diff options
42 files changed, 510 insertions, 276 deletions
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 1ebb4b943876..4a01ffa4350a 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -88,7 +88,7 @@ config WIREGUARD select CRYPTO_CURVE25519_X86 if X86 && 64BIT select ARM_CRYPTO if ARM select ARM64_CRYPTO if ARM64 - select CRYPTO_CHACHA20_NEON if (ARM || ARM64) && KERNEL_MODE_NEON + select CRYPTO_CHACHA20_NEON if ARM || (ARM64 && KERNEL_MODE_NEON) select CRYPTO_POLY1305_NEON if ARM64 && KERNEL_MODE_NEON select CRYPTO_POLY1305_ARM if ARM select CRYPTO_CURVE25519_NEON if ARM && KERNEL_MODE_NEON diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index ae86ded1e2a1..a162499bcafc 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -543,6 +543,19 @@ static void b53_port_set_mcast_flood(struct b53_device *dev, int port, b53_write16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, mc); } +static void b53_port_set_learning(struct b53_device *dev, int port, + bool learning) +{ + u16 reg; + + b53_read16(dev, B53_CTRL_PAGE, B53_DIS_LEARNING, ®); + if (learning) + reg &= ~BIT(port); + else + reg |= BIT(port); + b53_write16(dev, B53_CTRL_PAGE, B53_DIS_LEARNING, reg); +} + int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) { struct b53_device *dev = ds->priv; @@ -557,6 +570,7 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) b53_port_set_ucast_flood(dev, port, true); b53_port_set_mcast_flood(dev, port, true); + b53_port_set_learning(dev, port, false); if (dev->ops->irq_enable) ret = dev->ops->irq_enable(dev, port); @@ -691,6 +705,7 @@ static void b53_enable_cpu_port(struct b53_device *dev, int port) b53_port_set_ucast_flood(dev, port, true); b53_port_set_mcast_flood(dev, port, true); + b53_port_set_learning(dev, port, false); } static void b53_enable_mib(struct b53_device *dev) @@ -1953,19 +1968,20 @@ void b53_br_fast_age(struct dsa_switch *ds, int port) } EXPORT_SYMBOL(b53_br_fast_age); -static int b53_br_flags_pre(struct dsa_switch *ds, int port, - struct switchdev_brport_flags flags, - struct netlink_ext_ack *extack) +int b53_br_flags_pre(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) { - if (flags.mask & ~(BR_FLOOD | BR_MCAST_FLOOD)) + if (flags.mask & ~(BR_FLOOD | BR_MCAST_FLOOD | BR_LEARNING)) return -EINVAL; return 0; } +EXPORT_SYMBOL(b53_br_flags_pre); -static int b53_br_flags(struct dsa_switch *ds, int port, - struct switchdev_brport_flags flags, - struct netlink_ext_ack *extack) +int b53_br_flags(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) { if (flags.mask & BR_FLOOD) b53_port_set_ucast_flood(ds->priv, port, @@ -1973,17 +1989,22 @@ static int b53_br_flags(struct dsa_switch *ds, int port, if (flags.mask & BR_MCAST_FLOOD) b53_port_set_mcast_flood(ds->priv, port, !!(flags.val & BR_MCAST_FLOOD)); + if (flags.mask & BR_LEARNING) + b53_port_set_learning(ds->priv, port, + !!(flags.val & BR_LEARNING)); return 0; } +EXPORT_SYMBOL(b53_br_flags); -static int b53_set_mrouter(struct dsa_switch *ds, int port, bool mrouter, - struct netlink_ext_ack *extack) +int b53_set_mrouter(struct dsa_switch *ds, int port, bool mrouter, + struct netlink_ext_ack *extack) { b53_port_set_mcast_flood(ds->priv, port, mrouter); return 0; } +EXPORT_SYMBOL(b53_set_mrouter); static bool b53_possible_cpu_port(struct dsa_switch *ds, int port) { diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index faf983fbca82..8419bb7f4505 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -326,6 +326,14 @@ int b53_br_join(struct dsa_switch *ds, int port, struct net_device *bridge); void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *bridge); void b53_br_set_stp_state(struct dsa_switch *ds, int port, u8 state); void b53_br_fast_age(struct dsa_switch *ds, int port); +int b53_br_flags_pre(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); +int b53_br_flags(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); +int b53_set_mrouter(struct dsa_switch *ds, int port, bool mrouter, + struct netlink_ext_ack *extack); int b53_setup_devlink_resources(struct dsa_switch *ds); void b53_port_event(struct dsa_switch *ds, int port); void b53_phylink_validate(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h index c90985c294a2..b2c539a42154 100644 --- a/drivers/net/dsa/b53/b53_regs.h +++ b/drivers/net/dsa/b53/b53_regs.h @@ -115,6 +115,7 @@ #define B53_UC_FLOOD_MASK 0x32 #define B53_MC_FLOOD_MASK 0x34 #define B53_IPMC_FLOOD_MASK 0x36 +#define B53_DIS_LEARNING 0x3c /* * Override Ports 0-7 State on devices with xMII interfaces (8 bit) diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 1857aa9aa84a..5ee8103b8e9c 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -223,23 +223,10 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port, reg &= ~P_TXQ_PSM_VDD(port); core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL); - /* Enable learning */ - reg = core_readl(priv, CORE_DIS_LEARN); - reg &= ~BIT(port); - core_writel(priv, reg, CORE_DIS_LEARN); - /* Enable Broadcom tags for that port if requested */ - if (priv->brcm_tag_mask & BIT(port)) { + if (priv->brcm_tag_mask & BIT(port)) b53_brcm_hdr_setup(ds, port); - /* Disable learning on ASP port */ - if (port == 7) { - reg = core_readl(priv, CORE_DIS_LEARN); - reg |= BIT(port); - core_writel(priv, reg, CORE_DIS_LEARN); - } - } - /* Configure Traffic Class to QoS mapping, allow each priority to map * to a different queue number */ @@ -1117,7 +1104,10 @@ static const struct dsa_switch_ops bcm_sf2_ops = { .set_mac_eee = b53_set_mac_eee, .port_bridge_join = b53_br_join, .port_bridge_leave = b53_br_leave, + .port_pre_bridge_flags = b53_br_flags_pre, + .port_bridge_flags = b53_br_flags, .port_stp_state_set = b53_br_set_stp_state, + .port_set_mrouter = b53_set_mrouter, .port_fast_age = b53_br_fast_age, .port_vlan_filtering = b53_vlan_filtering, .port_vlan_add = b53_vlan_add, diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index dd5c8a9038bb..a60ce9030581 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -223,8 +223,6 @@ #define AG71XX_REG_RX_SM 0x01b0 #define AG71XX_REG_TX_SM 0x01b4 -#define ETH_SWITCH_HEADER_LEN 2 - #define AG71XX_DEFAULT_MSG_ENABLE \ (NETIF_MSG_DRV \ | NETIF_MSG_PROBE \ @@ -933,7 +931,7 @@ static void ag71xx_hw_setup(struct ag71xx *ag) static unsigned int ag71xx_max_frame_len(unsigned int mtu) { - return ETH_SWITCH_HEADER_LEN + ETH_HLEN + VLAN_HLEN + mtu + ETH_FCS_LEN; + return ETH_HLEN + VLAN_HLEN + mtu + ETH_FCS_LEN; } static void ag71xx_hw_set_macaddr(struct ag71xx *ag, unsigned char *mac) diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index fd8767213165..977f097fc7bf 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1192,7 +1192,6 @@ static int bcm_enet_stop(struct net_device *dev) kdev = &priv->pdev->dev; netif_stop_queue(dev); - netdev_reset_queue(dev); napi_disable(&priv->napi); if (priv->has_phy) phy_stop(dev->phydev); @@ -1231,6 +1230,9 @@ static int bcm_enet_stop(struct net_device *dev) if (priv->has_phy) phy_disconnect(dev->phydev); + /* reset BQL after forced tx reclaim to prevent kernel panic */ + netdev_reset_queue(dev); + return 0; } @@ -2343,7 +2345,6 @@ static int bcm_enetsw_stop(struct net_device *dev) del_timer_sync(&priv->swphy_poll); netif_stop_queue(dev); - netdev_reset_queue(dev); napi_disable(&priv->napi); del_timer_sync(&priv->rx_timeout); @@ -2371,6 +2372,9 @@ static int bcm_enetsw_stop(struct net_device *dev) free_irq(priv->irq_tx, dev); free_irq(priv->irq_rx, dev); + /* reset BQL after forced tx reclaim to prevent kernel panic */ + netdev_reset_queue(dev); + return 0; } diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index ccfe52a50a66..720dc99bd1fc 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2670,7 +2670,6 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, u32 hash; u64 ns; - np = container_of(&portal, struct dpaa_napi_portal, p); dpaa_fq = container_of(fq, struct dpaa_fq, fq_base); fd_status = be32_to_cpu(fd->status); fd_format = qm_fd_get_format(fd); @@ -2685,6 +2684,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, percpu_priv = this_cpu_ptr(priv->percpu_priv); percpu_stats = &percpu_priv->stats; + np = &percpu_priv->np; if (unlikely(dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi))) return qman_cb_dqrr_stop; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index a8a2b5f683a2..c70dec65a572 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -5083,7 +5083,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) enum i40e_admin_queue_err adq_err; struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - bool is_reset_needed; + u32 reset_needed = 0; i40e_status status; u32 i, j; @@ -5128,9 +5128,11 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) flags_complete: changed_flags = orig_flags ^ new_flags; - is_reset_needed = !!(changed_flags & (I40E_FLAG_VEB_STATS_ENABLED | - I40E_FLAG_LEGACY_RX | I40E_FLAG_SOURCE_PRUNING_DISABLED | - I40E_FLAG_DISABLE_FW_LLDP)); + if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) + reset_needed = I40E_PF_RESET_AND_REBUILD_FLAG; + if (changed_flags & (I40E_FLAG_VEB_STATS_ENABLED | + I40E_FLAG_LEGACY_RX | I40E_FLAG_SOURCE_PRUNING_DISABLED)) + reset_needed = BIT(__I40E_PF_RESET_REQUESTED); /* Before we finalize any flag changes, we need to perform some * checks to ensure that the changes are supported and safe. @@ -5252,7 +5254,7 @@ flags_complete: case I40E_AQ_RC_EEXIST: dev_warn(&pf->pdev->dev, "FW LLDP agent is already running\n"); - is_reset_needed = false; + reset_needed = 0; break; case I40E_AQ_RC_EPERM: dev_warn(&pf->pdev->dev, @@ -5281,8 +5283,8 @@ flags_complete: /* Issue reset to cause things to take effect, as additional bits * are added we will need to create a mask of bits requiring reset */ - if (is_reset_needed) - i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true); + if (reset_needed) + i40e_do_reset(pf, reset_needed, true); return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 8bb8eb65add9..353deae139f9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2616,7 +2616,7 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) return; if (!test_and_clear_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state)) return; - if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) { + if (test_bit(__I40E_VF_DISABLE, pf->state)) { set_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state); return; } @@ -2634,7 +2634,6 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) } } } - clear_bit(__I40E_VF_DISABLE, pf->state); } /** @@ -5937,7 +5936,7 @@ static int i40e_add_channel(struct i40e_pf *pf, u16 uplink_seid, ch->enabled_tc = !i40e_is_channel_macvlan(ch) && enabled_tc; ch->seid = ctxt.seid; ch->vsi_number = ctxt.vsi_number; - ch->stat_counter_idx = cpu_to_le16(ctxt.info.stat_counter_idx); + ch->stat_counter_idx = le16_to_cpu(ctxt.info.stat_counter_idx); /* copy just the sections touched not the entire info * since not all sections are valid as returned by @@ -7977,8 +7976,8 @@ static inline void i40e_set_cld_element(struct i40e_cloud_filter *filter, struct i40e_aqc_cloud_filters_element_data *cld) { - int i, j; u32 ipa; + int i; memset(cld, 0, sizeof(*cld)); ether_addr_copy(cld->outer_mac, filter->dst_mac); @@ -7989,14 +7988,14 @@ i40e_set_cld_element(struct i40e_cloud_filter *filter, if (filter->n_proto == ETH_P_IPV6) { #define IPV6_MAX_INDEX (ARRAY_SIZE(filter->dst_ipv6) - 1) - for (i = 0, j = 0; i < ARRAY_SIZE(filter->dst_ipv6); - i++, j += 2) { + for (i = 0; i < ARRAY_SIZE(filter->dst_ipv6); i++) { ipa = be32_to_cpu(filter->dst_ipv6[IPV6_MAX_INDEX - i]); - ipa = cpu_to_le32(ipa); - memcpy(&cld->ipaddr.raw_v6.data[j], &ipa, sizeof(ipa)); + + *(__le32 *)&cld->ipaddr.raw_v6.data[i * 2] = cpu_to_le32(ipa); } } else { ipa = be32_to_cpu(filter->dst_ipv4); + memcpy(&cld->ipaddr.v4.data, &ipa, sizeof(ipa)); } @@ -8044,6 +8043,8 @@ int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, if (filter->flags >= ARRAY_SIZE(flag_table)) return I40E_ERR_CONFIG; + memset(&cld_filter, 0, sizeof(cld_filter)); + /* copy element needed to add cloud filter from filter */ i40e_set_cld_element(filter, &cld_filter); @@ -8107,10 +8108,13 @@ int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, return -EOPNOTSUPP; /* adding filter using src_port/src_ip is not supported at this stage */ - if (filter->src_port || filter->src_ipv4 || + if (filter->src_port || + (filter->src_ipv4 && filter->n_proto != ETH_P_IPV6) || !ipv6_addr_any(&filter->ip.v6.src_ip6)) return -EOPNOTSUPP; + memset(&cld_filter, 0, sizeof(cld_filter)); + /* copy element needed to add cloud filter from filter */ i40e_set_cld_element(filter, &cld_filter.element); @@ -8134,7 +8138,7 @@ int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT); } - } else if (filter->dst_ipv4 || + } else if ((filter->dst_ipv4 && filter->n_proto != ETH_P_IPV6) || !ipv6_addr_any(&filter->ip.v6.dst_ip6)) { cld_filter.element.flags = cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_IP_PORT); @@ -8928,11 +8932,6 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) dev_dbg(&pf->pdev->dev, "PFR requested\n"); i40e_handle_reset_warning(pf, lock_acquired); - dev_info(&pf->pdev->dev, - pf->flags & I40E_FLAG_DISABLE_FW_LLDP ? - "FW LLDP is disabled\n" : - "FW LLDP is enabled\n"); - } else if (reset_flags & I40E_PF_RESET_AND_REBUILD_FLAG) { /* Request a PF Reset * @@ -8940,6 +8939,10 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) */ i40e_prep_for_reset(pf); i40e_reset_and_rebuild(pf, true, lock_acquired); + dev_info(&pf->pdev->dev, + pf->flags & I40E_FLAG_DISABLE_FW_LLDP ? + "FW LLDP is disabled\n" : + "FW LLDP is enabled\n"); } else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) { int v; @@ -10462,7 +10465,6 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) int old_recovery_mode_bit = test_bit(__I40E_RECOVERY_MODE, pf->state); struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; struct i40e_hw *hw = &pf->hw; - u8 set_fc_aq_fail = 0; i40e_status ret; u32 val; int v; @@ -10605,13 +10607,6 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) i40e_stat_str(&pf->hw, ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); - /* make sure our flow control settings are restored */ - ret = i40e_set_fc(&pf->hw, &set_fc_aq_fail, true); - if (ret) - dev_dbg(&pf->pdev->dev, "setting flow control: ret = %s last_status = %s\n", - i40e_stat_str(&pf->hw, ret), - i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); - /* Rebuild the VSIs and VEBs that existed before reset. * They are still in our local switch element arrays, so only * need to rebuild the switch model in the HW. @@ -12191,6 +12186,8 @@ i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf) struct i40e_aqc_configure_partition_bw_data bw_data; i40e_status status; + memset(&bw_data, 0, sizeof(bw_data)); + /* Set the valid bit for this PF */ bw_data.pf_valid_bits = cpu_to_le16(BIT(pf->hw.pf_id)); bw_data.max_bw[pf->hw.pf_id] = pf->max_bw & I40E_ALT_BW_VALUE_MASK; @@ -15198,7 +15195,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) int err; u32 val; u32 i; - u8 set_fc_aq_fail; err = pci_enable_device_mem(pdev); if (err) @@ -15537,24 +15533,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } INIT_LIST_HEAD(&pf->vsi[pf->lan_vsi]->ch_list); - /* Make sure flow control is set according to current settings */ - err = i40e_set_fc(hw, &set_fc_aq_fail, true); - if (set_fc_aq_fail & I40E_SET_FC_AQ_FAIL_GET) - dev_dbg(&pf->pdev->dev, - "Set fc with err %s aq_err %s on get_phy_cap\n", - i40e_stat_str(hw, err), - i40e_aq_str(hw, hw->aq.asq_last_status)); - if (set_fc_aq_fail & I40E_SET_FC_AQ_FAIL_SET) - dev_dbg(&pf->pdev->dev, - "Set fc with err %s aq_err %s on set_phy_config\n", - i40e_stat_str(hw, err), - i40e_aq_str(hw, hw->aq.asq_last_status)); - if (set_fc_aq_fail & I40E_SET_FC_AQ_FAIL_UPDATE) - dev_dbg(&pf->pdev->dev, - "Set fc with err %s aq_err %s on get_link_info\n", - i40e_stat_str(hw, err), - i40e_aq_str(hw, hw->aq.asq_last_status)); - /* if FDIR VSI was set up, start it now */ for (i = 0; i < pf->num_alloc_vsi; i++) { if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) { @@ -15611,6 +15589,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) { dev_info(&pdev->dev, "setup of misc vector failed: %d\n", err); + i40e_cloud_filter_exit(pf); + i40e_fdir_teardown(pf); goto err_vsis; } } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index f6f1af94cca0..627794b31e33 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1948,7 +1948,7 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring, skb_record_rx_queue(skb, rx_ring->queue_index); if (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) { - u16 vlan_tag = rx_desc->wb.qword0.lo_dword.l2tag1; + __le16 vlan_tag = rx_desc->wb.qword0.lo_dword.l2tag1; __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), le16_to_cpu(vlan_tag)); @@ -3223,13 +3223,16 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, l4_proto = ip.v4->protocol; } else if (*tx_flags & I40E_TX_FLAGS_IPV6) { + int ret; + tunnel |= I40E_TX_CTX_EXT_IP_IPV6; exthdr = ip.hdr + sizeof(*ip.v6); l4_proto = ip.v6->nexthdr; - if (l4.hdr != exthdr) - ipv6_skip_exthdr(skb, exthdr - skb->data, - &l4_proto, &frag_off); + ret = ipv6_skip_exthdr(skb, exthdr - skb->data, + &l4_proto, &frag_off); + if (ret < 0) + return -1; } /* define outer transport */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 4f11f7bf75d1..fc32c5019b0f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -453,7 +453,7 @@ static void i40e_set_rs_bit(struct i40e_ring *xdp_ring) struct i40e_tx_desc *tx_desc; tx_desc = I40E_TX_DESC(xdp_ring, ntu); - tx_desc->cmd_type_offset_bsz |= (I40E_TX_DESC_CMD_RS << I40E_TXD_QW1_CMD_SHIFT); + tx_desc->cmd_type_offset_bsz |= cpu_to_le64(I40E_TX_DESC_CMD_RS << I40E_TXD_QW1_CMD_SHIFT); } /** diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 0507369bb54d..1767c60056c5 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4699,9 +4699,10 @@ static void mvpp2_irqs_deinit(struct mvpp2_port *port) } } -static bool mvpp22_rss_is_supported(void) +static bool mvpp22_rss_is_supported(struct mvpp2_port *port) { - return queue_mode == MVPP2_QDIST_MULTI_MODE; + return (queue_mode == MVPP2_QDIST_MULTI_MODE) && + !(port->flags & MVPP2_F_LOOPBACK); } static int mvpp2_open(struct net_device *dev) @@ -5513,7 +5514,7 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev, struct mvpp2_port *port = netdev_priv(dev); int ret = 0, i, loc = 0; - if (!mvpp22_rss_is_supported()) + if (!mvpp22_rss_is_supported(port)) return -EOPNOTSUPP; switch (info->cmd) { @@ -5548,7 +5549,7 @@ static int mvpp2_ethtool_set_rxnfc(struct net_device *dev, struct mvpp2_port *port = netdev_priv(dev); int ret = 0; - if (!mvpp22_rss_is_supported()) + if (!mvpp22_rss_is_supported(port)) return -EOPNOTSUPP; switch (info->cmd) { @@ -5569,7 +5570,9 @@ static int mvpp2_ethtool_set_rxnfc(struct net_device *dev, static u32 mvpp2_ethtool_get_rxfh_indir_size(struct net_device *dev) { - return mvpp22_rss_is_supported() ? MVPP22_RSS_TABLE_ENTRIES : 0; + struct mvpp2_port *port = netdev_priv(dev); + + return mvpp22_rss_is_supported(port) ? MVPP22_RSS_TABLE_ENTRIES : 0; } static int mvpp2_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, @@ -5578,7 +5581,7 @@ static int mvpp2_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, struct mvpp2_port *port = netdev_priv(dev); int ret = 0; - if (!mvpp22_rss_is_supported()) + if (!mvpp22_rss_is_supported(port)) return -EOPNOTSUPP; if (indir) @@ -5596,7 +5599,7 @@ static int mvpp2_ethtool_set_rxfh(struct net_device *dev, const u32 *indir, struct mvpp2_port *port = netdev_priv(dev); int ret = 0; - if (!mvpp22_rss_is_supported()) + if (!mvpp22_rss_is_supported(port)) return -EOPNOTSUPP; if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_CRC32) @@ -5617,7 +5620,7 @@ static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir, struct mvpp2_port *port = netdev_priv(dev); int ret = 0; - if (!mvpp22_rss_is_supported()) + if (!mvpp22_rss_is_supported(port)) return -EOPNOTSUPP; if (rss_context >= MVPP22_N_RSS_TABLES) return -EINVAL; @@ -5639,7 +5642,7 @@ static int mvpp2_ethtool_set_rxfh_context(struct net_device *dev, struct mvpp2_port *port = netdev_priv(dev); int ret; - if (!mvpp22_rss_is_supported()) + if (!mvpp22_rss_is_supported(port)) return -EOPNOTSUPP; if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_CRC32) @@ -5956,7 +5959,7 @@ static int mvpp2_port_init(struct mvpp2_port *port) mvpp2_cls_oversize_rxq_set(port); mvpp2_cls_port_config(port); - if (mvpp22_rss_is_supported()) + if (mvpp22_rss_is_supported(port)) mvpp22_port_rss_init(port); /* Provide an initial Rx packet size */ @@ -6861,7 +6864,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev->hw_features |= features | NETIF_F_RXCSUM | NETIF_F_GRO | NETIF_F_HW_VLAN_CTAG_FILTER; - if (mvpp22_rss_is_supported()) { + if (mvpp22_rss_is_supported(port)) { dev->hw_features |= NETIF_F_RXHASH; dev->features |= NETIF_F_NTUPLE; } diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index ebe1406c6e64..dbec8e187a68 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4806,12 +4806,11 @@ static struct net_device *sky2_init_netdev(struct sky2_hw *hw, unsigned port, if (!is_valid_ether_addr(dev->dev_addr)) { struct sockaddr sa = { AF_UNSPEC }; - netdev_warn(dev, - "Invalid MAC address, defaulting to random\n"); + dev_warn(&hw->pdev->dev, "Invalid MAC address, defaulting to random\n"); eth_hw_addr_random(dev); memcpy(sa.sa_data, dev->dev_addr, ETH_ALEN); if (sky2_set_mac_address(dev, &sa)) - netdev_warn(dev, "Failed to set MAC address.\n"); + dev_warn(&hw->pdev->dev, "Failed to set MAC address.\n"); } return dev; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 394f43add85c..a99e71bc7b3c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -4986,6 +4986,7 @@ static int mlx4_do_mirror_rule(struct mlx4_dev *dev, struct res_fs_rule *fs_rule if (!fs_rule->mirr_mbox) { mlx4_err(dev, "rule mirroring mailbox is null\n"); + mlx4_free_cmd_mailbox(dev, mailbox); return -EINVAL; } memcpy(mailbox->buf, fs_rule->mirr_mbox, fs_rule->mirr_mbox_size); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 56985542e202..44bb133c3000 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -316,6 +316,32 @@ static int tc_setup_cbs(struct stmmac_priv *priv, if (!priv->dma_cap.av) return -EOPNOTSUPP; + /* Port Transmit Rate and Speed Divider */ + switch (priv->speed) { + case SPEED_10000: + ptr = 32; + speed_div = 10000000; + break; + case SPEED_5000: + ptr = 32; + speed_div = 5000000; + break; + case SPEED_2500: + ptr = 8; + speed_div = 2500000; + break; + case SPEED_1000: + ptr = 8; + speed_div = 1000000; + break; + case SPEED_100: + ptr = 4; + speed_div = 100000; + break; + default: + return -EOPNOTSUPP; + } + mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use; if (mode_to_use == MTL_QUEUE_DCB && qopt->enable) { ret = stmmac_dma_qmode(priv, priv->ioaddr, queue, MTL_QUEUE_AVB); @@ -332,10 +358,6 @@ static int tc_setup_cbs(struct stmmac_priv *priv, priv->plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; } - /* Port Transmit Rate and Speed Divider */ - ptr = (priv->speed == SPEED_100) ? 4 : 8; - speed_div = (priv->speed == SPEED_100) ? 100000 : 1000000; - /* Final adjustments for HW */ value = div_s64(qopt->idleslope * 1024ll * ptr, speed_div); priv->plat->tx_queues_cfg[queue].idle_slope = value & GENMASK(31, 0); diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 9a70f05baf6e..39c00f050fbd 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -543,7 +543,6 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) && mtu < ntohs(iph->tot_len)) { netdev_dbg(dev, "packet too big, fragmentation needed\n"); - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); goto err_rt; diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c index 3e431737c1ba..a00a667454a9 100644 --- a/drivers/net/phy/icplus.c +++ b/drivers/net/phy/icplus.c @@ -239,7 +239,7 @@ static int ip101a_g_config_intr_pin(struct phy_device *phydev) oldpage = phy_select_page(phydev, IP101G_DEFAULT_PAGE); if (oldpage < 0) - return oldpage; + goto out; /* configure the RXER/INTR_32 pin of the 32-pin IP101GR if needed: */ switch (priv->sel_intr32) { @@ -314,7 +314,7 @@ static int ip101a_g_read_status(struct phy_device *phydev) oldpage = phy_select_page(phydev, IP101G_DEFAULT_PAGE); if (oldpage < 0) - return oldpage; + goto out; ret = __phy_read(phydev, IP10XX_SPEC_CTRL_STATUS); if (ret < 0) @@ -349,7 +349,8 @@ out: static int ip101a_g_config_mdix(struct phy_device *phydev) { u16 ctrl = 0, ctrl2 = 0; - int oldpage, ret; + int oldpage; + int ret = 0; switch (phydev->mdix_ctrl) { case ETH_TP_MDI: @@ -367,7 +368,7 @@ static int ip101a_g_config_mdix(struct phy_device *phydev) oldpage = phy_select_page(phydev, IP101G_DEFAULT_PAGE); if (oldpage < 0) - return oldpage; + goto out; ret = __phy_modify(phydev, IP10XX_SPEC_CTRL_STATUS, IP101A_G_AUTO_MDIX_DIS, ctrl); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 2d7cc63bef89..b246817f3405 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -2632,21 +2632,24 @@ static inline u8 rtl8152_get_speed(struct r8152 *tp) return ocp_read_byte(tp, MCU_TYPE_PLA, PLA_PHYSTATUS); } -static void rtl_set_eee_plus(struct r8152 *tp) +static void rtl_eee_plus_en(struct r8152 *tp, bool enable) { u32 ocp_data; - u8 speed; - speed = rtl8152_get_speed(tp); - if (speed & _10bps) { - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EEEP_CR); + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EEEP_CR); + if (enable) ocp_data |= EEEP_CR_EEEP_TX; - ocp_write_word(tp, MCU_TYPE_PLA, PLA_EEEP_CR, ocp_data); - } else { - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EEEP_CR); + else ocp_data &= ~EEEP_CR_EEEP_TX; - ocp_write_word(tp, MCU_TYPE_PLA, PLA_EEEP_CR, ocp_data); - } + ocp_write_word(tp, MCU_TYPE_PLA, PLA_EEEP_CR, ocp_data); +} + +static void rtl_set_eee_plus(struct r8152 *tp) +{ + if (rtl8152_get_speed(tp) & _10bps) + rtl_eee_plus_en(tp, true); + else + rtl_eee_plus_en(tp, false); } static void rxdy_gated_en(struct r8152 *tp, bool enable) @@ -3150,10 +3153,22 @@ static void r8153b_ups_flags(struct r8152 *tp) ocp_write_dword(tp, MCU_TYPE_USB, USB_UPS_FLAGS, ups_flags); } -static void r8153b_green_en(struct r8152 *tp, bool enable) +static void rtl_green_en(struct r8152 *tp, bool enable) { u16 data; + data = sram_read(tp, SRAM_GREEN_CFG); + if (enable) + data |= GREEN_ETH_EN; + else + data &= ~GREEN_ETH_EN; + sram_write(tp, SRAM_GREEN_CFG, data); + + tp->ups_info.green = enable; +} + +static void r8153b_green_en(struct r8152 *tp, bool enable) +{ if (enable) { sram_write(tp, 0x8045, 0); /* 10M abiq&ldvbias */ sram_write(tp, 0x804d, 0x1222); /* 100M short abiq&ldvbias */ @@ -3164,11 +3179,7 @@ static void r8153b_green_en(struct r8152 *tp, bool enable) sram_write(tp, 0x805d, 0x2444); /* 1000M short abiq&ldvbias */ } - data = sram_read(tp, SRAM_GREEN_CFG); - data |= GREEN_ETH_EN; - sram_write(tp, SRAM_GREEN_CFG, data); - - tp->ups_info.green = enable; + rtl_green_en(tp, true); } static u16 r8153_phy_status(struct r8152 *tp, u16 desired) @@ -3360,7 +3371,7 @@ static void rtl8153b_runtime_enable(struct r8152 *tp, bool enable) r8153b_ups_en(tp, false); r8153_queue_wake(tp, false); rtl_runtime_suspend_enable(tp, false); - if (tp->udev->speed != USB_SPEED_HIGH) + if (tp->udev->speed >= USB_SPEED_SUPER) r8153b_u1u2en(tp, true); } } @@ -5056,7 +5067,7 @@ static void rtl8153b_up(struct r8152 *tp) r8153_aldps_en(tp, true); - if (tp->udev->speed != USB_SPEED_HIGH) + if (tp->udev->speed >= USB_SPEED_SUPER) r8153b_u1u2en(tp, true); } @@ -5572,8 +5583,9 @@ static void r8153b_init(struct r8152 *tp) ocp_data |= POLL_LINK_CHG; ocp_write_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS, ocp_data); - if (tp->udev->speed != USB_SPEED_HIGH) + if (tp->udev->speed >= USB_SPEED_SUPER) r8153b_u1u2en(tp, true); + usb_enable_lpm(tp->udev); /* MAC clock speed down */ @@ -5756,6 +5768,9 @@ static int rtl8152_runtime_suspend(struct r8152 *tp) struct net_device *netdev = tp->netdev; int ret = 0; + if (!tp->rtl_ops.autosuspend_en) + return -EBUSY; + set_bit(SELECTIVE_SUSPEND, &tp->flags); smp_mb__after_atomic(); @@ -6155,6 +6170,11 @@ rtl_ethtool_get_eee(struct net_device *net, struct ethtool_eee *edata) struct r8152 *tp = netdev_priv(net); int ret; + if (!tp->rtl_ops.eee_get) { + ret = -EOPNOTSUPP; + goto out; + } + ret = usb_autopm_get_interface(tp->intf); if (ret < 0) goto out; @@ -6177,6 +6197,11 @@ rtl_ethtool_set_eee(struct net_device *net, struct ethtool_eee *edata) struct r8152 *tp = netdev_priv(net); int ret; + if (!tp->rtl_ops.eee_set) { + ret = -EOPNOTSUPP; + goto out; + } + ret = usb_autopm_get_interface(tp->intf); if (ret < 0) goto out; @@ -6576,7 +6601,7 @@ static int rtl_ops_init(struct r8152 *tp) default: ret = -ENODEV; - netif_err(tp, probe, tp->netdev, "Unknown Device\n"); + dev_err(&tp->intf->dev, "Unknown Device\n"); break; } @@ -6833,7 +6858,7 @@ static int rtl8152_probe(struct usb_interface *intf, ret = register_netdev(netdev); if (ret != 0) { - netif_err(tp, probe, netdev, "couldn't register the device\n"); + dev_err(&intf->dev, "couldn't register the device\n"); goto out1; } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 3929e437382b..666dd201c3d5 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -4721,7 +4721,6 @@ static void vxlan_destroy_tunnels(struct net *net, struct list_head *head) struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan, *next; struct net_device *dev, *aux; - unsigned int h; for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &vxlan_link_ops) @@ -4735,14 +4734,13 @@ static void vxlan_destroy_tunnels(struct net *net, struct list_head *head) unregister_netdevice_queue(vxlan->dev, head); } - for (h = 0; h < PORT_HASH_SIZE; ++h) - WARN_ON_ONCE(!hlist_empty(&vn->sock_list[h])); } static void __net_exit vxlan_exit_batch_net(struct list_head *net_list) { struct net *net; LIST_HEAD(list); + unsigned int h; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { @@ -4755,6 +4753,13 @@ static void __net_exit vxlan_exit_batch_net(struct list_head *net_list) unregister_netdevice_many(&list); rtnl_unlock(); + + list_for_each_entry(net, net_list, exit_list) { + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + + for (h = 0; h < PORT_HASH_SIZE; ++h) + WARN_ON_ONCE(!hlist_empty(&vn->sock_list[h])); + } } static struct pernet_operations vxlan_net_ops = { diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index a3ed49cd95c3..551ddaaaf540 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -138,7 +138,7 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) else if (skb->protocol == htons(ETH_P_IPV6)) net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n", dev->name, &ipv6_hdr(skb)->daddr); - goto err; + goto err_icmp; } family = READ_ONCE(peer->endpoint.addr.sa_family); @@ -157,7 +157,7 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) } else { struct sk_buff *segs = skb_gso_segment(skb, 0); - if (unlikely(IS_ERR(segs))) { + if (IS_ERR(segs)) { ret = PTR_ERR(segs); goto err_peer; } @@ -201,12 +201,13 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) err_peer: wg_peer_put(peer); -err: - ++dev->stats.tx_errors; +err_icmp: if (skb->protocol == htons(ETH_P_IP)) icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); else if (skb->protocol == htons(ETH_P_IPV6)) icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); +err: + ++dev->stats.tx_errors; kfree_skb(skb); return ret; } @@ -234,8 +235,8 @@ static void wg_destruct(struct net_device *dev) destroy_workqueue(wg->handshake_receive_wq); destroy_workqueue(wg->handshake_send_wq); destroy_workqueue(wg->packet_crypt_wq); - wg_packet_queue_free(&wg->decrypt_queue, true); - wg_packet_queue_free(&wg->encrypt_queue, true); + wg_packet_queue_free(&wg->decrypt_queue); + wg_packet_queue_free(&wg->encrypt_queue); rcu_barrier(); /* Wait for all the peers to be actually freed. */ wg_ratelimiter_uninit(); memzero_explicit(&wg->static_identity, sizeof(wg->static_identity)); @@ -337,12 +338,12 @@ static int wg_newlink(struct net *src_net, struct net_device *dev, goto err_destroy_handshake_send; ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker, - true, MAX_QUEUED_PACKETS); + MAX_QUEUED_PACKETS); if (ret < 0) goto err_destroy_packet_crypt; ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker, - true, MAX_QUEUED_PACKETS); + MAX_QUEUED_PACKETS); if (ret < 0) goto err_free_encrypt_queue; @@ -367,9 +368,9 @@ static int wg_newlink(struct net *src_net, struct net_device *dev, err_uninit_ratelimiter: wg_ratelimiter_uninit(); err_free_decrypt_queue: - wg_packet_queue_free(&wg->decrypt_queue, true); + wg_packet_queue_free(&wg->decrypt_queue); err_free_encrypt_queue: - wg_packet_queue_free(&wg->encrypt_queue, true); + wg_packet_queue_free(&wg->encrypt_queue); err_destroy_packet_crypt: destroy_workqueue(wg->packet_crypt_wq); err_destroy_handshake_send: diff --git a/drivers/net/wireguard/device.h b/drivers/net/wireguard/device.h index 4d0144e16947..854bc3d97150 100644 --- a/drivers/net/wireguard/device.h +++ b/drivers/net/wireguard/device.h @@ -27,13 +27,14 @@ struct multicore_worker { struct crypt_queue { struct ptr_ring ring; - union { - struct { - struct multicore_worker __percpu *worker; - int last_cpu; - }; - struct work_struct work; - }; + struct multicore_worker __percpu *worker; + int last_cpu; +}; + +struct prev_queue { + struct sk_buff *head, *tail, *peeked; + struct { struct sk_buff *next, *prev; } empty; // Match first 2 members of struct sk_buff. + atomic_t count; }; struct wg_device { diff --git a/drivers/net/wireguard/peer.c b/drivers/net/wireguard/peer.c index b3b6370e6b95..cd5cb0292cb6 100644 --- a/drivers/net/wireguard/peer.c +++ b/drivers/net/wireguard/peer.c @@ -32,27 +32,22 @@ struct wg_peer *wg_peer_create(struct wg_device *wg, peer = kzalloc(sizeof(*peer), GFP_KERNEL); if (unlikely(!peer)) return ERR_PTR(ret); - peer->device = wg; + if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL)) + goto err; + peer->device = wg; wg_noise_handshake_init(&peer->handshake, &wg->static_identity, public_key, preshared_key, peer); - if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL)) - goto err_1; - if (wg_packet_queue_init(&peer->tx_queue, wg_packet_tx_worker, false, - MAX_QUEUED_PACKETS)) - goto err_2; - if (wg_packet_queue_init(&peer->rx_queue, NULL, false, - MAX_QUEUED_PACKETS)) - goto err_3; - peer->internal_id = atomic64_inc_return(&peer_counter); peer->serial_work_cpu = nr_cpumask_bits; wg_cookie_init(&peer->latest_cookie); wg_timers_init(peer); wg_cookie_checker_precompute_peer_keys(peer); spin_lock_init(&peer->keypairs.keypair_update_lock); - INIT_WORK(&peer->transmit_handshake_work, - wg_packet_handshake_send_worker); + INIT_WORK(&peer->transmit_handshake_work, wg_packet_handshake_send_worker); + INIT_WORK(&peer->transmit_packet_work, wg_packet_tx_worker); + wg_prev_queue_init(&peer->tx_queue); + wg_prev_queue_init(&peer->rx_queue); rwlock_init(&peer->endpoint_lock); kref_init(&peer->refcount); skb_queue_head_init(&peer->staged_packet_queue); @@ -68,11 +63,7 @@ struct wg_peer *wg_peer_create(struct wg_device *wg, pr_debug("%s: Peer %llu created\n", wg->dev->name, peer->internal_id); return peer; -err_3: - wg_packet_queue_free(&peer->tx_queue, false); -err_2: - dst_cache_destroy(&peer->endpoint_cache); -err_1: +err: kfree(peer); return ERR_PTR(ret); } @@ -197,8 +188,7 @@ static void rcu_release(struct rcu_head *rcu) struct wg_peer *peer = container_of(rcu, struct wg_peer, rcu); dst_cache_destroy(&peer->endpoint_cache); - wg_packet_queue_free(&peer->rx_queue, false); - wg_packet_queue_free(&peer->tx_queue, false); + WARN_ON(wg_prev_queue_peek(&peer->tx_queue) || wg_prev_queue_peek(&peer->rx_queue)); /* The final zeroing takes care of clearing any remaining handshake key * material and other potentially sensitive information. diff --git a/drivers/net/wireguard/peer.h b/drivers/net/wireguard/peer.h index 23af40922997..8d53b687a1d1 100644 --- a/drivers/net/wireguard/peer.h +++ b/drivers/net/wireguard/peer.h @@ -36,16 +36,17 @@ struct endpoint { struct wg_peer { struct wg_device *device; - struct crypt_queue tx_queue, rx_queue; + struct prev_queue tx_queue, rx_queue; struct sk_buff_head staged_packet_queue; int serial_work_cpu; + bool is_dead; struct noise_keypairs keypairs; struct endpoint endpoint; struct dst_cache endpoint_cache; rwlock_t endpoint_lock; struct noise_handshake handshake; atomic64_t last_sent_handshake; - struct work_struct transmit_handshake_work, clear_peer_work; + struct work_struct transmit_handshake_work, clear_peer_work, transmit_packet_work; struct cookie latest_cookie; struct hlist_node pubkey_hash; u64 rx_bytes, tx_bytes; @@ -61,9 +62,8 @@ struct wg_peer { struct rcu_head rcu; struct list_head peer_list; struct list_head allowedips_list; - u64 internal_id; struct napi_struct napi; - bool is_dead; + u64 internal_id; }; struct wg_peer *wg_peer_create(struct wg_device *wg, diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c index 71b8e80b58e1..48e7b982a307 100644 --- a/drivers/net/wireguard/queueing.c +++ b/drivers/net/wireguard/queueing.c @@ -9,8 +9,7 @@ struct multicore_worker __percpu * wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr) { int cpu; - struct multicore_worker __percpu *worker = - alloc_percpu(struct multicore_worker); + struct multicore_worker __percpu *worker = alloc_percpu(struct multicore_worker); if (!worker) return NULL; @@ -23,7 +22,7 @@ wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr) } int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, - bool multicore, unsigned int len) + unsigned int len) { int ret; @@ -31,25 +30,78 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL); if (ret) return ret; - if (function) { - if (multicore) { - queue->worker = wg_packet_percpu_multicore_worker_alloc( - function, queue); - if (!queue->worker) { - ptr_ring_cleanup(&queue->ring, NULL); - return -ENOMEM; - } - } else { - INIT_WORK(&queue->work, function); - } + queue->worker = wg_packet_percpu_multicore_worker_alloc(function, queue); + if (!queue->worker) { + ptr_ring_cleanup(&queue->ring, NULL); + return -ENOMEM; } return 0; } -void wg_packet_queue_free(struct crypt_queue *queue, bool multicore) +void wg_packet_queue_free(struct crypt_queue *queue) { - if (multicore) - free_percpu(queue->worker); + free_percpu(queue->worker); WARN_ON(!__ptr_ring_empty(&queue->ring)); ptr_ring_cleanup(&queue->ring, NULL); } + +#define NEXT(skb) ((skb)->prev) +#define STUB(queue) ((struct sk_buff *)&queue->empty) + +void wg_prev_queue_init(struct prev_queue *queue) +{ + NEXT(STUB(queue)) = NULL; + queue->head = queue->tail = STUB(queue); + queue->peeked = NULL; + atomic_set(&queue->count, 0); + BUILD_BUG_ON( + offsetof(struct sk_buff, next) != offsetof(struct prev_queue, empty.next) - + offsetof(struct prev_queue, empty) || + offsetof(struct sk_buff, prev) != offsetof(struct prev_queue, empty.prev) - + offsetof(struct prev_queue, empty)); +} + +static void __wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb) +{ + WRITE_ONCE(NEXT(skb), NULL); + WRITE_ONCE(NEXT(xchg_release(&queue->head, skb)), skb); +} + +bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb) +{ + if (!atomic_add_unless(&queue->count, 1, MAX_QUEUED_PACKETS)) + return false; + __wg_prev_queue_enqueue(queue, skb); + return true; +} + +struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue) +{ + struct sk_buff *tail = queue->tail, *next = smp_load_acquire(&NEXT(tail)); + + if (tail == STUB(queue)) { + if (!next) + return NULL; + queue->tail = next; + tail = next; + next = smp_load_acquire(&NEXT(next)); + } + if (next) { + queue->tail = next; + atomic_dec(&queue->count); + return tail; + } + if (tail != READ_ONCE(queue->head)) + return NULL; + __wg_prev_queue_enqueue(queue, STUB(queue)); + next = smp_load_acquire(&NEXT(tail)); + if (next) { + queue->tail = next; + atomic_dec(&queue->count); + return tail; + } + return NULL; +} + +#undef NEXT +#undef STUB diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h index dfb674e03076..4ef2944a68bc 100644 --- a/drivers/net/wireguard/queueing.h +++ b/drivers/net/wireguard/queueing.h @@ -17,12 +17,13 @@ struct wg_device; struct wg_peer; struct multicore_worker; struct crypt_queue; +struct prev_queue; struct sk_buff; /* queueing.c APIs: */ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, - bool multicore, unsigned int len); -void wg_packet_queue_free(struct crypt_queue *queue, bool multicore); + unsigned int len); +void wg_packet_queue_free(struct crypt_queue *queue); struct multicore_worker __percpu * wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr); @@ -135,8 +136,31 @@ static inline int wg_cpumask_next_online(int *next) return cpu; } +void wg_prev_queue_init(struct prev_queue *queue); + +/* Multi producer */ +bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb); + +/* Single consumer */ +struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue); + +/* Single consumer */ +static inline struct sk_buff *wg_prev_queue_peek(struct prev_queue *queue) +{ + if (queue->peeked) + return queue->peeked; + queue->peeked = wg_prev_queue_dequeue(queue); + return queue->peeked; +} + +/* Single consumer */ +static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue) +{ + queue->peeked = NULL; +} + static inline int wg_queue_enqueue_per_device_and_peer( - struct crypt_queue *device_queue, struct crypt_queue *peer_queue, + struct crypt_queue *device_queue, struct prev_queue *peer_queue, struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu) { int cpu; @@ -145,8 +169,9 @@ static inline int wg_queue_enqueue_per_device_and_peer( /* We first queue this up for the peer ingestion, but the consumer * will wait for the state to change to CRYPTED or DEAD before. */ - if (unlikely(ptr_ring_produce_bh(&peer_queue->ring, skb))) + if (unlikely(!wg_prev_queue_enqueue(peer_queue, skb))) return -ENOSPC; + /* Then we queue it up in the device queue, which consumes the * packet as soon as it can. */ @@ -157,9 +182,7 @@ static inline int wg_queue_enqueue_per_device_and_peer( return 0; } -static inline void wg_queue_enqueue_per_peer(struct crypt_queue *queue, - struct sk_buff *skb, - enum packet_state state) +static inline void wg_queue_enqueue_per_peer_tx(struct sk_buff *skb, enum packet_state state) { /* We take a reference, because as soon as we call atomic_set, the * peer can be freed from below us. @@ -167,14 +190,12 @@ static inline void wg_queue_enqueue_per_peer(struct crypt_queue *queue, struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb)); atomic_set_release(&PACKET_CB(skb)->state, state); - queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, - peer->internal_id), - peer->device->packet_crypt_wq, &queue->work); + queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, peer->internal_id), + peer->device->packet_crypt_wq, &peer->transmit_packet_work); wg_peer_put(peer); } -static inline void wg_queue_enqueue_per_peer_napi(struct sk_buff *skb, - enum packet_state state) +static inline void wg_queue_enqueue_per_peer_rx(struct sk_buff *skb, enum packet_state state) { /* We take a reference, because as soon as we call atomic_set, the * peer can be freed from below us. diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 2c9551ea6dc7..7dc84bcca261 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -444,7 +444,6 @@ packet_processed: int wg_packet_rx_poll(struct napi_struct *napi, int budget) { struct wg_peer *peer = container_of(napi, struct wg_peer, napi); - struct crypt_queue *queue = &peer->rx_queue; struct noise_keypair *keypair; struct endpoint endpoint; enum packet_state state; @@ -455,11 +454,10 @@ int wg_packet_rx_poll(struct napi_struct *napi, int budget) if (unlikely(budget <= 0)) return 0; - while ((skb = __ptr_ring_peek(&queue->ring)) != NULL && + while ((skb = wg_prev_queue_peek(&peer->rx_queue)) != NULL && (state = atomic_read_acquire(&PACKET_CB(skb)->state)) != PACKET_STATE_UNCRYPTED) { - __ptr_ring_discard_one(&queue->ring); - peer = PACKET_PEER(skb); + wg_prev_queue_drop_peeked(&peer->rx_queue); keypair = PACKET_CB(skb)->keypair; free = true; @@ -508,7 +506,7 @@ void wg_packet_decrypt_worker(struct work_struct *work) enum packet_state state = likely(decrypt_packet(skb, PACKET_CB(skb)->keypair)) ? PACKET_STATE_CRYPTED : PACKET_STATE_DEAD; - wg_queue_enqueue_per_peer_napi(skb, state); + wg_queue_enqueue_per_peer_rx(skb, state); if (need_resched()) cond_resched(); } @@ -531,12 +529,10 @@ static void wg_packet_consume_data(struct wg_device *wg, struct sk_buff *skb) if (unlikely(READ_ONCE(peer->is_dead))) goto err; - ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, - &peer->rx_queue, skb, - wg->packet_crypt_wq, - &wg->decrypt_queue.last_cpu); + ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, &peer->rx_queue, skb, + wg->packet_crypt_wq, &wg->decrypt_queue.last_cpu); if (unlikely(ret == -EPIPE)) - wg_queue_enqueue_per_peer_napi(skb, PACKET_STATE_DEAD); + wg_queue_enqueue_per_peer_rx(skb, PACKET_STATE_DEAD); if (likely(!ret || ret == -EPIPE)) { rcu_read_unlock_bh(); return; diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index f74b9341ab0f..5368f7c35b4b 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -239,8 +239,7 @@ void wg_packet_send_keepalive(struct wg_peer *peer) wg_packet_send_staged_packets(peer); } -static void wg_packet_create_data_done(struct sk_buff *first, - struct wg_peer *peer) +static void wg_packet_create_data_done(struct wg_peer *peer, struct sk_buff *first) { struct sk_buff *skb, *next; bool is_keepalive, data_sent = false; @@ -262,22 +261,19 @@ static void wg_packet_create_data_done(struct sk_buff *first, void wg_packet_tx_worker(struct work_struct *work) { - struct crypt_queue *queue = container_of(work, struct crypt_queue, - work); + struct wg_peer *peer = container_of(work, struct wg_peer, transmit_packet_work); struct noise_keypair *keypair; enum packet_state state; struct sk_buff *first; - struct wg_peer *peer; - while ((first = __ptr_ring_peek(&queue->ring)) != NULL && + while ((first = wg_prev_queue_peek(&peer->tx_queue)) != NULL && (state = atomic_read_acquire(&PACKET_CB(first)->state)) != PACKET_STATE_UNCRYPTED) { - __ptr_ring_discard_one(&queue->ring); - peer = PACKET_PEER(first); + wg_prev_queue_drop_peeked(&peer->tx_queue); keypair = PACKET_CB(first)->keypair; if (likely(state == PACKET_STATE_CRYPTED)) - wg_packet_create_data_done(first, peer); + wg_packet_create_data_done(peer, first); else kfree_skb_list(first); @@ -306,16 +302,14 @@ void wg_packet_encrypt_worker(struct work_struct *work) break; } } - wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first, - state); + wg_queue_enqueue_per_peer_tx(first, state); if (need_resched()) cond_resched(); } } -static void wg_packet_create_data(struct sk_buff *first) +static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first) { - struct wg_peer *peer = PACKET_PEER(first); struct wg_device *wg = peer->device; int ret = -EINVAL; @@ -323,13 +317,10 @@ static void wg_packet_create_data(struct sk_buff *first) if (unlikely(READ_ONCE(peer->is_dead))) goto err; - ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, - &peer->tx_queue, first, - wg->packet_crypt_wq, - &wg->encrypt_queue.last_cpu); + ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first, + wg->packet_crypt_wq, &wg->encrypt_queue.last_cpu); if (unlikely(ret == -EPIPE)) - wg_queue_enqueue_per_peer(&peer->tx_queue, first, - PACKET_STATE_DEAD); + wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD); err: rcu_read_unlock_bh(); if (likely(!ret || ret == -EPIPE)) @@ -393,7 +384,7 @@ void wg_packet_send_staged_packets(struct wg_peer *peer) packets.prev->next = NULL; wg_peer_get(keypair->entry.peer); PACKET_CB(packets.next)->keypair = keypair; - wg_packet_create_data(packets.next); + wg_packet_create_data(peer, packets.next); return; out_invalid: diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c index 410b318e57fb..d9ad850daa79 100644 --- a/drivers/net/wireguard/socket.c +++ b/drivers/net/wireguard/socket.c @@ -53,7 +53,7 @@ static int send4(struct wg_device *wg, struct sk_buff *skb, if (unlikely(!inet_confirm_addr(sock_net(sock), NULL, 0, fl.saddr, RT_SCOPE_HOST))) { endpoint->src4.s_addr = 0; - *(__force __be32 *)&endpoint->src_if4 = 0; + endpoint->src_if4 = 0; fl.saddr = 0; if (cache) dst_cache_reset(cache); @@ -63,7 +63,7 @@ static int send4(struct wg_device *wg, struct sk_buff *skb, PTR_ERR(rt) == -EINVAL) || (!IS_ERR(rt) && rt->dst.dev->ifindex != endpoint->src_if4)))) { endpoint->src4.s_addr = 0; - *(__force __be32 *)&endpoint->src_if4 = 0; + endpoint->src_if4 = 0; fl.saddr = 0; if (cache) dst_cache_reset(cache); @@ -71,7 +71,7 @@ static int send4(struct wg_device *wg, struct sk_buff *skb, ip_rt_put(rt); rt = ip_route_output_flow(sock_net(sock), &fl, sock); } - if (unlikely(IS_ERR(rt))) { + if (IS_ERR(rt)) { ret = PTR_ERR(rt); net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); @@ -138,7 +138,7 @@ static int send6(struct wg_device *wg, struct sk_buff *skb, } dst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(sock), sock, &fl, NULL); - if (unlikely(IS_ERR(dst))) { + if (IS_ERR(dst)) { ret = PTR_ERR(dst); net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 452d8978ffc7..9055cb380ee2 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -3,6 +3,7 @@ #define _LINUX_ICMPV6_H #include <linux/skbuff.h> +#include <linux/ipv6.h> #include <uapi/linux/icmpv6.h> static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) @@ -15,13 +16,16 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) #if IS_ENABLED(CONFIG_IPV6) typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr); + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm); void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr); + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm); #if IS_BUILTIN(CONFIG_IPV6) -static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +static inline void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm) { - icmp6_send(skb, type, code, info, NULL); + icmp6_send(skb, type, code, info, NULL, parm); } static inline int inet6_register_icmp_sender(ip6_icmp_send_t *fn) { @@ -34,18 +38,28 @@ static inline int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) return 0; } #else -extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info); +extern void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); #endif +static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +{ + __icmpv6_send(skb, type, code, info, IP6CB(skb)); +} + int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); #if IS_ENABLED(CONFIG_NF_NAT) void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); #else -#define icmpv6_ndo_send icmpv6_send +static inline void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) +{ + struct inet6_skb_parm parm = { 0 }; + __icmpv6_send(skb_in, type, code, info, &parm); +} #endif #else diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 9d1f29f0c512..70b2ad3b9884 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -85,7 +85,6 @@ struct ipv6_params { __s32 autoconf; }; extern struct ipv6_params ipv6_defaults; -#include <linux/icmpv6.h> #include <linux/tcp.h> #include <linux/udp.h> diff --git a/include/net/icmp.h b/include/net/icmp.h index 9ac2d2672a93..fd84adc47963 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -46,7 +46,11 @@ static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 #if IS_ENABLED(CONFIG_NF_NAT) void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info); #else -#define icmp_ndo_send icmp_send +static inline void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) +{ + struct ip_options opts = { 0 }; + __icmp_send(skb_in, type, code, info, &opts); +} #endif int icmp_rcv(struct sk_buff *skb); diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index a45572cfb71a..3589224c8da9 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -9,6 +9,7 @@ menuconfig NET_DSA tristate "Distributed Switch Architecture" depends on HAVE_NET_DSA depends on BRIDGE || BRIDGE=n + depends on HSR || HSR=n select GRO_CELLS select NET_SWITCHDEV select PHYLINK diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 396b492c804f..616e2dc1c8fa 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -775,13 +775,14 @@ EXPORT_SYMBOL(__icmp_send); void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct sk_buff *cloned_skb = NULL; + struct ip_options opts = { 0 }; enum ip_conntrack_info ctinfo; struct nf_conn *ct; __be32 orig_ip; ct = nf_ct_get(skb_in, &ctinfo); if (!ct || !(ct->status & IPS_SRC_NAT)) { - icmp_send(skb_in, type, code, info); + __icmp_send(skb_in, type, code, info, &opts); return; } @@ -796,7 +797,7 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) orig_ip = ip_hdr(skb_in)->saddr; ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip; - icmp_send(skb_in, type, code, info); + __icmp_send(skb_in, type, code, info, &opts); ip_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index f3d05866692e..fd1f896115c1 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -331,10 +331,9 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st } #if IS_ENABLED(CONFIG_IPV6_MIP6) -static void mip6_addr_swap(struct sk_buff *skb) +static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) { struct ipv6hdr *iph = ipv6_hdr(skb); - struct inet6_skb_parm *opt = IP6CB(skb); struct ipv6_destopt_hao *hao; struct in6_addr tmp; int off; @@ -351,7 +350,7 @@ static void mip6_addr_swap(struct sk_buff *skb) } } #else -static inline void mip6_addr_swap(struct sk_buff *skb) {} +static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {} #endif static struct dst_entry *icmpv6_route_lookup(struct net *net, @@ -446,7 +445,8 @@ static int icmp6_iif(const struct sk_buff *skb) * Send an ICMP message in response to a packet in error */ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr) + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm) { struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -542,7 +542,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type)) goto out_bh_enable; - mip6_addr_swap(skb); + mip6_addr_swap(skb, parm); sk = icmpv6_xmit_lock(net); if (!sk) @@ -559,7 +559,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, /* select a more meaningful saddr from input if */ struct net_device *in_netdev; - in_netdev = dev_get_by_index(net, IP6CB(skb)->iif); + in_netdev = dev_get_by_index(net, parm->iif); if (in_netdev) { ipv6_dev_get_saddr(net, in_netdev, &fl6.daddr, inet6_sk(sk)->srcprefs, @@ -640,7 +640,7 @@ EXPORT_SYMBOL(icmp6_send); */ void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { - icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL); + icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb)); kfree_skb(skb); } @@ -697,10 +697,10 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, } if (type == ICMP_TIME_EXCEEDED) icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); else icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); if (rt) ip6_rt_put(rt); diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c index 70c8c2f36c98..9e3574880cb0 100644 --- a/net/ipv6/ip6_icmp.c +++ b/net/ipv6/ip6_icmp.c @@ -33,23 +33,25 @@ int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) } EXPORT_SYMBOL(inet6_unregister_icmp_sender); -void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm) { ip6_icmp_send_t *send; rcu_read_lock(); send = rcu_dereference(ip6_icmp_send); if (send) - send(skb, type, code, info, NULL); + send(skb, type, code, info, NULL, parm); rcu_read_unlock(); } -EXPORT_SYMBOL(icmpv6_send); +EXPORT_SYMBOL(__icmpv6_send); #endif #if IS_ENABLED(CONFIG_NF_NAT) #include <net/netfilter/nf_conntrack.h> void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) { + struct inet6_skb_parm parm = { 0 }; struct sk_buff *cloned_skb = NULL; enum ip_conntrack_info ctinfo; struct in6_addr orig_ip; @@ -57,7 +59,7 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) ct = nf_ct_get(skb_in, &ctinfo); if (!ct || !(ct->status & IPS_SRC_NAT)) { - icmpv6_send(skb_in, type, code, info); + __icmpv6_send(skb_in, type, code, info, &parm); return; } @@ -72,7 +74,7 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) orig_ip = ipv6_hdr(skb_in)->saddr; ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6; - icmpv6_send(skb_in, type, code, info); + __icmpv6_send(skb_in, type, code, info, &parm); ipv6_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b63574d6b812..444a38681e93 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -411,6 +411,7 @@ static void clear_3rdack_retransmission(struct sock *sk) } static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, + bool snd_data_fin_enable, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) @@ -428,9 +429,10 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, if (!skb) return false; - /* MPC/MPJ needed only on 3rd ack packet */ - if (subflow->fully_established || - subflow->snd_isn != TCP_SKB_CB(skb)->seq) + /* MPC/MPJ needed only on 3rd ack packet, DATA_FIN and TCP shutdown take precedence */ + if (subflow->fully_established || snd_data_fin_enable || + subflow->snd_isn != TCP_SKB_CB(skb)->seq || + sk->sk_state != TCP_ESTABLISHED) return false; if (subflow->mp_capable) { @@ -502,20 +504,20 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, } static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, + bool snd_data_fin_enable, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - u64 snd_data_fin_enable, ack_seq; unsigned int dss_size = 0; struct mptcp_ext *mpext; unsigned int ack_size; bool ret = false; + u64 ack_seq; mpext = skb ? mptcp_get_ext(skb) : NULL; - snd_data_fin_enable = mptcp_data_fin_enabled(msk); if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) { unsigned int map_size; @@ -717,12 +719,15 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); unsigned int opt_size = 0; + bool snd_data_fin; bool ret = false; opts->suboptions = 0; - if (unlikely(mptcp_check_fallback(sk))) + if (unlikely(__mptcp_check_fallback(msk))) return false; /* prevent adding of any MPTCP related options on reset packet @@ -731,10 +736,10 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) return false; - if (mptcp_established_options_mp(sk, skb, &opt_size, remaining, opts)) + snd_data_fin = mptcp_data_fin_enabled(msk); + if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, remaining, opts)) ret = true; - else if (mptcp_established_options_dss(sk, skb, &opt_size, remaining, - opts)) + else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts)) ret = true; /* we reserved enough space for the above options, and exceeding the diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a57f3eab7b6a..c5d5e68940ea 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -11,6 +11,7 @@ #include <linux/netdevice.h> #include <linux/sched/signal.h> #include <linux/atomic.h> +#include <linux/igmp.h> #include <net/sock.h> #include <net/inet_common.h> #include <net/inet_hashtables.h> @@ -19,6 +20,7 @@ #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/transp_v6.h> +#include <net/addrconf.h> #endif #include <net/mptcp.h> #include <net/xfrm.h> @@ -2264,13 +2266,12 @@ static void mptcp_worker(struct work_struct *work) __mptcp_check_send_data_fin(sk); mptcp_check_data_fin(sk); - /* if the msk data is completely acked, or the socket timedout, - * there is no point in keeping around an orphaned sk + /* There is no point in keeping around an orphaned sk timedout or + * closed, but we need the msk around to reply to incoming DATA_FIN, + * even if it is orphaned and in FIN_WAIT2 state */ if (sock_flag(sk, SOCK_DEAD) && - (mptcp_check_close_timeout(sk) || - (state != sk->sk_state && - ((1 << inet_sk_state_load(sk)) & (TCPF_CLOSE | TCPF_FIN_WAIT2))))) { + (mptcp_check_close_timeout(sk) || sk->sk_state == TCP_CLOSE)) { inet_sk_state_store(sk, TCP_CLOSE); __mptcp_destroy_sock(sk); goto unlock; @@ -3375,10 +3376,34 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, return mask; } +static int mptcp_release(struct socket *sock) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = sock->sk; + struct mptcp_sock *msk; + + if (!sk) + return 0; + + lock_sock(sk); + + msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ip_mc_drop_socket(ssk); + } + + release_sock(sk); + + return inet_release(sock); +} + static const struct proto_ops mptcp_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, - .release = inet_release, + .release = mptcp_release, .bind = mptcp_bind, .connect = mptcp_stream_connect, .socketpair = sock_no_socketpair, @@ -3470,10 +3495,35 @@ void __init mptcp_proto_init(void) } #if IS_ENABLED(CONFIG_MPTCP_IPV6) +static int mptcp6_release(struct socket *sock) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk; + struct sock *sk = sock->sk; + + if (!sk) + return 0; + + lock_sock(sk); + + msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ip_mc_drop_socket(ssk); + ipv6_sock_mc_close(ssk); + ipv6_sock_ac_close(ssk); + } + + release_sock(sk); + return inet6_release(sock); +} + static const struct proto_ops mptcp_v6_stream_ops = { .family = PF_INET6, .owner = THIS_MODULE, - .release = inet6_release, + .release = mptcp6_release, .bind = mptcp_bind, .connect = mptcp_stream_connect, .socketpair = sock_no_socketpair, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 06e233410e0e..e1fbcab257e6 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1096,6 +1096,12 @@ static void subflow_data_ready(struct sock *sk) msk = mptcp_sk(parent); if (state & TCPF_LISTEN) { + /* MPJ subflow are removed from accept queue before reaching here, + * avoid stray wakeups + */ + if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) + return; + set_bit(MPTCP_DATA_READY, &msk->flags); parent->sk_data_ready(parent); return; diff --git a/net/qrtr/tun.c b/net/qrtr/tun.c index b238c40a9984..304b41fea5ab 100644 --- a/net/qrtr/tun.c +++ b/net/qrtr/tun.c @@ -31,6 +31,7 @@ static int qrtr_tun_send(struct qrtr_endpoint *ep, struct sk_buff *skb) static int qrtr_tun_open(struct inode *inode, struct file *filp) { struct qrtr_tun *tun; + int ret; tun = kzalloc(sizeof(*tun), GFP_KERNEL); if (!tun) @@ -43,7 +44,16 @@ static int qrtr_tun_open(struct inode *inode, struct file *filp) filp->private_data = tun; - return qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO); + ret = qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO); + if (ret) + goto out; + + return 0; + +out: + filp->private_data = NULL; + kfree(tun); + return ret; } static ssize_t qrtr_tun_read_iter(struct kiocb *iocb, struct iov_iter *to) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 2409e522c68f..d097b5c15faa 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1417,6 +1417,21 @@ static int fl_validate_ct_state(u16 state, struct nlattr *tb, return -EINVAL; } + if (state & TCA_FLOWER_KEY_CT_FLAGS_INVALID && + state & ~(TCA_FLOWER_KEY_CT_FLAGS_TRACKED | + TCA_FLOWER_KEY_CT_FLAGS_INVALID)) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "when inv is set, only trk may be set"); + return -EINVAL; + } + + if (state & TCA_FLOWER_KEY_CT_FLAGS_NEW && + state & TCA_FLOWER_KEY_CT_FLAGS_REPLY) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "new and rpl are mutually exclusive"); + return -EINVAL; + } + return 0; } diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 74c69b75f6f5..7ed7cd95e58f 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -39,7 +39,7 @@ ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; } ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; } ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; } sleep() { read -t "$1" -N 1 || true; } -waitiperf() { pretty "${1//*-}" "wait for iperf:5201 pid $2"; while [[ $(ss -N "$1" -tlpH 'sport = 5201') != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; } +waitiperf() { pretty "${1//*-}" "wait for iperf:${3:-5201} pid $2"; while [[ $(ss -N "$1" -tlpH "sport = ${3:-5201}") != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; } waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; } waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; } @@ -141,6 +141,19 @@ tests() { n2 iperf3 -s -1 -B fd00::2 & waitiperf $netns2 $! n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2 + + # TCP over IPv4, in parallel + for max in 4 5 50; do + local pids=( ) + for ((i=0; i < max; ++i)) do + n2 iperf3 -p $(( 5200 + i )) -s -1 -B 192.168.241.2 & + pids+=( $! ); waitiperf $netns2 $! $(( 5200 + i )) + done + for ((i=0; i < max; ++i)) do + n1 iperf3 -Z -t 3 -p $(( 5200 + i )) -c 192.168.241.2 & + done + wait "${pids[@]}" + done } [[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}" |