diff options
43 files changed, 521 insertions, 252 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index ea8194ac8970..83fd8480d0d6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9266,7 +9266,6 @@ M: Ido Schimmel <idosch@nvidia.com> L: bridge@lists.linux.dev L: netdev@vger.kernel.org S: Maintained -W: http://www.linuxfoundation.org/en/Net:Bridge F: include/linux/if_bridge.h F: include/uapi/linux/if_bridge.h F: include/linux/netfilter_bridge/ diff --git a/drivers/net/dsa/hirschmann/hellcreek_ptp.c b/drivers/net/dsa/hirschmann/hellcreek_ptp.c index bfe21f9f7dcd..cb23bea9c21b 100644 --- a/drivers/net/dsa/hirschmann/hellcreek_ptp.c +++ b/drivers/net/dsa/hirschmann/hellcreek_ptp.c @@ -376,8 +376,18 @@ static int hellcreek_led_setup(struct hellcreek *hellcreek) hellcreek_set_brightness(hellcreek, STATUS_OUT_IS_GM, 1); /* Register both leds */ - led_classdev_register(hellcreek->dev, &hellcreek->led_sync_good); - led_classdev_register(hellcreek->dev, &hellcreek->led_is_gm); + ret = led_classdev_register(hellcreek->dev, &hellcreek->led_sync_good); + if (ret) { + dev_err(hellcreek->dev, "Failed to register sync_good LED\n"); + goto out; + } + + ret = led_classdev_register(hellcreek->dev, &hellcreek->led_is_gm); + if (ret) { + dev_err(hellcreek->dev, "Failed to register is_gm LED\n"); + led_classdev_unregister(&hellcreek->led_sync_good); + goto out; + } ret = 0; diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c index b1ae3b9de3d1..5a1496fff445 100644 --- a/drivers/net/dsa/microchip/lan937x_main.c +++ b/drivers/net/dsa/microchip/lan937x_main.c @@ -540,6 +540,7 @@ static void lan937x_set_tune_adj(struct ksz_device *dev, int port, ksz_pread16(dev, port, reg, &data16); /* Update tune Adjust */ + data16 &= ~PORT_TUNE_ADJ; data16 |= FIELD_PREP(PORT_TUNE_ADJ, val); ksz_pwrite16(dev, port, reg, data16); diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 691361b25407..c0e17035db18 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -282,7 +282,7 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth, if (!airoha_is_valid_gdm_port(eth, port)) return -EINVAL; - if (dsa_port >= 0) + if (dsa_port >= 0 || eth->ports[1]) pse_port = port->id == 4 ? FE_PSE_PORT_GDM4 : port->id; else diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index cb004fd16252..5bb31c8fab39 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1296,7 +1296,8 @@ static void be_xmit_flush(struct be_adapter *adapter, struct be_tx_obj *txo) (adapter->bmc_filt_mask & BMC_FILT_MULTICAST) static bool be_send_pkt_to_bmc(struct be_adapter *adapter, - struct sk_buff **skb) + struct sk_buff **skb, + struct be_wrb_params *wrb_params) { struct ethhdr *eh = (struct ethhdr *)(*skb)->data; bool os2bmc = false; @@ -1360,7 +1361,7 @@ done: * to BMC, asic expects the vlan to be inline in the packet. */ if (os2bmc) - *skb = be_insert_vlan_in_pkt(adapter, *skb, NULL); + *skb = be_insert_vlan_in_pkt(adapter, *skb, wrb_params); return os2bmc; } @@ -1387,7 +1388,7 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev) /* if os2bmc is enabled and if the pkt is destined to bmc, * enqueue the pkt a 2nd time with mgmt bit set. */ - if (be_send_pkt_to_bmc(adapter, &skb)) { + if (be_send_pkt_to_bmc(adapter, &skb, &wrb_params)) { BE_WRB_F_SET(wrb_params.features, OS2BMC, 1); wrb_cnt = be_xmit_enqueue(adapter, txo, skb, &wrb_params); if (unlikely(!wrb_cnt)) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index fb0f6365a6d6..8ec0f7d0fceb 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -3246,7 +3246,7 @@ void ice_ptp_init(struct ice_pf *pf) err = ice_ptp_init_port(pf, &ptp->port); if (err) - goto err_exit; + goto err_clean_pf; /* Start the PHY timestamping block */ ice_ptp_reset_phy_timestamping(pf); @@ -3263,13 +3263,19 @@ void ice_ptp_init(struct ice_pf *pf) dev_info(ice_pf_to_dev(pf), "PTP init successful\n"); return; +err_clean_pf: + mutex_destroy(&ptp->port.ps_lock); + ice_ptp_cleanup_pf(pf); err_exit: /* If we registered a PTP clock, release it */ if (pf->ptp.clock) { ptp_clock_unregister(ptp->clock); pf->ptp.clock = NULL; } - ptp->state = ICE_PTP_ERROR; + /* Keep ICE_PTP_UNINIT state to avoid ambiguity at driver unload + * and to avoid duplicated resources release. + */ + ptp->state = ICE_PTP_UNINIT; dev_err(ice_pf_to_dev(pf), "PTP failed %d\n", err); } @@ -3282,9 +3288,19 @@ err_exit: */ void ice_ptp_release(struct ice_pf *pf) { - if (pf->ptp.state != ICE_PTP_READY) + if (pf->ptp.state == ICE_PTP_UNINIT) return; + if (pf->ptp.state != ICE_PTP_READY) { + mutex_destroy(&pf->ptp.port.ps_lock); + ice_ptp_cleanup_pf(pf); + if (pf->ptp.clock) { + ptp_clock_unregister(pf->ptp.clock); + pf->ptp.clock = NULL; + } + return; + } + pf->ptp.state = ICE_PTP_UNINIT; /* Disable timestamping for both Tx and Rx */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c index 8c46481d2e1f..8cf4ff697572 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_main.c +++ b/drivers/net/ethernet/intel/idpf/idpf_main.c @@ -63,6 +63,8 @@ destroy_wqs: destroy_workqueue(adapter->vc_event_wq); for (i = 0; i < adapter->max_vports; i++) { + if (!adapter->vport_config[i]) + continue; kfree(adapter->vport_config[i]->user_config.q_coalesce); kfree(adapter->vport_config[i]); adapter->vport_config[i] = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index e18a850c615c..aa3b5878e3da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -324,10 +324,8 @@ err_xa: free_irq(irq->map.virq, &irq->nh); err_req_irq: #ifdef CONFIG_RFS_ACCEL - if (i && rmap && *rmap) { - free_irq_cpu_rmap(*rmap); - *rmap = NULL; - } + if (i && rmap && *rmap) + irq_cpu_rmap_remove(*rmap, irq->map.virq); err_irq_rmap: #endif if (i && pci_msix_can_alloc_dyn(dev->pdev)) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c b/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c index b032d5a4b3b8..10f5bc4892fc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c @@ -601,6 +601,8 @@ int mlxsw_linecard_devlink_info_get(struct mlxsw_linecard *linecard, err = devlink_info_version_fixed_put(req, DEVLINK_INFO_VERSION_GENERIC_FW_PSID, info->psid); + if (err) + goto unlock; sprintf(buf, "%u.%u.%u", info->fw_major, info->fw_minor, info->fw_sub_minor); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 6a4a81c63451..353fd9ca89a6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -830,8 +830,10 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp, return -EINVAL; rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie); - if (!rule) - return -EINVAL; + if (!rule) { + err = -EINVAL; + goto err_rule_get_stats; + } err = mlxsw_sp_acl_rule_get_stats(mlxsw_sp, rule, &packets, &bytes, &drops, &lastuse, &used_hw_stats); diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 847fa62c80df..e338bfc8b7b2 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -4,6 +4,7 @@ * Copyright (c) 2019-2020 Marvell International Ltd. */ +#include <linux/array_size.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> @@ -960,7 +961,7 @@ static inline void qede_tpa_cont(struct qede_dev *edev, { int i; - for (i = 0; cqe->len_list[i]; i++) + for (i = 0; cqe->len_list[i] && i < ARRAY_SIZE(cqe->len_list); i++) qede_fill_frag_skb(edev, rxq, cqe->tpa_agg_index, le16_to_cpu(cqe->len_list[i])); @@ -985,7 +986,7 @@ static int qede_tpa_end(struct qede_dev *edev, dma_unmap_page(rxq->dev, tpa_info->buffer.mapping, PAGE_SIZE, rxq->data_direction); - for (i = 0; cqe->len_list[i]; i++) + for (i = 0; cqe->len_list[i] && i < ARRAY_SIZE(cqe->len_list); i++) qede_fill_frag_skb(edev, rxq, cqe->tpa_agg_index, le16_to_cpu(cqe->len_list[i])); if (unlikely(i > 1)) diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c index 5ee8e8980393..591866fc9055 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c @@ -260,6 +260,7 @@ void gelic_card_down(struct gelic_card *card) if (atomic_dec_if_positive(&card->users) == 0) { pr_debug("%s: real do\n", __func__); napi_disable(&card->napi); + timer_delete_sync(&card->rx_oom_timer); /* * Disable irq. Wireless interrupts will * be disabled later if any @@ -970,7 +971,8 @@ static void gelic_net_pass_skb_up(struct gelic_descr *descr, * gelic_card_decode_one_descr - processes an rx descriptor * @card: card structure * - * returns 1 if a packet has been sent to the stack, otherwise 0 + * returns 1 if a packet has been sent to the stack, -ENOMEM on skb alloc + * failure, otherwise 0 * * processes an rx descriptor by iommu-unmapping the data buffer and passing * the packet up to the stack @@ -981,16 +983,18 @@ static int gelic_card_decode_one_descr(struct gelic_card *card) struct gelic_descr_chain *chain = &card->rx_chain; struct gelic_descr *descr = chain->head; struct net_device *netdev = NULL; - int dmac_chain_ended; + int dmac_chain_ended = 0; + int prepare_rx_ret; status = gelic_descr_get_status(descr); if (status == GELIC_DESCR_DMA_CARDOWNED) return 0; - if (status == GELIC_DESCR_DMA_NOT_IN_USE) { + if (status == GELIC_DESCR_DMA_NOT_IN_USE || !descr->skb) { dev_dbg(ctodev(card), "dormant descr? %p\n", descr); - return 0; + dmac_chain_ended = 1; + goto refill; } /* netdevice select */ @@ -1048,9 +1052,10 @@ static int gelic_card_decode_one_descr(struct gelic_card *card) refill: /* is the current descriptor terminated with next_descr == NULL? */ - dmac_chain_ended = - be32_to_cpu(descr->hw_regs.dmac_cmd_status) & - GELIC_DESCR_RX_DMA_CHAIN_END; + if (!dmac_chain_ended) + dmac_chain_ended = + be32_to_cpu(descr->hw_regs.dmac_cmd_status) & + GELIC_DESCR_RX_DMA_CHAIN_END; /* * So that always DMAC can see the end * of the descriptor chain to avoid @@ -1062,10 +1067,11 @@ refill: gelic_descr_set_status(descr, GELIC_DESCR_DMA_NOT_IN_USE); /* - * this call can fail, but for now, just leave this - * descriptor without skb + * this call can fail, propagate the error */ - gelic_descr_prepare_rx(card, descr); + prepare_rx_ret = gelic_descr_prepare_rx(card, descr); + if (prepare_rx_ret) + return prepare_rx_ret; chain->tail = descr; chain->head = descr->next; @@ -1087,6 +1093,13 @@ refill: return 1; } +static void gelic_rx_oom_timer(struct timer_list *t) +{ + struct gelic_card *card = timer_container_of(card, t, rx_oom_timer); + + napi_schedule(&card->napi); +} + /** * gelic_net_poll - NAPI poll function called by the stack to return packets * @napi: napi structure @@ -1099,14 +1112,22 @@ static int gelic_net_poll(struct napi_struct *napi, int budget) { struct gelic_card *card = container_of(napi, struct gelic_card, napi); int packets_done = 0; + int work_result = 0; while (packets_done < budget) { - if (!gelic_card_decode_one_descr(card)) + work_result = gelic_card_decode_one_descr(card); + if (work_result != 1) break; packets_done++; } + if (work_result == -ENOMEM) { + napi_complete_done(napi, packets_done); + mod_timer(&card->rx_oom_timer, jiffies + 1); + return packets_done; + } + if (packets_done < budget) { napi_complete_done(napi, packets_done); gelic_card_rx_irq_on(card); @@ -1576,6 +1597,8 @@ static struct gelic_card *gelic_alloc_card_net(struct net_device **netdev) mutex_init(&card->updown_lock); atomic_set(&card->users, 0); + timer_setup(&card->rx_oom_timer, gelic_rx_oom_timer, 0); + return card; } diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.h b/drivers/net/ethernet/toshiba/ps3_gelic_net.h index f7d7931e51b7..c10f1984a5a1 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.h +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.h @@ -268,6 +268,7 @@ struct gelic_vlan_id { struct gelic_card { struct napi_struct napi; struct net_device *netdev[GELIC_PORT_MAX]; + struct timer_list rx_oom_timer; /* * hypervisor requires irq_status should be * 8 bytes aligned, but u64 member is diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 9d7799ea1c17..918244308215 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -637,6 +637,9 @@ static int phylink_validate(struct phylink *pl, unsigned long *supported, static void phylink_fill_fixedlink_supported(unsigned long *supported) { + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, supported); linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, supported); linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, supported); linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, supported); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index a3046142cb8e..35dd89aff4a9 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -392,14 +392,12 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) } /* Restore Eth hdr pulled by dev_forward_skb/eth_type_trans */ __skb_push(skb, ETH_HLEN); - /* Depend on prior success packets started NAPI consumer via - * __veth_xdp_flush(). Cancel TXQ stop if consumer stopped, - * paired with empty check in veth_poll(). - */ netif_tx_stop_queue(txq); - smp_mb__after_atomic(); - if (unlikely(__ptr_ring_empty(&rq->xdp_ring))) - netif_tx_wake_queue(txq); + /* Makes sure NAPI peer consumer runs. Consumer is responsible + * for starting txq again, until then ndo_start_xmit (this + * function) will not be invoked by the netstack again. + */ + __veth_xdp_flush(rq); break; case NET_RX_DROP: /* same as NET_XMIT_DROP */ drop: @@ -900,17 +898,9 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { - struct veth_priv *priv = netdev_priv(rq->dev); - int queue_idx = rq->xdp_rxq.queue_index; - struct netdev_queue *peer_txq; - struct net_device *peer_dev; int i, done = 0, n_xdpf = 0; void *xdpf[VETH_XDP_BATCH]; - /* NAPI functions as RCU section */ - peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held()); - peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL; - for (i = 0; i < budget; i++) { void *ptr = __ptr_ring_consume(&rq->xdp_ring); @@ -959,9 +949,6 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget, rq->stats.vs.xdp_packets += done; u64_stats_update_end(&rq->stats.syncp); - if (peer_txq && unlikely(netif_tx_queue_stopped(peer_txq))) - netif_tx_wake_queue(peer_txq); - return done; } @@ -969,12 +956,20 @@ static int veth_poll(struct napi_struct *napi, int budget) { struct veth_rq *rq = container_of(napi, struct veth_rq, xdp_napi); + struct veth_priv *priv = netdev_priv(rq->dev); + int queue_idx = rq->xdp_rxq.queue_index; + struct netdev_queue *peer_txq; struct veth_stats stats = {}; + struct net_device *peer_dev; struct veth_xdp_tx_bq bq; int done; bq.count = 0; + /* NAPI functions as RCU section */ + peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held()); + peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL; + xdp_set_return_frame_no_direct(); done = veth_xdp_rcv(rq, budget, &bq, &stats); @@ -996,6 +991,13 @@ static int veth_poll(struct napi_struct *napi, int budget) veth_xdp_flush(rq, &bq); xdp_clear_return_frame_no_direct(); + /* Release backpressure per NAPI poll */ + smp_rmb(); /* Paired with netif_tx_stop_queue set_bit */ + if (peer_txq && netif_tx_queue_stopped(peer_txq)) { + txq_trans_cond_update(peer_txq); + netif_tx_wake_queue(peer_txq); + } + return done; } diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c index ab904a7def1b..080c4f8a655a 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.c +++ b/drivers/net/wireless/realtek/rtw89/fw.c @@ -7694,6 +7694,13 @@ int rtw89_hw_scan_add_chan_list_ax(struct rtw89_dev *rtwdev, INIT_LIST_HEAD(&list); list_for_each_entry_safe(ch_info, tmp, &scan_info->chan_list, list) { + /* The operating channel (tx_null == true) should + * not be last in the list, to avoid breaking + * RTL8851BU and RTL8832BU. + */ + if (list_len + 1 == RTW89_SCAN_LIST_LIMIT_AX && ch_info->tx_null) + break; + list_move_tail(&ch_info->list, &list); list_len++; diff --git a/drivers/s390/net/ctcm_mpc.c b/drivers/s390/net/ctcm_mpc.c index 0aeafa772fb1..407b7c516658 100644 --- a/drivers/s390/net/ctcm_mpc.c +++ b/drivers/s390/net/ctcm_mpc.c @@ -701,7 +701,6 @@ static void mpc_rcvd_sweep_req(struct mpcg_info *mpcginfo) grp->sweep_req_pend_num--; ctcmpc_send_sweep_resp(ch); - kfree(mpcginfo); return; } diff --git a/include/net/xfrm.h b/include/net/xfrm.h index f3014e4f54fc..0a14daaa5dd4 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -536,7 +536,8 @@ static inline int xfrm_af2proto(unsigned int family) static inline const struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto) { - if ((ipproto == IPPROTO_IPIP && x->props.family == AF_INET) || + if ((x->sel.family != AF_UNSPEC) || + (ipproto == IPPROTO_IPIP && x->props.family == AF_INET) || (ipproto == IPPROTO_IPV6 && x->props.family == AF_INET6)) return &x->inner_mode; else diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index ad54b12d4b4c..8bb71a10dba0 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -443,6 +443,9 @@ static int generic_hwtstamp_ioctl_lower(struct net_device *dev, int cmd, struct ifreq ifrr; int err; + if (!kernel_cfg->ifr) + return -EINVAL; + strscpy_pad(ifrr.ifr_name, dev->name, IFNAMSIZ); ifrr.ifr_ifru = kernel_cfg->ifr->ifr_ifru; diff --git a/net/devlink/rate.c b/net/devlink/rate.c index 264fb82cba19..d157a8419bca 100644 --- a/net/devlink/rate.c +++ b/net/devlink/rate.c @@ -828,13 +828,15 @@ void devl_rate_nodes_destroy(struct devlink *devlink) if (!devlink_rate->parent) continue; - refcount_dec(&devlink_rate->parent->refcnt); if (devlink_rate_is_leaf(devlink_rate)) ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv, NULL, NULL); else if (devlink_rate_is_node(devlink_rate)) ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv, NULL, NULL); + + refcount_dec(&devlink_rate->parent->refcnt); + devlink_rate->parent = NULL; } list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) { if (devlink_rate_is_node(devlink_rate)) { diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index e0d94270da28..05828d4cb6cd 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -122,8 +122,10 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - __be16 type = x->inner_mode.family == AF_INET6 ? htons(ETH_P_IPV6) - : htons(ETH_P_IP); + const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, + XFRM_MODE_SKB_CB(skb)->protocol); + __be16 type = inner_mode->family == AF_INET6 ? htons(ETH_P_IPV6) + : htons(ETH_P_IP); return skb_eth_gso_segment(skb, features, type); } diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 7b41fb4f00b5..22410243ebe8 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -158,8 +158,10 @@ static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - __be16 type = x->inner_mode.family == AF_INET ? htons(ETH_P_IP) - : htons(ETH_P_IPV6); + const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, + XFRM_MODE_SKB_CB(skb)->protocol); + __be16 type = inner_mode->family == AF_INET ? htons(ETH_P_IP) + : htons(ETH_P_IPV6); return skb_eth_gso_segment(skb, features, type); } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 369a2f2e459c..0710281dd95a 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1246,9 +1246,9 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns else l2tp_build_l2tpv3_header(session, __skb_push(skb, session->hdr_len)); - /* Reset skb netfilter state */ - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); + /* Reset control buffer */ + memset(skb->cb, 0, sizeof(skb->cb)); + nf_reset_ct(skb); /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 1103b3341a70..f24ae7d40e88 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -838,8 +838,11 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, opts->suboptions = 0; + /* Force later mptcp_write_options(), but do not use any actual + * option space. + */ if (unlikely(__mptcp_check_fallback(msk) && !mptcp_check_infinite_map(skb))) - return false; + return true; if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) { if (mptcp_established_options_fastclose(sk, &opt_size, remaining, opts) || @@ -1041,6 +1044,31 @@ static void __mptcp_snd_una_update(struct mptcp_sock *msk, u64 new_snd_una) WRITE_ONCE(msk->snd_una, new_snd_una); } +static void rwin_update(struct mptcp_sock *msk, struct sock *ssk, + struct sk_buff *skb) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct tcp_sock *tp = tcp_sk(ssk); + u64 mptcp_rcv_wnd; + + /* Avoid touching extra cachelines if TCP is going to accept this + * skb without filling the TCP-level window even with a possibly + * outdated mptcp-level rwin. + */ + if (!skb->len || skb->len < tcp_receive_window(tp)) + return; + + mptcp_rcv_wnd = atomic64_read(&msk->rcv_wnd_sent); + if (!after64(mptcp_rcv_wnd, subflow->rcv_wnd_sent)) + return; + + /* Some other subflow grew the mptcp-level rwin since rcv_wup, + * resync. + */ + tp->rcv_wnd += mptcp_rcv_wnd - subflow->rcv_wnd_sent; + subflow->rcv_wnd_sent = mptcp_rcv_wnd; +} + static void ack_update_msk(struct mptcp_sock *msk, struct sock *ssk, struct mptcp_options_received *mp_opt) @@ -1208,6 +1236,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) */ if (mp_opt.use_ack) ack_update_msk(msk, sk, &mp_opt); + rwin_update(msk, sk, skb); /* Zero-data-length packets are dropped by the caller and not * propagated to the MPTCP layer, so the skb extension does not @@ -1294,6 +1323,10 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) if (rcv_wnd_new != rcv_wnd_old) { raise_win: + /* The msk-level rcv wnd is after the tcp level one, + * sync the latter. + */ + rcv_wnd_new = rcv_wnd_old; win = rcv_wnd_old - ack_seq; tp->rcv_wnd = min_t(u64, win, U32_MAX); new_win = tp->rcv_wnd; @@ -1317,6 +1350,21 @@ raise_win: update_wspace: WRITE_ONCE(msk->old_wspace, tp->rcv_wnd); + subflow->rcv_wnd_sent = rcv_wnd_new; +} + +static void mptcp_track_rwin(struct tcp_sock *tp) +{ + const struct sock *ssk = (const struct sock *)tp; + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk; + + if (!ssk) + return; + + subflow = mptcp_subflow_ctx(ssk); + msk = mptcp_sk(subflow->conn); + WRITE_ONCE(msk->old_wspace, tp->rcv_wnd); } __sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) @@ -1611,6 +1659,10 @@ mp_rst: opts->reset_transient, opts->reset_reason); return; + } else if (unlikely(!opts->suboptions)) { + /* Fallback to TCP */ + mptcp_track_rwin(tp); + return; } if (OPTION_MPTCP_PRIO & opts->suboptions) { diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 2ff1b9499568..9604b91902b8 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -18,6 +18,7 @@ struct mptcp_pm_add_entry { u8 retrans_times; struct timer_list add_timer; struct mptcp_sock *sock; + struct rcu_head rcu; }; static DEFINE_SPINLOCK(mptcp_pm_list_lock); @@ -155,7 +156,7 @@ bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk, entry = mptcp_pm_del_add_timer(msk, addr, false); ret = entry; - kfree(entry); + kfree_rcu(entry, rcu); return ret; } @@ -345,22 +346,27 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, { struct mptcp_pm_add_entry *entry; struct sock *sk = (struct sock *)msk; - struct timer_list *add_timer = NULL; + bool stop_timer = false; + + rcu_read_lock(); spin_lock_bh(&msk->pm.lock); entry = mptcp_lookup_anno_list_by_saddr(msk, addr); if (entry && (!check_id || entry->addr.id == addr->id)) { entry->retrans_times = ADD_ADDR_RETRANS_MAX; - add_timer = &entry->add_timer; + stop_timer = true; } if (!check_id && entry) list_del(&entry->list); spin_unlock_bh(&msk->pm.lock); - /* no lock, because sk_stop_timer_sync() is calling timer_delete_sync() */ - if (add_timer) - sk_stop_timer_sync(sk, add_timer); + /* Note: entry might have been removed by another thread. + * We hold rcu_read_lock() to ensure it is not freed under us. + */ + if (stop_timer) + sk_stop_timer_sync(sk, &entry->add_timer); + rcu_read_unlock(); return entry; } @@ -415,7 +421,7 @@ static void mptcp_pm_free_anno_list(struct mptcp_sock *msk) list_for_each_entry_safe(entry, tmp, &free_list, list) { sk_stop_timer_sync(sk, &entry->add_timer); - kfree(entry); + kfree_rcu(entry, rcu); } } diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index 2ae95476dba3..0a50fd5edc06 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -672,7 +672,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) void mptcp_pm_nl_rm_addr(struct mptcp_sock *msk, u8 rm_id) { - if (rm_id && WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { + if (rm_id && !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { u8 limit_add_addr_accepted = mptcp_pm_get_limit_add_addr_accepted(msk); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 90b4aeca2596..33b5dce431c2 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -78,6 +78,13 @@ bool __mptcp_try_fallback(struct mptcp_sock *msk, int fb_mib) if (__mptcp_check_fallback(msk)) return true; + /* The caller possibly is not holding the msk socket lock, but + * in the fallback case only the current subflow is touching + * the OoO queue. + */ + if (!RB_EMPTY_ROOT(&msk->out_of_order_queue)) + return false; + spin_lock_bh(&msk->fallback_lock); if (!msk->allow_infinite_fallback) { spin_unlock_bh(&msk->fallback_lock); @@ -937,14 +944,19 @@ static void mptcp_reset_rtx_timer(struct sock *sk) bool mptcp_schedule_work(struct sock *sk) { - if (inet_sk_state_load(sk) != TCP_CLOSE && - schedule_work(&mptcp_sk(sk)->work)) { - /* each subflow already holds a reference to the sk, and the - * workqueue is invoked by a subflow, so sk can't go away here. - */ - sock_hold(sk); + if (inet_sk_state_load(sk) == TCP_CLOSE) + return false; + + /* Get a reference on this socket, mptcp_worker() will release it. + * As mptcp_worker() might complete before us, we can not avoid + * a sock_hold()/sock_put() if schedule_work() returns false. + */ + sock_hold(sk); + + if (schedule_work(&mptcp_sk(sk)->work)) return true; - } + + sock_put(sk); return false; } @@ -2399,7 +2411,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) /* flags for __mptcp_close_ssk() */ #define MPTCP_CF_PUSH BIT(1) -#define MPTCP_CF_FASTCLOSE BIT(2) /* be sure to send a reset only if the caller asked for it, also * clean completely the subflow status when the subflow reaches @@ -2410,7 +2421,7 @@ static void __mptcp_subflow_disconnect(struct sock *ssk, unsigned int flags) { if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || - (flags & MPTCP_CF_FASTCLOSE)) { + subflow->send_fastclose) { /* The MPTCP code never wait on the subflow sockets, TCP-level * disconnect should never fail */ @@ -2457,14 +2468,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); - if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { - /* be sure to force the tcp_close path - * to generate the egress reset - */ - ssk->sk_lingertime = 0; - sock_set_flag(ssk, SOCK_LINGER); - subflow->send_fastclose = 1; - } + if (subflow->send_fastclose && ssk->sk_state != TCP_CLOSE) + tcp_set_state(ssk, TCP_CLOSE); need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { @@ -2560,7 +2565,8 @@ static void __mptcp_close_subflow(struct sock *sk) if (ssk_state != TCP_CLOSE && (ssk_state != TCP_CLOSE_WAIT || - inet_sk_state_load(sk) != TCP_ESTABLISHED)) + inet_sk_state_load(sk) != TCP_ESTABLISHED || + __mptcp_check_fallback(msk))) continue; /* 'subflow_data_ready' will re-sched once rx queue is empty */ @@ -2768,9 +2774,26 @@ static void mptcp_do_fastclose(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); mptcp_set_state(sk, TCP_CLOSE); - mptcp_for_each_subflow_safe(msk, subflow, tmp) - __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), - subflow, MPTCP_CF_FASTCLOSE); + + /* Explicitly send the fastclose reset as need */ + if (__mptcp_check_fallback(msk)) + return; + + mptcp_for_each_subflow_safe(msk, subflow, tmp) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + lock_sock(ssk); + + /* Some subflow socket states don't allow/need a reset.*/ + if ((1 << ssk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + goto unlock; + + subflow->send_fastclose = 1; + tcp_send_active_reset(ssk, ssk->sk_allocation, + SK_RST_REASON_TCP_ABORT_ON_CLOSE); +unlock: + release_sock(ssk); + } } static void mptcp_worker(struct work_struct *work) @@ -2797,7 +2820,11 @@ static void mptcp_worker(struct work_struct *work) __mptcp_close_subflow(sk); if (mptcp_close_tout_expired(sk)) { + struct mptcp_subflow_context *subflow, *tmp; + mptcp_do_fastclose(sk); + mptcp_for_each_subflow_safe(msk, subflow, tmp) + __mptcp_close_ssk(sk, subflow->tcp_sock, subflow, 0); mptcp_close_wake_up(sk); } @@ -3222,7 +3249,8 @@ static int mptcp_disconnect(struct sock *sk, int flags) /* msk->subflow is still intact, the following will not free the first * subflow */ - mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE); + mptcp_do_fastclose(sk); + mptcp_destroy_common(msk); /* The first subflow is already in TCP_CLOSE status, the following * can't overlap with a fallback anymore @@ -3401,7 +3429,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT; } -void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) +void mptcp_destroy_common(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow, *tmp; struct sock *sk = (struct sock *)msk; @@ -3410,7 +3438,7 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) /* join list will be eventually flushed (with rst) at sock lock release time */ mptcp_for_each_subflow_safe(msk, subflow, tmp) - __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, flags); + __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, 0); __skb_queue_purge(&sk->sk_receive_queue); skb_rbtree_purge(&msk->out_of_order_queue); @@ -3428,7 +3456,7 @@ static void mptcp_destroy(struct sock *sk) /* allow the following to close even the initial subflow */ msk->free_first = 1; - mptcp_destroy_common(msk, 0); + mptcp_destroy_common(msk); sk_sockets_allocated_dec(sk); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 379a88e14e8d..6ca97096607c 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -509,6 +509,7 @@ struct mptcp_subflow_context { u64 remote_key; u64 idsn; u64 map_seq; + u64 rcv_wnd_sent; u32 snd_isn; u32 token; u32 rel_write_seq; @@ -976,7 +977,7 @@ static inline void mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) local_bh_enable(); } -void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags); +void mptcp_destroy_common(struct mptcp_sock *msk); #define MPTCP_TOKEN_MAX_RETRIES 4 diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2832e0794197..792ca44a461d 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -572,69 +572,6 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } -static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key, - const struct nlattr *a) -{ - struct nshhdr *nh; - size_t length; - int err; - u8 flags; - u8 ttl; - int i; - - struct ovs_key_nsh key; - struct ovs_key_nsh mask; - - err = nsh_key_from_nlattr(a, &key, &mask); - if (err) - return err; - - /* Make sure the NSH base header is there */ - if (!pskb_may_pull(skb, skb_network_offset(skb) + NSH_BASE_HDR_LEN)) - return -ENOMEM; - - nh = nsh_hdr(skb); - length = nsh_hdr_len(nh); - - /* Make sure the whole NSH header is there */ - err = skb_ensure_writable(skb, skb_network_offset(skb) + - length); - if (unlikely(err)) - return err; - - nh = nsh_hdr(skb); - skb_postpull_rcsum(skb, nh, length); - flags = nsh_get_flags(nh); - flags = OVS_MASKED(flags, key.base.flags, mask.base.flags); - flow_key->nsh.base.flags = flags; - ttl = nsh_get_ttl(nh); - ttl = OVS_MASKED(ttl, key.base.ttl, mask.base.ttl); - flow_key->nsh.base.ttl = ttl; - nsh_set_flags_and_ttl(nh, flags, ttl); - nh->path_hdr = OVS_MASKED(nh->path_hdr, key.base.path_hdr, - mask.base.path_hdr); - flow_key->nsh.base.path_hdr = nh->path_hdr; - switch (nh->mdtype) { - case NSH_M_TYPE1: - for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) { - nh->md1.context[i] = - OVS_MASKED(nh->md1.context[i], key.context[i], - mask.context[i]); - } - memcpy(flow_key->nsh.context, nh->md1.context, - sizeof(nh->md1.context)); - break; - case NSH_M_TYPE2: - memset(flow_key->nsh.context, 0, - sizeof(flow_key->nsh.context)); - break; - default: - return -EINVAL; - } - skb_postpush_rcsum(skb, nh, length); - return 0; -} - /* Must follow skb_ensure_writable() since that can move the skb data. */ static void set_tp_port(struct sk_buff *skb, __be16 *port, __be16 new_port, __sum16 *check) @@ -1130,10 +1067,6 @@ static int execute_masked_set_action(struct sk_buff *skb, get_mask(a, struct ovs_key_ethernet *)); break; - case OVS_KEY_ATTR_NSH: - err = set_nsh(skb, flow_key, a); - break; - case OVS_KEY_ATTR_IPV4: err = set_ipv4(skb, flow_key, nla_data(a), get_mask(a, struct ovs_key_ipv4 *)); @@ -1170,6 +1103,7 @@ static int execute_masked_set_action(struct sk_buff *skb, case OVS_KEY_ATTR_CT_LABELS: case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4: case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6: + case OVS_KEY_ATTR_NSH: err = -EINVAL; break; } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index ad64bb9ab5e2..1cb4f97335d8 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1305,6 +1305,11 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, return 0; } +/* + * Constructs NSH header 'nh' from attributes of OVS_ACTION_ATTR_PUSH_NSH, + * where 'nh' points to a memory block of 'size' bytes. It's assumed that + * attributes were previously validated with validate_push_nsh(). + */ int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh, size_t size) { @@ -1314,8 +1319,6 @@ int nsh_hdr_from_nlattr(const struct nlattr *attr, u8 ttl = 0; int mdlen = 0; - /* validate_nsh has check this, so we needn't do duplicate check here - */ if (size < NSH_BASE_HDR_LEN) return -ENOBUFS; @@ -1359,46 +1362,6 @@ int nsh_hdr_from_nlattr(const struct nlattr *attr, return 0; } -int nsh_key_from_nlattr(const struct nlattr *attr, - struct ovs_key_nsh *nsh, struct ovs_key_nsh *nsh_mask) -{ - struct nlattr *a; - int rem; - - /* validate_nsh has check this, so we needn't do duplicate check here - */ - nla_for_each_nested(a, attr, rem) { - int type = nla_type(a); - - switch (type) { - case OVS_NSH_KEY_ATTR_BASE: { - const struct ovs_nsh_key_base *base = nla_data(a); - const struct ovs_nsh_key_base *base_mask = base + 1; - - nsh->base = *base; - nsh_mask->base = *base_mask; - break; - } - case OVS_NSH_KEY_ATTR_MD1: { - const struct ovs_nsh_key_md1 *md1 = nla_data(a); - const struct ovs_nsh_key_md1 *md1_mask = md1 + 1; - - memcpy(nsh->context, md1->context, sizeof(*md1)); - memcpy(nsh_mask->context, md1_mask->context, - sizeof(*md1_mask)); - break; - } - case OVS_NSH_KEY_ATTR_MD2: - /* Not supported yet */ - return -ENOTSUPP; - default: - return -EINVAL; - } - } - - return 0; -} - static int nsh_key_put_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool is_push_nsh, bool log) @@ -2839,17 +2802,13 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, return err; } -static bool validate_nsh(const struct nlattr *attr, bool is_mask, - bool is_push_nsh, bool log) +static bool validate_push_nsh(const struct nlattr *attr, bool log) { struct sw_flow_match match; struct sw_flow_key key; - int ret = 0; ovs_match_init(&match, &key, true, NULL); - ret = nsh_key_put_from_nlattr(attr, &match, is_mask, - is_push_nsh, log); - return !ret; + return !nsh_key_put_from_nlattr(attr, &match, false, true, log); } /* Return false if there are any non-masked bits set. @@ -2997,13 +2956,6 @@ static int validate_set(const struct nlattr *a, break; - case OVS_KEY_ATTR_NSH: - if (eth_type != htons(ETH_P_NSH)) - return -EINVAL; - if (!validate_nsh(nla_data(a), masked, false, log)) - return -EINVAL; - break; - default: return -EINVAL; } @@ -3437,7 +3389,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return -EINVAL; } mac_proto = MAC_PROTO_NONE; - if (!validate_nsh(nla_data(a), false, true, true)) + if (!validate_push_nsh(nla_data(a), log)) return -EINVAL; break; diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index fe7f77fc5f18..ff8cdecbe346 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -65,8 +65,6 @@ int ovs_nla_put_actions(const struct nlattr *attr, void ovs_nla_free_flow_actions(struct sw_flow_actions *); void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *); -int nsh_key_from_nlattr(const struct nlattr *attr, struct ovs_key_nsh *nsh, - struct ovs_key_nsh *nsh_mask); int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh, size_t size); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 768098dec231..833c3616d2a2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2954,6 +2954,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, u = unix_sk(sk); +redo: /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg */ @@ -2965,7 +2966,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, struct sk_buff *skb, *last; int chunk; -redo: unix_state_lock(sk); if (sock_flag(sk, SOCK_DEAD)) { err = -ECONNRESET; @@ -3015,7 +3015,6 @@ again: goto out; } - mutex_lock(&u->iolock); goto redo; unlock: unix_state_unlock(sk); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 76763247a377..a9ca9c3b87b3 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1661,18 +1661,40 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, timeout = schedule_timeout(timeout); lock_sock(sk); - if (signal_pending(current)) { - err = sock_intr_errno(timeout); - sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE; - sock->state = SS_UNCONNECTED; - vsock_transport_cancel_pkt(vsk); - vsock_remove_connected(vsk); - goto out_wait; - } else if ((sk->sk_state != TCP_ESTABLISHED) && (timeout == 0)) { - err = -ETIMEDOUT; + /* Connection established. Whatever happens to socket once we + * release it, that's not connect()'s concern. No need to go + * into signal and timeout handling. Call it a day. + * + * Note that allowing to "reset" an already established socket + * here is racy and insecure. + */ + if (sk->sk_state == TCP_ESTABLISHED) + break; + + /* If connection was _not_ established and a signal/timeout came + * to be, we want the socket's state reset. User space may want + * to retry. + * + * sk_state != TCP_ESTABLISHED implies that socket is not on + * vsock_connected_table. We keep the binding and the transport + * assigned. + */ + if (signal_pending(current) || timeout == 0) { + err = timeout == 0 ? -ETIMEDOUT : sock_intr_errno(timeout); + + /* Listener might have already responded with + * VIRTIO_VSOCK_OP_RESPONSE. Its handling expects our + * sk_state == TCP_SYN_SENT, which hereby we break. + * In such case VIRTIO_VSOCK_OP_RST will follow. + */ sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; + + /* Try to cancel VIRTIO_VSOCK_OP_REQUEST skb sent out by + * transport->connect(). + */ vsock_transport_cancel_pkt(vsk); + goto out_wait; } diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 44b9de6e4e77..52ae0e034d29 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -438,7 +438,7 @@ ok: check_tunnel_size = x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->props.mode == XFRM_MODE_TUNNEL; - switch (x->inner_mode.family) { + switch (skb_dst(skb)->ops->family) { case AF_INET: /* Check for IPv4 options */ if (ip_hdr(skb)->ihl != 5) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 9077730ff7d0..54222fcbd7fd 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -698,7 +698,7 @@ static void xfrm_get_inner_ipproto(struct sk_buff *skb, struct xfrm_state *x) return; if (x->outer_mode.encap == XFRM_MODE_TUNNEL) { - switch (x->outer_mode.family) { + switch (skb_dst(skb)->ops->family) { case AF_INET: xo->inner_ipproto = ip_hdr(skb)->protocol; break; @@ -772,8 +772,12 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) /* Exclusive direct xmit for tunnel mode, as * some filtering or matching rules may apply * in transport mode. + * Locally generated packets also require + * the normal XFRM path for L2 header setup, + * as the hardware needs the L2 header to match + * for encryption, so skip direct output as well. */ - if (x->props.mode == XFRM_MODE_TUNNEL) + if (x->props.mode == XFRM_MODE_TUNNEL && !skb->sk) return xfrm_dev_direct_output(sk, x, skb); return xfrm_output_resume(sk, skb, 0); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d213ca3653a8..9e14e453b55c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -592,6 +592,7 @@ void xfrm_state_free(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_free); +static void xfrm_state_delete_tunnel(struct xfrm_state *x); static void xfrm_state_gc_destroy(struct xfrm_state *x) { if (x->mode_cbs && x->mode_cbs->destroy_state) @@ -607,6 +608,7 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) kfree(x->replay_esn); kfree(x->preplay_esn); xfrm_unset_type_offload(x); + xfrm_state_delete_tunnel(x); if (x->type) { x->type->destructor(x); xfrm_put_type(x->type); @@ -806,7 +808,6 @@ void __xfrm_state_destroy(struct xfrm_state *x) } EXPORT_SYMBOL(__xfrm_state_destroy); -static void xfrm_state_delete_tunnel(struct xfrm_state *x); int __xfrm_state_delete(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -2073,6 +2074,7 @@ static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig, return x; error: + x->km.state = XFRM_STATE_DEAD; xfrm_state_put(x); out: return NULL; @@ -2157,11 +2159,15 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, xfrm_state_insert(xc); } else { if (xfrm_state_add(xc) < 0) - goto error; + goto error_add; } return xc; +error_add: + if (xuo) + xfrm_dev_state_delete(xc); error: + xc->km.state = XFRM_STATE_DEAD; xfrm_state_put(xc); return NULL; } @@ -2191,14 +2197,18 @@ int xfrm_state_update(struct xfrm_state *x) } if (x1->km.state == XFRM_STATE_ACQ) { - if (x->dir && x1->dir != x->dir) + if (x->dir && x1->dir != x->dir) { + to_put = x1; goto out; + } __xfrm_state_insert(x); x = NULL; } else { - if (x1->dir != x->dir) + if (x1->dir != x->dir) { + to_put = x1; goto out; + } } err = 0; @@ -3298,6 +3308,7 @@ out_bydst: void xfrm_state_fini(struct net *net) { unsigned int sz; + int i; flush_work(&net->xfrm.state_hash_work); xfrm_state_flush(net, 0, false); @@ -3305,14 +3316,17 @@ void xfrm_state_fini(struct net *net) WARN_ON(!list_empty(&net->xfrm.state_all)); + for (i = 0; i <= net->xfrm.state_hmask; i++) { + WARN_ON(!hlist_empty(net->xfrm.state_byseq + i)); + WARN_ON(!hlist_empty(net->xfrm.state_byspi + i)); + WARN_ON(!hlist_empty(net->xfrm.state_bysrc + i)); + WARN_ON(!hlist_empty(net->xfrm.state_bydst + i)); + } + sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head); - WARN_ON(!hlist_empty(net->xfrm.state_byseq)); xfrm_hash_free(net->xfrm.state_byseq, sz); - WARN_ON(!hlist_empty(net->xfrm.state_byspi)); xfrm_hash_free(net->xfrm.state_byspi, sz); - WARN_ON(!hlist_empty(net->xfrm.state_bysrc)); xfrm_hash_free(net->xfrm.state_bysrc, sz); - WARN_ON(!hlist_empty(net->xfrm.state_bydst)); xfrm_hash_free(net->xfrm.state_bydst, sz); free_percpu(net->xfrm.state_cache_input); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 010c9e6638c0..403b5ecac2c5 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -947,8 +947,11 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, if (attrs[XFRMA_SA_PCPU]) { x->pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]); - if (x->pcpu_num >= num_possible_cpus()) + if (x->pcpu_num >= num_possible_cpus()) { + err = -ERANGE; + NL_SET_ERR_MSG(extack, "pCPU number too big"); goto error; + } } err = __xfrm_init_state(x, extack); @@ -3035,6 +3038,9 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, } xfrm_state_free(x); + xfrm_dev_policy_delete(xp); + xfrm_dev_policy_free(xp); + security_xfrm_policy_free(xp->security); kfree(xp); return 0; diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 439101b518ee..8f9850a71f54 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -45,6 +45,7 @@ skf_net_off socket so_incoming_cpu so_netns_cookie +so_peek_off so_txtime so_rcv_listener stress_reuseport_listen diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index de805cbbdf69..528d14c598bb 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -6,6 +6,7 @@ TEST_GEN_PROGS := \ scm_inq \ scm_pidfd \ scm_rights \ + so_peek_off \ unix_connect \ # end of TEST_GEN_PROGS diff --git a/tools/testing/selftests/net/af_unix/so_peek_off.c b/tools/testing/selftests/net/af_unix/so_peek_off.c new file mode 100644 index 000000000000..1a77728128e5 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/so_peek_off.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2025 Google LLC */ + +#include <stdlib.h> +#include <unistd.h> + +#include <sys/socket.h> + +#include "../../kselftest_harness.h" + +FIXTURE(so_peek_off) +{ + int fd[2]; /* 0: sender, 1: receiver */ +}; + +FIXTURE_VARIANT(so_peek_off) +{ + int type; +}; + +FIXTURE_VARIANT_ADD(so_peek_off, stream) +{ + .type = SOCK_STREAM, +}; + +FIXTURE_VARIANT_ADD(so_peek_off, dgram) +{ + .type = SOCK_DGRAM, +}; + +FIXTURE_VARIANT_ADD(so_peek_off, seqpacket) +{ + .type = SOCK_SEQPACKET, +}; + +FIXTURE_SETUP(so_peek_off) +{ + struct timeval timeout = { + .tv_sec = 0, + .tv_usec = 3000, + }; + int ret; + + ret = socketpair(AF_UNIX, variant->type, 0, self->fd); + ASSERT_EQ(0, ret); + + ret = setsockopt(self->fd[1], SOL_SOCKET, SO_RCVTIMEO_NEW, + &timeout, sizeof(timeout)); + ASSERT_EQ(0, ret); + + ret = setsockopt(self->fd[1], SOL_SOCKET, SO_PEEK_OFF, + &(int){0}, sizeof(int)); + ASSERT_EQ(0, ret); +} + +FIXTURE_TEARDOWN(so_peek_off) +{ + close_range(self->fd[0], self->fd[1], 0); +} + +#define sendeq(fd, str, flags) \ + do { \ + int bytes, len = strlen(str); \ + \ + bytes = send(fd, str, len, flags); \ + ASSERT_EQ(len, bytes); \ + } while (0) + +#define recveq(fd, str, buflen, flags) \ + do { \ + char buf[(buflen) + 1] = {}; \ + int bytes; \ + \ + bytes = recv(fd, buf, buflen, flags); \ + ASSERT_NE(-1, bytes); \ + ASSERT_STREQ(str, buf); \ + } while (0) + +#define async \ + for (pid_t pid = (pid = fork(), \ + pid < 0 ? \ + __TH_LOG("Failed to start async {}"), \ + _metadata->exit_code = KSFT_FAIL, \ + __bail(1, _metadata), \ + 0xdead : \ + pid); \ + !pid; exit(0)) + +TEST_F(so_peek_off, single_chunk) +{ + sendeq(self->fd[0], "aaaabbbb", 0); + + recveq(self->fd[1], "aaaa", 4, MSG_PEEK); + recveq(self->fd[1], "bbbb", 100, MSG_PEEK); +} + +TEST_F(so_peek_off, two_chunks) +{ + sendeq(self->fd[0], "aaaa", 0); + sendeq(self->fd[0], "bbbb", 0); + + recveq(self->fd[1], "aaaa", 4, MSG_PEEK); + recveq(self->fd[1], "bbbb", 100, MSG_PEEK); +} + +TEST_F(so_peek_off, two_chunks_blocking) +{ + async { + usleep(1000); + sendeq(self->fd[0], "aaaa", 0); + } + + recveq(self->fd[1], "aaaa", 4, MSG_PEEK); + + async { + usleep(1000); + sendeq(self->fd[0], "bbbb", 0); + } + + /* goto again; -> goto redo; in unix_stream_read_generic(). */ + recveq(self->fd[1], "bbbb", 100, MSG_PEEK); +} + +TEST_F(so_peek_off, two_chunks_overlap) +{ + sendeq(self->fd[0], "aaaa", 0); + recveq(self->fd[1], "aa", 2, MSG_PEEK); + + sendeq(self->fd[0], "bbbb", 0); + + if (variant->type == SOCK_STREAM) { + /* SOCK_STREAM tries to fill the buffer. */ + recveq(self->fd[1], "aabb", 4, MSG_PEEK); + recveq(self->fd[1], "bb", 100, MSG_PEEK); + } else { + /* SOCK_DGRAM and SOCK_SEQPACKET returns at the skb boundary. */ + recveq(self->fd[1], "aa", 100, MSG_PEEK); + recveq(self->fd[1], "bbbb", 100, MSG_PEEK); + } +} + +TEST_F(so_peek_off, two_chunks_overlap_blocking) +{ + async { + usleep(1000); + sendeq(self->fd[0], "aaaa", 0); + } + + recveq(self->fd[1], "aa", 2, MSG_PEEK); + + async { + usleep(1000); + sendeq(self->fd[0], "bbbb", 0); + } + + /* Even SOCK_STREAM does not wait if at least one byte is read. */ + recveq(self->fd[1], "aa", 100, MSG_PEEK); + + recveq(self->fd[1], "bbbb", 100, MSG_PEEK); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/forwarding/lib_sh_test.sh b/tools/testing/selftests/net/forwarding/lib_sh_test.sh index ff2accccaf4d..b4eda6c6199e 100755 --- a/tools/testing/selftests/net/forwarding/lib_sh_test.sh +++ b/tools/testing/selftests/net/forwarding/lib_sh_test.sh @@ -30,6 +30,11 @@ tfail() do_test "tfail" false } +tfail2() +{ + do_test "tfail2" false +} + txfail() { FAIL_TO_XFAIL=yes do_test "txfail" false @@ -132,6 +137,8 @@ test_ret() ret_subtest $ksft_fail "tfail" txfail tfail ret_subtest $ksft_xfail "txfail" txfail txfail + + ret_subtest $ksft_fail "tfail2" tfail2 tfail } exit_status_tests_run() diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index feba4ef69a54..f448bafb3f20 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -43,7 +43,7 @@ __ksft_status_merge() weights[$i]=$((weight++)) done - if [[ ${weights[$a]} > ${weights[$b]} ]]; then + if [[ ${weights[$a]} -ge ${weights[$b]} ]]; then echo "$a" return 0 else diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 41503c241989..43f31f8d587f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3500,7 +3500,6 @@ fullmesh_tests() fastclose_tests() { if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then - MPTCP_LIB_SUBTEST_FLAKY=1 test_linkfail=1024 fastclose=client \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 @@ -3509,7 +3508,6 @@ fastclose_tests() fi if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then - MPTCP_LIB_SUBTEST_FLAKY=1 test_linkfail=1024 fastclose=server \ run_tests $ns1 $ns2 10.0.1.1 join_rst_nr=1 \ @@ -3806,7 +3804,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns2 2 2 - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns1 @@ -3839,7 +3837,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns2 @@ -3867,7 +3865,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns2 @@ -3888,7 +3886,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns2 @@ -3912,7 +3910,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns2 1 1 - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns1 @@ -3943,7 +3941,7 @@ endpoint_tests() pm_nl_set_limits $ns1 2 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - { test_linkfail=128 speed=slow \ + { timeout_test=120 test_linkfail=128 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! @@ -3970,7 +3968,7 @@ endpoint_tests() pm_nl_set_limits $ns2 0 3 pm_nl_add_endpoint $ns2 10.0.1.2 id 1 dev ns2eth1 flags subflow pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! @@ -4048,7 +4046,7 @@ endpoint_tests() # broadcast IP: no packet for this address will be received on ns1 pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal pm_nl_add_endpoint $ns1 10.0.1.1 id 42 flags signal - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! @@ -4057,38 +4055,45 @@ endpoint_tests() $ns1 10.0.2.1 id 1 flags signal chk_subflow_nr "before delete" 2 chk_mptcp_info subflows 1 subflows 1 + chk_mptcp_info add_addr_signal 2 add_addr_accepted 1 pm_nl_del_endpoint $ns1 1 10.0.2.1 pm_nl_del_endpoint $ns1 2 224.0.0.1 sleep 0.5 chk_subflow_nr "after delete" 1 chk_mptcp_info subflows 0 subflows 0 + chk_mptcp_info add_addr_signal 0 add_addr_accepted 0 pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal wait_mpj $ns2 chk_subflow_nr "after re-add" 3 chk_mptcp_info subflows 2 subflows 2 + chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 pm_nl_del_endpoint $ns1 42 10.0.1.1 sleep 0.5 chk_subflow_nr "after delete ID 0" 2 chk_mptcp_info subflows 2 subflows 2 + chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal wait_mpj $ns2 chk_subflow_nr "after re-add ID 0" 3 chk_mptcp_info subflows 3 subflows 3 + chk_mptcp_info add_addr_signal 3 add_addr_accepted 2 pm_nl_del_endpoint $ns1 99 10.0.1.1 sleep 0.5 chk_subflow_nr "after re-delete ID 0" 2 chk_mptcp_info subflows 2 subflows 2 + chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 pm_nl_add_endpoint $ns1 10.0.1.1 id 88 flags signal wait_mpj $ns2 chk_subflow_nr "after re-re-add ID 0" 3 chk_mptcp_info subflows 3 subflows 3 + chk_mptcp_info add_addr_signal 3 add_addr_accepted 2 mptcp_lib_kill_group_wait $tests_pid kill_events_pids @@ -4121,7 +4126,7 @@ endpoint_tests() # broadcast IP: no packet for this address will be received on ns1 pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow - { test_linkfail=128 speed=20 \ + { timeout_test=120 test_linkfail=128 speed=20 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! |