes; + vsi->net_stats.rx_packets = vsi_stats->rx_packets; + vsi->net_stats.rx_bytes = vsi_stats->rx_bytes; + + kfree(vsi_stats); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index bf7247c6f58e..442b031b0edc 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -705,7 +705,7 @@ static int ice_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm) scaled_ppm = -scaled_ppm; } - while ((u64)scaled_ppm > div_u64(U64_MAX, incval)) { + while ((u64)scaled_ppm > div64_u64(U64_MAX, incval)) { /* handle overflow by scaling down the scaled_ppm and * the divisor, losing some precision */ @@ -1540,19 +1540,16 @@ static void ice_ptp_tx_tstamp_work(struct kthread_work *work) if (err) continue; - /* Check if the timestamp is valid */ - if (!(raw_tstamp & ICE_PTP_TS_VALID)) + /* Check if the timestamp is invalid or stale */ + if (!(raw_tstamp & ICE_PTP_TS_VALID) || + raw_tstamp == tx->tstamps[idx].cached_tstamp) continue; - /* clear the timestamp register, so that it won't show valid - * again when re-used. - */ - ice_clear_phy_tstamp(hw, tx->quad, phy_idx); - /* The timestamp is valid, so we'll go ahead and clear this * index and then send the timestamp up to the stack. */ spin_lock(&tx->lock); + tx->tstamps[idx].cached_tstamp = raw_tstamp; clear_bit(idx, tx->in_use); skb = tx->tstamps[idx].skb; tx->tstamps[idx].skb = NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index f71ad317d6c8..53c15fc9d996 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -55,15 +55,21 @@ struct ice_perout_channel { * struct ice_tx_tstamp - Tracking for a single Tx timestamp * @skb: pointer to the SKB for this timestamp request * @start: jiffies when the timestamp was first requested + * @cached_tstamp: last read timestamp * * This structure tracks a single timestamp request. The SKB pointer is * provided when initiating a request. The start time is used to ensure that * we discard old requests that were not fulfilled within a 2 second time * window. + * Timestamp values in the PHY are read only and do not get cleared except at + * hardware reset or when a new timestamp value is captured. The cached_tstamp + * field is used to detect the case where a new timestamp has not yet been + * captured, ensuring that we avoid sending stale timestamp data to the stack. */ struct ice_tx_tstamp { struct sk_buff *skb; unsigned long start; + u64 cached_tstamp; }; /** diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 793f4a9fc2cd..183d93033890 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -3796,10 +3796,13 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { * ice_find_recp - find a recipe * @hw: pointer to the hardware structure * @lkup_exts: extension sequence to match + * @tun_type: type of recipe tunnel * * Returns index of matching recipe, or ICE_MAX_NUM_RECIPES if not found. */ -static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts) +static u16 +ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, + enum ice_sw_tunnel_type tun_type) { bool refresh_required = true; struct ice_sw_recipe *recp; @@ -3860,8 +3863,9 @@ static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts) } /* If for "i"th recipe the found was never set to false * then it means we found our match + * Also tun type of recipe needs to be checked */ - if (found) + if (found && recp[i].tun_type == tun_type) return i; /* Return the recipe ID */ } } @@ -4651,11 +4655,12 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, } /* Look for a recipe which matches our requested fv / mask list */ - *rid = ice_find_recp(hw, lkup_exts); + *rid = ice_find_recp(hw, lkup_exts, rinfo->tun_type); if (*rid < ICE_MAX_NUM_RECIPES) /* Success if found a recipe that match the existing criteria */ goto err_unroll; + rm->tun_type = rinfo->tun_type; /* Recipe we need does not exist, add a recipe */ status = ice_add_sw_recipe(hw, rm, profiles); if (status) @@ -4958,11 +4963,13 @@ ice_fill_adv_packet_tun(struct ice_hw *hw, enum ice_sw_tunnel_type tun_type, switch (tun_type) { case ICE_SW_TUN_VXLAN: + if (!ice_get_open_tunnel_port(hw, &open_port, TNL_VXLAN)) + return ICE_ERR_CFG; + break; case ICE_SW_TUN_GENEVE: - if (!ice_get_open_tunnel_port(hw, &open_port)) + if (!ice_get_open_tunnel_port(hw, &open_port, TNL_GENEVE)) return ICE_ERR_CFG; break; - default: /* Nothing needs to be done for this tunnel type */ return 0; @@ -5555,7 +5562,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, if (status) return status; - rid = ice_find_recp(hw, &lkup_exts); + rid = ice_find_recp(hw, &lkup_exts, rinfo->tun_type); /* If did not find a recipe that match the existing criteria */ if (rid == ICE_MAX_NUM_RECIPES) return ICE_ERR_PARAM; diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index e5d23feb6701..25cca5c4ae57 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -74,21 +74,13 @@ static enum ice_protocol_type ice_proto_type_from_ipv6(bool inner) return inner ? ICE_IPV6_IL : ICE_IPV6_OFOS; } -static enum ice_protocol_type -ice_proto_type_from_l4_port(bool inner, u16 ip_proto) +static enum ice_protocol_type ice_proto_type_from_l4_port(u16 ip_proto) { - if (inner) { - switch (ip_proto) { - case IPPROTO_UDP: - return ICE_UDP_ILOS; - } - } else { - switch (ip_proto) { - case IPPROTO_TCP: - return ICE_TCP_IL; - case IPPROTO_UDP: - return ICE_UDP_OF; - } + switch (ip_proto) { + case IPPROTO_TCP: + return ICE_TCP_IL; + case IPPROTO_UDP: + return ICE_UDP_ILOS; } return 0; @@ -191,8 +183,9 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, i++; } - if (flags & ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT) { - list[i].type = ice_proto_type_from_l4_port(false, hdr->l3_key.ip_proto); + if ((flags & ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT) && + hdr->l3_key.ip_proto == IPPROTO_UDP) { + list[i].type = ICE_UDP_OF; list[i].h_u.l4_hdr.dst_port = hdr->l4_key.dst_port; list[i].m_u.l4_hdr.dst_port = hdr->l4_mask.dst_port; i++; @@ -317,7 +310,7 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, ICE_TC_FLWR_FIELD_SRC_L4_PORT)) { struct ice_tc_l4_hdr *l4_key, *l4_mask; - list[i].type = ice_proto_type_from_l4_port(inner, headers->l3_key.ip_proto); + list[i].type = ice_proto_type_from_l4_port(headers->l3_key.ip_proto); l4_key = &headers->l4_key; l4_mask = &headers->l4_mask; @@ -802,7 +795,8 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, headers->l3_mask.ttl = match.mask->ttl; } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS) && + fltr->tunnel_type != TNL_VXLAN && fltr->tunnel_type != TNL_GENEVE) { struct flow_match_ports match; flow_rule_match_enc_ports(rule, &match); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index bc3ba19dc88f..dccf09eefc75 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -419,7 +419,10 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring) } rx_skip_free: - memset(rx_ring->rx_buf, 0, sizeof(*rx_ring->rx_buf) * rx_ring->count); + if (rx_ring->xsk_pool) + memset(rx_ring->xdp_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->xdp_buf))); + else + memset(rx_ring->rx_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->rx_buf))); /* Zero out the descriptor ring */ size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), @@ -446,8 +449,13 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring) if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) xdp_rxq_info_unreg(&rx_ring->xdp_rxq); rx_ring->xdp_prog = NULL; - devm_kfree(rx_ring->dev, rx_ring->rx_buf); - rx_ring->rx_buf = NULL; + if (rx_ring->xsk_pool) { + kfree(rx_ring->xdp_buf); + rx_ring->xdp_buf = NULL; + } else { + kfree(rx_ring->rx_buf); + rx_ring->rx_buf = NULL; + } if (rx_ring->desc) { size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), @@ -475,8 +483,7 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) /* warn if we are about to overwrite the pointer */ WARN_ON(rx_ring->rx_buf); rx_ring->rx_buf = - devm_kcalloc(dev, sizeof(*rx_ring->rx_buf), rx_ring->count, - GFP_KERNEL); + kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL); if (!rx_ring->rx_buf) return -ENOMEM; @@ -505,7 +512,7 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) return 0; err: - devm_kfree(dev, rx_ring->rx_buf); + kfree(rx_ring->rx_buf); rx_ring->rx_buf = NULL; return -ENOMEM; } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index c56dd1749903..b7b3bd4816f0 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -24,7 +24,6 @@ #define ICE_MAX_DATA_PER_TXD_ALIGNED \ (~(ICE_MAX_READ_REQ_SIZE - 1) & ICE_MAX_DATA_PER_TXD) -#define ICE_RX_BUF_WRITE 16 /* Must be power of 2 */ #define ICE_MAX_TXQ_PER_TXQG 128 /* Attempt to maximize the headroom available for incoming frames. We use a 2K diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 217ff5e9a6f1..6427e7ec93de 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -1617,6 +1617,7 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) ice_vc_set_default_allowlist(vf); ice_vf_fdir_exit(vf); + ice_vf_fdir_init(vf); /* clean VF control VSI when resetting VFs since it should be * setup only when VF creates its first FDIR rule. */ @@ -1747,6 +1748,7 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) } ice_vf_fdir_exit(vf); + ice_vf_fdir_init(vf); /* clean VF control VSI when resetting VF since it should be setup * only when VF creates its first FDIR rule. */ @@ -2021,6 +2023,10 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) if (ret) goto err_unroll_sriov; + /* rearm global interrupts */ + if (test_and_clear_bit(ICE_OICR_INTR_DIS, pf->state)) + ice_irq_dynamic_ena(hw, NULL, NULL); + return 0; err_unroll_sriov: diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index ff55cb415b11..c895351b25e0 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -12,6 +12,11 @@ #include "ice_txrx_lib.h" #include "ice_lib.h" +static struct xdp_buff **ice_xdp_buf(struct ice_rx_ring *rx_ring, u32 idx) +{ + return &rx_ring->xdp_buf[idx]; +} + /** * ice_qp_reset_stats - Resets all stats for rings of given index * @vsi: VSI that contains rings of interest @@ -372,7 +377,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) dma_addr_t dma; rx_desc = ICE_RX_DESC(rx_ring, ntu); - xdp = &rx_ring->xdp_buf[ntu]; + xdp = ice_xdp_buf(rx_ring, ntu); nb_buffs = min_t(u16, count, rx_ring->count - ntu); nb_buffs = xsk_buff_alloc_batch(rx_ring->xsk_pool, xdp, nb_buffs); @@ -383,20 +388,16 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) while (i--) { dma = xsk_buff_xdp_get_dma(*xdp); rx_desc->read.pkt_addr = cpu_to_le64(dma); + rx_desc->wb.status_error0 = 0; rx_desc++; xdp++; } ntu += nb_buffs; - if (ntu == rx_ring->count) { - rx_desc = ICE_RX_DESC(rx_ring, 0); - xdp = rx_ring->xdp_buf; + if (ntu == rx_ring->count) ntu = 0; - } - /* clear the status bits for the next_to_use descriptor */ - rx_desc->wb.status_error0 = 0; ice_release_rx_desc(rx_ring, ntu); return count == nb_buffs; @@ -418,19 +419,18 @@ static void ice_bump_ntc(struct ice_rx_ring *rx_ring) /** * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer * @rx_ring: Rx ring - * @xdp_arr: Pointer to the SW ring of xdp_buff pointers + * @xdp: Pointer to XDP buffer * * This function allocates a new skb from a zero-copy Rx buffer. * * Returns the skb on success, NULL on failure. */ static struct sk_buff * -ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff **xdp_arr) +ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) { - struct xdp_buff *xdp = *xdp_arr; + unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start; unsigned int metasize = xdp->data - xdp->data_meta; unsigned int datasize = xdp->data_end - xdp->data; - unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start; struct sk_buff *skb; skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard, @@ -444,7 +444,6 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff **xdp_arr) skb_metadata_set(skb, metasize); xsk_buff_free(xdp); - *xdp_arr = NULL; return skb; } @@ -506,7 +505,6 @@ out_failure: int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; - u16 cleaned_count = ICE_DESC_UNUSED(rx_ring); struct ice_tx_ring *xdp_ring; unsigned int xdp_xmit = 0; struct bpf_prog *xdp_prog; @@ -521,7 +519,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) while (likely(total_rx_packets < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; unsigned int size, xdp_res = 0; - struct xdp_buff **xdp; + struct xdp_buff *xdp; struct sk_buff *skb; u16 stat_err_bits; u16 vlan_tag = 0; @@ -539,31 +537,35 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) */ dma_rmb(); + xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean); + size = le16_to_cpu(rx_desc->wb.pkt_len) & ICE_RX_FLX_DESC_PKT_LEN_M; - if (!size) - break; + if (!size) { + xdp->data = NULL; + xdp->data_end = NULL; + xdp->data_hard_start = NULL; + xdp->data_meta = NULL; + goto construct_skb; + } - xdp = &rx_ring->xdp_buf[rx_ring->next_to_clean]; - xsk_buff_set_size(*xdp, size); - xsk_buff_dma_sync_for_cpu(*xdp, rx_ring->xsk_pool); + xsk_buff_set_size(xdp, size); + xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool); - xdp_res = ice_run_xdp_zc(rx_ring, *xdp, xdp_prog, xdp_ring); + xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring); if (xdp_res) { if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) xdp_xmit |= xdp_res; else - xsk_buff_free(*xdp); + xsk_buff_free(xdp); - *xdp = NULL; total_rx_bytes += size; total_rx_packets++; - cleaned_count++; ice_bump_ntc(rx_ring); continue; } - +construct_skb: /* XDP_PASS path */ skb = ice_construct_skb_zc(rx_ring, xdp); if (!skb) { @@ -571,7 +573,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) break; } - cleaned_count++; ice_bump_ntc(rx_ring); if (eth_skb_pad(skb)) { @@ -593,8 +594,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) ice_receive_skb(rx_ring, skb, vlan_tag); } - if (cleaned_count >= ICE_RX_BUF_WRITE) - failure = !ice_alloc_rx_bufs_zc(rx_ring, cleaned_count); + failure = !ice_alloc_rx_bufs_zc(rx_ring, ICE_DESC_UNUSED(rx_ring)); ice_finalize_xdp_rx(xdp_ring, xdp_xmit); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); @@ -810,15 +810,14 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi) */ void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { - u16 i; - - for (i = 0; i < rx_ring->count; i++) { - struct xdp_buff **xdp = &rx_ring->xdp_buf[i]; + u16 count_mask = rx_ring->count - 1; + u16 ntc = rx_ring->next_to_clean; + u16 ntu = rx_ring->next_to_use; - if (!xdp) - continue; + for ( ; ntc != ntu; ntc = (ntc + 1) & count_mask) { + struct xdp_buff *xdp = *ice_xdp_buf(rx_ring, ntc); - *xdp = NULL; + xsk_buff_free(xdp); } } diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 836be0d3b291..446894dde182 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -7648,6 +7648,20 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, struct vf_mac_filter *entry = NULL; int ret = 0; + if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && + !vf_data->trusted) { + dev_warn(&pdev->dev, + "VF %d requested MAC filter but is administratively denied\n", + vf); + return -EINVAL; + } + if (!is_valid_ether_addr(addr)) { + dev_warn(&pdev->dev, + "VF %d attempted to set invalid MAC filter\n", + vf); + return -EINVAL; + } + switch (info) { case E1000_VF_MAC_FILTER_CLR: /* remove all unicast MAC filters related to the current VF */ @@ -7661,20 +7675,6 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, } break; case E1000_VF_MAC_FILTER_ADD: - if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && - !vf_data->trusted) { - dev_warn(&pdev->dev, - "VF %d requested MAC filter but is administratively denied\n", - vf); - return -EINVAL; - } - if (!is_valid_ether_addr(addr)) { - dev_warn(&pdev->dev, - "VF %d attempted to set invalid MAC filter\n", - vf); - return -EINVAL; - } - /* try to find empty slot in the list */ list_for_each(pos, &adapter->vf_macs.l) { entry = list_entry(pos, struct vf_mac_filter, l); @@ -8026,7 +8026,7 @@ static int igb_poll(struct napi_struct *napi, int budget) if (likely(napi_complete_done(napi, work_done))) igb_ring_irq_enable(q_vector); - return min(work_done, budget - 1); + return work_done; } /** @@ -9254,7 +9254,7 @@ static int __maybe_unused igb_suspend(struct device *dev) return __igb_shutdown(to_pci_dev(dev), NULL, 0); } -static int __maybe_unused igb_resume(struct device *dev) +static int __maybe_unused __igb_resume(struct device *dev, bool rpm) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -9297,17 +9297,24 @@ static int __maybe_unused igb_resume(struct device *dev) wr32(E1000_WUS, ~0); - rtnl_lock(); + if (!rpm) + rtnl_lock(); if (!err && netif_running(netdev)) err = __igb_open(netdev, true); if (!err) netif_device_attach(netdev); - rtnl_unlock(); + if (!rpm) + rtnl_unlock(); return err; } +static int __maybe_unused igb_resume(struct device *dev) +{ + return __igb_resume(dev, false); +} + static int __maybe_unused igb_runtime_idle(struct device *dev) { struct net_device *netdev = dev_get_drvdata(dev); @@ -9326,7 +9333,7 @@ static int __maybe_unused igb_runtime_suspend(struct device *dev) static int __maybe_unused igb_runtime_resume(struct device *dev) { - return igb_resume(dev); + return __igb_resume(dev, true); } static void igb_shutdown(struct pci_dev *pdev) @@ -9442,7 +9449,7 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, * @pdev: Pointer to PCI device * * Restart the card from scratch, as if from a cold-boot. Implementation - * resembles the first-half of the igb_resume routine. + * resembles the first-half of the __igb_resume routine. **/ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev) { @@ -9482,7 +9489,7 @@ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev) * * This callback is called when the error recovery driver tells us that * its OK to resume normal operation. Implementation resembles the - * second-half of the igb_resume routine. + * second-half of the __igb_resume routine. */ static void igb_io_resume(struct pci_dev *pdev) { diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 74ccd622251a..4d988da68394 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2859,6 +2859,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; err_hw_init: + netif_napi_del(&adapter->rx_ring->napi); kfree(adapter->tx_ring); kfree(adapter->rx_ring); err_sw_init: diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c index b2ef9fde97b3..b6807e16eea9 100644 --- a/drivers/net/ethernet/intel/igc/igc_i225.c +++ b/drivers/net/ethernet/intel/igc/igc_i225.c @@ -636,7 +636,7 @@ s32 igc_set_ltr_i225(struct igc_hw *hw, bool link) ltrv = rd32(IGC_LTRMAXV); if (ltr_max != (ltrv & IGC_LTRMAXV_LTRV_MASK)) { ltrv = IGC_LTRMAXV_LSNP_REQ | ltr_max | - (scale_min << IGC_LTRMAXV_SCALE_SHIFT); + (scale_max << IGC_LTRMAXV_SCALE_SHIFT); wr32(IGC_LTRMAXV, ltrv); } } diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 8e448288ee26..d28a80a00953 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -5467,6 +5467,9 @@ static irqreturn_t igc_intr_msi(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } + if (icr & IGC_ICR_TS) + igc_tsync_interrupt(adapter); + napi_schedule(&q_vector->napi); return IRQ_HANDLED; @@ -5510,6 +5513,9 @@ static irqreturn_t igc_intr(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } + if (icr & IGC_ICR_TS) + igc_tsync_interrupt(adapter); + napi_schedule(&q_vector->napi); return IRQ_HANDLED; diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 30568e3544cd..4f9245aa79a1 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -768,7 +768,20 @@ int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr) */ static bool igc_is_crosststamp_supported(struct igc_adapter *adapter) { - return IS_ENABLED(CONFIG_X86_TSC) ? pcie_ptm_enabled(adapter->pdev) : false; + if (!IS_ENABLED(CONFIG_X86_TSC)) + return false; + + /* FIXME: it was noticed that enabling support for PCIe PTM in + * some i225-V models could cause lockups when bringing the + * interface up/down. There should be no downsides to + * disabling crosstimestamping support for i225-V, as it + * doesn't have any PTP support. That way we gain some time + * while root causing the issue. + */ + if (adapter->pdev->device == IGC_DEV_ID_I225_V) + return false; + + return pcie_ptm_enabled(adapter->pdev); } static struct system_counterval_t igc_device_tstamp_to_system(u64 tstamp) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 0f9f022260d7..45e2ec4d264d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -5531,6 +5531,10 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) if (!speed && hw->mac.ops.get_link_capabilities) { ret = hw->mac.ops.get_link_capabilities(hw, &speed, &autoneg); + /* remove NBASE-T speeds from default autonegotiation + * to accommodate broken network switches in the field + * which cannot cope with advertised NBASE-T speeds + */ speed &= ~(IXGBE_LINK_SPEED_5GB_FULL | IXGBE_LINK_SPEED_2_5GB_FULL); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 9724ffb16518..e4b50c7781ff 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -3405,6 +3405,9 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) /* flush pending Tx transactions */ ixgbe_clear_tx_pending(hw); + /* set MDIO speed before talking to the PHY in case it's the 1st time */ + ixgbe_set_mdio_speed(hw); + /* PHY ops must be identified and initialized prior to reset */ status = hw->phy.ops.init(hw); if (status == IXGBE_ERR_SFP_NOT_SUPPORTED || |