diff options
81 files changed, 782 insertions, 451 deletions
diff --git a/Documentation/networking/bareudp.rst b/Documentation/networking/bareudp.rst index ff406563ea88..b9d04ee6dac1 100644 --- a/Documentation/networking/bareudp.rst +++ b/Documentation/networking/bareudp.rst @@ -8,9 +8,8 @@ There are various L3 encapsulation standards using UDP being discussed to leverage the UDP based load balancing capability of different networks. MPLSoUDP (__ https://tools.ietf.org/html/rfc7510) is one among them. -The Bareudp tunnel module provides a generic L3 encapsulation tunnelling -support for tunnelling different L3 protocols like MPLS, IP, NSH etc. inside -a UDP tunnel. +The Bareudp tunnel module provides a generic L3 encapsulation support for +tunnelling different L3 protocols like MPLS, IP, NSH etc. inside a UDP tunnel. Special Handling ---------------- diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst index 1e3f3ffee248..2014307fbe63 100644 --- a/Documentation/networking/devlink/devlink-trap.rst +++ b/Documentation/networking/devlink/devlink-trap.rst @@ -486,6 +486,10 @@ narrow. The description of these groups must be added to the following table: - Contains packet traps for packets that should be locally delivered after routing, but do not match more specific packet traps (e.g., ``ipv4_bgp``) + * - ``external_delivery`` + - Contains packet traps for packets that should be routed through an + external interface (e.g., management interface) that does not belong to + the same device (e.g., switch ASIC) as the ingress interface * - ``ipv6`` - Contains packet traps for various IPv6 control packets (e.g., Router Advertisements) diff --git a/MAINTAINERS b/MAINTAINERS index e02479a5d4d2..4e2698cc7e23 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -782,7 +782,7 @@ F: include/dt-bindings/reset/altr,rst-mgr-a10sr.h F: include/linux/mfd/altera-a10sr.h ALTERA TRIPLE SPEED ETHERNET DRIVER -M: Thor Thayer <thor.thayer@linux.intel.com> +M: Joyce Ooi <joyce.ooi@intel.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/altera/ diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c index d9fd70280482..7f814da3c2d0 100644 --- a/drivers/atm/atmtcp.c +++ b/drivers/atm/atmtcp.c @@ -433,9 +433,15 @@ static int atmtcp_remove_persistent(int itf) return -EMEDIUMTYPE; } dev_data = PRIV(dev); - if (!dev_data->persist) return 0; + if (!dev_data->persist) { + atm_dev_put(dev); + return 0; + } dev_data->persist = 0; - if (PRIV(dev)->vcc) return 0; + if (PRIV(dev)->vcc) { + atm_dev_put(dev); + return 0; + } kfree(dev_data); atm_dev_put(dev); atm_dev_deregister(dev); diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 3dd46cd55114..88e7900853db 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -407,19 +407,34 @@ free_dst: return err; } +static bool bareudp_proto_valid(struct bareudp_dev *bareudp, __be16 proto) +{ + if (bareudp->ethertype == proto) + return true; + + if (!bareudp->multi_proto_mode) + return false; + + if (bareudp->ethertype == htons(ETH_P_MPLS_UC) && + proto == htons(ETH_P_MPLS_MC)) + return true; + + if (bareudp->ethertype == htons(ETH_P_IP) && + proto == htons(ETH_P_IPV6)) + return true; + + return false; +} + static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); struct ip_tunnel_info *info = NULL; int err; - if (skb->protocol != bareudp->ethertype) { - if (!bareudp->multi_proto_mode || - (skb->protocol != htons(ETH_P_MPLS_MC) && - skb->protocol != htons(ETH_P_IPV6))) { - err = -EINVAL; - goto tx_error; - } + if (!bareudp_proto_valid(bareudp, skb->protocol)) { + err = -EINVAL; + goto tx_error; } info = skb_tunnel_info(skb); diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 8d13ea370db1..66e67b24a887 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2446,6 +2446,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) port->reset = devm_reset_control_get_exclusive(dev, NULL); if (IS_ERR(port->reset)) { dev_err(dev, "no reset\n"); + clk_disable_unprepare(port->pclk); return PTR_ERR(port->reset); } reset_control_reset(port->reset); @@ -2501,8 +2502,10 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) IRQF_SHARED, port_names[port->id], port); - if (ret) + if (ret) { + clk_disable_unprepare(port->pclk); return ret; + } ret = register_netdev(netdev); if (!ret) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 33c481d11116..71ed4c54f6d5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1093,16 +1093,8 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, int k, sizeoflast; dma_addr_t dma; - if (type == DESC_TYPE_SKB) { - struct sk_buff *skb = (struct sk_buff *)priv; - int ret; - - ret = hns3_fill_skb_desc(ring, skb, desc); - if (unlikely(ret < 0)) - return ret; - - dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); - } else if (type == DESC_TYPE_FRAGLIST_SKB) { + if (type == DESC_TYPE_FRAGLIST_SKB || + type == DESC_TYPE_SKB) { struct sk_buff *skb = (struct sk_buff *)priv; dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); @@ -1439,6 +1431,10 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) next_to_use_head = ring->next_to_use; + ret = hns3_fill_skb_desc(ring, skb, &ring->desc[ring->next_to_use]); + if (unlikely(ret < 0)) + goto fill_err; + ret = hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB); if (unlikely(ret < 0)) goto fill_err; @@ -4140,8 +4136,8 @@ static void hns3_link_status_change(struct hnae3_handle *handle, bool linkup) return; if (linkup) { - netif_carrier_on(netdev); netif_tx_wake_all_queues(netdev); + netif_carrier_on(netdev); if (netif_msg_link(handle)) netdev_info(netdev, "link up\n"); } else { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index bb4a6327035d..36575e72a915 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -5806,9 +5806,9 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle, /* to avoid rule conflict, when user configure rule by ethtool, * we need to clear all arfs rules */ + spin_lock_bh(&hdev->fd_rule_lock); hclge_clear_arfs_rules(handle); - spin_lock_bh(&hdev->fd_rule_lock); ret = hclge_fd_config_rule(hdev, rule); spin_unlock_bh(&hdev->fd_rule_lock); @@ -5851,6 +5851,7 @@ static int hclge_del_fd_entry(struct hnae3_handle *handle, return ret; } +/* make sure being called after lock up with fd_rule_lock */ static void hclge_del_all_fd_entries(struct hnae3_handle *handle, bool clear_list) { @@ -5863,7 +5864,6 @@ static void hclge_del_all_fd_entries(struct hnae3_handle *handle, if (!hnae3_dev_fd_supported(hdev)) return; - spin_lock_bh(&hdev->fd_rule_lock); for_each_set_bit(location, hdev->fd_bmap, hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]) hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true, location, @@ -5880,8 +5880,6 @@ static void hclge_del_all_fd_entries(struct hnae3_handle *handle, bitmap_zero(hdev->fd_bmap, hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]); } - - spin_unlock_bh(&hdev->fd_rule_lock); } static int hclge_restore_fd_entries(struct hnae3_handle *handle) @@ -6263,7 +6261,7 @@ static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id, u16 flow_id, struct flow_keys *fkeys) { struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_fd_rule_tuples new_tuples; + struct hclge_fd_rule_tuples new_tuples = {}; struct hclge_dev *hdev = vport->back; struct hclge_fd_rule *rule; u16 tmp_queue_id; @@ -6273,19 +6271,17 @@ static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id, if (!hnae3_dev_fd_supported(hdev)) return -EOPNOTSUPP; - memset(&new_tuples, 0, sizeof(new_tuples)); - hclge_fd_get_flow_tuples(fkeys, &new_tuples); - - spin_lock_bh(&hdev->fd_rule_lock); - /* when there is already fd rule existed add by user, * arfs should not work */ + spin_lock_bh(&hdev->fd_rule_lock); if (hdev->fd_active_type == HCLGE_FD_EP_ACTIVE) { spin_unlock_bh(&hdev->fd_rule_lock); return -EOPNOTSUPP; } + hclge_fd_get_flow_tuples(fkeys, &new_tuples); + /* check is there flow director filter existed for this flow, * if not, create a new filter for it; * if filter exist with different queue id, modify the filter; @@ -6368,6 +6364,7 @@ static void hclge_rfs_filter_expire(struct hclge_dev *hdev) #endif } +/* make sure being called after lock up with fd_rule_lock */ static void hclge_clear_arfs_rules(struct hnae3_handle *handle) { #ifdef CONFIG_RFS_ACCEL @@ -6420,10 +6417,14 @@ static void hclge_enable_fd(struct hnae3_handle *handle, bool enable) hdev->fd_en = enable; clear = hdev->fd_active_type == HCLGE_FD_ARFS_ACTIVE; - if (!enable) + + if (!enable) { + spin_lock_bh(&hdev->fd_rule_lock); hclge_del_all_fd_entries(handle, clear); - else + spin_unlock_bh(&hdev->fd_rule_lock); + } else { hclge_restore_fd_entries(handle); + } } static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) @@ -6886,8 +6887,9 @@ static void hclge_ae_stop(struct hnae3_handle *handle) int i; set_bit(HCLGE_STATE_DOWN, &hdev->state); - + spin_lock_bh(&hdev->fd_rule_lock); hclge_clear_arfs_rules(handle); + spin_unlock_bh(&hdev->fd_rule_lock); /* If it is not PF reset, the firmware will disable the MAC, * so it only need to stop phy here. @@ -9040,11 +9042,12 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, bool writen_to_tbl = false; int ret = 0; - /* When device is resetting, firmware is unable to handle - * mailbox. Just record the vlan id, and remove it after + /* When device is resetting or reset failed, firmware is unable to + * handle mailbox. Just record the vlan id, and remove it after * reset finished. */ - if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && is_kill) { + if ((test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) || + test_bit(HCLGE_STATE_RST_FAIL, &hdev->state)) && is_kill) { set_bit(vlan_id, vport->vlan_del_fail_bmap); return -EBUSY; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index a10b022d1951..9162856de1b1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1592,11 +1592,12 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle, if (proto != htons(ETH_P_8021Q)) return -EPROTONOSUPPORT; - /* When device is resetting, firmware is unable to handle - * mailbox. Just record the vlan id, and remove it after + /* When device is resetting or reset failed, firmware is unable to + * handle mailbox. Just record the vlan id, and remove it after * reset finished. */ - if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state) && is_kill) { + if ((test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state) || + test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state)) && is_kill) { set_bit(vlan_id, hdev->vlan_del_fail_bmap); return -EBUSY; } @@ -3439,23 +3440,36 @@ void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state, { struct hnae3_handle *nic = &hdev->nic; struct hclge_vf_to_pf_msg send_msg; + int ret; rtnl_lock(); - hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT); - rtnl_unlock(); + + if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state) || + test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state)) { + dev_warn(&hdev->pdev->dev, + "is resetting when updating port based vlan info\n"); + rtnl_unlock(); + return; + } + + ret = hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT); + if (ret) { + rtnl_unlock(); + return; + } /* send msg to PF and wait update port based vlan info */ hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN, HCLGE_MBX_PORT_BASE_VLAN_CFG); memcpy(send_msg.data, port_base_vlan_info, data_size); - hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); - - if (state == HNAE3_PORT_BASE_VLAN_DISABLE) - nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_DISABLE; - else - nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_ENABLE; + ret = hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); + if (!ret) { + if (state == HNAE3_PORT_BASE_VLAN_DISABLE) + nic->port_base_vlan_state = state; + else + nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_ENABLE; + } - rtnl_lock(); hclgevf_notify_client(hdev, HNAE3_UP_CLIENT); rtnl_unlock(); } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 0fd7eae25fe9..5afb3c9c52d2 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3206,7 +3206,7 @@ req_rx_irq_failed: req_tx_irq_failed: for (j = 0; j < i; j++) { free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]); - irq_dispose_mapping(adapter->rx_scrq[j]->irq); + irq_dispose_mapping(adapter->tx_scrq[j]->irq); } release_sub_crqs(adapter, 1); return rc; diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index f999cca37a8a..489bb5b59475 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -301,10 +301,8 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) */ hw->dev_spec.ich8lan.ulp_state = e1000_ulp_state_unknown; ret_val = e1000_disable_ulp_lpt_lp(hw, true); - if (ret_val) { + if (ret_val) e_warn("Failed to disable ULP\n"); - goto out; - } ret_val = hw->phy.ops.acquire(hw); if (ret_val) { diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 8bb3db2cbd41..6e5861bfb0fa 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6224,9 +6224,18 @@ static void igb_reset_task(struct work_struct *work) struct igb_adapter *adapter; adapter = container_of(work, struct igb_adapter, reset_task); + rtnl_lock(); + /* If we're already down or resetting, just bail */ + if (test_bit(__IGB_DOWN, &adapter->state) || + test_bit(__IGB_RESETTING, &adapter->state)) { + rtnl_unlock(); + return; + } + igb_dump(adapter); netdev_err(adapter->netdev, "Reset adapter\n"); igb_reinit_locked(adapter); + rtnl_unlock(); } /** diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 64786568af0d..75a8c407e815 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1730,10 +1730,12 @@ static void otx2_reset_task(struct work_struct *work) if (!netif_running(pf->netdev)) return; + rtnl_lock(); otx2_stop(pf->netdev); pf->reset_count++; otx2_open(pf->netdev); netif_trans_update(pf->netdev); + rtnl_unlock(); } static const struct net_device_ops otx2_netdev_ops = { @@ -2111,6 +2113,7 @@ static void otx2_remove(struct pci_dev *pdev) pf = netdev_priv(netdev); + cancel_work_sync(&pf->reset_task); /* Disable link notifications */ otx2_cgx_config_linkevents(pf, false); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index f4227517dc8e..92a3db69a6cd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -617,6 +617,8 @@ static void otx2vf_remove(struct pci_dev *pdev) vf = netdev_priv(netdev); + cancel_work_sync(&vf->reset_task); + unregister_netdev(netdev); otx2vf_disable_mbox_intr(vf); otx2_detach_resources(&vf->mbox); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index f6a1f8666f95..a1c45b39a230 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -171,11 +171,21 @@ static int mt7621_gmac0_rgmii_adjust(struct mtk_eth *eth, return 0; } -static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth, int speed) +static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth, + phy_interface_t interface, int speed) { u32 val; int ret; + if (interface == PHY_INTERFACE_MODE_TRGMII) { + mtk_w32(eth, TRGMII_MODE, INTF_MODE); + val = 500000000; + ret = clk_set_rate(eth->clks[MTK_CLK_TRGPLL], val); + if (ret) + dev_err(eth->dev, "Failed to set trgmii pll: %d\n", ret); + return; + } + val = (speed == SPEED_1000) ? INTF_MODE_RGMII_1000 : INTF_MODE_RGMII_10_100; mtk_w32(eth, val, INTF_MODE); @@ -262,10 +272,9 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode, state->interface)) goto err_phy; } else { - if (state->interface != - PHY_INTERFACE_MODE_TRGMII) - mtk_gmac0_rgmii_adjust(mac->hw, - state->speed); + mtk_gmac0_rgmii_adjust(mac->hw, + state->interface, + state->speed); /* mt7623_pad_clk_setup */ for (i = 0 ; i < NUM_TRGMII_CTRL; i++) @@ -2882,6 +2891,8 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) eth->netdev[id]->irq = eth->irq[0]; eth->netdev[id]->dev.of_node = np; + eth->netdev[id]->max_mtu = MTK_MAX_RX_LENGTH - MTK_RX_ETH_HLEN; + return 0; free_netdev: diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 3d9aa7da95e9..2d3e45780719 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4356,12 +4356,14 @@ end: static void mlx4_shutdown(struct pci_dev *pdev) { struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev); + struct mlx4_dev *dev = persist->dev; mlx4_info(persist->dev, "mlx4_shutdown was called\n"); mutex_lock(&persist->interface_state_mutex); if (persist->interface_state & MLX4_INTERFACE_STATE_UP) mlx4_unload_one(pdev); mutex_unlock(&persist->interface_state_mutex); + mlx4_pci_disable_device(dev); } static const struct pci_error_handlers mlx4_err_handler = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c index bdb71332cbf2..3e44e4d820c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c @@ -183,13 +183,16 @@ void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw, static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev) { - struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5e_rep_priv *rpriv; + struct mlx5e_priv *priv; /* A given netdev is not a representor or not a slave of LAG configuration */ if (!mlx5e_eswitch_rep(netdev) || !bond_slave_get_rtnl(netdev)) return false; + priv = netdev_priv(netdev); + rpriv = priv->ppriv; + /* Egress acl forward to vport is supported only non-uplink representor */ return rpriv->rep->vport != MLX5_VPORT_UPLINK; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index eefeb1cdc2ee..245a99f69641 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -551,19 +551,31 @@ static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb, } } - tun_dst = tun_rx_dst(enc_opts.key.len); + if (key.enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + tun_dst = __ip_tun_set_dst(key.enc_ipv4.src, key.enc_ipv4.dst, + key.enc_ip.tos, key.enc_ip.ttl, + key.enc_tp.dst, TUNNEL_KEY, + key32_to_tunnel_id(key.enc_key_id.keyid), + enc_opts.key.len); + } else if (key.enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + tun_dst = __ipv6_tun_set_dst(&key.enc_ipv6.src, &key.enc_ipv6.dst, + key.enc_ip.tos, key.enc_ip.ttl, + key.enc_tp.dst, 0, TUNNEL_KEY, + key32_to_tunnel_id(key.enc_key_id.keyid), + enc_opts.key.len); + } else { + netdev_dbg(priv->netdev, + "Couldn't restore tunnel, unsupported addr_type: %d\n", + key.enc_control.addr_type); + return false; + } + if (!tun_dst) { - WARN_ON_ONCE(true); + netdev_dbg(priv->netdev, "Couldn't restore tunnel, no tun_dst\n"); return false; } - ip_tunnel_key_init(&tun_dst->u.tun_info.key, - key.enc_ipv4.src, key.enc_ipv4.dst, - key.enc_ip.tos, key.enc_ip.ttl, - 0, /* label */ - key.enc_tp.src, key.enc_tp.dst, - key32_to_tunnel_id(key.enc_key_id.keyid), - TUNNEL_KEY); + tun_dst->u.tun_info.key.tp_src = key.enc_tp.src; if (enc_opts.key.len) ip_tunnel_info_opts_set(&tun_dst->u.tun_info, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c index 951ea26d96bc..e472ed0eacfb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c @@ -301,6 +301,8 @@ static int mlx5e_tc_tun_parse_geneve_params(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_misc, misc_v, geneve_protocol_type, ETH_P_TEB); } + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c index 58b13192df23..2805416c32a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c @@ -80,6 +80,8 @@ static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv, gre_key.key, be32_to_cpu(enc_keyid.key->keyid)); } + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c index 37b176801bcc..038a0f1cecec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c @@ -136,6 +136,8 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni, be32_to_cpu(enc_keyid.key->keyid)); + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 081f15074cac..3b892ec301b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -419,7 +419,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq, &rq->wq_ctrl); if (err) - return err; + goto err_rq_wq_destroy; rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR]; @@ -470,7 +470,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq, &rq->wq_ctrl); if (err) - return err; + goto err_rq_wq_destroy; rq->wqe.wq.db = &rq->wqe.wq.db[MLX5_RCV_DBR]; @@ -3069,6 +3069,25 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv) priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE; } +static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev, + enum mlx5_port_status state) +{ + struct mlx5_eswitch *esw = mdev->priv.eswitch; + int vport_admin_state; + + mlx5_set_port_admin_status(mdev, state); + + if (!MLX5_ESWITCH_MANAGER(mdev) || mlx5_eswitch_mode(esw) == MLX5_ESWITCH_OFFLOADS) + return; + + if (state == MLX5_PORT_UP) + vport_admin_state = MLX5_VPORT_ADMIN_STATE_AUTO; + else + vport_admin_state = MLX5_VPORT_ADMIN_STATE_DOWN; + + mlx5_eswitch_set_vport_state(esw, MLX5_VPORT_UPLINK, vport_admin_state); +} + int mlx5e_open_locked(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -3101,7 +3120,7 @@ int mlx5e_open(struct net_device *netdev) mutex_lock(&priv->state_lock); err = mlx5e_open_locked(netdev); if (!err) - mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP); + mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_UP); mutex_unlock(&priv->state_lock); return err; @@ -3135,7 +3154,7 @@ int mlx5e_close(struct net_device *netdev) return -ENODEV; mutex_lock(&priv->state_lock); - mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_DOWN); + mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_DOWN); err = mlx5e_close_locked(netdev); mutex_unlock(&priv->state_lock); @@ -5182,7 +5201,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) /* Marking the link as currently not needed by the Driver */ if (!netif_running(netdev)) - mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN); + mlx5e_modify_admin_state(mdev, MLX5_PORT_DOWN); mlx5e_set_netdev_mtu_boundaries(priv); mlx5e_set_dev_port_mtu(priv); @@ -5390,6 +5409,8 @@ err_cleanup_tx: profile->cleanup_tx(priv); out: + set_bit(MLX5E_STATE_DESTROYING, &priv->state); + cancel_work_sync(&priv->update_stats_work); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 006807e04eda..9519a61bd8ec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -936,6 +936,7 @@ err_close_drop_rq: static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) { + mlx5e_ethtool_cleanup_steering(priv); rep_vport_rx_rule_destroy(priv); mlx5e_destroy_rep_root_ft(priv); mlx5e_destroy_ttc_table(priv, &priv->fs.ttc); @@ -1080,6 +1081,8 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) mlx5e_rep_tc_enable(priv); + mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK, + 0, 0, MLX5_VPORT_ADMIN_STATE_AUTO); mlx5_lag_add(mdev, netdev); priv->events_nb.notifier_call = uplink_rep_async_event; mlx5_notifier_register(mdev, &priv->events_nb); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index cc8412151ca0..fcedb5bdca9e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2356,6 +2356,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, match.key->vlan_priority); *match_level = MLX5_MATCH_L2; + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 1116ab9bea6c..43005caff09e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1608,7 +1608,7 @@ abort: mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); } - + esw_destroy_tsar(esw); return err; } @@ -1653,8 +1653,6 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf) else if (esw->mode == MLX5_ESWITCH_OFFLOADS) esw_offloads_disable(esw); - esw_destroy_tsar(esw); - old_mode = esw->mode; esw->mode = MLX5_ESWITCH_NONE; @@ -1664,6 +1662,8 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf) mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); } + esw_destroy_tsar(esw); + if (clear_vf) mlx5_eswitch_clear_vf_vports_info(esw); } @@ -1826,6 +1826,8 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); + int opmod = MLX5_VPORT_STATE_OP_MOD_ESW_VPORT; + int other_vport = 1; int err = 0; if (!ESW_ALLOWED(esw)) @@ -1833,15 +1835,17 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, if (IS_ERR(evport)) return PTR_ERR(evport); + if (vport == MLX5_VPORT_UPLINK) { + opmod = MLX5_VPORT_STATE_OP_MOD_UPLINK; + other_vport = 0; + vport = 0; + } mutex_lock(&esw->state_lock); - err = mlx5_modify_vport_admin_state(esw->dev, - MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - vport, 1, link_state); + err = mlx5_modify_vport_admin_state(esw->dev, opmod, vport, other_vport, link_state); if (err) { - mlx5_core_warn(esw->dev, - "Failed to set vport %d link state, err = %d", - vport, err); + mlx5_core_warn(esw->dev, "Failed to set vport %d link state, opmod = %d, err = %d", + vport, opmod, err); goto unlock; } @@ -1883,8 +1887,6 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); int err = 0; - if (!ESW_ALLOWED(esw)) - return -EPERM; if (IS_ERR(evport)) return PTR_ERR(evport); if (vlan > 4095 || qos > 7) @@ -1912,6 +1914,9 @@ int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, u8 set_flags = 0; int err; + if (!ESW_ALLOWED(esw)) + return -EPERM; + if (vlan || qos) set_flags = SET_VLAN_STRIP | SET_VLAN_INSERT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index a5175e98c0b3..5785596f13f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -680,6 +680,8 @@ static inline int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) { r static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf) {} static inline bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) { return true; } static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; } +static inline +int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { return 0; } static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev) { return ERR_PTR(-EOPNOTSUPP); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 060354bb211a..ed75353c56b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -236,6 +236,15 @@ static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw, return &esw->offloads.vport_reps[idx]; } +static void +mlx5_eswitch_set_rule_flow_source(struct mlx5_eswitch *esw, + struct mlx5_flow_spec *spec, + struct mlx5_esw_flow_attr *attr) +{ + if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) && + attr && attr->in_rep && attr->in_rep->vport == MLX5_VPORT_UPLINK) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; +} static void mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, @@ -259,9 +268,6 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, mlx5_eswitch_get_vport_metadata_mask()); spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2; - misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); - if (memchr_inv(misc, 0, MLX5_ST_SZ_BYTES(fte_match_set_misc))) - spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; } else { misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport); @@ -279,10 +285,6 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; } - - if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) && - attr->in_rep->vport == MLX5_VPORT_UPLINK) - spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; } struct mlx5_flow_handle * @@ -396,6 +398,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, goto err_esw_get; } + mlx5_eswitch_set_rule_flow_source(esw, spec, attr); + if (mlx5_eswitch_termtbl_required(esw, attr, &flow_act, spec)) rule = mlx5_eswitch_add_termtbl_rule(esw, fdb, spec, attr, &flow_act, dest, i); @@ -462,6 +466,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, i++; mlx5_eswitch_set_rule_source_port(esw, spec, attr); + mlx5_eswitch_set_rule_flow_source(esw, spec, attr); if (attr->outer_match_level != MLX5_MATCH_NONE) spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 13e2fb79c21a..2569bb6228b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -797,7 +797,7 @@ static struct mlx5_flow_table *find_closest_ft_recursive(struct fs_node *root, return ft; } -/* If reverse if false then return the first flow table in next priority of +/* If reverse is false then return the first flow table in next priority of * prio in the tree, else return the last flow table in the previous priority * of prio in the tree. */ @@ -829,34 +829,16 @@ static struct mlx5_flow_table *find_prev_chained_ft(struct fs_prio *prio) return find_closest_ft(prio, true); } -static struct fs_prio *find_fwd_ns_prio(struct mlx5_flow_root_namespace *root, - struct mlx5_flow_namespace *ns) -{ - struct mlx5_flow_namespace *root_ns = &root->ns; - struct fs_prio *iter_prio; - struct fs_prio *prio; - - fs_get_obj(prio, ns->node.parent); - list_for_each_entry(iter_prio, &root_ns->node.children, node.list) { - if (iter_prio == prio && - !list_is_last(&prio->node.children, &iter_prio->node.list)) - return list_next_entry(iter_prio, node.list); - } - return NULL; -} - static struct mlx5_flow_table *find_next_fwd_ft(struct mlx5_flow_table *ft, struct mlx5_flow_act *flow_act) { - struct mlx5_flow_root_namespace *root = find_root(&ft->node); struct fs_prio *prio; + bool next_ns; - if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS) - prio = find_fwd_ns_prio(root, ft->ns); - else - fs_get_obj(prio, ft->node.parent); + next_ns = flow_act->action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS; + fs_get_obj(prio, next_ns ? ft->ns->node.parent : ft->node.parent); - return (prio) ? find_next_chained_ft(prio) : NULL; + return find_next_chained_ft(prio); } static int connect_fts_in_prio(struct mlx5_core_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index ef0706d15a5b..2d55b7c22c03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -273,17 +273,17 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp, if (rq->extts.index >= clock->ptp_info.n_pins) return -EINVAL; + pin = ptp_find_pin(clock->ptp, PTP_PF_EXTTS, rq->extts.index); + if (pin < 0) + return -EBUSY; + if (on) { - pin = ptp_find_pin(clock->ptp, PTP_PF_EXTTS, rq->extts.index); - if (pin < 0) - return -EBUSY; pin_mode = MLX5_PIN_MODE_IN; pattern = !!(rq->extts.flags & PTP_FALLING_EDGE); field_select = MLX5_MTPPS_FS_PIN_MODE | MLX5_MTPPS_FS_PATTERN | MLX5_MTPPS_FS_ENABLE; } else { - pin = rq->extts.index; field_select = MLX5_MTPPS_FS_ENABLE; } @@ -331,12 +331,12 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, if (rq->perout.index >= clock->ptp_info.n_pins) return -EINVAL; - if (on) { - pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, - rq->perout.index); - if (pin < 0) - return -EBUSY; + pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, + rq->perout.index); + if (pin < 0) + return -EBUSY; + if (on) { pin_mode = MLX5_PIN_MODE_OUT; pattern = MLX5_OUT_PATTERN_PERIODIC; ts.tv_sec = rq->perout.period.sec; @@ -362,7 +362,6 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, MLX5_MTPPS_FS_ENABLE | MLX5_MTPPS_FS_TIME_STAMP; } else { - pin = rq->perout.index; field_select = MLX5_MTPPS_FS_ENABLE; } @@ -409,10 +408,31 @@ static int mlx5_ptp_enable(struct ptp_clock_info *ptp, return 0; } +enum { + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_IN = BIT(0), + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_OUT = BIT(1), +}; + static int mlx5_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, enum ptp_pin_function func, unsigned int chan) { - return (func == PTP_PF_PHYSYNC) ? -EOPNOTSUPP : 0; + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); + + switch (func) { + case PTP_PF_NONE: + return 0; + case PTP_PF_EXTTS: + return !(clock->pps_info.pin_caps[pin] & + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_IN); + case PTP_PF_PEROUT: + return !(clock->pps_info.pin_caps[pin] & + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_OUT); + default: + return -EOPNOTSUPP; + } + + return -EOPNOTSUPP; } static const struct ptp_clock_info mlx5_ptp_clock_info = { @@ -432,6 +452,38 @@ static const struct ptp_clock_info mlx5_ptp_clock_info = { .verify = NULL, }; +static int mlx5_query_mtpps_pin_mode(struct mlx5_core_dev *mdev, u8 pin, + u32 *mtpps, u32 mtpps_size) +{ + u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {}; + + MLX5_SET(mtpps_reg, in, pin, pin); + + return mlx5_core_access_reg(mdev, in, sizeof(in), mtpps, + mtpps_size, MLX5_REG_MTPPS, 0, 0); +} + +static int mlx5_get_pps_pin_mode(struct mlx5_clock *clock, u8 pin) +{ + struct mlx5_core_dev *mdev = clock->mdev; + u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {}; + u8 mode; + int err; + + err = mlx5_query_mtpps_pin_mode(mdev, pin, out, sizeof(out)); + if (err || !MLX5_GET(mtpps_reg, out, enable)) + return PTP_PF_NONE; + + mode = MLX5_GET(mtpps_reg, out, pin_mode); + + if (mode == MLX5_PIN_MODE_IN) + return PTP_PF_EXTTS; + else if (mode == MLX5_PIN_MODE_OUT) + return PTP_PF_PEROUT; + + return PTP_PF_NONE; +} + static int mlx5_init_pin_config(struct mlx5_clock *clock) { int i; @@ -451,8 +503,8 @@ static int mlx5_init_pin_config(struct mlx5_clock *clock) sizeof(clock->ptp_info.pin_config[i].name), "mlx5_pps%d", i); clock->ptp_info.pin_config[i].index = i; - clock->ptp_info.pin_config[i].func = PTP_PF_NONE; - clock->ptp_info.pin_config[i].chan = i; + clock->ptp_info.pin_config[i].func = mlx5_get_pps_pin_mode(clock, i); + clock->ptp_info.pin_config[i].chan = 0; } return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index d6d6fe64887b..71b6185b4904 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1814,7 +1814,7 @@ static int mlxsw_core_reg_access_emad(struct mlxsw_core *mlxsw_core, err = mlxsw_emad_reg_access(mlxsw_core, reg, payload, type, trans, bulk_list, cb, cb_priv, tid); if (err) { - kfree(trans); + kfree_rcu(trans, rcu); return err; } return 0; @@ -2051,11 +2051,13 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, break; } } - rcu_read_unlock(); - if (!found) + if (!found) { + rcu_read_unlock(); goto drop; + } rxl->func(skb, local_port, rxl_item->priv); + rcu_read_unlock(); return; drop: diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index fcb88d4271bf..8ac987c8c8bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5536,6 +5536,7 @@ enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST, MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY, MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP, + MLXSW_REG_HTGT_TRAP_GROUP_SP_EXTERNAL_ROUTE, MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME, MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP, MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 019ed503aadf..0521e9d48c45 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -5001,15 +5001,6 @@ static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, static bool mlxsw_sp_fib6_rt_should_ignore(const struct fib6_info *rt) { - /* Packets with link-local destination IP arriving to the router - * are trapped to the CPU, so no need to program specific routes - * for them. Only allow prefix routes (usually one fe80::/64) so - * that packets are trapped for the right reason. - */ - if ((ipv6_addr_type(&rt->fib6_dst.addr) & IPV6_ADDR_LINKLOCAL) && - (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST))) - return true; - /* Multicast routes aren't supported, so ignore them. Neighbour * Discovery packets are specifically trapped. */ @@ -8078,16 +8069,6 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, mlxsw_sp->router = router; router->mlxsw_sp = mlxsw_sp; - router->inetaddr_nb.notifier_call = mlxsw_sp_inetaddr_event; - err = register_inetaddr_notifier(&router->inetaddr_nb); - if (err) - goto err_register_inetaddr_notifier; - - router->inet6addr_nb.notifier_call = mlxsw_sp_inet6addr_event; - err = register_inet6addr_notifier(&router->inet6addr_nb); - if (err) - goto err_register_inet6addr_notifier; - INIT_LIST_HEAD(&mlxsw_sp->router->nexthop_neighs_list); err = __mlxsw_sp_router_init(mlxsw_sp); if (err) @@ -8128,12 +8109,6 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_neigh_init; - mlxsw_sp->router->netevent_nb.notifier_call = - mlxsw_sp_router_netevent_event; - err = register_netevent_notifier(&mlxsw_sp->router->netevent_nb); - if (err) - goto err_register_netevent_notifier; - err = mlxsw_sp_mp_hash_init(mlxsw_sp); if (err) goto err_mp_hash_init; @@ -8142,6 +8117,22 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_dscp_init; + router->inetaddr_nb.notifier_call = mlxsw_sp_inetaddr_event; + err = register_inetaddr_notifier(&router->inetaddr_nb); + if (err) + goto err_register_inetaddr_notifier; + + router->inet6addr_nb.notifier_call = mlxsw_sp_inet6addr_event; + err = register_inet6addr_notifier(&router->inet6addr_nb); + if (err) + goto err_register_inet6addr_notifier; + + mlxsw_sp->router->netevent_nb.notifier_call = + mlxsw_sp_router_netevent_event; + err = register_netevent_notifier(&mlxsw_sp->router->netevent_nb); + if (err) + goto err_register_netevent_notifier; + mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event; err = register_fib_notifier(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->router->fib_nb, @@ -8152,10 +8143,15 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, return 0; err_register_fib_notifier: -err_dscp_init: -err_mp_hash_init: unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); err_register_netevent_notifier: + unregister_inet6addr_notifier(&router->inet6addr_nb); +err_register_inet6addr_notifier: + unregister_inetaddr_notifier(&router->inetaddr_nb); +err_register_inetaddr_notifier: + mlxsw_core_flush_owq(); +err_dscp_init: +err_mp_hash_init: mlxsw_sp_neigh_fini(mlxsw_sp); err_neigh_init: mlxsw_sp_vrs_fini(mlxsw_sp); @@ -8174,10 +8170,6 @@ err_ipips_init: err_rifs_init: __mlxsw_sp_router_fini(mlxsw_sp); err_router_init: - unregister_inet6addr_notifier(&router->inet6addr_nb); -err_register_inet6addr_notifier: - unregister_inetaddr_notifier(&router->inetaddr_nb); -err_register_inetaddr_notifier: mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); return err; @@ -8188,6 +8180,9 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->router->fib_nb); unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); + unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb); + unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb); + mlxsw_core_flush_owq(); mlxsw_sp_neigh_fini(mlxsw_sp); mlxsw_sp_vrs_fini(mlxsw_sp); mlxsw_sp_mr_fini(mlxsw_sp); @@ -8197,8 +8192,6 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_sp_ipips_fini(mlxsw_sp); mlxsw_sp_rifs_fini(mlxsw_sp); __mlxsw_sp_router_fini(mlxsw_sp); - unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb); - unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb); mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index 157a42c63066..1e38dfe7cf64 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -328,6 +328,9 @@ mlxsw_sp_trap_policer_items_arr[] = { { .policer = MLXSW_SP_TRAP_POLICER(18, 1024, 128), }, + { + .policer = MLXSW_SP_TRAP_POLICER(19, 1024, 512), + }, }; static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = { @@ -422,6 +425,11 @@ static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = { .priority = 2, }, { + .group = DEVLINK_TRAP_GROUP_GENERIC(EXTERNAL_DELIVERY, 19), + .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_EXTERNAL_ROUTE, + .priority = 1, + }, + { .group = DEVLINK_TRAP_GROUP_GENERIC(IPV6, 15), .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6, .priority = 2, @@ -882,11 +890,11 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = { }, }, { - .trap = MLXSW_SP_TRAP_CONTROL(EXTERNAL_ROUTE, LOCAL_DELIVERY, + .trap = MLXSW_SP_TRAP_CONTROL(EXTERNAL_ROUTE, EXTERNAL_DELIVERY, TRAP), .listeners_arr = { - MLXSW_SP_RXL_MARK(RTR_INGRESS0, IP2ME, TRAP_TO_CPU, - false), + MLXSW_SP_RXL_MARK(RTR_INGRESS0, EXTERNAL_ROUTE, + TRAP_TO_CPU, false), }, }, { diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 9cfe1fd98c30..f17da67a4622 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -748,21 +748,21 @@ void ocelot_get_txtstamp(struct ocelot *ocelot) spin_unlock_irqrestore(&port->tx_skbs.lock, flags); - /* Next ts */ - ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT); + /* Get the h/w timestamp */ + ocelot_get_hwtimestamp(ocelot, &ts); if (unlikely(!skb_match)) continue; - /* Get the h/w timestamp */ - ocelot_get_hwtimestamp(ocelot, &ts); - /* Set the timestamp into the skb */ memset(&shhwtstamps, 0, sizeof(shhwtstamps)); shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); skb_tstamp_tx(skb_match, &shhwtstamps); dev_kfree_skb_any(skb_match); + + /* Next ts */ + ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT); } } EXPORT_SYMBOL(ocelot_get_txtstamp); diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index d2708a57f2ff..4075f5e59955 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -1299,19 +1299,21 @@ static int nixge_probe(struct platform_device *pdev) netif_napi_add(ndev, &priv->napi, nixge_poll, NAPI_POLL_WEIGHT); err = nixge_of_get_resources(pdev); if (err) - return err; + goto free_netdev; __nixge_hw_set_mac_address(ndev); priv->tx_irq = platform_get_irq_byname(pdev, "tx"); if (priv->tx_irq < 0) { netdev_err(ndev, "could not find 'tx' irq"); - return priv->tx_irq; + err = priv->tx_irq; + goto free_netdev; } priv->rx_irq = platform_get_irq_byname(pdev, "rx"); if (priv->rx_irq < 0) { netdev_err(ndev, "could not find 'rx' irq"); - return priv->rx_irq; + err = priv->rx_irq; + goto free_netdev; } priv->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 5fd31ba56937..e55d41546cff 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2001,7 +2001,7 @@ int ionic_reset_queues(struct ionic_lif *lif, ionic_reset_cb cb, void *arg) netif_device_detach(lif->netdev); err = ionic_stop(lif->netdev); if (err) - return err; + goto reset_out; } if (cb) @@ -2011,6 +2011,8 @@ int ionic_reset_queues(struct ionic_lif *lif, ionic_reset_cb cb, void *arg) err = ionic_open(lif->netdev); netif_device_attach(lif->netdev); } + +reset_out: mutex_unlock(&lif->queue_lock); return err; diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 5f123a8cf68e..d2fdb5430d27 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2261,12 +2261,14 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs, minor = get_free_serial_index(); if (minor < 0) - goto exit; + goto exit2; /* register our minor number */ serial->parent->dev = tty_port_register_device_attr(&serial->port, tty_drv, minor, &serial->parent->interface->dev, serial->parent, hso_serial_dev_groups); + if (IS_ERR(serial->parent->dev)) + goto exit2; /* fill in specific data for later use */ serial->minor = minor; @@ -2311,6 +2313,7 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs, return 0; exit: hso_serial_tty_unregister(serial); +exit2: hso_serial_common_free(serial); return -1; } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index eccbf4cd7149..442507f25aad 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -377,10 +377,6 @@ struct lan78xx_net { struct tasklet_struct bh; struct delayed_work wq; - struct usb_host_endpoint *ep_blkin; - struct usb_host_endpoint *ep_blkout; - struct usb_host_endpoint *ep_intr; - int msg_enable; struct urb *urb_intr; @@ -2860,78 +2856,12 @@ lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net) return NETDEV_TX_OK; } -static int -lan78xx_get_endpoints(struct lan78xx_net *dev, struct usb_interface *intf) -{ - int tmp; - struct usb_host_interface *alt = NULL; - struct usb_host_endpoint *in = NULL, *out = NULL; - struct usb_host_endpoint *status = NULL; - - for (tmp = 0; tmp < intf->num_altsetting; tmp++) { - unsigned ep; - - in = NULL; - out = NULL; - status = NULL; - alt = intf->altsetting + tmp; - - for (ep = 0; ep < alt->desc.bNumEndpoints; ep++) { - struct usb_host_endpoint *e; - int intr = 0; - - e = alt->endpoint + ep; - switch (e->desc.bmAttributes) { - case USB_ENDPOINT_XFER_INT: - if (!usb_endpoint_dir_in(&e->desc)) - continue; - intr = 1; - /* FALLTHROUGH */ - case USB_ENDPOINT_XFER_BULK: - break; - default: - continue; - } - if (usb_endpoint_dir_in(&e->desc)) { - if (!intr && !in) - in = e; - else if (intr && !status) - status = e; - } else { - if (!out) - out = e; - } - } - if (in && out) - break; - } - if (!alt || !in || !out) - return -EINVAL; - - dev->pipe_in = usb_rcvbulkpipe(dev->udev, - in->desc.bEndpointAddress & - USB_ENDPOINT_NUMBER_MASK); - dev->pipe_out = usb_sndbulkpipe(dev->udev, - out->desc.bEndpointAddress & - USB_ENDPOINT_NUMBER_MASK); - dev->ep_intr = status; - - return 0; -} - static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf) { struct lan78xx_priv *pdata = NULL; int ret; int i; - ret = lan78xx_get_endpoints(dev, intf); - if (ret) { - netdev_warn(dev->net, "lan78xx_get_endpoints failed: %d\n", - ret); - return ret; - } - dev->data[0] = (unsigned long)kzalloc(sizeof(*pdata), GFP_KERNEL); pdata = (struct lan78xx_priv *)(dev->data[0]); @@ -3700,6 +3630,7 @@ static void lan78xx_stat_monitor(struct timer_list *t) static int lan78xx_probe(struct usb_interface *intf, const struct usb_device_id *id) { + struct usb_host_endpoint *ep_blkin, *ep_blkout, *ep_intr; struct lan78xx_net *dev; struct net_device *netdev; struct usb_device *udev; @@ -3748,6 +3679,34 @@ static int lan78xx_probe(struct usb_interface *intf, mutex_init(&dev->stats.access_lock); + if (intf->cur_altsetting->desc.bNumEndpoints < 3) { + ret = -ENODEV; + goto out2; + } + + dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE); + ep_blkin = usb_pipe_endpoint(udev, dev->pipe_in); + if (!ep_blkin || !usb_endpoint_is_bulk_in(&ep_blkin->desc)) { + ret = -ENODEV; + goto out2; + } + + dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE); + ep_blkout = usb_pipe_endpoint(udev, dev->pipe_out); + if (!ep_blkout || !usb_endpoint_is_bulk_out(&ep_blkout->desc)) { + ret = -ENODEV; + goto out2; + } + + ep_intr = &intf->cur_altsetting->endpoint[2]; + if (!usb_endpoint_is_int_in(&ep_intr->desc)) { + ret = -ENODEV; + goto out2; + } + + dev->pipe_intr = usb_rcvintpipe(dev->udev, + usb_endpoint_num(&ep_intr->desc)); + ret = lan78xx_bind(dev, intf); if (ret < 0) goto out2; @@ -3759,18 +3718,7 @@ static int lan78xx_probe(struct usb_interface *intf, netdev->max_mtu = MAX_SINGLE_PACKET_SIZE; netif_set_gso_max_size(netdev, MAX_SINGLE_PACKET_SIZE - MAX_HEADER); - dev->ep_blkin = (intf->cur_altsetting)->endpoint + 0; - dev->ep_blkout = (intf->cur_altsetting)->endpoint + 1; - dev->ep_intr = (intf->cur_altsetting)->endpoint + 2; - - dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE); - dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE); - - dev->pipe_intr = usb_rcvintpipe(dev->udev, - dev->ep_intr->desc.bEndpointAddress & - USB_ENDPOINT_NUMBER_MASK); - period = dev->ep_intr->desc.bInterval; - + period = ep_intr->desc.bInterval; maxp = usb_maxpacket(dev->udev, dev->pipe_intr, 0); buf = kmalloc(maxp, GFP_KERNEL); if (buf) { @@ -3783,6 +3731,7 @@ static int lan78xx_probe(struct usb_interface *intf, usb_fill_int_urb(dev->urb_intr, dev->udev, dev->pipe_intr, buf, maxp, intr_complete, dev, period); + dev->urb_intr->transfer_flags |= URB_FREE_BUFFER; } } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 89d85dcb200e..a7c3939264b0 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1376,6 +1376,7 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, for (h = 0; h < FDB_HASH_SIZE; ++h) { struct vxlan_fdb *f; + rcu_read_lock(); hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) { struct vxlan_rdst *rd; @@ -1387,8 +1388,10 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, NULL); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto out; + } skip_nh: *idx += 1; continue; @@ -1403,12 +1406,15 @@ skip_nh: cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto out; + } skip: *idx += 1; } } + rcu_read_unlock(); } out: return err; @@ -3070,8 +3076,10 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all) if (!do_all && (f->state & (NUD_PERMANENT | NUD_NOARP))) continue; /* the all_zeros_mac entry is deleted at vxlan_uninit */ - if (!is_zero_ether_addr(f->eth_addr)) - vxlan_fdb_destroy(vxlan, f, true, true); + if (is_zero_ether_addr(f->eth_addr) && + f->vni == vxlan->cfg.vni) + continue; + vxlan_fdb_destroy(vxlan, f, true, true); } spin_unlock_bh(&vxlan->hash_lock[h]); } diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 073b79eacc99..1340e02b14ef 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4381,6 +4381,7 @@ struct mlx5_ifc_query_vport_state_out_bits { enum { MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT = 0x0, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT = 0x1, + MLX5_VPORT_STATE_OP_MOD_UPLINK = 0x2, }; struct mlx5_ifc_arm_monitor_counter_in_bits { diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index d3432ee65de7..68dab3e08aad 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -84,7 +84,7 @@ struct bucket_table { struct lockdep_map dep_map; - struct rhash_lock_head *buckets[] ____cacheline_aligned_in_smp; + struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; /* @@ -261,13 +261,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, void *arg); void rhashtable_destroy(struct rhashtable *ht); -struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash); -struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash); -struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht, - struct bucket_table *tbl, - unsigned int hash); +struct rhash_lock_head __rcu **rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash); +struct rhash_lock_head __rcu **__rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash); +struct rhash_lock_head __rcu **rht_bucket_nested_insert( + struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash); #define rht_dereference(p, ht) \ rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht)) @@ -284,21 +283,21 @@ struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht, #define rht_entry(tpos, pos, member) \ ({ tpos = container_of(pos, typeof(*tpos), member); 1; }) -static inline struct rhash_lock_head *const *rht_bucket( +static inline struct rhash_lock_head __rcu *const *rht_bucket( const struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } -static inline struct rhash_lock_head **rht_bucket_var( +static inline struct rhash_lock_head __rcu **rht_bucket_var( struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } -static inline struct rhash_lock_head **rht_bucket_insert( +static inline struct rhash_lock_head __rcu **rht_bucket_insert( struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) : @@ -325,7 +324,7 @@ static inline struct rhash_lock_head **rht_bucket_insert( */ static inline void rht_lock(struct bucket_table *tbl, - struct rhash_lock_head **bkt) + struct rhash_lock_head __rcu **bkt) { local_bh_disable(); bit_spin_lock(0, (unsigned long *)bkt); @@ -333,7 +332,7 @@ static inline void rht_lock(struct bucket_table *tbl, } static inline void rht_lock_nested(struct bucket_table *tbl, - struct rhash_lock_head **bucket, + struct rhash_lock_head __rcu **bucket, unsigned int subclass) { local_bh_disable(); @@ -342,18 +341,18 @@ static inline void rht_lock_nested(struct bucket_table *tbl, } static inline void rht_unlock(struct bucket_table *tbl, - struct rhash_lock_head **bkt) + struct rhash_lock_head __rcu **bkt) { lock_map_release(&tbl->dep_map); bit_spin_unlock(0, (unsigned long *)bkt); local_bh_enable(); } -static inline struct rhash_head __rcu *__rht_ptr( - struct rhash_lock_head *const *bkt) +static inline struct rhash_head *__rht_ptr( + struct rhash_lock_head *p, struct rhash_lock_head __rcu *const *bkt) { - return (struct rhash_head __rcu *) - ((unsigned long)*bkt & ~BIT(0) ?: + return (struct rhash_head *) + ((unsigned long)p & ~BIT(0) ?: (unsigned long)RHT_NULLS_MARKER(bkt)); } @@ -365,47 +364,41 @@ static inline struct rhash_head __rcu *__rht_ptr( * access is guaranteed, such as when destroying the table. */ static inline struct rhash_head *rht_ptr_rcu( - struct rhash_lock_head *const *bkt) + struct rhash_lock_head __rcu *const *bkt) { - struct rhash_head __rcu *p = __rht_ptr(bkt); - - return rcu_dereference(p); + return __rht_ptr(rcu_dereference(*bkt), bkt); } static inline struct rhash_head *rht_ptr( - struct rhash_lock_head *const *bkt, + struct rhash_lock_head __rcu *const *bkt, struct bucket_table *tbl, unsigned int hash) { - return rht_dereference_bucket(__rht_ptr(bkt), tbl, hash); + return __rht_ptr(rht_dereference_bucket(*bkt, tbl, hash), bkt); } static inline struct rhash_head *rht_ptr_exclusive( - struct rhash_lock_head *const *bkt) + struct rhash_lock_head __rcu *const *bkt) { - return rcu_dereference_protected(__rht_ptr(bkt), 1); + return __rht_ptr(rcu_dereference_protected(*bkt, 1), bkt); } -static inline void rht_assign_locked(struct rhash_lock_head **bkt, +static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt, struct rhash_head *obj) { - struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; - if (rht_is_a_nulls(obj)) obj = NULL; - rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(0))); + rcu_assign_pointer(*bkt, (void *)((unsigned long)obj | BIT(0))); } static inline void rht_assign_unlock(struct bucket_table *tbl, - struct rhash_lock_head **bkt, + struct rhash_lock_head __rcu **bkt, struct rhash_head *obj) { - struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; - if (rht_is_a_nulls(obj)) obj = NULL; lock_map_release(&tbl->dep_map); - rcu_assign_pointer(*p, obj); + rcu_assign_pointer(*bkt, (void *)obj); preempt_enable(); __release(bitlock); local_bh_enable(); @@ -593,7 +586,7 @@ static inline struct rhash_head *__rhashtable_lookup( .ht = ht, .key = key, }; - struct rhash_lock_head *const *bkt; + struct rhash_lock_head __rcu *const *bkt; struct bucket_table *tbl; struct rhash_head *he; unsigned int hash; @@ -709,7 +702,7 @@ static inline void *__rhashtable_insert_fast( .ht = ht, .key = key, }; - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct bucket_table *tbl; struct rhash_head *head; @@ -995,7 +988,7 @@ static inline int __rhashtable_remove_fast_one( struct rhash_head *obj, const struct rhashtable_params params, bool rhlist) { - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; unsigned int hash; @@ -1147,7 +1140,7 @@ static inline int __rhashtable_replace_fast( struct rhash_head *obj_old, struct rhash_head *obj_new, const struct rhashtable_params params) { - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; unsigned int hash; diff --git a/include/net/addrconf.h b/include/net/addrconf.h index fdb07105384c..8418b7d38468 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -274,6 +274,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); +void __ipv6_sock_ac_close(struct sock *sk); void ipv6_sock_ac_close(struct sock *sk); int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr); diff --git a/include/net/devlink.h b/include/net/devlink.h index 1df6dfec26c2..95b0322a2a82 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -718,6 +718,7 @@ enum devlink_trap_group_generic_id { DEVLINK_TRAP_GROUP_GENERIC_ID_PIM, DEVLINK_TRAP_GROUP_GENERIC_ID_UC_LB, DEVLINK_TRAP_GROUP_GENERIC_ID_LOCAL_DELIVERY, + DEVLINK_TRAP_GROUP_GENERIC_ID_EXTERNAL_DELIVERY, DEVLINK_TRAP_GROUP_GENERIC_ID_IPV6, DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_EVENT, DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_GENERAL, @@ -915,6 +916,8 @@ enum devlink_trap_group_generic_id { "uc_loopback" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_LOCAL_DELIVERY \ "local_delivery" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_EXTERNAL_DELIVERY \ + "external_delivery" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_IPV6 \ "ipv6" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_PTP_EVENT \ diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c7d213c9f9d8..51f65d23ebaf 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -941,7 +941,7 @@ struct xfrm_dst { static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) { #ifdef CONFIG_XFRM - if (dst->xfrm) { + if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { const struct xfrm_dst *xdst = (const struct xfrm_dst *) dst; return xdst->path; @@ -953,7 +953,7 @@ static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) static inline struct dst_entry *xfrm_dst_child(const struct dst_entry *dst) { #ifdef CONFIG_XFRM - if (dst->xfrm) { + if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { struct xfrm_dst *xdst = (struct xfrm_dst *) dst; return xdst->child; } @@ -1630,13 +1630,16 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, void *); void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net); int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl); -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, - u8 type, int dir, +struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, + const struct xfrm_mark *mark, + u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, u8, - int dir, u32 id, int delete, int *err); +struct xfrm_policy *xfrm_policy_byid(struct net *net, + const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, u32 id, int delete, + int *err); int xfrm_policy_flush(struct net *net, u8 type, bool task_valid); void xfrm_policy_hash_rebuild(struct net *net); u32 xfrm_get_acqseq(void); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9a1a98dd9e97..0443600146dc 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4058,6 +4058,11 @@ static int __btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, const char *tname, *sym; u32 btf_id, i; + if (!btf_vmlinux) { + bpf_log(log, "btf_vmlinux doesn't exist\n"); + return -EINVAL; + } + if (IS_ERR(btf_vmlinux)) { bpf_log(log, "btf_vmlinux is malformed\n"); return -EINVAL; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index b4b288a3c3c9..b32cc8ce8ff6 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -779,15 +779,20 @@ static void htab_elem_free_rcu(struct rcu_head *head) htab_elem_free(htab, l); } -static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) { struct bpf_map *map = &htab->map; + void *ptr; if (map->ops->map_fd_put_ptr) { - void *ptr = fd_htab_map_get_ptr(map, l); - + ptr = fd_htab_map_get_ptr(map, l); map->ops->map_fd_put_ptr(ptr); } +} + +static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +{ + htab_put_fd_value(htab, l); if (htab_is_prealloc(htab)) { __pcpu_freelist_push(&htab->freelist, &l->fnode); @@ -839,6 +844,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, */ pl_new = this_cpu_ptr(htab->extra_elems); l_new = *pl_new; + htab_put_fd_value(htab, old_elem); *pl_new = old_elem; } else { struct pcpu_freelist_node *l; diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 9f6890aedd1a..c949c1e3b87c 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -31,7 +31,7 @@ union nested_table { union nested_table __rcu *table; - struct rhash_lock_head *bucket; + struct rhash_lock_head __rcu *bucket; }; static u32 head_hashfn(struct rhashtable *ht, @@ -222,7 +222,7 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht, } static int rhashtable_rehash_one(struct rhashtable *ht, - struct rhash_lock_head **bkt, + struct rhash_lock_head __rcu **bkt, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); @@ -275,7 +275,7 @@ static int rhashtable_rehash_chain(struct rhashtable *ht, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); - struct rhash_lock_head **bkt = rht_bucket_var(old_tbl, old_hash); + struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash); int err; if (!bkt) @@ -485,7 +485,7 @@ fail: } static void *rhashtable_lookup_one(struct rhashtable *ht, - struct rhash_lock_head **bkt, + struct rhash_lock_head __rcu **bkt, struct bucket_table *tbl, unsigned int hash, const void *key, struct rhash_head *obj) { @@ -535,12 +535,10 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, return ERR_PTR(-ENOENT); } -static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht, - struct rhash_lock_head **bkt, - struct bucket_table *tbl, - unsigned int hash, - struct rhash_head *obj, - void *data) +static struct bucket_table *rhashtable_insert_one( + struct rhashtable *ht, struct rhash_lock_head __rcu **bkt, + struct bucket_table *tbl, unsigned int hash, struct rhash_head *obj, + void *data) { struct bucket_table *new_tbl; struct rhash_head *head; @@ -591,7 +589,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, { struct bucket_table *new_tbl; struct bucket_table *tbl; - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; unsigned int hash; void *data; @@ -1173,8 +1171,8 @@ void rhashtable_destroy(struct rhashtable *ht) } EXPORT_SYMBOL_GPL(rhashtable_destroy); -struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash) +struct rhash_lock_head __rcu **__rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); unsigned int index = hash & ((1 << tbl->nest) - 1); @@ -1202,10 +1200,10 @@ struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl, } EXPORT_SYMBOL_GPL(__rht_bucket_nested); -struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash) +struct rhash_lock_head __rcu **rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash) { - static struct rhash_lock_head *rhnull; + static struct rhash_lock_head __rcu *rhnull; if (!rhnull) INIT_RHT_NULLS_HEAD(rhnull); @@ -1213,9 +1211,8 @@ struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl, } EXPORT_SYMBOL_GPL(rht_bucket_nested); -struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht, - struct bucket_table *tbl, - unsigned int hash) +struct rhash_lock_head __rcu **rht_bucket_nested_insert( + struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); unsigned int index = hash & ((1 << tbl->nest) - 1); diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c index 1905e01c3aa9..4494ea6056cd 100644 --- a/net/bpfilter/bpfilter_kern.c +++ b/net/bpfilter/bpfilter_kern.c @@ -39,7 +39,7 @@ static int __bpfilter_process_sockopt(struct sock *sk, int optname, { struct mbox_request req; struct mbox_reply reply; - loff_t pos; + loff_t pos = 0; ssize_t n; int ret = -EFAULT; diff --git a/net/compat.c b/net/compat.c index 5e3041a2c37d..434838bef5f8 100644 --- a/net/compat.c +++ b/net/compat.c @@ -202,7 +202,7 @@ int cmsghdr_from_user_compat_to_kern(struct msghdr *kmsg, struct sock *sk, /* Advance. */ kcmsg = (struct cmsghdr *)((char *)kcmsg + tmp); - ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, ucmlen); + ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, cmsg.cmsg_len); } /* diff --git a/net/core/devlink.c b/net/core/devlink.c index 2cafbc808b09..47f14a2f25fb 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1065,7 +1065,9 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -1266,7 +1268,9 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, devlink, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -1498,7 +1502,9 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -3299,7 +3305,9 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -3569,7 +3577,9 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -4518,7 +4528,9 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); mutex_unlock(&devlink->lock); - if (err && err != -EOPNOTSUPP) + if (err == -EOPNOTSUPP) + err = 0; + else if (err) break; idx++; } @@ -8567,6 +8579,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(PIM), DEVLINK_TRAP_GROUP(UC_LB), DEVLINK_TRAP_GROUP(LOCAL_DELIVERY), + DEVLINK_TRAP_GROUP(EXTERNAL_DELIVERY), DEVLINK_TRAP_GROUP(IPV6), DEVLINK_TRAP_GROUP(PTP_EVENT), DEVLINK_TRAP_GROUP(PTP_GENERAL), diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 248f1c1959a6..3c65f71d0e82 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1864,7 +1864,7 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) while ((l = leaf_walk_rcu(&tp, key)) != NULL) { struct key_vector *local_l = NULL, *local_tp; - hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + hlist_for_each_entry(fa, &l->leaf, fa_list) { struct fib_alias *new_fa; if (local_tb->tb_id != fa->tb_id) diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 893261230ffc..dacdea7fcb62 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -183,7 +183,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) return 0; } -void ipv6_sock_ac_close(struct sock *sk) +void __ipv6_sock_ac_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev = NULL; @@ -191,10 +191,7 @@ void ipv6_sock_ac_close(struct sock *sk) struct net *net = sock_net(sk); int prev_index; - if (!np->ipv6_ac_list) - return; - - rtnl_lock(); + ASSERT_RTNL(); pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; @@ -211,6 +208,16 @@ void ipv6_sock_ac_close(struct sock *sk) sock_kfree_s(sk, pac, sizeof(*pac)); pac = next; } +} + +void ipv6_sock_ac_close(struct sock *sk) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + + if (!np->ipv6_ac_list) + return; + rtnl_lock(); + __ipv6_sock_ac_close(sk); rtnl_unlock(); } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index c43592771126..52c2f063529f 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -805,10 +805,17 @@ int esp6_input_done2(struct sk_buff *skb, int err) if (x->encap) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); + int offset = skb_network_offset(skb) + sizeof(*ip6h); struct xfrm_encap_tmpl *encap = x->encap; - struct udphdr *uh = (void *)(skb_network_header(skb) + hdr_len); - struct tcphdr *th = (void *)(skb_network_header(skb) + hdr_len); - __be16 source; + u8 nexthdr = ip6h->nexthdr; + __be16 frag_off, source; + struct udphdr *uh; + struct tcphdr *th; + + offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); + uh = (void *)(skb->data + offset); + th = (void *)(skb->data + offset); + hdr_len += offset; switch (x->encap->encap_type) { case TCP_ENCAP_ESPINTCP: diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 20576e87a5f7..76f9e41859a2 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -240,6 +240,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, fl6_free_socklist(sk); __ipv6_sock_mc_close(sk); + __ipv6_sock_ac_close(sk); /* * Sock is moving from IPv6 to IPv4 (sk_prot), so diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f3279810d765..4c36bd0c7930 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3685,14 +3685,14 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, rt->fib6_src.plen = cfg->fc_src_len; #endif if (nh) { - if (!nexthop_get(nh)) { - NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); - goto out; - } if (rt->fib6_src.plen) { NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); goto out; } + if (!nexthop_get(nh)) { + NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); + goto out; + } rt->nh = nh; fib6_nh = nexthop_fib6_nh(rt->nh); } else { diff --git a/net/key/af_key.c b/net/key/af_key.c index b67ed3a8486c..a915bc86620a 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1849,6 +1849,13 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; + if ((xfilter->sadb_x_filter_splen >= + (sizeof(xfrm_address_t) << 3)) || + (xfilter->sadb_x_filter_dplen >= + (sizeof(xfrm_address_t) << 3))) { + mutex_unlock(&pfk->dump_lock); + return -EINVAL; + } filter = kmalloc(sizeof(*filter), GFP_KERNEL); if (filter == NULL) { mutex_unlock(&pfk->dump_lock); @@ -2400,7 +2407,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa return err; } - xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_bysel_ctx(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, pol->sadb_x_policy_dir - 1, &sel, pol_ctx, 1, &err); security_xfrm_policy_free(pol_ctx); @@ -2651,7 +2658,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_ return -EINVAL; delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2); - xp = xfrm_policy_byid(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_byid(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, dir, pol->sadb_x_policy_id, delete, &err); if (xp == NULL) return -ENOENT; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 9b360544ad6f..1079a07e43e4 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2166,6 +2166,7 @@ static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev) ieee80211_stop_mesh(sdata); mutex_lock(&sdata->local->mtx); ieee80211_vif_release_channel(sdata); + kfree(sdata->u.mesh.ie); mutex_unlock(&sdata->local->mtx); return 0; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 5f1ca25b6c97..e88beb3ff6db 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -617,6 +617,19 @@ int mesh_add_he_oper_ie(struct ieee80211_sub_if_data *sdata, int mesh_add_he_6ghz_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { + struct ieee80211_supported_band *sband; + const struct ieee80211_sband_iftype_data *iftd; + + sband = ieee80211_get_sband(sdata); + if (!sband) + return -EINVAL; + + iftd = ieee80211_get_sband_iftype_data(sband, + NL80211_IFTYPE_MESH_POINT); + /* The device doesn't support HE in mesh mode or at all */ + if (!iftd) + return 0; + ieee80211_ie_build_he_6ghz_cap(sdata, skb); return 0; } diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 117519bf33d6..aca608ae313f 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -521,6 +521,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, del_timer_sync(&mpath->timer); atomic_dec(&sdata->u.mesh.mpaths); atomic_dec(&tbl->entries); + mesh_path_flush_pending(mpath); kfree_rcu(mpath, rcu); } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index cd8487bc6fc2..af4cc5fb678e 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1923,9 +1923,7 @@ void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local, if (sta) { tx_pending = atomic_sub_return(tx_airtime, &sta->airtime[ac].aql_tx_pending); - if (WARN_ONCE(tx_pending < 0, - "STA %pM AC %d txq pending airtime underflow: %u, %u", - sta->addr, ac, tx_pending, tx_airtime)) + if (tx_pending < 0) atomic_cmpxchg(&sta->airtime[ac].aql_tx_pending, tx_pending, 0); } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1a2941e5244f..3529d1368068 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4230,11 +4230,12 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) goto out_free; + memset(info, 0, sizeof(*info)); + if (unlikely(!multicast && skb->sk && skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)) - ieee80211_store_ack_skb(local, skb, &info->flags, NULL); - - memset(info, 0, sizeof(*info)); + info->ack_frame_id = ieee80211_store_ack_skb(local, skb, + &info->flags, NULL); if (unlikely(sdata->control_port_protocol == ehdr->h_proto)) { if (sdata->control_port_no_encrypt) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 21c94094a699..dd9f5c7a1ade 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2878,6 +2878,10 @@ void ieee80211_ie_build_he_6ghz_cap(struct ieee80211_sub_if_data *sdata, if (WARN_ON(!iftd)) return; + /* Check for device HE 6 GHz capability before adding element */ + if (!iftd->he_6ghz_capa.capa) + return; + cap = le16_to_cpu(iftd->he_6ghz_capa.capa); cap &= ~IEEE80211_HE_6GHZ_CAP_SM_PS; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3980fbb6f31e..c0abe738e7d3 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1833,7 +1833,7 @@ do_connect: /* on successful connect, the msk state will be moved to established by * subflow_finish_connect() */ - if (!err || err == EINPROGRESS) + if (!err || err == -EINPROGRESS) mptcp_copy_inaddrs(sock->sk, ssock->sk); else inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk)); diff --git a/net/rds/recv.c b/net/rds/recv.c index c8404971d5ab..aba4afe4dfed 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -450,12 +450,13 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc, int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msghdr) { struct rds_notifier *notifier; - struct rds_rdma_notify cmsg = { 0 }; /* fill holes with zero */ + struct rds_rdma_notify cmsg; unsigned int count = 0, max_messages = ~0U; unsigned long flags; LIST_HEAD(copy); int err = 0; + memset(&cmsg, 0, sizeof(cmsg)); /* fill holes with zero */ /* put_cmsg copies to user space and thus may sleep. We can't do this * with rs_lock held, so first grab as many notifications as we can stuff diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f07970207b54..38a46167523f 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -288,7 +288,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, */ ret = rxrpc_connect_call(rx, call, cp, srx, gfp); if (ret < 0) - goto error; + goto error_attached_to_socket; trace_rxrpc_call(call->debug_id, rxrpc_call_connected, atomic_read(&call->usage), here, NULL); @@ -308,18 +308,29 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, error_dup_user_ID: write_unlock(&rx->call_lock); release_sock(&rx->sk); - ret = -EEXIST; - -error: __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - RX_CALL_DEAD, ret); + RX_CALL_DEAD, -EEXIST); trace_rxrpc_call(call->debug_id, rxrpc_call_error, - atomic_read(&call->usage), here, ERR_PTR(ret)); + atomic_read(&call->usage), here, ERR_PTR(-EEXIST)); rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); - _leave(" = %d", ret); - return ERR_PTR(ret); + _leave(" = -EEXIST"); + return ERR_PTR(-EEXIST); + + /* We got an error, but the call is attached to the socket and is in + * need of release. However, we might now race with recvmsg() when + * completing the call queues it. Return 0 from sys_sendmsg() and + * leave the error to recvmsg() to deal with. + */ +error_attached_to_socket: + trace_rxrpc_call(call->debug_id, rxrpc_call_error, + atomic_read(&call->usage), here, ERR_PTR(ret)); + set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); + __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + RX_CALL_DEAD, ret); + _leave(" = c=%08x [err]", call->debug_id); + return call; } /* diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 19e141eeed17..8cbe0bf20ed5 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -212,9 +212,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) call->peer->cong_cwnd = call->cong_cwnd; - spin_lock_bh(&conn->params.peer->lock); - hlist_del_rcu(&call->error_link); - spin_unlock_bh(&conn->params.peer->lock); + if (!hlist_unhashed(&call->error_link)) { + spin_lock_bh(&call->peer->lock); + hlist_del_rcu(&call->error_link); + spin_unlock_bh(&call->peer->lock); + } if (rxrpc_is_client_call(call)) return rxrpc_disconnect_client_call(call); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 490b1927215c..efecc5a8f67d 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -620,7 +620,7 @@ try_again: goto error_unlock_call; } - if (msg->msg_name) { + if (msg->msg_name && call->peer) { struct sockaddr_rxrpc *srx = msg->msg_name; size_t len = sizeof(call->peer->srx); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 03a30d014bb6..f3f6da6e4ad2 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -681,6 +681,9 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (IS_ERR(call)) return PTR_ERR(call); /* ... and we have the call lock. */ + ret = 0; + if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) + goto out_put_unlock; } else { switch (READ_ONCE(call->state)) { case RXRPC_CALL_UNINITIALISED: diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 5928efb6449c..6ed1652d1e26 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1543,10 +1543,10 @@ static int __init ct_init_module(void) return 0; -err_tbl_init: - destroy_workqueue(act_ct_wq); err_register: tcf_ct_flow_tables_uninit(); +err_tbl_init: + destroy_workqueue(act_ct_wq); return err; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0e07fb8585fb..7fbca0854265 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -13266,13 +13266,13 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info) if (!wdev_running(wdev)) return -ENETDOWN; } - - if (!vcmd->doit) - return -EOPNOTSUPP; } else { wdev = NULL; } + if (!vcmd->doit) + return -EOPNOTSUPP; + if (info->attrs[NL80211_ATTR_VENDOR_DATA]) { data = nla_data(info->attrs[NL80211_ATTR_VENDOR_DATA]); len = nla_len(info->attrs[NL80211_ATTR_VENDOR_DATA]); diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index 100e29682b48..827ccdf2db57 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -15,6 +15,7 @@ static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb, { if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf || !sk_rmem_schedule(sk, skb, skb->truesize)) { + XFRM_INC_STATS(sock_net(sk), LINUX_MIB_XFRMINERROR); kfree_skb(skb); return; } @@ -49,23 +50,51 @@ static void espintcp_rcv(struct strparser *strp, struct sk_buff *skb) struct espintcp_ctx *ctx = container_of(strp, struct espintcp_ctx, strp); struct strp_msg *rxm = strp_msg(skb); + int len = rxm->full_len - 2; u32 nonesp_marker; int err; + /* keepalive packet? */ + if (unlikely(len == 1)) { + u8 data; + + err = skb_copy_bits(skb, rxm->offset + 2, &data, 1); + if (err < 0) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR); + kfree_skb(skb); + return; + } + + if (data == 0xff) { + kfree_skb(skb); + return; + } + } + + /* drop other short messages */ + if (unlikely(len <= sizeof(nonesp_marker))) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR); + kfree_skb(skb); + return; + } + err = skb_copy_bits(skb, rxm->offset + 2, &nonesp_marker, sizeof(nonesp_marker)); if (err < 0) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR); kfree_skb(skb); return; } /* remove header, leave non-ESP marker/SPI */ if (!__pskb_pull(skb, rxm->offset + 2)) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINERROR); kfree_skb(skb); return; } if (pskb_trim(skb, rxm->full_len - 2) != 0) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINERROR); kfree_skb(skb); return; } @@ -91,7 +120,7 @@ static int espintcp_parse(struct strparser *strp, struct sk_buff *skb) return err; len = be16_to_cpu(blen); - if (len < 6) + if (len < 2) return -EINVAL; return len; @@ -109,8 +138,11 @@ static int espintcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, flags |= nonblock ? MSG_DONTWAIT : 0; skb = __skb_recv_datagram(sk, &ctx->ike_queue, flags, &off, &err); - if (!skb) + if (!skb) { + if (err == -EAGAIN && sk->sk_shutdown & RCV_SHUTDOWN) + return 0; return err; + } copied = len; if (copied > skb->len) @@ -213,7 +245,7 @@ retry: return 0; } -static int espintcp_push_msgs(struct sock *sk) +static int espintcp_push_msgs(struct sock *sk, int flags) { struct espintcp_ctx *ctx = espintcp_getctx(sk); struct espintcp_msg *emsg = &ctx->partial; @@ -227,12 +259,12 @@ static int espintcp_push_msgs(struct sock *sk) ctx->tx_running = 1; if (emsg->skb) - err = espintcp_sendskb_locked(sk, emsg, 0); + err = espintcp_sendskb_locked(sk, emsg, flags); else - err = espintcp_sendskmsg_locked(sk, emsg, 0); + err = espintcp_sendskmsg_locked(sk, emsg, flags); if (err == -EAGAIN) { ctx->tx_running = 0; - return 0; + return flags & MSG_DONTWAIT ? -EAGAIN : 0; } if (!err) memset(emsg, 0, sizeof(*emsg)); @@ -257,7 +289,7 @@ int espintcp_push_skb(struct sock *sk, struct sk_buff *skb) offset = skb_transport_offset(skb); len = skb->len - offset; - espintcp_push_msgs(sk); + espintcp_push_msgs(sk, 0); if (emsg->len) { kfree_skb(skb); @@ -270,7 +302,7 @@ int espintcp_push_skb(struct sock *sk, struct sk_buff *skb) emsg->len = len; emsg->skb = skb; - espintcp_push_msgs(sk); + espintcp_push_msgs(sk, 0); return 0; } @@ -287,7 +319,7 @@ static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) char buf[2] = {0}; int err, end; - if (msg->msg_flags) + if (msg->msg_flags & ~MSG_DONTWAIT) return -EOPNOTSUPP; if (size > MAX_ESPINTCP_MSG) @@ -298,9 +330,10 @@ static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) lock_sock(sk); - err = espintcp_push_msgs(sk); + err = espintcp_push_msgs(sk, msg->msg_flags & MSG_DONTWAIT); if (err < 0) { - err = -ENOBUFS; + if (err != -EAGAIN || !(msg->msg_flags & MSG_DONTWAIT)) + err = -ENOBUFS; goto unlock; } @@ -337,10 +370,9 @@ static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) tcp_rate_check_app_limited(sk); - err = espintcp_push_msgs(sk); + err = espintcp_push_msgs(sk, msg->msg_flags & MSG_DONTWAIT); /* this message could be partially sent, keep it */ - if (err < 0) - goto unlock; + release_sock(sk); return size; @@ -374,7 +406,7 @@ static void espintcp_tx_work(struct work_struct *work) lock_sock(sk); if (!ctx->tx_running) - espintcp_push_msgs(sk); + espintcp_push_msgs(sk, 0); release_sock(sk); } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 564aa6492e7c..19c5e0fa3f44 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -39,7 +39,7 @@ #ifdef CONFIG_XFRM_STATISTICS #include <net/snmp.h> #endif -#ifdef CONFIG_INET_ESPINTCP +#ifdef CONFIG_XFRM_ESPINTCP #include <net/espintcp.h> #endif @@ -1433,14 +1433,10 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, spin_unlock_bh(&pq->hold_queue.lock); } -static bool xfrm_policy_mark_match(struct xfrm_policy *policy, - struct xfrm_policy *pol) +static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark, + struct xfrm_policy *pol) { - if (policy->mark.v == pol->mark.v && - policy->priority == pol->priority) - return true; - - return false; + return mark->v == pol->mark.v && mark->m == pol->mark.m; } static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed) @@ -1503,7 +1499,7 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain, if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && - xfrm_policy_mark_match(policy, pol) && + xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { delpol = pol; @@ -1538,7 +1534,7 @@ static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain, if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && - xfrm_policy_mark_match(policy, pol) && + xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) @@ -1610,9 +1606,8 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) EXPORT_SYMBOL(xfrm_policy_insert); static struct xfrm_policy * -__xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, - u8 type, int dir, - struct xfrm_selector *sel, +__xfrm_policy_bysel_ctx(struct hlist_head *chain, const struct xfrm_mark *mark, + u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx) { struct xfrm_policy *pol; @@ -1623,7 +1618,7 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && pol->if_id == if_id && - (mark & pol->mark.m) == pol->mark.v && + xfrm_policy_mark_match(mark, pol) && !selector_cmp(sel, &pol->selector) && xfrm_sec_ctx_match(ctx, pol->security)) return pol; @@ -1632,11 +1627,10 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, return NULL; } -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, - u8 type, int dir, - struct xfrm_selector *sel, - struct xfrm_sec_ctx *ctx, int delete, - int *err) +struct xfrm_policy * +xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, struct xfrm_selector *sel, + struct xfrm_sec_ctx *ctx, int delete, int *err) { struct xfrm_pol_inexact_bin *bin = NULL; struct xfrm_policy *pol, *ret = NULL; @@ -1703,9 +1697,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, - u8 type, int dir, u32 id, int delete, - int *err) +struct xfrm_policy * +xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, u32 id, int delete, int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; @@ -1720,8 +1714,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, ret = NULL; hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && - pol->if_id == if_id && - (mark & pol->mark.m) == pol->mark.v) { + pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete( @@ -4156,7 +4149,7 @@ void __init xfrm_init(void) seqcount_init(&xfrm_policy_hash_generation); xfrm_input_init(); -#ifdef CONFIG_INET_ESPINTCP +#ifdef CONFIG_XFRM_ESPINTCP espintcp_init(); #endif diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index e6cfaa680ef3..fbb7d9d06478 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1863,7 +1863,6 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct km_event c; int delete; struct xfrm_mark m; - u32 mark = xfrm_mark_get(attrs, &m); u32 if_id = 0; p = nlmsg_data(nlh); @@ -1880,8 +1879,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + xfrm_mark_get(attrs, &m); + if (p->index) - xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, delete, &err); + xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, + p->index, delete, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -1898,8 +1900,8 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel, - ctx, delete, &err); + xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, + &p->sel, ctx, delete, &err); security_xfrm_policy_free(ctx); } if (xp == NULL) @@ -2166,7 +2168,6 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, u8 type = XFRM_POLICY_TYPE_MAIN; int err = -ENOENT; struct xfrm_mark m; - u32 mark = xfrm_mark_get(attrs, &m); u32 if_id = 0; err = copy_from_user_policy_type(&type, attrs); @@ -2180,8 +2181,11 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + xfrm_mark_get(attrs, &m); + if (p->index) - xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, 0, &err); + xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, p->index, + 0, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -2198,7 +2202,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, + xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, &p->sel, ctx, 0, &err); security_xfrm_policy_free(ctx); } diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c index f7ee8fa377ad..6ccecbd39476 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c @@ -5,10 +5,60 @@ #include "test_btf_map_in_map.skel.h" +static int duration; + +static __u32 bpf_map_id(struct bpf_map *map) +{ + struct bpf_map_info info; + __u32 info_len = sizeof(info); + int err; + + memset(&info, 0, info_len); + err = bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, &info_len); + if (err) + return 0; + return info.id; +} + +/* + * Trigger synchronize_rcu() in kernel. + * + * ARRAY_OF_MAPS/HASH_OF_MAPS lookup/update operations trigger synchronize_rcu() + * if looking up an existing non-NULL element or updating the map with a valid + * inner map FD. Use this fact to trigger synchronize_rcu(): create map-in-map, + * create a trivial ARRAY map, update map-in-map with ARRAY inner map. Then + * cleanup. At the end, at least one synchronize_rcu() would be called. + */ +static int kern_sync_rcu(void) +{ + int inner_map_fd, outer_map_fd, err, zero = 0; + + inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0); + if (CHECK(inner_map_fd < 0, "inner_map_create", "failed %d\n", -errno)) + return -1; + + outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL, + sizeof(int), inner_map_fd, 1, 0); + if (CHECK(outer_map_fd < 0, "outer_map_create", "failed %d\n", -errno)) { + close(inner_map_fd); + return -1; + } + + err = bpf_map_update_elem(outer_map_fd, &zero, &inner_map_fd, 0); + if (err) + err = -errno; + CHECK(err, "outer_map_update", "failed %d\n", err); + close(inner_map_fd); + close(outer_map_fd); + return err; +} + void test_btf_map_in_map(void) { - int duration = 0, err, key = 0, val; - struct test_btf_map_in_map* skel; + int err, key = 0, val, i; + struct test_btf_map_in_map *skel; + int outer_arr_fd, outer_hash_fd; + int fd, map1_fd, map2_fd, map1_id, map2_id; skel = test_btf_map_in_map__open_and_load(); if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n")) @@ -18,32 +68,78 @@ void test_btf_map_in_map(void) if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) goto cleanup; + map1_fd = bpf_map__fd(skel->maps.inner_map1); + map2_fd = bpf_map__fd(skel->maps.inner_map2); + outer_arr_fd = bpf_map__fd(skel->maps.outer_arr); + outer_hash_fd = bpf_map__fd(skel->maps.outer_hash); + /* inner1 = input, inner2 = input + 1 */ - val = bpf_map__fd(skel->maps.inner_map1); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); - val = bpf_map__fd(skel->maps.inner_map2); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + map1_fd = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(outer_arr_fd, &key, &map1_fd, 0); + map2_fd = bpf_map__fd(skel->maps.inner_map2); + bpf_map_update_elem(outer_hash_fd, &key, &map2_fd, 0); skel->bss->input = 1; usleep(1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + bpf_map_lookup_elem(map1_fd, &key, &val); CHECK(val != 1, "inner1", "got %d != exp %d\n", val, 1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + bpf_map_lookup_elem(map2_fd, &key, &val); CHECK(val != 2, "inner2", "got %d != exp %d\n", val, 2); /* inner1 = input + 1, inner2 = input */ - val = bpf_map__fd(skel->maps.inner_map2); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); - val = bpf_map__fd(skel->maps.inner_map1); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + bpf_map_update_elem(outer_arr_fd, &key, &map2_fd, 0); + bpf_map_update_elem(outer_hash_fd, &key, &map1_fd, 0); skel->bss->input = 3; usleep(1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + bpf_map_lookup_elem(map1_fd, &key, &val); CHECK(val != 4, "inner1", "got %d != exp %d\n", val, 4); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + bpf_map_lookup_elem(map2_fd, &key, &val); CHECK(val != 3, "inner2", "got %d != exp %d\n", val, 3); + for (i = 0; i < 5; i++) { + val = i % 2 ? map1_fd : map2_fd; + err = bpf_map_update_elem(outer_hash_fd, &key, &val, 0); + if (CHECK_FAIL(err)) { + printf("failed to update hash_of_maps on iter #%d\n", i); + goto cleanup; + } + err = bpf_map_update_elem(outer_arr_fd, &key, &val, 0); + if (CHECK_FAIL(err)) { + printf("failed to update hash_of_maps on iter #%d\n", i); + goto cleanup; + } + } + + map1_id = bpf_map_id(skel->maps.inner_map1); + map2_id = bpf_map_id(skel->maps.inner_map2); + CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n"); + CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n"); + + test_btf_map_in_map__destroy(skel); + skel = NULL; + + /* we need to either wait for or force synchronize_rcu(), before + * checking for "still exists" condition, otherwise map could still be + * resolvable by ID, causing false positives. + * + * Older kernels (5.8 and earlier) freed map only after two + * synchronize_rcu()s, so trigger two, to be entirely sure. + */ + CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); + CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); + + fd = bpf_map_get_fd_by_id(map1_id); + if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) { + close(fd); + goto cleanup; + } + fd = bpf_map_get_fd_by_id(map2_id); + if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) { + close(fd); + goto cleanup; + } + cleanup: test_btf_map_in_map__destroy(skel); } diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 8294ae3ffb3c..43c9cda199b8 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -318,6 +318,9 @@ class DebugfsDir: continue if os.path.isfile(p): + # We need to init trap_flow_action_cookie before read it + if f == "trap_flow_action_cookie": + cmd('echo deadbeef > %s/%s' % (path, f)) _, out = cmd('cat %s/%s' % (path, f)) dfs[f] = out.strip() elif os.path.isdir(p): diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c index 99f8f582c02b..c5e805980409 100644 --- a/tools/testing/selftests/bpf/verifier/event_output.c +++ b/tools/testing/selftests/bpf/verifier/event_output.c @@ -112,6 +112,7 @@ "perfevent for cgroup sockopt", .insns = { __PERF_EVENT_INSNS__ }, .prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .fixup_map_event_output = { 4 }, .result = ACCEPT, .retval = 1, diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index eb8e2a23bbb4..43a948feed26 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -252,8 +252,6 @@ check_highest_speed_is_chosen() fi local -a speeds_arr=($(common_speeds_get $h1 $h2 0 1)) - # Remove the first speed, h1 does not advertise this speed. - unset speeds_arr[0] max_speed=${speeds_arr[0]} for current in ${speeds_arr[@]}; do diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 8c8c7d79c38d..2c522f7a0aec 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -350,7 +350,8 @@ static int test_datapath(uint16_t typeflags, int port_off, int fds[2], fds_udp[2][2], ret; fprintf(stderr, "\ntest: datapath 0x%hx ports %hu,%hu\n", - typeflags, PORT_BASE, PORT_BASE + port_off); + typeflags, (uint16_t)PORT_BASE, + (uint16_t)(PORT_BASE + port_off)); fds[0] = sock_fanout_open(typeflags, 0); fds[1] = sock_fanout_open(typeflags, 0); diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c index 422e7761254d..bcb79ba1f214 100644 --- a/tools/testing/selftests/net/rxtimestamp.c +++ b/tools/testing/selftests/net/rxtimestamp.c @@ -329,8 +329,7 @@ int main(int argc, char **argv) bool all_tests = true; int arg_index = 0; int failures = 0; - int s, t; - char opt; + int s, t, opt; while ((opt = getopt_long(argc, argv, "", long_options, &arg_index)) != -1) { diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index ceaad78e9667..3155fbbf644b 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -121,7 +121,7 @@ static bool do_recv_one(int fdr, struct timed_send *ts) if (rbuf[0] != ts->data) error(1, 0, "payload mismatch. expected %c", ts->data); - if (labs(tstop - texpect) > cfg_variance_us) + if (llabs(tstop - texpect) > cfg_variance_us) error(1, 0, "exceeds variance (%d us)", cfg_variance_us); return false; diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 4555f88252ba..a61b7b3da549 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -344,7 +344,7 @@ int main(int argc, char *argv[]) { struct sockaddr_storage listenaddr, addr; unsigned int max_pacing_rate = 0; - size_t total = 0; + uint64_t total = 0; char *host = NULL; int fd, c, on = 1; char *buffer; @@ -473,12 +473,12 @@ int main(int argc, char *argv[]) zflg = 0; } while (total < FILE_SZ) { - ssize_t wr = FILE_SZ - total; + int64_t wr = FILE_SZ - total; if (wr > chunk_size) wr = chunk_size; /* Note : we just want to fill the pipe with 0 bytes */ - wr = send(fd, buffer, wr, zflg ? MSG_ZEROCOPY : 0); + wr = send(fd, buffer, (size_t)wr, zflg ? MSG_ZEROCOPY : 0); if (wr <= 0) break; total += wr; |