diff --git a/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst b/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst index eaa87dbe8848..d052ef40fe36 100644 --- a/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst +++ b/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst @@ -16,5 +16,5 @@ Contents Support ======= -If you got any problem, contact Wangxun support team via support@trustnetic.com +If you got any problem, contact Wangxun support team via nic-support@net-swift.com and Cc: netdev. diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index 4f9b4a18c74c..594094526648 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -76,7 +76,7 @@ void bond_debug_reregister(struct bonding *bond) d = debugfs_rename(bonding_debug_root, bond->debug_dir, bonding_debug_root, bond->dev->name); - if (d) { + if (!IS_ERR(d)) { bond->debug_dir = d; } else { netdev_warn(bond->dev, "failed to reregister, so just unregister old one\n"); diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 908fa89444c9..338f238f2043 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1309,14 +1309,26 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port) if (!priv->ports[port].pvid) mt7530_rmw(priv, MT7530_PVC_P(port), ACC_FRM_MASK, MT7530_VLAN_ACC_TAGGED); - } - /* Set the port as a user port which is to be able to recognize VID - * from incoming packets before fetching entry within the VLAN table. - */ - mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK, - VLAN_ATTR(MT7530_VLAN_USER) | - PVC_EG_TAG(MT7530_VLAN_EG_DISABLED)); + /* Set the port as a user port which is to be able to recognize + * VID from incoming packets before fetching entry within the + * VLAN table. + */ + mt7530_rmw(priv, MT7530_PVC_P(port), + VLAN_ATTR_MASK | PVC_EG_TAG_MASK, + VLAN_ATTR(MT7530_VLAN_USER) | + PVC_EG_TAG(MT7530_VLAN_EG_DISABLED)); + } else { + /* Also set CPU ports to the "user" VLAN port attribute, to + * allow VLAN classification, but keep the EG_TAG attribute as + * "consistent" (i.o.w. don't change its value) for packets + * received by the switch from the CPU, so that tagged packets + * are forwarded to user ports as tagged, and untagged as + * untagged. + */ + mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK, + VLAN_ATTR(MT7530_VLAN_USER)); + } } static void diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 72e42820713d..6cda31520c42 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -4627,25 +4627,26 @@ static int init_reset_optional(struct platform_device *pdev) if (ret) return dev_err_probe(&pdev->dev, ret, "failed to init SGMII PHY\n"); - } - ret = zynqmp_pm_is_function_supported(PM_IOCTL, IOCTL_SET_GEM_CONFIG); - if (!ret) { - u32 pm_info[2]; + ret = zynqmp_pm_is_function_supported(PM_IOCTL, IOCTL_SET_GEM_CONFIG); + if (!ret) { + u32 pm_info[2]; - ret = of_property_read_u32_array(pdev->dev.of_node, "power-domains", - pm_info, ARRAY_SIZE(pm_info)); - if (ret) { - dev_err(&pdev->dev, "Failed to read power management information\n"); - goto err_out_phy_exit; + ret = of_property_read_u32_array(pdev->dev.of_node, "power-domains", + pm_info, ARRAY_SIZE(pm_info)); + if (ret) { + dev_err(&pdev->dev, "Failed to read power management information\n"); + goto err_out_phy_exit; + } + ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_FIXED, 0); + if (ret) + goto err_out_phy_exit; + + ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_SGMII_MODE, 1); + if (ret) + goto err_out_phy_exit; } - ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_FIXED, 0); - if (ret) - goto err_out_phy_exit; - ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_SGMII_MODE, 1); - if (ret) - goto err_out_phy_exit; } /* Fully reset controller at hardware level if mapped in device tree */ 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" @@ -5068,6 +5070,24 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu) return 0; } +/** + * 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 @@ -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/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 3e232a65a0c3..bb95b40d25eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -245,8 +245,9 @@ void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev) pages = dev->priv.dbg.pages_debugfs; debugfs_create_u32("fw_pages_total", 0400, pages, &dev->priv.fw_pages); - debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.vfs_pages); - debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.host_pf_pages); + debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.page_counters[MLX5_VF]); + debugfs_create_u32("fw_pages_sfs", 0400, pages, &dev->priv.page_counters[MLX5_SF]); + debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.page_counters[MLX5_HOST_PF]); debugfs_create_u32("fw_pages_alloc_failed", 0400, pages, &dev->priv.fw_pages_alloc_failed); debugfs_create_u32("fw_pages_give_dropped", 0400, pages, &dev->priv.give_pages_dropped); debugfs_create_u32("fw_pages_reclaim_discard", 0400, pages, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 21831386b26e..5b05b884b5fb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -64,6 +64,7 @@ static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer) MLX5_GET(mtrc_cap, out, num_string_trace); tracer->str_db.num_string_db = MLX5_GET(mtrc_cap, out, num_string_db); tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner); + tracer->str_db.loaded = false; for (i = 0; i < tracer->str_db.num_string_db; i++) { mtrc_cap_sp = MLX5_ADDR_OF(mtrc_cap, out, string_db_param[i]); @@ -756,6 +757,7 @@ static int mlx5_fw_tracer_set_mtrc_conf(struct mlx5_fw_tracer *tracer) if (err) mlx5_core_warn(dev, "FWTracer: Failed to set tracer configurations %d\n", err); + tracer->buff.consumer_index = 0; return err; } @@ -820,7 +822,6 @@ static void mlx5_fw_tracer_ownership_change(struct work_struct *work) mlx5_core_dbg(tracer->dev, "FWTracer: ownership changed, current=(%d)\n", tracer->owner); if (tracer->owner) { tracer->owner = false; - tracer->buff.consumer_index = 0; return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index 464eb3a18450..cdc87ecae5d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -87,7 +87,7 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev) mlx5_host_pf_cleanup(dev); - err = mlx5_wait_for_pages(dev, &dev->priv.host_pf_pages); + err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]); if (err) mlx5_core_warn(dev, "Timeout reclaiming external host PF pages err(%d)\n", err); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index 8099a21e674c..ce85b48d327d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -438,10 +438,6 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb, switch (event) { case SWITCHDEV_FDB_ADD_TO_BRIDGE: - /* only handle the event on native eswtich of representor */ - if (!mlx5_esw_bridge_is_local(dev, rep, esw)) - break; - fdb_info = container_of(info, struct switchdev_notifier_fdb_info, info); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 1892ccb889b3..7cd36f4ac3ef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -443,7 +443,7 @@ void mlx5e_enable_cvlan_filter(struct mlx5e_flow_steering *fs, bool promisc) void mlx5e_disable_cvlan_filter(struct mlx5e_flow_steering *fs, bool promisc) { - if (fs->vlan->cvlan_filter_disabled) + if (!fs->vlan || fs->vlan->cvlan_filter_disabled) return; fs->vlan->cvlan_filter_disabled = true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index abcc614b6191..6c24f33a5ea5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -591,7 +591,8 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param rq->ix = c->ix; rq->channel = c; rq->mdev = mdev; - rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); + rq->hw_mtu = + MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN * !params->scatter_fcs_en; rq->xdpsq = &c->rq_xdpsq; rq->stats = &c->priv->channel_stats[c->ix]->rq; rq->ptp_cyc2time = mlx5_rq_ts_translator(mdev); @@ -1014,35 +1015,6 @@ int mlx5e_flush_rq(struct mlx5e_rq *rq, int curr_state) return mlx5e_rq_to_ready(rq, curr_state); } -static int mlx5e_modify_rq_scatter_fcs(struct mlx5e_rq *rq, bool enable) -{ - struct mlx5_core_dev *mdev = rq->mdev; - - void *in; - void *rqc; - int inlen; - int err; - - inlen = MLX5_ST_SZ_BYTES(modify_rq_in); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return -ENOMEM; - - rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx); - - MLX5_SET(modify_rq_in, in, rq_state, MLX5_RQC_STATE_RDY); - MLX5_SET64(modify_rq_in, in, modify_bitmask, - MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_SCATTER_FCS); - MLX5_SET(rqc, rqc, scatter_fcs, enable); - MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY); - - err = mlx5_core_modify_rq(mdev, rq->rqn, in); - - kvfree(in); - - return err; -} - static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd) { struct mlx5_core_dev *mdev = rq->mdev; @@ -3314,20 +3286,6 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) mlx5e_destroy_tises(priv); } -static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable) -{ - int err = 0; - int i; - - for (i = 0; i < chs->num; i++) { - err = mlx5e_modify_rq_scatter_fcs(&chs->c[i]->rq, enable); - if (err) - return err; - } - - return 0; -} - static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) { int err; @@ -3903,41 +3861,27 @@ static int mlx5e_set_rx_port_ts(struct mlx5_core_dev *mdev, bool enable) return mlx5_set_ports_check(mdev, in, sizeof(in)); } +static int mlx5e_set_rx_port_ts_wrap(struct mlx5e_priv *priv, void *ctx) +{ + struct mlx5_core_dev *mdev = priv->mdev; + bool enable = *(bool *)ctx; + + return mlx5e_set_rx_port_ts(mdev, enable); +} + static int set_feature_rx_fcs(struct net_device *netdev, bool enable) { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_channels *chs = &priv->channels; - struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_params new_params; int err; mutex_lock(&priv->state_lock); - if (enable) { - err = mlx5e_set_rx_port_ts(mdev, false); - if (err) - goto out; - - chs->params.scatter_fcs_en = true; - err = mlx5e_modify_channels_scatter_fcs(chs, true); - if (err) { - chs->params.scatter_fcs_en = false; - mlx5e_set_rx_port_ts(mdev, true); - } - } else { - chs->params.scatter_fcs_en = false; - err = mlx5e_modify_channels_scatter_fcs(chs, false); - if (err) { - chs->params.scatter_fcs_en = true; - goto out; - } - err = mlx5e_set_rx_port_ts(mdev, true); - if (err) { - mlx5_core_warn(mdev, "Failed to set RX port timestamp %d\n", err); - err = 0; - } - } - -out: + new_params = chs->params; + new_params.scatter_fcs_en = enable; + err = mlx5e_safe_switch_params(priv, &new_params, mlx5e_set_rx_port_ts_wrap, + &new_params.scatter_fcs_en, true); mutex_unlock(&priv->state_lock); return err; } @@ -4074,6 +4018,10 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev if (netdev->features & NETIF_F_GRO_HW) netdev_warn(netdev, "Disabling HW_GRO, not supported in switchdev mode\n"); + features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + if (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER) + netdev_warn(netdev, "Disabling HW_VLAN CTAG FILTERING, not supported in switchdev mode\n"); + return features; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index b176648d1343..3cdcb0e0b20f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -1715,7 +1715,7 @@ void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 struct mlx5_esw_bridge *bridge; port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); - if (!port || port->flags & MLX5_ESW_BRIDGE_PORT_FLAG_PEER) + if (!port) return; bridge = port->bridge; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index eff92dc0927c..e09518f887a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -189,16 +189,16 @@ static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate) } } -static int mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper) +static u32 mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper) { int rate, width; rate = mlx5_ptys_rate_enum_to_int(ib_proto_oper); if (rate < 0) - return -EINVAL; + return SPEED_UNKNOWN; width = mlx5_ptys_width_enum_to_int(ib_link_width_oper); if (width < 0) - return -EINVAL; + return SPEED_UNKNOWN; return rate * width; } @@ -221,16 +221,13 @@ static int mlx5i_get_link_ksettings(struct net_device *netdev, ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); speed = mlx5i_get_speed_settings(ib_link_width_oper, ib_proto_oper); - if (speed < 0) - return -EINVAL; + link_ksettings->base.speed = speed; + link_ksettings->base.duplex = speed == SPEED_UNKNOWN ? DUPLEX_UNKNOWN : DUPLEX_FULL; - link_ksettings->base.duplex = DUPLEX_FULL; link_ksettings->base.port = PORT_OTHER; link_ksettings->base.autoneg = AUTONEG_DISABLE; - link_ksettings->base.speed = speed; - return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 3d5f2a4b1fed..4e1b5757528a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -2110,7 +2110,7 @@ static int __init mlx5_init(void) mlx5_core_verify_params(); mlx5_register_debugfs(); - err = pci_register_driver(&mlx5_core_driver); + err = mlx5e_init(); if (err) goto err_debug; @@ -2118,16 +2118,16 @@ static int __init mlx5_init(void) if (err) goto err_sf; - err = mlx5e_init(); + err = pci_register_driver(&mlx5_core_driver); if (err) - goto err_en; + goto err_pci; return 0; -err_en: +err_pci: mlx5_sf_driver_unregister(); err_sf: - pci_unregister_driver(&mlx5_core_driver); + mlx5e_cleanup(); err_debug: mlx5_unregister_debugfs(); return err; @@ -2135,9 +2135,9 @@ err_debug: static void __exit mlx5_cleanup(void) { - mlx5e_cleanup(); - mlx5_sf_driver_unregister(); pci_unregister_driver(&mlx5_core_driver); + mlx5_sf_driver_unregister(); + mlx5e_cleanup(); mlx5_unregister_debugfs(); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 60596357bfc7..0eb50be175cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -74,6 +74,14 @@ static u32 get_function(u16 func_id, bool ec_function) return (u32)func_id | (ec_function << 16); } +static u16 func_id_to_type(struct mlx5_core_dev *dev, u16 func_id, bool ec_function) +{ + if (!func_id) + return mlx5_core_is_ecpf(dev) && !ec_function ? MLX5_HOST_PF : MLX5_PF; + + return func_id <= mlx5_core_max_vfs(dev) ? MLX5_VF : MLX5_SF; +} + static struct rb_root *page_root_per_function(struct mlx5_core_dev *dev, u32 function) { struct rb_root *root; @@ -332,6 +340,7 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0}; int inlen = MLX5_ST_SZ_BYTES(manage_pages_in); int notify_fail = event; + u16 func_type; u64 addr; int err; u32 *in; @@ -383,11 +392,9 @@ retry: goto out_dropped; } + func_type = func_id_to_type(dev, func_id, ec_function); + dev->priv.page_counters[func_type] += npages; dev->priv.fw_pages += npages; - if (func_id) - dev->priv.vfs_pages += npages; - else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.host_pf_pages += npages; mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n", npages, ec_function, func_id, err); @@ -414,6 +421,7 @@ static void release_all_pages(struct mlx5_core_dev *dev, u16 func_id, struct rb_root *root; struct rb_node *p; int npages = 0; + u16 func_type; root = xa_load(&dev->priv.page_root_xa, function); if (WARN_ON_ONCE(!root)) @@ -428,11 +436,9 @@ static void release_all_pages(struct mlx5_core_dev *dev, u16 func_id, free_fwp(dev, fwp, fwp->free_count); } + func_type = func_id_to_type(dev, func_id, ec_function); + dev->priv.page_counters[func_type] -= npages; dev->priv.fw_pages -= npages; - if (func_id) - dev->priv.vfs_pages -= npages; - else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.host_pf_pages -= npages; mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x\n", npages, ec_function, func_id); @@ -498,6 +504,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, int outlen = MLX5_ST_SZ_BYTES(manage_pages_out); u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {}; int num_claimed; + u16 func_type; u32 *out; int err; int i; @@ -549,11 +556,9 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, if (nclaimed) *nclaimed = num_claimed; + func_type = func_id_to_type(dev, func_id, ec_function); + dev->priv.page_counters[func_type] -= num_claimed; dev->priv.fw_pages -= num_claimed; - if (func_id) - dev->priv.vfs_pages -= num_claimed; - else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.host_pf_pages -= num_claimed; out_free: kvfree(out); @@ -706,12 +711,12 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) WARN(dev->priv.fw_pages, "FW pages counter is %d after reclaiming all pages\n", dev->priv.fw_pages); - WARN(dev->priv.vfs_pages, + WARN(dev->priv.page_counters[MLX5_VF], "VFs FW pages counter is %d after reclaiming all pages\n", - dev->priv.vfs_pages); - WARN(dev->priv.host_pf_pages, + dev->priv.page_counters[MLX5_VF]); + WARN(dev->priv.page_counters[MLX5_HOST_PF], "External host PF FW pages counter is %d after reclaiming all pages\n", - dev->priv.host_pf_pages); + dev->priv.page_counters[MLX5_HOST_PF]); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index c0e6c487c63c..3008e9ce2bbf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -147,7 +147,7 @@ mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf) mlx5_eswitch_disable_sriov(dev->priv.eswitch, clear_vf); - if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages)) + if (mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_VF])) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index b851141e03de..042ca0349124 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -1138,12 +1138,14 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, rule->flow_source)) return 0; + mlx5dr_domain_nic_lock(nic_dmn); + ret = mlx5dr_matcher_select_builders(matcher, nic_matcher, dr_rule_get_ipv(¶m->outer), dr_rule_get_ipv(¶m->inner)); if (ret) - return ret; + goto err_unlock; hw_ste_arr_is_opt = nic_matcher->num_of_builders <= DR_RULE_MAX_STES_OPTIMIZED; if (likely(hw_ste_arr_is_opt)) { @@ -1152,12 +1154,12 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, hw_ste_arr = kzalloc((nic_matcher->num_of_builders + DR_ACTION_MAX_STES) * DR_STE_SIZE, GFP_KERNEL); - if (!hw_ste_arr) - return -ENOMEM; + if (!hw_ste_arr) { + ret = -ENOMEM; + goto err_unlock; + } } - mlx5dr_domain_nic_lock(nic_dmn); - ret = mlx5dr_matcher_add_to_tbl_nic(dmn, nic_matcher); if (ret) goto free_hw_ste; @@ -1223,7 +1225,10 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, mlx5dr_domain_nic_unlock(nic_dmn); - goto out; + if (unlikely(!hw_ste_arr_is_opt)) + kfree(hw_ste_arr); + + return 0; free_rule: dr_rule_clean_rule_members(rule, nic_rule); @@ -1238,12 +1243,12 @@ remove_from_nic_tbl: mlx5dr_matcher_remove_from_tbl_nic(dmn, nic_matcher); free_hw_ste: - mlx5dr_domain_nic_unlock(nic_dmn); - -out: - if (unlikely(!hw_ste_arr_is_opt)) + if (!hw_ste_arr_is_opt) kfree(hw_ste_arr); +err_unlock: + mlx5dr_domain_nic_unlock(nic_dmn); + return ret; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c index 0ed1ea7727c5..69e76634f9aa 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c @@ -633,7 +633,7 @@ int sparx5_ptp_init(struct sparx5 *sparx5) /* Enable master counters */ spx5_wr(PTP_PTP_DOM_CFG_PTP_ENA_SET(0x7), sparx5, PTP_PTP_DOM_CFG); - for (i = 0; i < sparx5->port_count; i++) { + for (i = 0; i < SPX5_PORTS; i++) { port = sparx5->ports[i]; if (!port) continue; @@ -649,7 +649,7 @@ void sparx5_ptp_deinit(struct sparx5 *sparx5) struct sparx5_port *port; int i; - for (i = 0; i < sparx5->port_count; i++) { + for (i = 0; i < SPX5_PORTS; i++) { port = sparx5->ports[i]; if (!port) continue; 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/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index 7c0897e779dc..ee052404eb55 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -605,6 +605,18 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress, flow_rule_match_control(rule, &match); } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + + flow_rule_match_vlan(rule, &match); + filter->key_type = OCELOT_VCAP_KEY_ANY; + filter->vlan.vid.value = match.key->vlan_id; + filter->vlan.vid.mask = match.mask->vlan_id; + filter->vlan.pcp.value[0] = match.key->vlan_priority; + filter->vlan.pcp.mask[0] = match.mask->vlan_priority; + match_protocol = false; + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct flow_match_eth_addrs match; @@ -737,18 +749,6 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress, match_protocol = false; } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_match_vlan match; - - flow_rule_match_vlan(rule, &match); - filter->key_type = OCELOT_VCAP_KEY_ANY; - filter->vlan.vid.value = match.key->vlan_id; - filter->vlan.vid.mask = match.mask->vlan_id; - filter->vlan.pcp.value[0] = match.key->vlan_priority; - filter->vlan.pcp.mask[0] = match.mask->vlan_priority; - match_protocol = false; - } - finished_key_parsing: if (match_protocol && proto != ETH_P_ALL) { if (filter->block_id == VCAP_ES0) { diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c index 1a82f10c8853..2180ae94c744 100644 --- a/drivers/net/ethernet/mscc/ocelot_ptp.c +++ b/drivers/net/ethernet/mscc/ocelot_ptp.c @@ -335,8 +335,8 @@ static void ocelot_populate_ipv6_ptp_event_trap_key(struct ocelot_vcap_filter *trap) { trap->key_type = OCELOT_VCAP_KEY_IPV6; - trap->key.ipv4.proto.value[0] = IPPROTO_UDP; - trap->key.ipv4.proto.mask[0] = 0xff; + trap->key.ipv6.proto.value[0] = IPPROTO_UDP; + trap->key.ipv6.proto.mask[0] = 0xff; trap->key.ipv6.dport.value = PTP_EV_PORT; trap->key.ipv6.dport.mask = 0xffff; } @@ -355,8 +355,8 @@ static void ocelot_populate_ipv6_ptp_general_trap_key(struct ocelot_vcap_filter *trap) { trap->key_type = OCELOT_VCAP_KEY_IPV6; - trap->key.ipv4.proto.value[0] = IPPROTO_UDP; - trap->key.ipv4.proto.mask[0] = 0xff; + trap->key.ipv6.proto.value[0] = IPPROTO_UDP; + trap->key.ipv6.proto.mask[0] = 0xff; trap->key.ipv6.dport.value = PTP_GEN_PORT; trap->key.ipv6.dport.mask = 0xffff; } 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/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 626b9113e7c4..d911f4fd9af6 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -708,9 +708,16 @@ void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb, q->lif->index, q->name, q->hw_type, q->hw_index, q->head_idx, ring_doorbell); - if (ring_doorbell) + if (ring_doorbell) { ionic_dbell_ring(lif->kern_dbpage, q->hw_type, q->dbval | q->head_idx); + + q->dbell_jiffies = jiffies; + + if (q_to_qcq(q)->napi_qcq) + mod_timer(&q_to_qcq(q)->napi_qcq->napi_deadline, + jiffies + IONIC_NAPI_DEADLINE); + } } static bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index 2a1d7b9c07e7..bce3ca38669b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -25,6 +25,12 @@ #define IONIC_DEV_INFO_REG_COUNT 32 #define IONIC_DEV_CMD_REG_COUNT 32 +#define IONIC_NAPI_DEADLINE (HZ / 200) /* 5ms */ +#define IONIC_ADMIN_DOORBELL_DEADLINE (HZ / 2) /* 500ms */ +#define IONIC_TX_DOORBELL_DEADLINE (HZ / 100) /* 10ms */ +#define IONIC_RX_MIN_DOORBELL_DEADLINE (HZ / 100) /* 10ms */ +#define IONIC_RX_MAX_DOORBELL_DEADLINE (HZ * 5) /* 5s */ + struct ionic_dev_bar { void __iomem *vaddr; phys_addr_t bus_addr; @@ -216,6 +222,8 @@ struct ionic_queue { struct ionic_lif *lif; struct ionic_desc_info *info; u64 dbval; + unsigned long dbell_deadline; + unsigned long dbell_jiffies; u16 head_idx; u16 tail_idx; unsigned int index; @@ -361,4 +369,8 @@ void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, int ionic_heartbeat_check(struct ionic *ionic); bool ionic_is_fw_running(struct ionic_dev *idev); +bool ionic_adminq_poke_doorbell(struct ionic_queue *q); +bool ionic_txq_poke_doorbell(struct ionic_queue *q); +bool ionic_rxq_poke_doorbell(struct ionic_queue *q); + #endif /* _IONIC_DEV_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 4dd16c487f2b..63a78a9ac241 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -16,6 +16,7 @@ #include "ionic.h" #include "ionic_bus.h" +#include "ionic_dev.h" #include "ionic_lif.h" #include "ionic_txrx.h" #include "ionic_ethtool.h" @@ -200,6 +201,13 @@ void ionic_link_status_check_request(struct ionic_lif *lif, bool can_sleep) } } +static void ionic_napi_deadline(struct timer_list *timer) +{ + struct ionic_qcq *qcq = container_of(timer, struct ionic_qcq, napi_deadline); + + napi_schedule(&qcq->napi); +} + static irqreturn_t ionic_isr(int irq, void *data) { struct napi_struct *napi = data; @@ -269,6 +277,7 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) .oper = IONIC_Q_ENABLE, }, }; + int ret; idev = &lif->ionic->idev; dev = lif->ionic->dev; @@ -276,16 +285,24 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) dev_dbg(dev, "q_enable.index %d q_enable.qtype %d\n", ctx.cmd.q_control.index, ctx.cmd.q_control.type); + if (qcq->flags & IONIC_QCQ_F_INTR) + ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); + + ret = ionic_adminq_post_wait(lif, &ctx); + if (ret) + return ret; + + if (qcq->napi.poll) + napi_enable(&qcq->napi); + if (qcq->flags & IONIC_QCQ_F_INTR) { irq_set_affinity_hint(qcq->intr.vector, &qcq->intr.affinity_mask); - napi_enable(&qcq->napi); - ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, IONIC_INTR_MASK_CLEAR); } - return ionic_adminq_post_wait(lif, &ctx); + return 0; } static int ionic_qcq_disable(struct ionic_lif *lif, struct ionic_qcq *qcq, int fw_err) @@ -316,6 +333,7 @@ static int ionic_qcq_disable(struct ionic_lif *lif, struct ionic_qcq *qcq, int f synchronize_irq(qcq->intr.vector); irq_set_affinity_hint(qcq->intr.vector, NULL); napi_disable(&qcq->napi); + del_timer_sync(&qcq->napi_deadline); } /* If there was a previous fw communcation error, don't bother with @@ -451,6 +469,7 @@ static void ionic_link_qcq_interrupts(struct ionic_qcq *src_qcq, n_qcq->intr.vector = src_qcq->intr.vector; n_qcq->intr.index = src_qcq->intr.index; + n_qcq->napi_qcq = src_qcq->napi_qcq; } static int ionic_alloc_qcq_interrupt(struct ionic_lif *lif, struct ionic_qcq *qcq) @@ -564,13 +583,15 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, } if (flags & IONIC_QCQ_F_NOTIFYQ) { - int q_size, cq_size; + int q_size; - /* q & cq need to be contiguous in case of notifyq */ + /* q & cq need to be contiguous in NotifyQ, so alloc it all in q + * and don't alloc qc. We leave new->qc_size and new->qc_base + * as 0 to be sure we don't try to free it later. + */ q_size = ALIGN(num_descs * desc_size, PAGE_SIZE); - cq_size = ALIGN(num_descs * cq_desc_size, PAGE_SIZE); - - new->q_size = PAGE_SIZE + q_size + cq_size; + new->q_size = PAGE_SIZE + q_size + + ALIGN(num_descs * cq_desc_size, PAGE_SIZE); new->q_base = dma_alloc_coherent(dev, new->q_size, &new->q_base_pa, GFP_KERNEL); if (!new->q_base) { @@ -773,8 +794,14 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "txq->hw_type %d\n", q->hw_type); dev_dbg(dev, "txq->hw_index %d\n", q->hw_index); - if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + q->dbell_deadline = IONIC_TX_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) { netif_napi_add(lif->netdev, &qcq->napi, ionic_tx_napi); + qcq->napi_qcq = qcq; + timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0); + } qcq->flags |= IONIC_QCQ_F_INITED; @@ -828,11 +855,17 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "rxq->hw_type %d\n", q->hw_type); dev_dbg(dev, "rxq->hw_index %d\n", q->hw_index); + q->dbell_deadline = IONIC_RX_MIN_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) netif_napi_add(lif->netdev, &qcq->napi, ionic_rx_napi); else netif_napi_add(lif->netdev, &qcq->napi, ionic_txrx_napi); + qcq->napi_qcq = qcq; + timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0); + qcq->flags |= IONIC_QCQ_F_INITED; return 0; @@ -1150,6 +1183,7 @@ static int ionic_adminq_napi(struct napi_struct *napi, int budget) struct ionic_dev *idev = &lif->ionic->idev; unsigned long irqflags; unsigned int flags = 0; + bool resched = false; int rx_work = 0; int tx_work = 0; int n_work = 0; @@ -1187,6 +1221,16 @@ static int ionic_adminq_napi(struct napi_struct *napi, int budget) ionic_intr_credits(idev->intr_ctrl, intr->index, credits, flags); } + if (!a_work && ionic_adminq_poke_doorbell(&lif->adminqcq->q)) + resched = true; + if (lif->hwstamp_rxq && !rx_work && ionic_rxq_poke_doorbell(&lif->hwstamp_rxq->q)) + resched = true; + if (lif->hwstamp_txq && !tx_work && ionic_txq_poke_doorbell(&lif->hwstamp_txq->q)) + resched = true; + if (resched) + mod_timer(&lif->adminqcq->napi_deadline, + jiffies + IONIC_NAPI_DEADLINE); + return work_done; } @@ -3245,8 +3289,14 @@ static int ionic_lif_adminq_init(struct ionic_lif *lif) dev_dbg(dev, "adminq->hw_type %d\n", q->hw_type); dev_dbg(dev, "adminq->hw_index %d\n", q->hw_index); + q->dbell_deadline = IONIC_ADMIN_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + netif_napi_add(lif->netdev, &qcq->napi, ionic_adminq_napi); + qcq->napi_qcq = qcq; + timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0); + napi_enable(&qcq->napi); if (qcq->flags & IONIC_QCQ_F_INTR) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index a53984bf3544..734519895614 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -74,8 +74,10 @@ struct ionic_qcq { struct ionic_queue q; struct ionic_cq cq; struct ionic_intr_info intr; + struct timer_list napi_deadline; struct napi_struct napi; unsigned int flags; + struct ionic_qcq *napi_qcq; struct dentry *dentry; }; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index a13530ec4dd8..08c42b039d92 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -289,6 +289,35 @@ static void ionic_adminq_cb(struct ionic_queue *q, complete_all(&ctx->work); } +bool ionic_adminq_poke_doorbell(struct ionic_queue *q) +{ + struct ionic_lif *lif = q->lif; + unsigned long now, then, dif; + unsigned long irqflags; + + spin_lock_irqsave(&lif->adminq_lock, irqflags); + + if (q->tail_idx == q->head_idx) { + spin_unlock_irqrestore(&lif->adminq_lock, irqflags); + return false; + } + + now = READ_ONCE(jiffies); + then = q->dbell_jiffies; + dif = now - then; + + if (dif > q->dbell_deadline) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + + q->dbell_jiffies = now; + } + + spin_unlock_irqrestore(&lif->adminq_lock, irqflags); + + return true; +} + int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) { struct ionic_desc_info *desc_info; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 0c3977416cd1..f761780f0162 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -22,6 +22,67 @@ static inline void ionic_rxq_post(struct ionic_queue *q, bool ring_dbell, ionic_q_post(q, ring_dbell, cb_func, cb_arg); } +bool ionic_txq_poke_doorbell(struct ionic_queue *q) +{ + unsigned long now, then, dif; + struct netdev_queue *netdev_txq; + struct net_device *netdev; + + netdev = q->lif->netdev; + netdev_txq = netdev_get_tx_queue(netdev, q->index); + + HARD_TX_LOCK(netdev, netdev_txq, smp_processor_id()); + + if (q->tail_idx == q->head_idx) { + HARD_TX_UNLOCK(netdev, netdev_txq); + return false; + } + + now = READ_ONCE(jiffies); + then = q->dbell_jiffies; + dif = now - then; + + if (dif > q->dbell_deadline) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + + q->dbell_jiffies = now; + } + + HARD_TX_UNLOCK(netdev, netdev_txq); + + return true; +} + +bool ionic_rxq_poke_doorbell(struct ionic_queue *q) +{ + unsigned long now, then, dif; + + /* no lock, called from rx napi or txrx napi, nothing else can fill */ + + if (q->tail_idx == q->head_idx) + return false; + + now = READ_ONCE(jiffies); + then = q->dbell_jiffies; + dif = now - then; + + if (dif > q->dbell_deadline) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + + q->dbell_jiffies = now; + + dif = 2 * q->dbell_deadline; + if (dif > IONIC_RX_MAX_DOORBELL_DEADLINE) + dif = IONIC_RX_MAX_DOORBELL_DEADLINE; + + q->dbell_deadline = dif; + } + + return true; +} + static inline struct netdev_queue *q_to_ndq(struct ionic_queue *q) { return netdev_get_tx_queue(q->lif->netdev, q->index); @@ -424,6 +485,12 @@ void ionic_rx_fill(struct ionic_queue *q) ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, q->dbval | q->head_idx); + + q->dbell_deadline = IONIC_RX_MIN_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + + mod_timer(&q_to_qcq(q)->napi_qcq->napi_deadline, + jiffies + IONIC_NAPI_DEADLINE); } void ionic_rx_empty(struct ionic_queue *q) @@ -511,6 +578,9 @@ int ionic_tx_napi(struct napi_struct *napi, int budget) work_done, flags); } + if (!work_done && ionic_txq_poke_doorbell(&qcq->q)) + mod_timer(&qcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE); + return work_done; } @@ -544,23 +614,29 @@ int ionic_rx_napi(struct napi_struct *napi, int budget) work_done, flags); } + if (!work_done && ionic_rxq_poke_doorbell(&qcq->q)) + mod_timer(&qcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE); + return work_done; } int ionic_txrx_napi(struct napi_struct *napi, int budget) { - struct ionic_qcq *qcq = napi_to_qcq(napi); + struct ionic_qcq *rxqcq = napi_to_qcq(napi); struct ionic_cq *rxcq = napi_to_cq(napi); unsigned int qi = rxcq->bound_q->index; + struct ionic_qcq *txqcq; struct ionic_dev *idev; struct ionic_lif *lif; struct ionic_cq *txcq; + bool resched = false; u32 rx_work_done = 0; u32 tx_work_done = 0; u32 flags = 0; lif = rxcq->bound_q->lif; idev = &lif->ionic->idev; + txqcq = lif->txqcqs[qi]; txcq = &lif->txqcqs[qi]->cq; tx_work_done = ionic_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT, @@ -572,7 +648,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) ionic_rx_fill(rxcq->bound_q); if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) { - ionic_dim_update(qcq, 0); + ionic_dim_update(rxqcq, 0); flags |= IONIC_INTR_CRED_UNMASK; rxcq->bound_intr->rearm_count++; } @@ -583,6 +659,13 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) tx_work_done + rx_work_done, flags); } + if (!rx_work_done && ionic_rxq_poke_doorbell(&rxqcq->q)) + resched = true; + if (!tx_work_done && ionic_txq_poke_doorbell(&txqcq->q)) + resched = true; + if (resched) + mod_timer(&rxqcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE); + return rx_work_done; } 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/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index 5e41658b1e2f..a6015cd03bff 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -261,6 +261,8 @@ static struct phy_driver meson_gxl_phy[] = { .handle_interrupt = meson_gxl_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, { PHY_ID_MATCH_EXACT(0x01803301), .name = "Meson G12A Internal PHY", diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 09cc65c0da93..4d2519cdb801 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1812,10 +1812,9 @@ int phylink_fwnode_phy_connect(struct phylink *pl, ret = phy_attach_direct(pl->netdev, phy_dev, flags, pl->link_interface); - if (ret) { - phy_device_free(phy_dev); + phy_device_free(phy_dev); + if (ret) return ret; - } ret = phylink_bringup_phy(pl, phy_dev, pl->link_config.interface); if (ret) diff --git a/drivers/net/usb/plusb.c b/drivers/net/usb/plusb.c index 2c82fbcaab22..7a2b0094de51 100644 --- a/drivers/net/usb/plusb.c +++ b/drivers/net/usb/plusb.c @@ -57,9 +57,7 @@ static inline int pl_vendor_req(struct usbnet *dev, u8 req, u8 val, u8 index) { - return usbnet_read_cmd(dev, req, - USB_DIR_IN | USB_TYPE_VENDOR | - USB_RECIP_DEVICE, + return usbnet_write_cmd(dev, req, USB_TYPE_VENDOR | USB_RECIP_DEVICE, val, index, NULL, 0); } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 76ef2e4fde38..333c1fec72f8 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -573,6 +573,14 @@ struct mlx5_debugfs_entries { struct dentry *lag_debugfs; }; +enum mlx5_func_type { + MLX5_PF, + MLX5_VF, + MLX5_SF, + MLX5_HOST_PF, + MLX5_FUNC_TYPE_NUM, +}; + struct mlx5_ft_pool; struct mlx5_priv { /* IRQ table valid only for real pci devices PF or VF */ @@ -583,11 +591,10 @@ struct mlx5_priv { struct mlx5_nb pg_nb; struct workqueue_struct *pg_wq; struct xarray page_root_xa; - u32 fw_pages; atomic_t reg_pages; struct list_head free_list; - u32 vfs_pages; - u32 host_pf_pages; + u32 fw_pages; + u32 page_counters[MLX5_FUNC_TYPE_NUM]; u32 fw_pages_alloc_failed; u32 give_pages_dropped; u32 reclaim_pages_discard; diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index 874a92349bf5..283dec7e3645 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -18,6 +18,7 @@ #ifndef _UAPI_LINUX_IP_H #define _UAPI_LINUX_IP_H #include +#include #include #define IPTOS_TOS_MASK 0x1E diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 81f4243bebb1..53326dfc59ec 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -4,6 +4,7 @@ #include #include +#include #include #include 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/devlink.c b/net/core/devlink.c index 032d6d0a5ce6..909a10e4b0dd 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -9979,7 +9979,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, goto err_xa_alloc; devlink->netdevice_nb.notifier_call = devlink_netdevice_event; - ret = register_netdevice_notifier_net(net, &devlink->netdevice_nb); + ret = register_netdevice_notifier(&devlink->netdevice_nb); if (ret) goto err_register_netdevice_notifier; @@ -10171,8 +10171,7 @@ void devlink_free(struct devlink *devlink) xa_destroy(&devlink->snapshot_ids); xa_destroy(&devlink->ports); - WARN_ON_ONCE(unregister_netdevice_notifier_net(devlink_net(devlink), - &devlink->netdevice_nb)); + WARN_ON_ONCE(unregister_netdevice_notifier(&devlink->netdevice_nb)); xa_erase(&devlinks, devlink->index); @@ -10503,6 +10502,8 @@ static int devlink_netdevice_event(struct notifier_block *nb, break; case NETDEV_REGISTER: case NETDEV_CHANGENAME: + if (devlink_net(devlink) != dev_net(netdev)) + return NOTIFY_OK; /* Set the netdev on top of previously set type. Note this * event happens also during net namespace change so here * we take into account netdev pointer appearing in this @@ -10512,6 +10513,8 @@ static int devlink_netdevice_event(struct notifier_block *nb, netdev); break; case NETDEV_UNREGISTER: + if (devlink_net(devlink) != dev_net(netdev)) + return NOTIFY_OK; /* Clear netdev pointer, but not the type. This event happens * also during net namespace change so we need to clear * pointer to netdev that is going to another net namespace. diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f00a79fc301b..4edd2176e238 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -269,7 +269,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) (n->nud_state == NUD_NOARP) || (tbl->is_multicast && tbl->is_multicast(n->primary_key)) || - time_after(tref, n->updated)) + !time_in_range(n->updated, tref, jiffies)) remove = true; write_unlock(&n->lock); @@ -289,7 +289,17 @@ static int neigh_forced_gc(struct neigh_table *tbl) static void neigh_add_timer(struct neighbour *n, unsigned long when) { + /* Use safe distance from the jiffies - LONG_MAX point while timer + * is running in DELAY/PROBE state but still show to user space + * large times in the past. + */ + unsigned long mint = jiffies - (LONG_MAX - 86400 * HZ); + neigh_hold(n); + if (!time_in_range(n->confirmed, mint, jiffies)) + n->confirmed = mint; + if (time_before(n->used, n->confirmed)) + n->used = n->confirmed; if (unlikely(mod_timer(&n->timer, when))) { printk("NEIGH: BUG, double timer add, state is %x\n", n->nud_state); @@ -1001,12 +1011,14 @@ static void neigh_periodic_work(struct work_struct *work) goto next_elt; } - if (time_before(n->used, n->confirmed)) + if (time_before(n->used, n->confirmed) && + time_is_before_eq_jiffies(n->confirmed)) n->used = n->confirmed; if (refcount_read(&n->refcnt) == 1 && (state == NUD_FAILED || - time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { + !time_in_range_open(jiffies, n->used, + n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { *np = n->next; neigh_mark_dead(n); write_unlock(&n->lock); 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/rds/message.c b/net/rds/message.c index b47e4f0a1639..c19c93561227 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -104,9 +104,9 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs, spin_lock_irqsave(&q->lock, flags); head = &q->zcookie_head; if (!list_empty(head)) { - info = list_entry(head, struct rds_msg_zcopy_info, - rs_zcookie_next); - if (info && rds_zcookie_add(info, cookie)) { + info = list_first_entry(head, struct rds_msg_zcopy_info, + rs_zcookie_next); + if (rds_zcookie_add(info, cookie)) { spin_unlock_irqrestore(&q->lock, flags); kfree(rds_info_from_znotifier(znotif)); /* caller invokes rds_wake_sk_sleep() */ 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/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index a0f62fa02e06..8cbf45a8bcdc 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -5,6 +5,7 @@ * Based on code and translator idea by: Florian Westphal */ #include +#include #include #include @@ -302,7 +303,7 @@ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src) nla_for_each_attr(nla, attrs, len, remaining) { int err; - switch (type) { + switch (nlh_src->nlmsg_type) { case XFRM_MSG_NEWSPDINFO: err = xfrm_nla_cpy(dst, nla, nla_len(nla)); break; @@ -437,6 +438,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } + type = array_index_nospec(type, XFRMA_MAX + 1); if (nla_len(nla) < compat_policy[type].len) { NL_SET_ERR_MSG(extack, "Attribute bad length"); return -EOPNOTSUPP; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index c06e54a10540..436d29640ac2 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -279,8 +279,7 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) - ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)), - ipipv6_hdr(skb)); + ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipipv6_hdr(skb)); if (!(x->props.flags & XFRM_STATE_NOECN)) ipip6_ecn_decapsulate(skb); diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 1f99dc469027..35279c220bd7 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -310,6 +310,52 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } +static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type, unsigned short family) +{ + struct sec_path *sp; + + sp = skb_sec_path(skb); + if (sp && (sp->len || sp->olen) && + !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + goto discard; + + XFRM_SPI_SKB_CB(skb)->family = family; + if (family == AF_INET) { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + } else { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + } + + return xfrm_input(skb, nexthdr, spi, encap_type); +discard: + kfree_skb(skb); + return 0; +} + +static int xfrmi4_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); +} + +static int xfrmi6_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], + 0, 0, AF_INET6); +} + +static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); +} + +static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); +} + static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -945,8 +991,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrm6_rcv, - .input_handler = xfrm_input, + .handler = xfrmi6_rcv, + .input_handler = xfrmi6_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -996,8 +1042,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrm4_rcv, - .input_handler = xfrm_input, + .handler = xfrmi4_rcv, + .input_handler = xfrmi4_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e9eb82c5457d..5c61ec04b839 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -336,7 +336,7 @@ static void xfrm_policy_timer(struct timer_list *t) } if (xp->lft.hard_use_expires_seconds) { time64_t tmo = xp->lft.hard_use_expires_seconds + - (xp->curlft.use_time ? : xp->curlft.add_time) - now; + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) goto expired; if (tmo < next) @@ -354,7 +354,7 @@ static void xfrm_policy_timer(struct timer_list *t) } if (xp->lft.soft_use_expires_seconds) { time64_t tmo = xp->lft.soft_use_expires_seconds + - (xp->curlft.use_time ? : xp->curlft.add_time) - now; + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) { warn = 1; tmo = XFRM_KM_TIMEOUT; @@ -3661,7 +3661,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, return 1; } - pol->curlft.use_time = ktime_get_real_seconds(); + /* This lockless write can happen from different cpus. */ + WRITE_ONCE(pol->curlft.use_time, ktime_get_real_seconds()); pols[0] = pol; npols++; @@ -3676,7 +3677,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, xfrm_pol_put(pols[0]); return 0; } - pols[1]->curlft.use_time = ktime_get_real_seconds(); + /* This write can happen from different cpus. */ + WRITE_ONCE(pols[1]->curlft.use_time, + ktime_get_real_seconds()); npols++; } } @@ -3742,6 +3745,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; } + if (if_id) + secpath_reset(skb); + xfrm_pols_put(pols, npols); return 1; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 89c731f4f0c7..00afe831c71c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -577,7 +577,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) if (x->km.state == XFRM_STATE_EXPIRED) goto expired; if (x->lft.hard_add_expires_seconds) { - long tmo = x->lft.hard_add_expires_seconds + + time64_t tmo = x->lft.hard_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { if (x->xflags & XFRM_SOFT_EXPIRE) { @@ -594,8 +594,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) next = tmo; } if (x->lft.hard_use_expires_seconds) { - long tmo = x->lft.hard_use_expires_seconds + - (x->curlft.use_time ? : now) - now; + time64_t tmo = x->lft.hard_use_expires_seconds + + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) goto expired; if (tmo < next) @@ -604,7 +604,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) if (x->km.dying) goto resched; if (x->lft.soft_add_expires_seconds) { - long tmo = x->lft.soft_add_expires_seconds + + time64_t tmo = x->lft.soft_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { warn = 1; @@ -616,8 +616,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) } } if (x->lft.soft_use_expires_seconds) { - long tmo = x->lft.soft_use_expires_seconds + - (x->curlft.use_time ? : now) - now; + time64_t tmo = x->lft.soft_use_expires_seconds + + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) warn = 1; else if (tmo < next) @@ -1906,7 +1906,7 @@ out: hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); - if (x1->curlft.use_time) + if (READ_ONCE(x1->curlft.use_time)) xfrm_state_check_expire(x1); if (x->props.smark.m || x->props.smark.v || x->if_id) { @@ -1940,8 +1940,8 @@ int xfrm_state_check_expire(struct xfrm_state *x) { xfrm_dev_state_update_curlft(x); - if (!x->curlft.use_time) - x->curlft.use_time = ktime_get_real_seconds(); + if (!READ_ONCE(x->curlft.use_time)) + WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds()); if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index 9c79bbcce5a8..aff0a59f92d9 100755 --- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh +++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh @@ -246,7 +246,7 @@ test_vlan_ingress_modify() bridge vlan add dev $swp2 vid 300 tc filter add dev $swp1 ingress chain $(IS1 2) pref 3 \ - protocol 802.1Q flower skip_sw vlan_id 200 \ + protocol 802.1Q flower skip_sw vlan_id 200 src_mac $h1_mac \ action vlan modify id 300 \ action goto chain $(IS2 0 0) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 1c4f866de7d7..3d8e4ebda1b6 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -914,14 +914,14 @@ sysctl_set() local value=$1; shift SYSCTL_ORIG[$key]=$(sysctl -n $key) - sysctl -qw $key=$value + sysctl -qw $key="$value" } sysctl_restore() { local key=$1; shift - sysctl -qw $key=${SYSCTL_ORIG["$key"]} + sysctl -qw $key="${SYSCTL_ORIG[$key]}" } forwarding_enable() 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