diff options
24 files changed, 355 insertions, 135 deletions
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index d02b55b6aa9c..3e08847505ce 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -5524,7 +5524,7 @@ bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw) * returned by the firmware is a 16 bit * value, but is indexed * by [fls(speed) - 1] */ -static const u32 ice_aq_to_link_speed[15] = { +static const u32 ice_aq_to_link_speed[] = { SPEED_10, /* BIT(0) */ SPEED_100, SPEED_1000, @@ -5536,10 +5536,6 @@ static const u32 ice_aq_to_link_speed[15] = { SPEED_40000, SPEED_50000, SPEED_100000, /* BIT(10) */ - 0, - 0, - 0, - 0 /* BIT(14) */ }; /** @@ -5550,5 +5546,8 @@ static const u32 ice_aq_to_link_speed[15] = { */ u32 ice_get_link_speed(u16 index) { + if (index >= ARRAY_SIZE(ice_aq_to_link_speed)) + return 0; + return ice_aq_to_link_speed[index]; } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 5f86e4111fa9..b288a01a321a 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5541,7 +5541,7 @@ static int __init ice_module_init(void) 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_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); return -ENOMEM; diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 9b762f7972ce..61f844d22512 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -5420,7 +5420,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, */ status = ice_add_special_words(rinfo, lkup_exts, ice_is_dvm_ena(hw)); if (status) - goto err_free_lkup_exts; + goto err_unroll; /* Group match words into recipes using preferred recipe grouping * criteria. diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index faba0f857cd9..95f392ab9670 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -1681,7 +1681,7 @@ ice_tc_forward_to_queue(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr, struct ice_vsi *ch_vsi = NULL; u16 queue = act->rx_queue; - if (queue > vsi->num_rxq) { + if (queue >= vsi->num_rxq) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because specified queue is invalid"); return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c index d4a4001b6e5d..f56fa94ff3d0 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c @@ -39,7 +39,7 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd); } -static const u32 ice_legacy_aq_to_vc_speed[15] = { +static const u32 ice_legacy_aq_to_vc_speed[] = { VIRTCHNL_LINK_SPEED_100MB, /* BIT(0) */ VIRTCHNL_LINK_SPEED_100MB, VIRTCHNL_LINK_SPEED_1GB, @@ -51,10 +51,6 @@ static const u32 ice_legacy_aq_to_vc_speed[15] = { VIRTCHNL_LINK_SPEED_40GB, VIRTCHNL_LINK_SPEED_40GB, VIRTCHNL_LINK_SPEED_40GB, - VIRTCHNL_LINK_SPEED_UNKNOWN, - VIRTCHNL_LINK_SPEED_UNKNOWN, - VIRTCHNL_LINK_SPEED_UNKNOWN, - VIRTCHNL_LINK_SPEED_UNKNOWN /* BIT(14) */ }; /** @@ -71,21 +67,20 @@ static const u32 ice_legacy_aq_to_vc_speed[15] = { */ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) { - u32 speed; + /* convert a BIT() value into an array index */ + u32 index = fls(link_speed) - 1; - if (adv_link_support) { - /* convert a BIT() value into an array index */ - speed = ice_get_link_speed(fls(link_speed) - 1); - } else { + if (adv_link_support) + return ice_get_link_speed(index); + else if (index < ARRAY_SIZE(ice_legacy_aq_to_vc_speed)) /* Virtchnl speeds are not defined for every speed supported in * the hardware. To maintain compatibility with older AVF * drivers, while reporting the speed the new speed values are * resolved to the closest known virtchnl speeds */ - speed = ice_legacy_aq_to_vc_speed[fls(link_speed) - 1]; - } + return ice_legacy_aq_to_vc_speed[index]; - return speed; + return VIRTCHNL_LINK_SPEED_UNKNOWN; } /* The mailbox overflow detection algorithm helps to check if there diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c index 5ecc0ee9a78e..b1ffb81893d4 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -44,13 +44,17 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) /* outer VLAN ops regardless of port VLAN config */ vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; if (ice_vf_is_port_vlan_ena(vf)) { /* setup outer VLAN ops */ vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; + /* all Rx traffic should be in the domain of the + * assigned port VLAN, so prevent disabling Rx VLAN + * filtering + */ + vlan_ops->dis_rx_filtering = noop_vlan; vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; @@ -63,6 +67,9 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; } else { + vlan_ops->dis_rx_filtering = + ice_vsi_dis_rx_vlan_filtering; + if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) vlan_ops->ena_rx_filtering = noop_vlan; else @@ -96,7 +103,14 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; + /* all Rx traffic should be in the domain of the + * assigned port VLAN, so prevent disabling Rx VLAN + * filtering + */ + vlan_ops->dis_rx_filtering = noop_vlan; } else { + vlan_ops->dis_rx_filtering = + ice_vsi_dis_rx_vlan_filtering; if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) vlan_ops->ena_rx_filtering = noop_vlan; else diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 44b1740dc098..1dd2a7fee8d4 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2942,7 +2942,9 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) if (tx_buffer->next_to_watch && time_after(jiffies, tx_buffer->time_stamp + (adapter->tx_timeout_factor * HZ)) && - !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF)) { + !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF) && + (rd32(IGC_TDH(tx_ring->reg_idx)) != + readl(tx_ring->tail))) { /* detected Tx unit hang */ netdev_err(tx_ring->netdev, "Detected Tx Unit Hang\n" @@ -5069,6 +5071,24 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu) } /** + * igc_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + * @txqueue: queue number that timed out + **/ +static void igc_tx_timeout(struct net_device *netdev, + unsigned int __always_unused txqueue) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + + /* Do the reset outside of interrupt context */ + adapter->tx_timeout_count++; + schedule_work(&adapter->reset_task); + wr32(IGC_EICS, + (adapter->eims_enable_mask & ~adapter->eims_other)); +} + +/** * igc_get_stats64 - Get System Network Statistics * @netdev: network interface device structure * @stats: rtnl_link_stats64 pointer @@ -5495,7 +5515,7 @@ static void igc_watchdog_task(struct work_struct *work) case SPEED_100: case SPEED_1000: case SPEED_2500: - adapter->tx_timeout_factor = 7; + adapter->tx_timeout_factor = 1; break; } @@ -6320,6 +6340,7 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_set_rx_mode = igc_set_rx_mode, .ndo_set_mac_address = igc_set_mac, .ndo_change_mtu = igc_change_mtu, + .ndo_tx_timeout = igc_tx_timeout, .ndo_get_stats64 = igc_get_stats64, .ndo_fix_features = igc_fix_features, .ndo_set_features = igc_set_features, diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index d56eda6397a4..e3123723522e 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1570,8 +1570,8 @@ static struct page_pool *mtk_create_page_pool(struct mtk_eth *eth, if (IS_ERR(pp)) return pp; - err = __xdp_rxq_info_reg(xdp_q, ð->dummy_dev, eth->rx_napi.napi_id, - id, PAGE_SIZE); + err = __xdp_rxq_info_reg(xdp_q, ð->dummy_dev, id, + eth->rx_napi.napi_id, PAGE_SIZE); if (err < 0) goto err_free_pp; @@ -1870,7 +1870,9 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, while (done < budget) { unsigned int pktlen, *rxdcsum; + bool has_hwaccel_tag = false; struct net_device *netdev; + u16 vlan_proto, vlan_tci; dma_addr_t dma_addr; u32 hash, reason; int mac = 0; @@ -2010,27 +2012,29 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) { if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { - if (trxd.rxd3 & RX_DMA_VTAG_V2) - __vlan_hwaccel_put_tag(skb, - htons(RX_DMA_VPID(trxd.rxd4)), - RX_DMA_VID(trxd.rxd4)); + if (trxd.rxd3 & RX_DMA_VTAG_V2) { + vlan_proto = RX_DMA_VPID(trxd.rxd4); + vlan_tci = RX_DMA_VID(trxd.rxd4); + has_hwaccel_tag = true; + } } else if (trxd.rxd2 & RX_DMA_VTAG) { - __vlan_hwaccel_put_tag(skb, htons(RX_DMA_VPID(trxd.rxd3)), - RX_DMA_VID(trxd.rxd3)); + vlan_proto = RX_DMA_VPID(trxd.rxd3); + vlan_tci = RX_DMA_VID(trxd.rxd3); + has_hwaccel_tag = true; } } /* When using VLAN untagging in combination with DSA, the * hardware treats the MTK special tag as a VLAN and untags it. */ - if (skb_vlan_tag_present(skb) && netdev_uses_dsa(netdev)) { - unsigned int port = ntohs(skb->vlan_proto) & GENMASK(2, 0); + if (has_hwaccel_tag && netdev_uses_dsa(netdev)) { + unsigned int port = vlan_proto & GENMASK(2, 0); if (port < ARRAY_SIZE(eth->dsa_meta) && eth->dsa_meta[port]) skb_dst_set_noref(skb, ð->dsa_meta[port]->dst); - - __vlan_hwaccel_clear_tag(skb); + } else if (has_hwaccel_tag) { + __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vlan_tci); } skb_record_rx_queue(skb, 0); @@ -3111,7 +3115,7 @@ static void mtk_gdm_config(struct mtk_eth *eth, u32 config) val |= config; - if (!i && eth->netdev[0] && netdev_uses_dsa(eth->netdev[0])) + if (eth->netdev[i] && netdev_uses_dsa(eth->netdev[i])) val |= MTK_GDMA_SPECIAL_TAG; mtk_w32(eth, val, MTK_GDMA_FWD_CFG(i)); @@ -3177,8 +3181,7 @@ static int mtk_open(struct net_device *dev) struct mtk_eth *eth = mac->hw; int i, err; - if ((mtk_uses_dsa(dev) && !eth->prog) && - !(mac->id == 1 && MTK_HAS_CAPS(eth->soc->caps, MTK_GMAC1_TRGMII))) { + if (mtk_uses_dsa(dev) && !eth->prog) { for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) { struct metadata_dst *md_dst = eth->dsa_meta[i]; @@ -3195,8 +3198,7 @@ static int mtk_open(struct net_device *dev) } } else { /* Hardware special tag parsing needs to be disabled if at least - * one MAC does not use DSA, or the second MAC of the MT7621 and - * MT7623 SoCs is being used. + * one MAC does not use DSA. */ u32 val = mtk_r32(eth, MTK_CDMP_IG_CTRL); val &= ~MTK_CDMP_STAG_EN; diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index b144f2237748..f9b8f372ec8a 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1217,9 +1217,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) unsigned int max_queues_per_port = num_online_cpus(); struct gdma_context *gc = pci_get_drvdata(pdev); struct gdma_irq_context *gic; - unsigned int max_irqs; - u16 *cpus; - cpumask_var_t req_mask; + unsigned int max_irqs, cpu; int nvec, irq; int err, i = 0, j; @@ -1240,21 +1238,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) goto free_irq_vector; } - if (!zalloc_cpumask_var(&req_mask, GFP_KERNEL)) { - err = -ENOMEM; - goto free_irq; - } - - cpus = kcalloc(nvec, sizeof(*cpus), GFP_KERNEL); - if (!cpus) { - err = -ENOMEM; - goto free_mask; - } - for (i = 0; i < nvec; i++) - cpus[i] = cpumask_local_spread(i, gc->numa_node); - for (i = 0; i < nvec; i++) { - cpumask_set_cpu(cpus[i], req_mask); gic = &gc->irq_contexts[i]; gic->handler = NULL; gic->arg = NULL; @@ -1269,17 +1253,16 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) irq = pci_irq_vector(pdev, i); if (irq < 0) { err = irq; - goto free_mask; + goto free_irq; } err = request_irq(irq, mana_gd_intr, 0, gic->name, gic); if (err) - goto free_mask; - irq_set_affinity_and_hint(irq, req_mask); - cpumask_clear(req_mask); + goto free_irq; + + cpu = cpumask_local_spread(i, gc->numa_node); + irq_set_affinity_and_hint(irq, cpumask_of(cpu)); } - free_cpumask_var(req_mask); - kfree(cpus); err = mana_gd_alloc_res_map(nvec, &gc->msix_resource); if (err) @@ -1290,13 +1273,12 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) return 0; -free_mask: - free_cpumask_var(req_mask); - kfree(cpus); free_irq: for (j = i - 1; j >= 0; j--) { irq = pci_irq_vector(pdev, j); gic = &gc->irq_contexts[j]; + + irq_update_affinity_hint(irq, NULL); free_irq(irq, gic); } @@ -1324,6 +1306,9 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev) continue; gic = &gc->irq_contexts[i]; + + /* Need to clear the hint before free_irq */ + irq_update_affinity_hint(irq, NULL); free_irq(irq, gic); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index a4a89ef3f18b..cc97b3d00414 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -293,35 +293,131 @@ nfp_net_set_fec_link_mode(struct nfp_eth_table_port *eth_port, } } -static const u16 nfp_eth_media_table[] = { - [NFP_MEDIA_1000BASE_CX] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, - [NFP_MEDIA_1000BASE_KX] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, - [NFP_MEDIA_10GBASE_KX4] = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, - [NFP_MEDIA_10GBASE_KR] = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, - [NFP_MEDIA_10GBASE_CX4] = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, - [NFP_MEDIA_10GBASE_CR] = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, - [NFP_MEDIA_10GBASE_SR] = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, - [NFP_MEDIA_10GBASE_ER] = ETHTOOL_LINK_MODE_10000baseER_Full_BIT, - [NFP_MEDIA_25GBASE_KR] = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, - [NFP_MEDIA_25GBASE_KR_S] = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, - [NFP_MEDIA_25GBASE_CR] = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, - [NFP_MEDIA_25GBASE_CR_S] = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, - [NFP_MEDIA_25GBASE_SR] = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, - [NFP_MEDIA_40GBASE_CR4] = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, - [NFP_MEDIA_40GBASE_KR4] = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, - [NFP_MEDIA_40GBASE_SR4] = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, - [NFP_MEDIA_40GBASE_LR4] = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, - [NFP_MEDIA_50GBASE_KR] = ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, - [NFP_MEDIA_50GBASE_SR] = ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, - [NFP_MEDIA_50GBASE_CR] = ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, - [NFP_MEDIA_50GBASE_LR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, - [NFP_MEDIA_50GBASE_ER] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, - [NFP_MEDIA_50GBASE_FR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, - [NFP_MEDIA_100GBASE_KR4] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, - [NFP_MEDIA_100GBASE_SR4] = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, - [NFP_MEDIA_100GBASE_CR4] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, - [NFP_MEDIA_100GBASE_KP4] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, - [NFP_MEDIA_100GBASE_CR10] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, +static const struct nfp_eth_media_link_mode { + u16 ethtool_link_mode; + u16 speed; +} nfp_eth_media_table[NFP_MEDIA_LINK_MODES_NUMBER] = { + [NFP_MEDIA_1000BASE_CX] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + .speed = NFP_SPEED_1G, + }, + [NFP_MEDIA_1000BASE_KX] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + .speed = NFP_SPEED_1G, + }, + [NFP_MEDIA_10GBASE_KX4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_KR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_CX4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_CR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_SR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_ER] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseER_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_25GBASE_KR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_KR_S] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_CR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_CR_S] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_SR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_40GBASE_CR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_40GBASE_KR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_40GBASE_SR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_40GBASE_LR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_50GBASE_KR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_SR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_CR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_LR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_ER] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_FR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_100GBASE_KR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_SR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_CR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_KP4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_CR10] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, +}; + +static const unsigned int nfp_eth_speed_map[NFP_SUP_SPEED_NUMBER] = { + [NFP_SPEED_1G] = SPEED_1000, + [NFP_SPEED_10G] = SPEED_10000, + [NFP_SPEED_25G] = SPEED_25000, + [NFP_SPEED_40G] = SPEED_40000, + [NFP_SPEED_50G] = SPEED_50000, + [NFP_SPEED_100G] = SPEED_100000, }; static void nfp_add_media_link_mode(struct nfp_port *port, @@ -334,8 +430,12 @@ static void nfp_add_media_link_mode(struct nfp_port *port, }; struct nfp_cpp *cpp = port->app->cpp; - if (nfp_eth_read_media(cpp, ðm)) + if (nfp_eth_read_media(cpp, ðm)) { + bitmap_fill(port->speed_bitmap, NFP_SUP_SPEED_NUMBER); return; + } + + bitmap_zero(port->speed_bitmap, NFP_SUP_SPEED_NUMBER); for (u32 i = 0; i < 2; i++) { supported_modes[i] = le64_to_cpu(ethm.supported_modes[i]); @@ -344,20 +444,26 @@ static void nfp_add_media_link_mode(struct nfp_port *port, for (u32 i = 0; i < NFP_MEDIA_LINK_MODES_NUMBER; i++) { if (i < 64) { - if (supported_modes[0] & BIT_ULL(i)) - __set_bit(nfp_eth_media_table[i], + if (supported_modes[0] & BIT_ULL(i)) { + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.supported); + __set_bit(nfp_eth_media_table[i].speed, + port->speed_bitmap); + } if (advertised_modes[0] & BIT_ULL(i)) - __set_bit(nfp_eth_media_table[i], + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.advertising); } else { - if (supported_modes[1] & BIT_ULL(i - 64)) - __set_bit(nfp_eth_media_table[i], + if (supported_modes[1] & BIT_ULL(i - 64)) { + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.supported); + __set_bit(nfp_eth_media_table[i].speed, + port->speed_bitmap); + } if (advertised_modes[1] & BIT_ULL(i - 64)) - __set_bit(nfp_eth_media_table[i], + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.advertising); } } @@ -468,6 +574,22 @@ nfp_net_set_link_ksettings(struct net_device *netdev, if (cmd->base.speed != SPEED_UNKNOWN) { u32 speed = cmd->base.speed / eth_port->lanes; + bool is_supported = false; + + for (u32 i = 0; i < NFP_SUP_SPEED_NUMBER; i++) { + if (cmd->base.speed == nfp_eth_speed_map[i] && + test_bit(i, port->speed_bitmap)) { + is_supported = true; + break; + } + } + + if (!is_supported) { + netdev_err(netdev, "Speed %u is not supported.\n", + cmd->base.speed); + err = -EINVAL; + goto err_bad_set; + } if (req_aneg) { netdev_err(netdev, "Speed changing is not allowed when working on autoneg mode.\n"); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h index f8cd157ca1d7..9c04f9f0e2c9 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h @@ -38,6 +38,16 @@ enum nfp_port_flags { NFP_PORT_CHANGED = 0, }; +enum { + NFP_SPEED_1G, + NFP_SPEED_10G, + NFP_SPEED_25G, + NFP_SPEED_40G, + NFP_SPEED_50G, + NFP_SPEED_100G, + NFP_SUP_SPEED_NUMBER +}; + /** * struct nfp_port - structure representing NFP port * @netdev: backpointer to associated netdev @@ -52,6 +62,7 @@ enum nfp_port_flags { * @eth_forced: for %NFP_PORT_PHYS_PORT port is forced UP or DOWN, don't change * @eth_port: for %NFP_PORT_PHYS_PORT translated ETH Table port entry * @eth_stats: for %NFP_PORT_PHYS_PORT MAC stats if available + * @speed_bitmap: for %NFP_PORT_PHYS_PORT supported speed bitmap * @pf_id: for %NFP_PORT_PF_PORT, %NFP_PORT_VF_PORT ID of the PCI PF (0-3) * @vf_id: for %NFP_PORT_VF_PORT ID of the PCI VF within @pf_id * @pf_split: for %NFP_PORT_PF_PORT %true if PCI PF has more than one vNIC @@ -78,6 +89,7 @@ struct nfp_port { bool eth_forced; struct nfp_eth_table_port *eth_port; u8 __iomem *eth_stats; + DECLARE_BITMAP(speed_bitmap, NFP_SUP_SPEED_NUMBER); }; /* NFP_PORT_PF_PORT, NFP_PORT_VF_PORT */ struct { diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index e02d1e3ef672..79f4e13620a4 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1034,7 +1034,7 @@ static int netvsc_dma_map(struct hv_device *hv_dev, packet->dma_range = kcalloc(page_count, sizeof(*packet->dma_range), - GFP_KERNEL); + GFP_ATOMIC); if (!packet->dma_range) return -ENOMEM; diff --git a/net/can/j1939/address-claim.c b/net/can/j1939/address-claim.c index f33c47327927..ca4ad6cdd5cb 100644 --- a/net/can/j1939/address-claim.c +++ b/net/can/j1939/address-claim.c @@ -165,6 +165,46 @@ static void j1939_ac_process(struct j1939_priv *priv, struct sk_buff *skb) * leaving this function. */ ecu = j1939_ecu_get_by_name_locked(priv, name); + + if (ecu && ecu->addr == skcb->addr.sa) { + /* The ISO 11783-5 standard, in "4.5.2 - Address claim + * requirements", states: + * d) No CF shall begin, or resume, transmission on the + * network until 250 ms after it has successfully claimed + * an address except when responding to a request for + * address-claimed. + * + * But "Figure 6" and "Figure 7" in "4.5.4.2 - Address-claim + * prioritization" show that the CF begins the transmission + * after 250 ms from the first AC (address-claimed) message + * even if it sends another AC message during that time window + * to resolve the address contention with another CF. + * + * As stated in "4.4.2.3 - Address-claimed message": + * In order to successfully claim an address, the CF sending + * an address claimed message shall not receive a contending + * claim from another CF for at least 250 ms. + * + * As stated in "4.4.3.2 - NAME management (NM) message": + * 1) A commanding CF can + * d) request that a CF with a specified NAME transmit + * the address-claimed message with its current NAME. + * 2) A target CF shall + * d) send an address-claimed message in response to a + * request for a matching NAME + * + * Taking the above arguments into account, the 250 ms wait is + * requested only during network initialization. + * + * Do not restart the timer on AC message if both the NAME and + * the address match and so if the address has already been + * claimed (timer has expired) or the AC message has been sent + * to resolve the contention with another CF (timer is still + * running). + */ + goto out_ecu_put; + } + if (!ecu && j1939_address_is_unicast(skcb->addr.sa)) ecu = j1939_ecu_create_locked(priv, name); diff --git a/net/core/sock.c b/net/core/sock.c index f954d5893e79..6f27c24016fe 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1531,6 +1531,8 @@ set_sndbuf: ret = -EINVAL; break; } + if ((u8)val == SOCK_TXREHASH_DEFAULT) + val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); /* Paired with READ_ONCE() in tcp_rtx_synack() */ WRITE_ONCE(sk->sk_txrehash, (u8)val); break; @@ -3451,7 +3453,6 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; - sk->sk_txrehash = SOCK_TXREHASH_DEFAULT; sk_rx_queue_clear(sk); /* diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 6c0ec2789943..cf11f10927e1 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -347,6 +347,7 @@ lookup_protocol: sk->sk_destruct = inet_sock_destruct; sk->sk_protocol = protocol; sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; + sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); inet->uc_ttl = -1; inet->mc_loop = 1; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d1f837579398..f2c43f67187d 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1225,9 +1225,6 @@ int inet_csk_listen_start(struct sock *sk) sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); - if (sk->sk_txrehash == SOCK_TXREHASH_DEFAULT) - sk->sk_txrehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); - /* There is race window here: we announce ourselves listening, * but this transition is still not validated by get_port(). * It is OK, because this socket enters to hash table only diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index fee9163382c2..847934763868 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -222,6 +222,7 @@ lookup_protocol: np->pmtudisc = IPV6_PMTUDISC_WANT; np->repflow = net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ESTABLISHED; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; + sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); /* Init the ipv4 part of the socket since we can have sockets * using v6 API for ipv4. diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 2ea7eae43bdb..10fe9771a852 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -998,8 +998,8 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, { int addrlen = sizeof(struct sockaddr_in); struct sockaddr_storage addr; - struct mptcp_sock *msk; struct socket *ssock; + struct sock *newsk; int backlog = 1024; int err; @@ -1008,11 +1008,13 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, if (err) return err; - msk = mptcp_sk(entry->lsk->sk); - if (!msk) + newsk = entry->lsk->sk; + if (!newsk) return -EINVAL; - ssock = __mptcp_nmpc_socket(msk); + lock_sock(newsk); + ssock = __mptcp_nmpc_socket(mptcp_sk(newsk)); + release_sock(newsk); if (!ssock) return -EINVAL; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 8cd6cc67c2c5..bc6c1f62a690 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2897,6 +2897,7 @@ bool __mptcp_close(struct sock *sk, long timeout) struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); bool do_cancel_work = false; + int subflows_alive = 0; sk->sk_shutdown = SHUTDOWN_MASK; @@ -2922,6 +2923,8 @@ cleanup: struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); + subflows_alive += ssk->sk_state != TCP_CLOSE; + /* since the close timeout takes precedence on the fail one, * cancel the latter */ @@ -2937,6 +2940,12 @@ cleanup: } sock_orphan(sk); + /* all the subflows are closed, only timeout can change the msk + * state, let's not keep resources busy for no reasons + */ + if (subflows_alive == 0) + inet_sk_state_store(sk, TCP_CLOSE); + sock_hold(sk); pr_debug("msk=%p state=%d", sk, sk->sk_state); if (msk->token) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index d4b1e6ec1b36..7f2c3727ab23 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -760,14 +760,21 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname, static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname, sockptr_t optval, unsigned int optlen) { + struct sock *sk = (struct sock *)msk; struct socket *sock; + int ret = -EINVAL; /* Limit to first subflow, before the connection establishment */ + lock_sock(sk); sock = __mptcp_nmpc_socket(msk); if (!sock) - return -EINVAL; + goto unlock; - return tcp_setsockopt(sock->sk, level, optname, optval, optlen); + ret = tcp_setsockopt(sock->sk, level, optname, optval, optlen); + +unlock: + release_sock(sk); + return ret; } static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ec54413fb31f..32904c76c6a1 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1399,6 +1399,7 @@ void __mptcp_error_report(struct sock *sk) mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); int err = sock_error(ssk); + int ssk_state; if (!err) continue; @@ -1409,7 +1410,14 @@ void __mptcp_error_report(struct sock *sk) if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) continue; - inet_sk_state_store(sk, inet_sk_state_load(ssk)); + /* We need to propagate only transition to CLOSE state. + * Orphaned socket will see such state change via + * subflow_sched_work_if_closed() and that path will properly + * destroy the msk as needed. + */ + ssk_state = inet_sk_state_load(ssk); + if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) + inet_sk_state_store(sk, ssk_state); sk->sk_err = -err; /* This barrier is coupled with smp_rmb() in mptcp_poll() */ @@ -1679,7 +1687,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, if (err) return err; - lock_sock(sf->sk); + lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING); /* the newly created socket has to be in the same cgroup as its parent */ mptcp_attach_cgroup(sk, sf->sk); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index cc28e41fb745..92f2975b6a82 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -433,7 +433,7 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) while (m) { unsigned int prio = ffz(~m); - if (WARN_ON_ONCE(prio > ARRAY_SIZE(p->inner.clprio))) + if (WARN_ON_ONCE(prio >= ARRAY_SIZE(p->inner.clprio))) break; m &= ~(1 << prio); diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index d11d3d566608..079f8f46849d 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -498,6 +498,12 @@ kill_events_pids() kill_wait $evts_ns2_pid } +kill_tests_wait() +{ + kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1) + wait +} + pm_nl_set_limits() { local ns=$1 @@ -1694,6 +1700,7 @@ chk_subflow_nr() local subflow_nr=$3 local cnt1 local cnt2 + local dump_stats if [ -n "${need_title}" ]; then printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" @@ -1711,7 +1718,12 @@ chk_subflow_nr() echo "[ ok ]" fi - [ "${dump_stats}" = 1 ] && ( ss -N $ns1 -tOni ; ss -N $ns1 -tOni | grep token; ip -n $ns1 mptcp endpoint ) + if [ "${dump_stats}" = 1 ]; then + ss -N $ns1 -tOni + ss -N $ns1 -tOni | grep token + ip -n $ns1 mptcp endpoint + dump_stats + fi } chk_link_usage() @@ -3049,7 +3061,7 @@ endpoint_tests() pm_nl_set_limits $ns1 2 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow 2>/dev/null & wait_mpj $ns1 pm_nl_check_endpoint 1 "creation" \ @@ -3062,14 +3074,14 @@ endpoint_tests() pm_nl_add_endpoint $ns2 10.0.2.2 flags signal pm_nl_check_endpoint 0 "modif is allowed" \ $ns2 10.0.2.2 id 1 flags signal - wait + kill_tests_wait fi if reset "delete and re-add"; then pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 4 0 0 slow & + run_tests $ns1 $ns2 10.0.1.1 4 0 0 speed_20 2>/dev/null & wait_mpj $ns2 pm_nl_del_endpoint $ns2 2 10.0.2.2 @@ -3079,7 +3091,7 @@ endpoint_tests() pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow wait_mpj $ns2 chk_subflow_nr "" "after re-add" 2 - wait + kill_tests_wait fi } diff --git a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh index 704997ffc244..8c3ac0a72545 100755 --- a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh +++ b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh @@ -293,19 +293,11 @@ setup-vm() { elif [[ -n $vtype && $vtype == "vnifilterg" ]]; then # Add per vni group config with 'bridge vni' api if [ -n "$group" ]; then - if [ "$family" == "v4" ]; then - if [ $mcast -eq 1 ]; then - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group - else - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group - fi - else - if [ $mcast -eq 1 ]; then - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group6 $group - else - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote6 $group - fi - fi + if [ $mcast -eq 1 ]; then + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group + else + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group + fi fi fi done |