diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-03-26 19:53:08 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-03-26 19:53:08 +0300 |
| commit | 453a4a5f97f0c95b7df458e6afb98d4ab057d90b (patch) | |
| tree | 449a7729af6ab59137da209abd37d11a97303ac7 | |
| parent | 75c78a4faa7efe3180d1ba4b323464e30f948a43 (diff) | |
| parent | db472c34a74770f39318ddb1efa986c0a8d5d86a (diff) | |
| download | linux-453a4a5f97f0c95b7df458e6afb98d4ab057d90b.tar.xz | |
Merge tag 'net-7.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni:
"Including fixes from Bluetooth, CAN, IPsec and Netfilter.
Notably, this includes the fix for the Bluetooth regression that you
were notified about. I'm not aware of any other pending regressions.
Current release - regressions:
- bluetooth:
- fix stack-out-of-bounds read in l2cap_ecred_conn_req
- fix regressions caused by reusing ident
- netfilter: revisit array resize logic
- eth: ice: set max queues in alloc_etherdev_mqs()
Previous releases - regressions:
- core: correctly handle tunneled traffic on IPV6_CSUM GSO fallback
- bluetooth:
- fix dangling pointer on mgmt_add_adv_patterns_monitor_complete
- fix deadlock in l2cap_conn_del()
- sched: codel: fix stale state for empty flows in fq_codel
- ipv6: remove permanent routes from tb6_gc_hlist when all exceptions expire.
- xfrm: fix skb_put() panic on non-linear skb during reassembly
- openvswitch:
- avoid releasing netdev before teardown completes
- validate MPLS set/set_masked payload length
- eth: iavf: fix out-of-bounds writes in iavf_get_ethtool_stats()
Previous releases - always broken:
- bluetooth: fix null-ptr-deref on l2cap_sock_ready_cb
- udp: fix wildcard bind conflict check when using hash2
- netfilter: fix use of uninitialized rtp_addr in process_sdp
- tls: Purge async_hold in tls_decrypt_async_wait()
- xfrm:
- prevent policy_hthresh.work from racing with netns teardown
- fix skb leak with espintcp and async crypto
- smc: fix double-free of smc_spd_priv when tee() duplicates splice pipe buffer
- can:
- add missing error handling to call can_ctrlmode_changelink()
- fix OOB heap access in cgw_csum_crc8_rel()
- eth:
- mana: fix use-after-free in add_adev() error path
- virtio-net: fix for VIRTIO_NET_F_GUEST_HDRLEN
- bcmasp: fix double free of WoL irq"
* tag 'net-7.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (90 commits)
net: macb: use the current queue number for stats
netfilter: ctnetlink: use netlink policy range checks
netfilter: nf_conntrack_sip: fix use of uninitialized rtp_addr in process_sdp
netfilter: nf_conntrack_expect: skip expectations in other netns via proc
netfilter: nf_conntrack_expect: store netns and zone in expectation
netfilter: ctnetlink: ensure safe access to master conntrack
netfilter: nf_conntrack_expect: use expect->helper
netfilter: nf_conntrack_expect: honor expectation helper field
netfilter: nft_set_rbtree: revisit array resize logic
netfilter: ip6t_rt: reject oversized addrnr in rt_mt6_check()
netfilter: nfnetlink_log: fix uninitialized padding leak in NFULA_PAYLOAD
tls: Purge async_hold in tls_decrypt_async_wait()
selftests: netfilter: nft_concat_range.sh: add check for flush+reload bug
netfilter: nft_set_pipapo_avx2: don't return non-matching entry on expiry
Bluetooth: btusb: clamp SCO altsetting table indices
Bluetooth: L2CAP: Fix ERTM re-init and zero pdu_len infinite loop
Bluetooth: L2CAP: Fix deadlock in l2cap_conn_del()
Bluetooth: btintel: serialize btintel_hw_error() with hci_req_sync_lock
Bluetooth: L2CAP: Fix send LE flow credits in ACL link
net: mana: fix use-after-free in add_adev() error path
...
86 files changed, 1057 insertions, 387 deletions
diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 246b6205c5e0..ab146894ba4e 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -251,11 +251,13 @@ void btintel_hw_error(struct hci_dev *hdev, u8 code) bt_dev_err(hdev, "Hardware error 0x%2.2x", code); + hci_req_sync_lock(hdev); + skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { bt_dev_err(hdev, "Reset after hardware error failed (%ld)", PTR_ERR(skb)); - return; + goto unlock; } kfree_skb(skb); @@ -263,18 +265,21 @@ void btintel_hw_error(struct hci_dev *hdev, u8 code) if (IS_ERR(skb)) { bt_dev_err(hdev, "Retrieving Intel exception info failed (%ld)", PTR_ERR(skb)); - return; + goto unlock; } if (skb->len != 13) { bt_dev_err(hdev, "Exception info size mismatch"); kfree_skb(skb); - return; + goto unlock; } bt_dev_err(hdev, "Exception info %s", (char *)(skb->data + 1)); kfree_skb(skb); + +unlock: + hci_req_sync_unlock(hdev); } EXPORT_SYMBOL_GPL(btintel_hw_error); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index a1c5eb993e47..5c535f3ab722 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -2376,8 +2376,11 @@ static void btusb_work(struct work_struct *work) if (data->air_mode == HCI_NOTIFY_ENABLE_SCO_CVSD) { if (hdev->voice_setting & 0x0020) { static const int alts[3] = { 2, 4, 5 }; + unsigned int sco_idx; - new_alts = alts[data->sco_num - 1]; + sco_idx = min_t(unsigned int, data->sco_num - 1, + ARRAY_SIZE(alts) - 1); + new_alts = alts[sco_idx]; } else { new_alts = data->sco_num; } diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c index 91acf24f1ef5..91c96ad12342 100644 --- a/drivers/bluetooth/hci_ll.c +++ b/drivers/bluetooth/hci_ll.c @@ -541,6 +541,8 @@ static int download_firmware(struct ll_device *lldev) if (err || !fw->data || !fw->size) { bt_dev_err(lldev->hu.hdev, "request_firmware failed(errno %d) for %s", err, bts_scr_name); + if (!err) + release_firmware(fw); return -EINVAL; } ptr = (void *)fw->data; diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 0498198a4696..766d455950f5 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -601,7 +601,9 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], /* We need synchronization with dev->stop() */ ASSERT_RTNL(); - can_ctrlmode_changelink(dev, data, extack); + err = can_ctrlmode_changelink(dev, data, extack); + if (err) + return err; if (data[IFLA_CAN_BITTIMING]) { struct can_bittiming bt; diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index bb7782582f40..0d0190ae094a 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -1225,7 +1225,11 @@ static int mcp251x_open(struct net_device *net) } mutex_lock(&priv->mcp_lock); - mcp251x_power_enable(priv->transceiver, 1); + ret = mcp251x_power_enable(priv->transceiver, 1); + if (ret) { + dev_err(&spi->dev, "failed to enable transceiver power: %pe\n", ERR_PTR(ret)); + goto out_close_candev; + } priv->force_quit = 0; priv->tx_skb = NULL; @@ -1272,6 +1276,7 @@ out_free_irq: mcp251x_hw_sleep(spi); out_close: mcp251x_power_enable(priv->transceiver, 0); +out_close_candev: close_candev(net); mutex_unlock(&priv->mcp_lock); if (release_irq) @@ -1516,11 +1521,25 @@ static int __maybe_unused mcp251x_can_resume(struct device *dev) { struct spi_device *spi = to_spi_device(dev); struct mcp251x_priv *priv = spi_get_drvdata(spi); + int ret = 0; - if (priv->after_suspend & AFTER_SUSPEND_POWER) - mcp251x_power_enable(priv->power, 1); - if (priv->after_suspend & AFTER_SUSPEND_UP) - mcp251x_power_enable(priv->transceiver, 1); + if (priv->after_suspend & AFTER_SUSPEND_POWER) { + ret = mcp251x_power_enable(priv->power, 1); + if (ret) { + dev_err(dev, "failed to restore power: %pe\n", ERR_PTR(ret)); + return ret; + } + } + + if (priv->after_suspend & AFTER_SUSPEND_UP) { + ret = mcp251x_power_enable(priv->transceiver, 1); + if (ret) { + dev_err(dev, "failed to restore transceiver power: %pe\n", ERR_PTR(ret)); + if (priv->after_suspend & AFTER_SUSPEND_POWER) + mcp251x_power_enable(priv->power, 0); + return ret; + } + } if (priv->after_suspend & (AFTER_SUSPEND_POWER | AFTER_SUSPEND_UP)) queue_work(priv->wq, &priv->restart_work); diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 42dbe8f93231..5724f8f2defd 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -227,7 +227,9 @@ static int airoha_ppe_get_wdma_info(struct net_device *dev, const u8 *addr, if (!dev) return -ENODEV; + rcu_read_lock(); err = dev_fill_forward_path(dev, addr, &stack); + rcu_read_unlock(); if (err) return err; diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index cd7dddeb91dd..9787c1857e13 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -25,7 +25,7 @@ config B44 select SSB select MII select PHYLIB - select FIXED_PHY if BCM47XX + select FIXED_PHY help If you have a network (Ethernet) controller of this type, say Y or M here. diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c index aa6d8606849f..972474893a6b 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c @@ -1152,12 +1152,6 @@ void bcmasp_enable_wol(struct bcmasp_intf *intf, bool en) } } -static void bcmasp_wol_irq_destroy(struct bcmasp_priv *priv) -{ - if (priv->wol_irq > 0) - free_irq(priv->wol_irq, priv); -} - static void bcmasp_eee_fixup(struct bcmasp_intf *intf, bool en) { u32 reg, phy_lpi_overwrite; @@ -1255,7 +1249,7 @@ static int bcmasp_probe(struct platform_device *pdev) if (priv->irq <= 0) return -EINVAL; - priv->clk = devm_clk_get_optional_enabled(dev, "sw_asp"); + priv->clk = devm_clk_get_optional(dev, "sw_asp"); if (IS_ERR(priv->clk)) return dev_err_probe(dev, PTR_ERR(priv->clk), "failed to request clock\n"); @@ -1283,6 +1277,10 @@ static int bcmasp_probe(struct platform_device *pdev) bcmasp_set_pdata(priv, pdata); + ret = clk_prepare_enable(priv->clk); + if (ret) + return dev_err_probe(dev, ret, "failed to start clock\n"); + /* Enable all clocks to ensure successful probing */ bcmasp_core_clock_set(priv, ASP_CTRL_CLOCK_CTRL_ASP_ALL_DISABLE, 0); @@ -1294,8 +1292,10 @@ static int bcmasp_probe(struct platform_device *pdev) ret = devm_request_irq(&pdev->dev, priv->irq, bcmasp_isr, 0, pdev->name, priv); - if (ret) - return dev_err_probe(dev, ret, "failed to request ASP interrupt: %d", ret); + if (ret) { + dev_err(dev, "Failed to request ASP interrupt: %d", ret); + goto err_clock_disable; + } /* Register mdio child nodes */ of_platform_populate(dev->of_node, bcmasp_mdio_of_match, NULL, dev); @@ -1307,13 +1307,17 @@ static int bcmasp_probe(struct platform_device *pdev) priv->mda_filters = devm_kcalloc(dev, priv->num_mda_filters, sizeof(*priv->mda_filters), GFP_KERNEL); - if (!priv->mda_filters) - return -ENOMEM; + if (!priv->mda_filters) { + ret = -ENOMEM; + goto err_clock_disable; + } priv->net_filters = devm_kcalloc(dev, priv->num_net_filters, sizeof(*priv->net_filters), GFP_KERNEL); - if (!priv->net_filters) - return -ENOMEM; + if (!priv->net_filters) { + ret = -ENOMEM; + goto err_clock_disable; + } bcmasp_core_init_filters(priv); @@ -1322,7 +1326,8 @@ static int bcmasp_probe(struct platform_device *pdev) ports_node = of_find_node_by_name(dev->of_node, "ethernet-ports"); if (!ports_node) { dev_warn(dev, "No ports found\n"); - return -EINVAL; + ret = -EINVAL; + goto err_clock_disable; } i = 0; @@ -1344,8 +1349,6 @@ static int bcmasp_probe(struct platform_device *pdev) */ bcmasp_core_clock_set(priv, 0, ASP_CTRL_CLOCK_CTRL_ASP_ALL_DISABLE); - clk_disable_unprepare(priv->clk); - /* Now do the registration of the network ports which will take care * of managing the clock properly. */ @@ -1358,13 +1361,16 @@ static int bcmasp_probe(struct platform_device *pdev) count++; } + clk_disable_unprepare(priv->clk); + dev_info(dev, "Initialized %d port(s)\n", count); return ret; err_cleanup: - bcmasp_wol_irq_destroy(priv); bcmasp_remove_intfs(priv); +err_clock_disable: + clk_disable_unprepare(priv->clk); return ret; } @@ -1376,7 +1382,6 @@ static void bcmasp_remove(struct platform_device *pdev) if (!priv) return; - bcmasp_wol_irq_destroy(priv); bcmasp_remove_intfs(priv); } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index c16ac9c76aa3..99e7d5cf3786 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1071,7 +1071,7 @@ static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb, int budge } if (tx_skb->skb) { - napi_consume_skb(tx_skb->skb, budget); + dev_consume_skb_any(tx_skb->skb); tx_skb->skb = NULL; } } @@ -3224,7 +3224,7 @@ static void gem_get_ethtool_stats(struct net_device *dev, spin_lock_irq(&bp->stats_lock); gem_update_stats(bp); memcpy(data, &bp->ethtool_stats, sizeof(u64) - * (GEM_STATS_LEN + QUEUE_STATS_LEN * MACB_MAX_QUEUES)); + * (GEM_STATS_LEN + QUEUE_STATS_LEN * bp->num_queues)); spin_unlock_irq(&bp->stats_lock); } @@ -5776,9 +5776,9 @@ static int __maybe_unused macb_suspend(struct device *dev) struct macb_queue *queue; struct in_device *idev; unsigned long flags; + u32 tmp, ifa_local; unsigned int q; int err; - u32 tmp; if (!device_may_wakeup(&bp->dev->dev)) phy_exit(bp->phy); @@ -5787,14 +5787,21 @@ static int __maybe_unused macb_suspend(struct device *dev) return 0; if (bp->wol & MACB_WOL_ENABLED) { - /* Check for IP address in WOL ARP mode */ - idev = __in_dev_get_rcu(bp->dev); - if (idev) - ifa = rcu_dereference(idev->ifa_list); - if ((bp->wolopts & WAKE_ARP) && !ifa) { - netdev_err(netdev, "IP address not assigned as required by WoL walk ARP\n"); - return -EOPNOTSUPP; + if (bp->wolopts & WAKE_ARP) { + /* Check for IP address in WOL ARP mode */ + rcu_read_lock(); + idev = __in_dev_get_rcu(bp->dev); + if (idev) + ifa = rcu_dereference(idev->ifa_list); + if (!ifa) { + rcu_read_unlock(); + netdev_err(netdev, "IP address not assigned as required by WoL walk ARP\n"); + return -EOPNOTSUPP; + } + ifa_local = be32_to_cpu(ifa->ifa_local); + rcu_read_unlock(); } + spin_lock_irqsave(&bp->lock, flags); /* Disable Tx and Rx engines before disabling the queues, @@ -5833,8 +5840,9 @@ static int __maybe_unused macb_suspend(struct device *dev) if (bp->wolopts & WAKE_ARP) { tmp |= MACB_BIT(ARP); /* write IP address into register */ - tmp |= MACB_BFEXT(IP, be32_to_cpu(ifa->ifa_local)); + tmp |= MACB_BFEXT(IP, ifa_local); } + spin_unlock_irqrestore(&bp->lock, flags); /* Change interrupt handler and * Enable WoL IRQ on queue 0 @@ -5847,11 +5855,12 @@ static int __maybe_unused macb_suspend(struct device *dev) dev_err(dev, "Unable to request IRQ %d (error %d)\n", bp->queues[0].irq, err); - spin_unlock_irqrestore(&bp->lock, flags); return err; } + spin_lock_irqsave(&bp->lock, flags); queue_writel(bp->queues, IER, GEM_BIT(WOL)); gem_writel(bp, WOL, tmp); + spin_unlock_irqrestore(&bp->lock, flags); } else { err = devm_request_irq(dev, bp->queues[0].irq, macb_wol_interrupt, IRQF_SHARED, netdev->name, bp->queues); @@ -5859,13 +5868,13 @@ static int __maybe_unused macb_suspend(struct device *dev) dev_err(dev, "Unable to request IRQ %d (error %d)\n", bp->queues[0].irq, err); - spin_unlock_irqrestore(&bp->lock, flags); return err; } + spin_lock_irqsave(&bp->lock, flags); queue_writel(bp->queues, IER, MACB_BIT(WOL)); macb_writel(bp, WOL, tmp); + spin_unlock_irqrestore(&bp->lock, flags); } - spin_unlock_irqrestore(&bp->lock, flags); enable_irq_wake(bp->queues[0].irq); } @@ -5932,6 +5941,8 @@ static int __maybe_unused macb_resume(struct device *dev) queue_readl(bp->queues, ISR); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) queue_writel(bp->queues, ISR, -1); + spin_unlock_irqrestore(&bp->lock, flags); + /* Replace interrupt handler on queue 0 */ devm_free_irq(dev, bp->queues[0].irq, bp->queues); err = devm_request_irq(dev, bp->queues[0].irq, macb_interrupt, @@ -5940,10 +5951,8 @@ static int __maybe_unused macb_resume(struct device *dev) dev_err(dev, "Unable to request IRQ %d (error %d)\n", bp->queues[0].irq, err); - spin_unlock_irqrestore(&bp->lock, flags); return err; } - spin_unlock_irqrestore(&bp->lock, flags); disable_irq_wake(bp->queues[0].irq); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index fed89d4f1e1d..2fe140ddebb2 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -813,6 +813,8 @@ static void enetc_get_ringparam(struct net_device *ndev, { struct enetc_ndev_priv *priv = netdev_priv(ndev); + ring->rx_max_pending = priv->rx_bd_count; + ring->tx_max_pending = priv->tx_bd_count; ring->rx_pending = priv->rx_bd_count; ring->tx_pending = priv->tx_bd_count; diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index ab67c709d5a0..1cd1f3f2930a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -313,14 +313,13 @@ static int iavf_get_sset_count(struct net_device *netdev, int sset) { /* Report the maximum number queues, even if not every queue is * currently configured. Since allocation of queues is in pairs, - * use netdev->real_num_tx_queues * 2. The real_num_tx_queues is set - * at device creation and never changes. + * use netdev->num_tx_queues * 2. The num_tx_queues is set at + * device creation and never changes. */ if (sset == ETH_SS_STATS) return IAVF_STATS_LEN + - (IAVF_QUEUE_STATS_LEN * 2 * - netdev->real_num_tx_queues); + (IAVF_QUEUE_STATS_LEN * 2 * netdev->num_tx_queues); else return -EINVAL; } @@ -345,19 +344,19 @@ static void iavf_get_ethtool_stats(struct net_device *netdev, iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats); rcu_read_lock(); - /* As num_active_queues describe both tx and rx queues, we can use - * it to iterate over rings' stats. + /* Use num_tx_queues to report stats for the maximum number of queues. + * Queues beyond num_active_queues will report zero. */ - for (i = 0; i < adapter->num_active_queues; i++) { - struct iavf_ring *ring; + for (i = 0; i < netdev->num_tx_queues; i++) { + struct iavf_ring *tx_ring = NULL, *rx_ring = NULL; - /* Tx rings stats */ - ring = &adapter->tx_rings[i]; - iavf_add_queue_stats(&data, ring); + if (i < adapter->num_active_queues) { + tx_ring = &adapter->tx_rings[i]; + rx_ring = &adapter->rx_rings[i]; + } - /* Rx rings stats */ - ring = &adapter->rx_rings[i]; - iavf_add_queue_stats(&data, ring); + iavf_add_queue_stats(&data, tx_ring); + iavf_add_queue_stats(&data, rx_ring); } rcu_read_unlock(); } @@ -376,9 +375,9 @@ static void iavf_get_stat_strings(struct net_device *netdev, u8 *data) iavf_add_stat_strings(&data, iavf_gstrings_stats); /* Queues are always allocated in pairs, so we just use - * real_num_tx_queues for both Tx and Rx queues. + * num_tx_queues for both Tx and Rx queues. */ - for (i = 0; i < netdev->real_num_tx_queues; i++) { + for (i = 0; i < netdev->num_tx_queues; i++) { iavf_add_stat_strings(&data, iavf_gstrings_queue_stats, "tx", i); iavf_add_stat_strings(&data, iavf_gstrings_queue_stats, diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 2b2b22af42be..eb3a48330cc1 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -840,6 +840,28 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid) } /** + * ice_get_max_txq - return the maximum number of Tx queues for in a PF + * @pf: PF structure + * + * Return: maximum number of Tx queues + */ +static inline int ice_get_max_txq(struct ice_pf *pf) +{ + return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_txq); +} + +/** + * ice_get_max_rxq - return the maximum number of Rx queues for in a PF + * @pf: PF structure + * + * Return: maximum number of Rx queues + */ +static inline int ice_get_max_rxq(struct ice_pf *pf) +{ + return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_rxq); +} + +/** * ice_get_main_vsi - Get the PF VSI * @pf: PF instance * diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 301947d53ede..e6a20af6f63d 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1930,6 +1930,17 @@ __ice_get_ethtool_stats(struct net_device *netdev, int i = 0; char *p; + if (ice_is_port_repr_netdev(netdev)) { + ice_update_eth_stats(vsi); + + for (j = 0; j < ICE_VSI_STATS_LEN; j++) { + p = (char *)vsi + ice_gstrings_vsi_stats[j].stat_offset; + data[i++] = (ice_gstrings_vsi_stats[j].sizeof_stat == + sizeof(u64)) ? *(u64 *)p : *(u32 *)p; + } + return; + } + ice_update_pf_stats(pf); ice_update_vsi_stats(vsi); @@ -1939,9 +1950,6 @@ __ice_get_ethtool_stats(struct net_device *netdev, sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } - if (ice_is_port_repr_netdev(netdev)) - return; - /* populate per queue stats */ rcu_read_lock(); @@ -3774,24 +3782,6 @@ ice_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) } /** - * ice_get_max_txq - return the maximum number of Tx queues for in a PF - * @pf: PF structure - */ -static int ice_get_max_txq(struct ice_pf *pf) -{ - return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_txq); -} - -/** - * ice_get_max_rxq - return the maximum number of Rx queues for in a PF - * @pf: PF structure - */ -static int ice_get_max_rxq(struct ice_pf *pf) -{ - return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_rxq); -} - -/** * ice_get_combined_cnt - return the current number of combined channels * @vsi: PF VSI pointer * diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index e7308e381e2f..3c36e3641b9e 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4699,8 +4699,8 @@ static int ice_cfg_netdev(struct ice_vsi *vsi) struct net_device *netdev; u8 mac_addr[ETH_ALEN]; - netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq, - vsi->alloc_rxq); + netdev = alloc_etherdev_mqs(sizeof(*np), ice_get_max_txq(vsi->back), + ice_get_max_rxq(vsi->back)); if (!netdev) return -ENOMEM; diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index 90f99443a922..096566c697f4 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -2,6 +2,7 @@ /* Copyright (C) 2019-2021, Intel Corporation. */ #include "ice.h" +#include "ice_lib.h" #include "ice_eswitch.h" #include "devlink/devlink.h" #include "devlink/port.h" @@ -67,7 +68,7 @@ ice_repr_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) return; vsi = repr->src_vsi; - ice_update_vsi_stats(vsi); + ice_update_eth_stats(vsi); eth_stats = &vsi->eth_stats; stats->tx_packets = eth_stats->tx_unicast + eth_stats->tx_broadcast + @@ -315,7 +316,7 @@ ice_repr_reg_netdev(struct net_device *netdev, const struct net_device_ops *ops) static int ice_repr_ready_vf(struct ice_repr *repr) { - return !ice_check_vf_ready_for_cfg(repr->vf); + return ice_check_vf_ready_for_cfg(repr->vf); } static int ice_repr_ready_sf(struct ice_repr *repr) diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h index b206fba092c8..ec1b75f039bb 100644 --- a/drivers/net/ethernet/intel/idpf/idpf.h +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -1066,7 +1066,7 @@ bool idpf_vport_set_hsplit(const struct idpf_vport *vport, u8 val); int idpf_idc_init(struct idpf_adapter *adapter); int idpf_idc_init_aux_core_dev(struct idpf_adapter *adapter, enum iidc_function_type ftype); -void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info); +void idpf_idc_deinit_core_aux_device(struct idpf_adapter *adapter); void idpf_idc_deinit_vport_aux_device(struct iidc_rdma_vport_dev_info *vdev_info); void idpf_idc_issue_reset_event(struct iidc_rdma_core_dev_info *cdev_info); void idpf_idc_vdev_mtu_event(struct iidc_rdma_vport_dev_info *vdev_info, diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c index bd4785fb8d3e..7e4f4ac92653 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_idc.c +++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c @@ -470,10 +470,11 @@ err_privd_alloc: /** * idpf_idc_deinit_core_aux_device - de-initialize Auxiliary Device(s) - * @cdev_info: IDC core device info pointer + * @adapter: driver private data structure */ -void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info) +void idpf_idc_deinit_core_aux_device(struct idpf_adapter *adapter) { + struct iidc_rdma_core_dev_info *cdev_info = adapter->cdev_info; struct iidc_rdma_priv_dev_info *privd; if (!cdev_info) @@ -485,6 +486,7 @@ void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info) kfree(privd->mapped_mem_regions); kfree(privd); kfree(cdev_info); + adapter->cdev_info = NULL; } /** diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 252259993022..f6b3b15364ff 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -1860,13 +1860,13 @@ static int idpf_rxq_group_alloc(struct idpf_vport *vport, idpf_queue_assign(HSPLIT_EN, q, hs); idpf_queue_assign(RSC_EN, q, rsc); - bufq_set->num_refillqs = num_rxq; bufq_set->refillqs = kcalloc(num_rxq, swq_size, GFP_KERNEL); if (!bufq_set->refillqs) { err = -ENOMEM; goto err_alloc; } + bufq_set->num_refillqs = num_rxq; for (unsigned int k = 0; k < bufq_set->num_refillqs; k++) { struct idpf_sw_queue *refillq = &bufq_set->refillqs[k]; diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index d5a877e1fef8..113ecfc16dd7 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -3668,7 +3668,7 @@ void idpf_vc_core_deinit(struct idpf_adapter *adapter) idpf_ptp_release(adapter); idpf_deinit_task(adapter); - idpf_idc_deinit_core_aux_device(adapter->cdev_info); + idpf_idc_deinit_core_aux_device(adapter); idpf_rel_rx_pt_lkup(adapter); idpf_intr_rel(adapter); diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index a3845edf0e48..f0b5dd752f08 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -3053,6 +3053,11 @@ static void lan743x_phylink_mac_link_up(struct phylink_config *config, else if (speed == SPEED_100) mac_cr |= MAC_CR_CFG_L_; + if (duplex == DUPLEX_FULL) + mac_cr |= MAC_CR_DPX_; + else + mac_cr &= ~MAC_CR_DPX_; + lan743x_csr_write(adapter, MAC_CR, mac_cr); lan743x_ptp_update_latency(adapter, speed); diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 9017e806ecda..dca62fb9a3a9 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -3425,6 +3425,7 @@ static int add_adev(struct gdma_dev *gd, const char *name) struct auxiliary_device *adev; struct mana_adev *madev; int ret; + int id; madev = kzalloc_obj(*madev); if (!madev) @@ -3434,7 +3435,8 @@ static int add_adev(struct gdma_dev *gd, const char *name) ret = mana_adev_idx_alloc(); if (ret < 0) goto idx_fail; - adev->id = ret; + id = ret; + adev->id = id; adev->name = name; adev->dev.parent = gd->gdma_context->dev; @@ -3460,7 +3462,7 @@ add_fail: auxiliary_device_uninit(adev); init_fail: - mana_adev_idx_free(adev->id); + mana_adev_idx_free(id); idx_fail: kfree(madev); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 8d040e611d5a..637e635bbf03 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1719,13 +1719,18 @@ static int ionic_set_mac_address(struct net_device *netdev, void *sa) if (ether_addr_equal(netdev->dev_addr, mac)) return 0; - err = ionic_program_mac(lif, mac); - if (err < 0) - return err; + /* Only program macs for virtual functions to avoid losing the permanent + * Mac across warm reset/reboot. + */ + if (lif->ionic->pdev->is_virtfn) { + err = ionic_program_mac(lif, mac); + if (err < 0) + return err; - if (err > 0) - netdev_dbg(netdev, "%s: SET and GET ATTR Mac are not equal-due to old FW running\n", - __func__); + if (err > 0) + netdev_dbg(netdev, "%s: SET and GET ATTR Mac are not equal-due to old FW running\n", + __func__); + } err = eth_prepare_mac_addr_change(netdev, addr); if (err) diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c index 0a3cf2f848a5..fd4e7622f123 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_common.c +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c @@ -962,7 +962,6 @@ static int emac_rx_packet_zc(struct prueth_emac *emac, u32 flow_id, pkt_len -= 4; cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL); psdata = cppi5_hdesc_get_psdata(desc_rx); - k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); count++; xsk_buff_set_size(xdp, pkt_len); xsk_buff_dma_sync_for_cpu(xdp); @@ -988,6 +987,7 @@ static int emac_rx_packet_zc(struct prueth_emac *emac, u32 flow_id, emac_dispatch_skb_zc(emac, xdp, psdata); xsk_buff_free(xdp); } + k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); } if (xdp_status & ICSSG_XDP_REDIR) @@ -1057,7 +1057,6 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id, u32 *xdp_state) /* firmware adds 4 CRC bytes, strip them */ pkt_len -= 4; cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL); - k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); /* if allocation fails we drop the packet but push the * descriptor back to the ring with old page to prevent a stall @@ -1115,6 +1114,7 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id, u32 *xdp_state) ndev->stats.rx_packets++; requeue: + k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); /* queue another RX DMA */ ret = prueth_dma_rx_push_mapped(emac, &emac->rx_chns, new_page, PRUETH_MAX_PKT_SIZE); diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index b7282f5c9632..120aeb539d9f 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -2058,6 +2058,68 @@ static const struct ethtool_ops team_ethtool_ops = { * rt netlink interface ***********************/ +/* For tx path we need a linkup && enabled port and for parse any port + * suffices. + */ +static struct team_port *team_header_port_get_rcu(struct team *team, + bool txable) +{ + struct team_port *port; + + list_for_each_entry_rcu(port, &team->port_list, list) { + if (!txable || team_port_txable(port)) + return port; + } + + return NULL; +} + +static int team_header_create(struct sk_buff *skb, struct net_device *team_dev, + unsigned short type, const void *daddr, + const void *saddr, unsigned int len) +{ + struct team *team = netdev_priv(team_dev); + const struct header_ops *port_ops; + struct team_port *port; + int ret = 0; + + rcu_read_lock(); + port = team_header_port_get_rcu(team, true); + if (port) { + port_ops = READ_ONCE(port->dev->header_ops); + if (port_ops && port_ops->create) + ret = port_ops->create(skb, port->dev, + type, daddr, saddr, len); + } + rcu_read_unlock(); + return ret; +} + +static int team_header_parse(const struct sk_buff *skb, + const struct net_device *team_dev, + unsigned char *haddr) +{ + struct team *team = netdev_priv(team_dev); + const struct header_ops *port_ops; + struct team_port *port; + int ret = 0; + + rcu_read_lock(); + port = team_header_port_get_rcu(team, false); + if (port) { + port_ops = READ_ONCE(port->dev->header_ops); + if (port_ops && port_ops->parse) + ret = port_ops->parse(skb, port->dev, haddr); + } + rcu_read_unlock(); + return ret; +} + +static const struct header_ops team_header_ops = { + .create = team_header_create, + .parse = team_header_parse, +}; + static void team_setup_by_port(struct net_device *dev, struct net_device *port_dev) { @@ -2066,7 +2128,8 @@ static void team_setup_by_port(struct net_device *dev, if (port_dev->type == ARPHRD_ETHER) dev->header_ops = team->header_ops_cache; else - dev->header_ops = port_dev->header_ops; + dev->header_ops = port_dev->header_ops ? + &team_header_ops : NULL; dev->type = port_dev->type; dev->hard_header_len = port_dev->hard_header_len; dev->needed_headroom = port_dev->needed_headroom; diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h index a5f93b6c4482..fa5cab9d3e55 100644 --- a/drivers/net/tun_vnet.h +++ b/drivers/net/tun_vnet.h @@ -244,7 +244,7 @@ tun_vnet_hdr_tnl_from_skb(unsigned int flags, if (virtio_net_hdr_tnl_from_skb(skb, tnl_hdr, has_tnl_offload, tun_vnet_is_little_endian(flags), - vlan_hlen, true)) { + vlan_hlen, true, false)) { struct virtio_net_hdr_v1 *hdr = &tnl_hdr->hash_hdr.hdr; struct skb_shared_info *sinfo = skb_shinfo(skb); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 72d6a9c6a5a2..ab2108ee206a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3267,8 +3267,12 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan) struct virtio_net_hdr_v1_hash_tunnel *hdr; int num_sg; unsigned hdr_len = vi->hdr_len; + bool feature_hdrlen; bool can_push; + feature_hdrlen = virtio_has_feature(vi->vdev, + VIRTIO_NET_F_GUEST_HDRLEN); + pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest); /* Make sure it's safe to cast between formats */ @@ -3288,7 +3292,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan) if (virtio_net_hdr_tnl_from_skb(skb, hdr, vi->tx_tnl, virtio_is_little_endian(vi->vdev), 0, - false)) + false, feature_hdrlen)) return -EPROTO; if (vi->mergeable_rx_bufs) @@ -3351,6 +3355,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) /* Don't wait up for transmitted skbs to be freed. */ if (!use_napi) { skb_orphan(skb); + skb_dst_drop(skb); nf_reset_ct(skb); } diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 75dabb763c65..f36d21b5bc19 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -207,6 +207,39 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, return __virtio_net_hdr_to_skb(skb, hdr, little_endian, hdr->gso_type); } +/* This function must be called after virtio_net_hdr_from_skb(). */ +static inline void __virtio_net_set_hdrlen(const struct sk_buff *skb, + struct virtio_net_hdr *hdr, + bool little_endian) +{ + u16 hdr_len; + + hdr_len = skb_transport_offset(skb); + + if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4) + hdr_len += sizeof(struct udphdr); + else + hdr_len += tcp_hdrlen(skb); + + hdr->hdr_len = __cpu_to_virtio16(little_endian, hdr_len); +} + +/* This function must be called after virtio_net_hdr_from_skb(). */ +static inline void __virtio_net_set_tnl_hdrlen(const struct sk_buff *skb, + struct virtio_net_hdr *hdr) +{ + u16 hdr_len; + + hdr_len = skb_inner_transport_offset(skb); + + if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4) + hdr_len += sizeof(struct udphdr); + else + hdr_len += inner_tcp_hdrlen(skb); + + hdr->hdr_len = __cpu_to_virtio16(true, hdr_len); +} + static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, bool little_endian, @@ -385,7 +418,8 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, bool tnl_hdr_negotiated, bool little_endian, int vlan_hlen, - bool has_data_valid) + bool has_data_valid, + bool feature_hdrlen) { struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr; unsigned int inner_nh, outer_th; @@ -394,9 +428,17 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, tnl_gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM); - if (!tnl_gso_type) - return virtio_net_hdr_from_skb(skb, hdr, little_endian, - has_data_valid, vlan_hlen); + if (!tnl_gso_type) { + ret = virtio_net_hdr_from_skb(skb, hdr, little_endian, + has_data_valid, vlan_hlen); + if (ret) + return ret; + + if (feature_hdrlen && hdr->hdr_len) + __virtio_net_set_hdrlen(skb, hdr, little_endian); + + return ret; + } /* Tunnel support not negotiated but skb ask for it. */ if (!tnl_hdr_negotiated) @@ -414,6 +456,9 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, if (ret) return ret; + if (feature_hdrlen && hdr->hdr_len) + __virtio_net_set_tnl_hdrlen(skb, hdr); + if (skb->protocol == htons(ETH_P_IPV6)) hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6; else diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 010f1a8fd15f..5172afee5494 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -658,6 +658,7 @@ struct l2cap_conn { struct sk_buff *rx_skb; __u32 rx_len; struct ida tx_ida; + __u8 tx_ident; struct sk_buff_head pending_rx; struct work_struct pending_rx_work; diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h index 78a27ac73070..b2c359c6dd1b 100644 --- a/include/net/codel_impl.h +++ b/include/net/codel_impl.h @@ -158,6 +158,7 @@ static struct sk_buff *codel_dequeue(void *ctx, bool drop; if (!skb) { + vars->first_above_time = 0; vars->dropping = false; return skb; } diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 5a979dcab538..6d936e9f2fd3 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -264,6 +264,20 @@ inet_bhashfn_portaddr(const struct inet_hashinfo *hinfo, const struct sock *sk, return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; } +static inline bool inet_use_hash2_on_bind(const struct sock *sk) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) { + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + return false; + + if (!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) + return true; + } +#endif + return sk->sk_rcv_saddr != htonl(INADDR_ANY); +} + struct inet_bind_hashbucket * inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 88b0dd4d8e09..9f8b6814a96a 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -507,12 +507,14 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt, void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int flags); +void fib6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args, + unsigned long now); void fib6_run_gc(unsigned long expires, struct net *net, bool force); - void fib6_gc_cleanup(void); int fib6_init(void); +#if IS_ENABLED(CONFIG_IPV6) /* Add the route to the gc list if it is not already there * * The callers should hold f6i->fib6_table->tb6_lock. @@ -545,6 +547,23 @@ static inline void fib6_remove_gc_list(struct fib6_info *f6i) hlist_del_init(&f6i->gc_link); } +static inline void fib6_may_remove_gc_list(struct net *net, + struct fib6_info *f6i) +{ + struct fib6_gc_args gc_args; + + if (hlist_unhashed(&f6i->gc_link)) + return; + + gc_args.timeout = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_interval); + gc_args.more = 0; + + rcu_read_lock(); + fib6_age_exceptions(f6i, &gc_args, jiffies); + rcu_read_unlock(); +} +#endif + struct ipv6_route_iter { struct seq_net_private p; struct fib6_walker w; diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 3384859a8921..8883575adcc1 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -83,6 +83,11 @@ void nf_conntrack_lock(spinlock_t *lock); extern spinlock_t nf_conntrack_expect_lock; +static inline void lockdep_nfct_expect_lock_held(void) +{ + lockdep_assert_held(&nf_conntrack_expect_lock); +} + /* ctnetlink code shared by both ctnetlink and nf_conntrack_bpf */ static inline void __nf_ct_set_timeout(struct nf_conn *ct, u64 timeout) diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 165e7a03b8e9..e9a8350e7ccf 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -22,10 +22,16 @@ struct nf_conntrack_expect { /* Hash member */ struct hlist_node hnode; + /* Network namespace */ + possible_net_t net; + /* We expect this tuple, with the following mask */ struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_mask mask; +#ifdef CONFIG_NF_CONNTRACK_ZONES + struct nf_conntrack_zone zone; +#endif /* Usage count. */ refcount_t use; @@ -40,7 +46,7 @@ struct nf_conntrack_expect { struct nf_conntrack_expect *this); /* Helper to assign to new connection */ - struct nf_conntrack_helper *helper; + struct nf_conntrack_helper __rcu *helper; /* The conntrack of the master connection */ struct nf_conn *master; @@ -62,7 +68,17 @@ struct nf_conntrack_expect { static inline struct net *nf_ct_exp_net(struct nf_conntrack_expect *exp) { - return nf_ct_net(exp->master); + return read_pnet(&exp->net); +} + +static inline bool nf_ct_exp_zone_equal_any(const struct nf_conntrack_expect *a, + const struct nf_conntrack_zone *b) +{ +#ifdef CONFIG_NF_CONNTRACK_ZONES + return a->zone.id == b->id; +#else + return true; +#endif } #define NF_CT_EXP_POLICY_NAME_LEN 16 diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 23dd647fe024..b73983a17e08 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -59,7 +59,7 @@ struct netns_xfrm { struct list_head inexact_bins; - struct sock *nlsk; + struct sock __rcu *nlsk; struct sock *nlsk_stash; u32 sysctl_aevent_etime; diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index 26071021e986..56b6b60a814f 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -159,5 +159,9 @@ enum ip_conntrack_expect_events { #define NF_CT_EXPECT_INACTIVE 0x2 #define NF_CT_EXPECT_USERSPACE 0x4 +#ifdef __KERNEL__ +#define NF_CT_EXPECT_MASK (NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE | \ + NF_CT_EXPECT_USERSPACE) +#endif #endif /* _UAPI_NF_CONNTRACK_COMMON_H */ diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 6eb59e9f2aa8..e6393f17576b 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -3095,7 +3095,7 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) * hci_connect_le serializes the connection attempts so only one * connection can be in BT_CONNECT at time. */ - if (conn->state == BT_CONNECT && hdev->req_status == HCI_REQ_PEND) { + if (conn->state == BT_CONNECT && READ_ONCE(hdev->req_status) == HCI_REQ_PEND) { switch (hci_skb_event(hdev->sent_cmd)) { case HCI_EV_CONN_COMPLETE: case HCI_EV_LE_CONN_COMPLETE: diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 31308c1de4ec..01f8ceeb1c0c 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -4126,7 +4126,7 @@ static int hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) kfree_skb(skb); } - if (hdev->req_status == HCI_REQ_PEND && + if (READ_ONCE(hdev->req_status) == HCI_REQ_PEND && !hci_dev_test_and_set_flag(hdev, HCI_CMD_PENDING)) { kfree_skb(hdev->req_skb); hdev->req_skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 3166914b0d6c..45d16639874a 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -25,11 +25,11 @@ static void hci_cmd_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, { bt_dev_dbg(hdev, "result 0x%2.2x", result); - if (hdev->req_status != HCI_REQ_PEND) + if (READ_ONCE(hdev->req_status) != HCI_REQ_PEND) return; hdev->req_result = result; - hdev->req_status = HCI_REQ_DONE; + WRITE_ONCE(hdev->req_status, HCI_REQ_DONE); /* Free the request command so it is not used as response */ kfree_skb(hdev->req_skb); @@ -167,20 +167,20 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, hci_cmd_sync_add(&req, opcode, plen, param, event, sk); - hdev->req_status = HCI_REQ_PEND; + WRITE_ONCE(hdev->req_status, HCI_REQ_PEND); err = hci_req_sync_run(&req); if (err < 0) return ERR_PTR(err); err = wait_event_interruptible_timeout(hdev->req_wait_q, - hdev->req_status != HCI_REQ_PEND, + READ_ONCE(hdev->req_status) != HCI_REQ_PEND, timeout); if (err == -ERESTARTSYS) return ERR_PTR(-EINTR); - switch (hdev->req_status) { + switch (READ_ONCE(hdev->req_status)) { case HCI_REQ_DONE: err = -bt_to_errno(hdev->req_result); break; @@ -194,7 +194,7 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, break; } - hdev->req_status = 0; + WRITE_ONCE(hdev->req_status, 0); hdev->req_result = 0; skb = hdev->req_rsp; hdev->req_rsp = NULL; @@ -665,9 +665,9 @@ void hci_cmd_sync_cancel(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); - if (hdev->req_status == HCI_REQ_PEND) { + if (READ_ONCE(hdev->req_status) == HCI_REQ_PEND) { hdev->req_result = err; - hdev->req_status = HCI_REQ_CANCELED; + WRITE_ONCE(hdev->req_status, HCI_REQ_CANCELED); queue_work(hdev->workqueue, &hdev->cmd_sync_cancel_work); } @@ -683,12 +683,12 @@ void hci_cmd_sync_cancel_sync(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); - if (hdev->req_status == HCI_REQ_PEND) { + if (READ_ONCE(hdev->req_status) == HCI_REQ_PEND) { /* req_result is __u32 so error must be positive to be properly * propagated. */ hdev->req_result = err < 0 ? -err : err; - hdev->req_status = HCI_REQ_CANCELED; + WRITE_ONCE(hdev->req_status, HCI_REQ_CANCELED); wake_up_interruptible(&hdev->req_wait_q); } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 5deb6c4f1e41..95c65fece39b 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -926,16 +926,39 @@ int l2cap_chan_check_security(struct l2cap_chan *chan, bool initiator) static int l2cap_get_ident(struct l2cap_conn *conn) { + u8 max; + int ident; + /* LE link does not support tools like l2ping so use the full range */ if (conn->hcon->type == LE_LINK) - return ida_alloc_range(&conn->tx_ida, 1, 255, GFP_ATOMIC); - + max = 255; /* Get next available identificator. * 1 - 128 are used by kernel. * 129 - 199 are reserved. * 200 - 254 are used by utilities like l2ping, etc. */ - return ida_alloc_range(&conn->tx_ida, 1, 128, GFP_ATOMIC); + else + max = 128; + + /* Allocate ident using min as last used + 1 (cyclic) */ + ident = ida_alloc_range(&conn->tx_ida, READ_ONCE(conn->tx_ident) + 1, + max, GFP_ATOMIC); + /* Force min 1 to start over */ + if (ident <= 0) { + ident = ida_alloc_range(&conn->tx_ida, 1, max, GFP_ATOMIC); + if (ident <= 0) { + /* If all idents are in use, log an error, this is + * extremely unlikely to happen and would indicate a bug + * in the code that idents are not being freed properly. + */ + BT_ERR("Unable to allocate ident: %d", ident); + return 0; + } + } + + WRITE_ONCE(conn->tx_ident, ident); + + return ident; } static void l2cap_send_acl(struct l2cap_conn *conn, struct sk_buff *skb, @@ -1748,6 +1771,9 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) BT_DBG("hcon %p conn %p, err %d", hcon, conn, err); + disable_delayed_work_sync(&conn->info_timer); + disable_delayed_work_sync(&conn->id_addr_timer); + mutex_lock(&conn->lock); kfree_skb(conn->rx_skb); @@ -1763,8 +1789,6 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) ida_destroy(&conn->tx_ida); - cancel_delayed_work_sync(&conn->id_addr_timer); - l2cap_unregister_all_users(conn); /* Force the connection to be immediately dropped */ @@ -1783,9 +1807,6 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) l2cap_chan_put(chan); } - if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) - cancel_delayed_work_sync(&conn->info_timer); - hci_chan_del(conn->hchan); conn->hchan = NULL; @@ -2377,6 +2398,9 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan, /* Remote device may have requested smaller PDUs */ pdu_len = min_t(size_t, pdu_len, chan->remote_mps); + if (!pdu_len) + return -EINVAL; + if (len <= pdu_len) { sar = L2CAP_SAR_UNSEGMENTED; sdu_len = 0; @@ -4312,14 +4336,16 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, if (test_bit(CONF_INPUT_DONE, &chan->conf_state)) { set_default_fcs(chan); - if (chan->mode == L2CAP_MODE_ERTM || - chan->mode == L2CAP_MODE_STREAMING) - err = l2cap_ertm_init(chan); + if (chan->state != BT_CONNECTED) { + if (chan->mode == L2CAP_MODE_ERTM || + chan->mode == L2CAP_MODE_STREAMING) + err = l2cap_ertm_init(chan); - if (err < 0) - l2cap_send_disconn_req(chan, -err); - else - l2cap_chan_ready(chan); + if (err < 0) + l2cap_send_disconn_req(chan, -err); + else + l2cap_chan_ready(chan); + } goto unlock; } @@ -5081,14 +5107,14 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, cmd_len -= sizeof(*req); num_scid = cmd_len / sizeof(u16); - /* Always respond with the same number of scids as in the request */ - rsp_len = cmd_len; - if (num_scid > L2CAP_ECRED_MAX_CID) { result = L2CAP_CR_LE_INVALID_PARAMS; goto response; } + /* Always respond with the same number of scids as in the request */ + rsp_len = cmd_len; + mtu = __le16_to_cpu(req->mtu); mps = __le16_to_cpu(req->mps); @@ -6607,6 +6633,10 @@ static void l2cap_chan_le_send_credits(struct l2cap_chan *chan) struct l2cap_le_credits pkt; u16 return_credits = l2cap_le_rx_credits(chan); + if (chan->mode != L2CAP_MODE_LE_FLOWCTL && + chan->mode != L2CAP_MODE_EXT_FLOWCTL) + return; + if (chan->rx_credits >= return_credits) return; @@ -6690,6 +6720,11 @@ static int l2cap_ecred_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) if (!chan->sdu) { u16 sdu_len; + if (!pskb_may_pull(skb, L2CAP_SDULEN_SIZE)) { + err = -EINVAL; + goto failed; + } + sdu_len = get_unaligned_le16(skb->data); skb_pull(skb, L2CAP_SDULEN_SIZE); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 597686790371..71e8c1b45bce 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1698,6 +1698,9 @@ static void l2cap_sock_ready_cb(struct l2cap_chan *chan) struct sock *sk = chan->data; struct sock *parent; + if (!sk) + return; + lock_sock(sk); parent = bt_sk(sk)->parent; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index d52238ce6a9a..e5f9287fb826 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -5355,7 +5355,7 @@ static void mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, * hci_adv_monitors_clear is about to be called which will take care of * freeing the adv_monitor instances. */ - if (status == -ECANCELED && !mgmt_pending_valid(hdev, cmd)) + if (status == -ECANCELED || !mgmt_pending_valid(hdev, cmd)) return; monitor = cmd->user_data; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index e7db50165879..584e059de20a 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -401,7 +401,7 @@ static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) struct sock *sk; sco_conn_lock(conn); - sk = conn->sk; + sk = sco_sock_hold(conn); sco_conn_unlock(conn); if (!sk) @@ -410,11 +410,15 @@ static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) BT_DBG("sk %p len %u", sk, skb->len); if (sk->sk_state != BT_CONNECTED) - goto drop; + goto drop_put; - if (!sock_queue_rcv_skb(sk, skb)) + if (!sock_queue_rcv_skb(sk, skb)) { + sock_put(sk); return; + } +drop_put: + sock_put(sk); drop: kfree_skb(skb); } diff --git a/net/can/af_can.c b/net/can/af_can.c index f70e2ba0aadc..7bc86b176b4d 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -469,7 +469,7 @@ int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id, rcv->can_id = can_id; rcv->mask = mask; - rcv->matches = 0; + atomic_long_set(&rcv->matches, 0); rcv->func = func; rcv->data = data; rcv->ident = ident; @@ -573,7 +573,7 @@ EXPORT_SYMBOL(can_rx_unregister); static inline void deliver(struct sk_buff *skb, struct receiver *rcv) { rcv->func(skb, rcv->data); - rcv->matches++; + atomic_long_inc(&rcv->matches); } static int can_rcv_filter(struct can_dev_rcv_lists *dev_rcv_lists, struct sk_buff *skb) diff --git a/net/can/af_can.h b/net/can/af_can.h index 22f3352c77fe..87887014f562 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -52,7 +52,7 @@ struct receiver { struct hlist_node list; canid_t can_id; canid_t mask; - unsigned long matches; + atomic_long_t matches; void (*func)(struct sk_buff *skb, void *data); void *data; char *ident; diff --git a/net/can/gw.c b/net/can/gw.c index 8ee4d67a07d3..0ec99f68aa45 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -375,10 +375,10 @@ static void cgw_csum_crc8_rel(struct canfd_frame *cf, return; if (from <= to) { - for (i = crc8->from_idx; i <= crc8->to_idx; i++) + for (i = from; i <= to; i++) crc = crc8->crctab[crc ^ cf->data[i]]; } else { - for (i = crc8->from_idx; i >= crc8->to_idx; i--) + for (i = from; i >= to; i--) crc = crc8->crctab[crc ^ cf->data[i]]; } @@ -397,7 +397,7 @@ static void cgw_csum_crc8_rel(struct canfd_frame *cf, break; } - cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; + cf->data[res] = crc ^ crc8->final_xor_val; } static void cgw_csum_crc8_pos(struct canfd_frame *cf, diff --git a/net/can/isotp.c b/net/can/isotp.c index da3b72e7afcc..2770f43f4951 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1248,12 +1248,6 @@ static int isotp_release(struct socket *sock) so->ifindex = 0; so->bound = 0; - if (so->rx.buf != so->rx.sbuf) - kfree(so->rx.buf); - - if (so->tx.buf != so->tx.sbuf) - kfree(so->tx.buf); - sock_orphan(sk); sock->sk = NULL; @@ -1622,6 +1616,21 @@ static int isotp_notifier(struct notifier_block *nb, unsigned long msg, return NOTIFY_DONE; } +static void isotp_sock_destruct(struct sock *sk) +{ + struct isotp_sock *so = isotp_sk(sk); + + /* do the standard CAN sock destruct work */ + can_sock_destruct(sk); + + /* free potential extended PDU buffers */ + if (so->rx.buf != so->rx.sbuf) + kfree(so->rx.buf); + + if (so->tx.buf != so->tx.sbuf) + kfree(so->tx.buf); +} + static int isotp_init(struct sock *sk) { struct isotp_sock *so = isotp_sk(sk); @@ -1666,6 +1675,9 @@ static int isotp_init(struct sock *sk) list_add_tail(&so->notifier, &isotp_notifier_list); spin_unlock(&isotp_notifier_lock); + /* re-assign default can_sock_destruct() reference */ + sk->sk_destruct = isotp_sock_destruct; + return 0; } diff --git a/net/can/proc.c b/net/can/proc.c index 0938bf7dd646..de4d05ae3459 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -196,7 +196,8 @@ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list, " %-5s %03x %08x %pK %pK %8ld %s\n"; seq_printf(m, fmt, DNAME(dev), r->can_id, r->mask, - r->func, r->data, r->matches, r->ident); + r->func, r->data, atomic_long_read(&r->matches), + r->ident); } } diff --git a/net/core/dev.c b/net/core/dev.c index 14a83f2035b9..fc5557062414 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3769,6 +3769,22 @@ static netdev_features_t dflt_features_check(struct sk_buff *skb, return vlan_features_check(skb, features); } +static bool skb_gso_has_extension_hdr(const struct sk_buff *skb) +{ + if (!skb->encapsulation) + return ((skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 || + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + vlan_get_protocol(skb) == htons(ETH_P_IPV6))) && + skb_transport_header_was_set(skb) && + skb_network_header_len(skb) != sizeof(struct ipv6hdr)); + else + return (!skb_inner_network_header_was_set(skb) || + ((skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 || + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + inner_ip_hdr(skb)->version == 6)) && + skb_inner_network_header_len(skb) != sizeof(struct ipv6hdr))); +} + static netdev_features_t gso_features_check(const struct sk_buff *skb, struct net_device *dev, netdev_features_t features) @@ -3816,11 +3832,7 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, * so neither does TSO that depends on it. */ if (features & NETIF_F_IPV6_CSUM && - (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 || - (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && - vlan_get_protocol(skb) == htons(ETH_P_IPV6))) && - skb_transport_header_was_set(skb) && - skb_network_header_len(skb) != sizeof(struct ipv6hdr)) + skb_gso_has_extension_hdr(skb)) features &= ~(NETIF_F_IPV6_CSUM | NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4); return features; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index dad4b1054955..fae8034efbff 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -629,6 +629,9 @@ int rtnl_link_register(struct rtnl_link_ops *ops) unlock: mutex_unlock(&link_ops_mutex); + if (err) + cleanup_srcu_struct(&ops->srcu); + return err; } EXPORT_SYMBOL_GPL(rtnl_link_register); @@ -707,11 +710,14 @@ static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev) goto out; ops = master_dev->rtnl_link_ops; - if (!ops || !ops->get_slave_size) + if (!ops) + goto out; + size += nla_total_size(strlen(ops->kind) + 1); /* IFLA_INFO_SLAVE_KIND */ + if (!ops->get_slave_size) goto out; /* IFLA_INFO_SLAVE_DATA + nested data */ - size = nla_total_size(sizeof(struct nlattr)) + - ops->get_slave_size(master_dev, dev); + size += nla_total_size(sizeof(struct nlattr)) + + ops->get_slave_size(master_dev, dev); out: rcu_read_unlock(); @@ -1267,6 +1273,21 @@ static size_t rtnl_dpll_pin_size(const struct net_device *dev) return size; } +static size_t rtnl_dev_parent_size(const struct net_device *dev) +{ + size_t size = 0; + + /* IFLA_PARENT_DEV_NAME */ + if (dev->dev.parent) + size += nla_total_size(strlen(dev_name(dev->dev.parent)) + 1); + + /* IFLA_PARENT_DEV_BUS_NAME */ + if (dev->dev.parent && dev->dev.parent->bus) + size += nla_total_size(strlen(dev->dev.parent->bus->name) + 1); + + return size; +} + static noinline size_t if_nlmsg_size(const struct net_device *dev, u32 ext_filter_mask) { @@ -1328,6 +1349,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(8) /* IFLA_MAX_PACING_OFFLOAD_HORIZON */ + nla_total_size(2) /* IFLA_HEADROOM */ + nla_total_size(2) /* IFLA_TAILROOM */ + + rtnl_dev_parent_size(dev) + 0; if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS)) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 2c922afadb8f..6dfc0bcdef65 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -235,10 +235,13 @@ static void esp_output_done(void *data, int err) xfrm_dev_resume(skb); } else { if (!err && - x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) - esp_output_tail_tcp(x, skb); - else + x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) { + err = esp_output_tail_tcp(x, skb); + if (err != -EINPROGRESS) + kfree_skb(skb); + } else { xfrm_output_resume(skb_to_full_sk(skb), skb, err); + } } } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 5dfac6ce1110..e961936b6be7 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -154,20 +154,6 @@ bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high) } EXPORT_SYMBOL(inet_sk_get_local_port_range); -static bool inet_use_bhash2_on_bind(const struct sock *sk) -{ -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) { - if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) - return false; - - if (!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) - return true; - } -#endif - return sk->sk_rcv_saddr != htonl(INADDR_ANY); -} - static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2, kuid_t uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) @@ -259,7 +245,7 @@ static int inet_csk_bind_conflict(const struct sock *sk, * checks separately because their spinlocks have to be acquired/released * independently of each other, to prevent possible deadlocks */ - if (inet_use_bhash2_on_bind(sk)) + if (inet_use_hash2_on_bind(sk)) return tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok); @@ -376,7 +362,7 @@ other_parity_scan: head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; spin_lock_bh(&head->lock); - if (inet_use_bhash2_on_bind(sk)) { + if (inet_use_hash2_on_bind(sk)) { if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, relax, false)) goto next_port; } @@ -562,7 +548,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) check_bind_conflict = false; } - if (check_bind_conflict && inet_use_bhash2_on_bind(sk)) { + if (check_bind_conflict && inet_use_hash2_on_bind(sk)) { if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, true, true)) goto fail_unlock; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index b60fad393e18..cb99a3c27053 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -287,7 +287,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, } else { hslot = udp_hashslot(udptable, net, snum); spin_lock_bh(&hslot->lock); - if (hslot->count > 10) { + if (inet_use_hash2_on_bind(sk) && hslot->count > 10) { int exist; unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 0e55f139e05d..f4e23b543585 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2862,7 +2862,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) fib6_add_gc_list(rt); } else { fib6_clean_expires(rt); - fib6_remove_gc_list(rt); + fib6_may_remove_gc_list(net, rt); } spin_unlock_bh(&table->tb6_lock); @@ -4840,7 +4840,7 @@ static int modify_prefix_route(struct net *net, struct inet6_ifaddr *ifp, if (!(flags & RTF_EXPIRES)) { fib6_clean_expires(f6i); - fib6_remove_gc_list(f6i); + fib6_may_remove_gc_list(net, f6i); } else { fib6_set_expires(f6i, expires); fib6_add_gc_list(f6i); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index e75da98f5283..9f75313734f8 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -271,10 +271,13 @@ static void esp_output_done(void *data, int err) xfrm_dev_resume(skb); } else { if (!err && - x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) - esp_output_tail_tcp(x, skb); - else + x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) { + err = esp_output_tail_tcp(x, skb); + if (err != -EINPROGRESS) + kfree_skb(skb); + } else { xfrm_output_resume(skb_to_full_sk(skb), skb, err); + } } } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 9058e71241dc..dd26657b6a4a 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1133,7 +1133,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, return -EEXIST; if (!(rt->fib6_flags & RTF_EXPIRES)) { fib6_clean_expires(iter); - fib6_remove_gc_list(iter); + fib6_may_remove_gc_list(info->nl_net, iter); } else { fib6_set_expires(iter, rt->expires); fib6_add_gc_list(iter); @@ -2348,6 +2348,17 @@ static void fib6_flush_trees(struct net *net) /* * Garbage collection */ +void fib6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args, + unsigned long now) +{ + bool may_expire = rt->fib6_flags & RTF_EXPIRES && rt->expires; + int old_more = gc_args->more; + + rt6_age_exceptions(rt, gc_args, now); + + if (!may_expire && old_more == gc_args->more) + fib6_remove_gc_list(rt); +} static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) { @@ -2370,7 +2381,7 @@ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) * Note, that clones are aged out * only if they are not in use now. */ - rt6_age_exceptions(rt, gc_args, now); + fib6_age_exceptions(rt, gc_args, now); return 0; } diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index 4ad8b2032f1f..5561bd9cea81 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -157,6 +157,10 @@ static int rt_mt6_check(const struct xt_mtchk_param *par) pr_debug("unknown flags %X\n", rtinfo->invflags); return -EINVAL; } + if (rtinfo->addrnr > IP6T_RT_HOPS) { + pr_debug("too many addresses specified\n"); + return -EINVAL; + } if ((rtinfo->flags & (IP6T_RT_RES | IP6T_RT_FST_MASK)) && (!(rtinfo->flags & IP6T_RT_TYP) || (rtinfo->rt_type != 0) || diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 08cd86f49bf9..cb521700cee7 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1033,7 +1033,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, if (!addrconf_finite_timeout(lifetime)) { fib6_clean_expires(rt); - fib6_remove_gc_list(rt); + fib6_may_remove_gc_list(net, rt); } else { fib6_set_expires(rt, jiffies + HZ * lifetime); fib6_add_gc_list(rt); diff --git a/net/key/af_key.c b/net/key/af_key.c index 0756bac62f7c..72ac2ace419d 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3518,7 +3518,7 @@ static int set_sadb_kmaddress(struct sk_buff *skb, const struct xfrm_kmaddress * static int set_ipsecrequest(struct sk_buff *skb, uint8_t proto, uint8_t mode, int level, - uint32_t reqid, uint8_t family, + uint32_t reqid, sa_family_t family, const xfrm_address_t *src, const xfrm_address_t *dst) { struct sadb_x_ipsecrequest *rq; @@ -3583,12 +3583,17 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, /* ipsecrequests */ for (i = 0, mp = m; i < num_bundles; i++, mp++) { - /* old locator pair */ - size_pol += sizeof(struct sadb_x_ipsecrequest) + - pfkey_sockaddr_pair_size(mp->old_family); - /* new locator pair */ - size_pol += sizeof(struct sadb_x_ipsecrequest) + - pfkey_sockaddr_pair_size(mp->new_family); + int pair_size; + + pair_size = pfkey_sockaddr_pair_size(mp->old_family); + if (!pair_size) + return -EINVAL; + size_pol += sizeof(struct sadb_x_ipsecrequest) + pair_size; + + pair_size = pfkey_sockaddr_pair_size(mp->new_family); + if (!pair_size) + return -EINVAL; + size_pol += sizeof(struct sadb_x_ipsecrequest) + pair_size; } size += sizeof(struct sadb_msg) + size_pol; diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c index a7552a46d6ac..4f39bf7c843f 100644 --- a/net/netfilter/nf_conntrack_broadcast.c +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -21,6 +21,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, unsigned int timeout) { const struct nf_conntrack_helper *helper; + struct net *net = read_pnet(&ct->ct_net); struct nf_conntrack_expect *exp; struct iphdr *iph = ip_hdr(skb); struct rtable *rt = skb_rtable(skb); @@ -70,8 +71,11 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, exp->expectfn = NULL; exp->flags = NF_CT_EXPECT_PERMANENT; exp->class = NF_CT_EXPECT_CLASS_DEFAULT; - exp->helper = NULL; - + rcu_assign_pointer(exp->helper, helper); + write_pnet(&exp->net, net); +#ifdef CONFIG_NF_CONNTRACK_ZONES + exp->zone = ct->zone; +#endif nf_ct_expect_related(exp, 0); nf_ct_expect_put(exp); diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 81baf2082604..9df159448b89 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -247,6 +247,8 @@ void nf_ct_expect_event_report(enum ip_conntrack_expect_events event, struct nf_ct_event_notifier *notify; struct nf_conntrack_ecache *e; + lockdep_nfct_expect_lock_held(); + rcu_read_lock(); notify = rcu_dereference(net->ct.nf_conntrack_event_cb); if (!notify) diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index cfc2daa3fc7f..24d0576d84b7 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -51,6 +51,7 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, struct net *net = nf_ct_exp_net(exp); struct nf_conntrack_net *cnet; + lockdep_nfct_expect_lock_held(); WARN_ON(!master_help); WARN_ON(timer_pending(&exp->timeout)); @@ -112,12 +113,14 @@ nf_ct_exp_equal(const struct nf_conntrack_tuple *tuple, const struct net *net) { return nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) && - net_eq(net, nf_ct_net(i->master)) && - nf_ct_zone_equal_any(i->master, zone); + net_eq(net, read_pnet(&i->net)) && + nf_ct_exp_zone_equal_any(i, zone); } bool nf_ct_remove_expect(struct nf_conntrack_expect *exp) { + lockdep_nfct_expect_lock_held(); + if (timer_delete(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); @@ -177,6 +180,8 @@ nf_ct_find_expectation(struct net *net, struct nf_conntrack_expect *i, *exp = NULL; unsigned int h; + lockdep_nfct_expect_lock_held(); + if (!cnet->expect_count) return NULL; @@ -309,12 +314,20 @@ struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me) } EXPORT_SYMBOL_GPL(nf_ct_expect_alloc); +/* This function can only be used from packet path, where accessing + * master's helper is safe, because the packet holds a reference on + * the conntrack object. Never use it from control plane. + */ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class, u_int8_t family, const union nf_inet_addr *saddr, const union nf_inet_addr *daddr, u_int8_t proto, const __be16 *src, const __be16 *dst) { + struct nf_conntrack_helper *helper = NULL; + struct nf_conn *ct = exp->master; + struct net *net = read_pnet(&ct->ct_net); + struct nf_conn_help *help; int len; if (family == AF_INET) @@ -325,7 +338,16 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class, exp->flags = 0; exp->class = class; exp->expectfn = NULL; - exp->helper = NULL; + + help = nfct_help(ct); + if (help) + helper = rcu_dereference(help->helper); + + rcu_assign_pointer(exp->helper, helper); + write_pnet(&exp->net, net); +#ifdef CONFIG_NF_CONNTRACK_ZONES + exp->zone = ct->zone; +#endif exp->tuple.src.l3num = family; exp->tuple.dst.protonum = proto; @@ -442,6 +464,8 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect, unsigned int h; int ret = 0; + lockdep_nfct_expect_lock_held(); + if (!master_help) { ret = -ESHUTDOWN; goto out; @@ -498,8 +522,9 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, nf_ct_expect_insert(expect); - spin_unlock_bh(&nf_conntrack_expect_lock); nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report); + spin_unlock_bh(&nf_conntrack_expect_lock); + return 0; out: spin_unlock_bh(&nf_conntrack_expect_lock); @@ -627,11 +652,15 @@ static int exp_seq_show(struct seq_file *s, void *v) { struct nf_conntrack_expect *expect; struct nf_conntrack_helper *helper; + struct net *net = seq_file_net(s); struct hlist_node *n = v; char *delim = ""; expect = hlist_entry(n, struct nf_conntrack_expect, hnode); + if (!net_eq(nf_ct_exp_net(expect), net)) + return 0; + if (expect->timeout.function) seq_printf(s, "%ld ", timer_pending(&expect->timeout) ? (long)(expect->timeout.expires - jiffies)/HZ : 0); @@ -654,7 +683,7 @@ static int exp_seq_show(struct seq_file *s, void *v) if (expect->flags & NF_CT_EXPECT_USERSPACE) seq_printf(s, "%sUSERSPACE", delim); - helper = rcu_dereference(nfct_help(expect->master)->helper); + helper = rcu_dereference(expect->helper); if (helper) { seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name); if (helper->expect_policy[expect->class].name[0]) diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index a2a0e22ccee1..3f5c50455b71 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -643,7 +643,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3, IPPROTO_TCP, NULL, &port); - exp->helper = &nf_conntrack_helper_h245; + rcu_assign_pointer(exp->helper, &nf_conntrack_helper_h245); nathook = rcu_dereference(nfct_h323_nat_hook); if (memcmp(&ct->tuplehash[dir].tuple.src.u3, @@ -767,7 +767,7 @@ static int expect_callforwarding(struct sk_buff *skb, nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct), &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); - exp->helper = nf_conntrack_helper_q931; + rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); nathook = rcu_dereference(nfct_h323_nat_hook); if (memcmp(&ct->tuplehash[dir].tuple.src.u3, @@ -1234,7 +1234,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3 : NULL, &ct->tuplehash[!dir].tuple.dst.u3, IPPROTO_TCP, NULL, &port); - exp->helper = nf_conntrack_helper_q931; + rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); exp->flags = NF_CT_EXPECT_PERMANENT; /* Accept multiple calls */ nathook = rcu_dereference(nfct_h323_nat_hook); @@ -1306,7 +1306,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct, nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct), &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_UDP, NULL, &port); - exp->helper = nf_conntrack_helper_ras; + rcu_assign_pointer(exp->helper, nf_conntrack_helper_ras); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect RAS "); @@ -1523,7 +1523,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); exp->flags = NF_CT_EXPECT_PERMANENT; - exp->helper = nf_conntrack_helper_q931; + rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); @@ -1577,7 +1577,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); exp->flags = NF_CT_EXPECT_PERMANENT; - exp->helper = nf_conntrack_helper_q931; + rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index ceb48c3ca0a4..1b330ba6613b 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -395,14 +395,10 @@ EXPORT_SYMBOL_GPL(nf_conntrack_helper_register); static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data) { - struct nf_conn_help *help = nfct_help(exp->master); const struct nf_conntrack_helper *me = data; const struct nf_conntrack_helper *this; - if (exp->helper == me) - return true; - - this = rcu_dereference_protected(help->helper, + this = rcu_dereference_protected(exp->helper, lockdep_is_held(&nf_conntrack_expect_lock)); return this == me; } @@ -421,6 +417,11 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) nf_ct_expect_iterate_destroy(expect_iter_me, NULL); nf_ct_iterate_destroy(unhelp, me); + + /* nf_ct_iterate_destroy() does an unconditional synchronize_rcu() as + * last step, this ensures rcu readers of exp->helper are done. + * No need for another synchronize_rcu() here. + */ } EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index c156574e1273..3f408f3713bb 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -910,8 +910,8 @@ struct ctnetlink_filter { }; static const struct nla_policy cta_filter_nla_policy[CTA_FILTER_MAX + 1] = { - [CTA_FILTER_ORIG_FLAGS] = { .type = NLA_U32 }, - [CTA_FILTER_REPLY_FLAGS] = { .type = NLA_U32 }, + [CTA_FILTER_ORIG_FLAGS] = NLA_POLICY_MASK(NLA_U32, CTA_FILTER_F_ALL), + [CTA_FILTER_REPLY_FLAGS] = NLA_POLICY_MASK(NLA_U32, CTA_FILTER_F_ALL), }; static int ctnetlink_parse_filter(const struct nlattr *attr, @@ -925,17 +925,11 @@ static int ctnetlink_parse_filter(const struct nlattr *attr, if (ret) return ret; - if (tb[CTA_FILTER_ORIG_FLAGS]) { + if (tb[CTA_FILTER_ORIG_FLAGS]) filter->orig_flags = nla_get_u32(tb[CTA_FILTER_ORIG_FLAGS]); - if (filter->orig_flags & ~CTA_FILTER_F_ALL) - return -EOPNOTSUPP; - } - if (tb[CTA_FILTER_REPLY_FLAGS]) { + if (tb[CTA_FILTER_REPLY_FLAGS]) filter->reply_flags = nla_get_u32(tb[CTA_FILTER_REPLY_FLAGS]); - if (filter->reply_flags & ~CTA_FILTER_F_ALL) - return -EOPNOTSUPP; - } return 0; } @@ -2634,7 +2628,7 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN - 1 }, [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, - [CTA_EXPECT_FLAGS] = { .type = NLA_U32 }, + [CTA_EXPECT_FLAGS] = NLA_POLICY_MASK(NLA_BE32, NF_CT_EXPECT_MASK), [CTA_EXPECT_CLASS] = { .type = NLA_U32 }, [CTA_EXPECT_NAT] = { .type = NLA_NESTED }, [CTA_EXPECT_FN] = { .type = NLA_NUL_STRING }, @@ -3012,7 +3006,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, { struct nf_conn *master = exp->master; long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ; - struct nf_conn_help *help; + struct nf_conntrack_helper *helper; #if IS_ENABLED(CONFIG_NF_NAT) struct nlattr *nest_parms; struct nf_conntrack_tuple nat_tuple = {}; @@ -3057,15 +3051,12 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) || nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class))) goto nla_put_failure; - help = nfct_help(master); - if (help) { - struct nf_conntrack_helper *helper; - helper = rcu_dereference(help->helper); - if (helper && - nla_put_string(skb, CTA_EXPECT_HELP_NAME, helper->name)) - goto nla_put_failure; - } + helper = rcu_dereference(exp->helper); + if (helper && + nla_put_string(skb, CTA_EXPECT_HELP_NAME, helper->name)) + goto nla_put_failure; + expfn = nf_ct_helper_expectfn_find_by_symbol(exp->expectfn); if (expfn != NULL && nla_put_string(skb, CTA_EXPECT_FN, expfn->name)) @@ -3358,31 +3349,37 @@ static int ctnetlink_get_expect(struct sk_buff *skb, if (err < 0) return err; + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb2) + return -ENOMEM; + + spin_lock_bh(&nf_conntrack_expect_lock); exp = nf_ct_expect_find_get(info->net, &zone, &tuple); - if (!exp) + if (!exp) { + spin_unlock_bh(&nf_conntrack_expect_lock); + kfree_skb(skb2); return -ENOENT; + } if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); + spin_unlock_bh(&nf_conntrack_expect_lock); + kfree_skb(skb2); return -ENOENT; } } - skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!skb2) { - nf_ct_expect_put(exp); - return -ENOMEM; - } - rcu_read_lock(); err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp); rcu_read_unlock(); nf_ct_expect_put(exp); + spin_unlock_bh(&nf_conntrack_expect_lock); + if (err <= 0) { kfree_skb(skb2); return -ENOMEM; @@ -3394,12 +3391,9 @@ static int ctnetlink_get_expect(struct sk_buff *skb, static bool expect_iter_name(struct nf_conntrack_expect *exp, void *data) { struct nf_conntrack_helper *helper; - const struct nf_conn_help *m_help; const char *name = data; - m_help = nfct_help(exp->master); - - helper = rcu_dereference(m_help->helper); + helper = rcu_dereference(exp->helper); if (!helper) return false; @@ -3432,22 +3426,26 @@ static int ctnetlink_del_expect(struct sk_buff *skb, if (err < 0) return err; + spin_lock_bh(&nf_conntrack_expect_lock); + /* bump usage count to 2 */ exp = nf_ct_expect_find_get(info->net, &zone, &tuple); - if (!exp) + if (!exp) { + spin_unlock_bh(&nf_conntrack_expect_lock); return -ENOENT; + } if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); + spin_unlock_bh(&nf_conntrack_expect_lock); return -ENOENT; } } /* after list removal, usage count == 1 */ - spin_lock_bh(&nf_conntrack_expect_lock); if (timer_delete(&exp->timeout)) { nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); @@ -3534,9 +3532,10 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask) { - u_int32_t class = 0; + struct net *net = read_pnet(&ct->ct_net); struct nf_conntrack_expect *exp; struct nf_conn_help *help; + u32 class = 0; int err; help = nfct_help(ct); @@ -3573,7 +3572,13 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, exp->class = class; exp->master = ct; - exp->helper = helper; + write_pnet(&exp->net, net); +#ifdef CONFIG_NF_CONNTRACK_ZONES + exp->zone = ct->zone; +#endif + if (!helper) + helper = rcu_dereference(help->helper); + rcu_assign_pointer(exp->helper, helper); exp->tuple = *tuple; exp->mask.src.u3 = mask->src.u3; exp->mask.src.u.all = mask->src.u.all; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 0c1d086e96cb..b67426c2189b 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1385,9 +1385,9 @@ nla_put_failure: } static const struct nla_policy tcp_nla_policy[CTA_PROTOINFO_TCP_MAX+1] = { - [CTA_PROTOINFO_TCP_STATE] = { .type = NLA_U8 }, - [CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] = { .type = NLA_U8 }, - [CTA_PROTOINFO_TCP_WSCALE_REPLY] = { .type = NLA_U8 }, + [CTA_PROTOINFO_TCP_STATE] = NLA_POLICY_MAX(NLA_U8, TCP_CONNTRACK_SYN_SENT2), + [CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] = NLA_POLICY_MAX(NLA_U8, TCP_MAX_WSCALE), + [CTA_PROTOINFO_TCP_WSCALE_REPLY] = NLA_POLICY_MAX(NLA_U8, TCP_MAX_WSCALE), [CTA_PROTOINFO_TCP_FLAGS_ORIGINAL] = { .len = sizeof(struct nf_ct_tcp_flags) }, [CTA_PROTOINFO_TCP_FLAGS_REPLY] = { .len = sizeof(struct nf_ct_tcp_flags) }, }; @@ -1414,10 +1414,6 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct) if (err < 0) return err; - if (tb[CTA_PROTOINFO_TCP_STATE] && - nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]) >= TCP_CONNTRACK_MAX) - return -EINVAL; - spin_lock_bh(&ct->lock); if (tb[CTA_PROTOINFO_TCP_STATE]) ct->proto.tcp.state = nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]); diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 4ab5ef71d96d..939502ff7c87 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -924,7 +924,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, exp = __nf_ct_expect_find(net, nf_ct_zone(ct), &tuple); if (!exp || exp->master == ct || - nfct_help(exp->master)->helper != nfct_help(ct)->helper || + exp->helper != nfct_help(ct)->helper || exp->class != class) break; #if IS_ENABLED(CONFIG_NF_NAT) @@ -1040,6 +1040,7 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, unsigned int port; const struct sdp_media_type *t; int ret = NF_ACCEPT; + bool have_rtp_addr = false; hooks = rcu_dereference(nf_nat_sip_hooks); @@ -1056,8 +1057,11 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, caddr_len = 0; if (ct_sip_parse_sdp_addr(ct, *dptr, sdpoff, *datalen, SDP_HDR_CONNECTION, SDP_HDR_MEDIA, - &matchoff, &matchlen, &caddr) > 0) + &matchoff, &matchlen, &caddr) > 0) { caddr_len = matchlen; + memcpy(&rtp_addr, &caddr, sizeof(rtp_addr)); + have_rtp_addr = true; + } mediaoff = sdpoff; for (i = 0; i < ARRAY_SIZE(sdp_media_types); ) { @@ -1091,9 +1095,11 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, &matchoff, &matchlen, &maddr) > 0) { maddr_len = matchlen; memcpy(&rtp_addr, &maddr, sizeof(rtp_addr)); - } else if (caddr_len) + have_rtp_addr = true; + } else if (caddr_len) { memcpy(&rtp_addr, &caddr, sizeof(rtp_addr)); - else { + have_rtp_addr = true; + } else { nf_ct_helper_log(skb, ct, "cannot parse SDP message"); return NF_DROP; } @@ -1125,7 +1131,7 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, /* Update session connection and owner addresses */ hooks = rcu_dereference(nf_nat_sip_hooks); - if (hooks && ct->status & IPS_NAT_MASK) + if (hooks && ct->status & IPS_NAT_MASK && have_rtp_addr) ret = hooks->sdp_session(skb, protoff, dataoff, dptr, datalen, sdpoff, &rtp_addr); @@ -1297,7 +1303,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, nf_ct_expect_init(exp, SIP_EXPECT_SIGNALLING, nf_ct_l3num(ct), saddr, &daddr, proto, NULL, &port); exp->timeout.expires = sip_timeout * HZ; - exp->helper = helper; + rcu_assign_pointer(exp->helper, helper); exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE; hooks = rcu_dereference(nf_nat_sip_hooks); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index b35a90955e2e..fcbe54940b2e 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -647,15 +647,11 @@ __build_packet_message(struct nfnl_log_net *log, if (data_len) { struct nlattr *nla; - int size = nla_attr_size(data_len); - if (skb_tailroom(inst->skb) < nla_total_size(data_len)) + nla = nla_reserve(inst->skb, NFULA_PAYLOAD, data_len); + if (!nla) goto nla_put_failure; - nla = skb_put(inst->skb, nla_total_size(data_len)); - nla->nla_type = NFULA_PAYLOAD; - nla->nla_len = size; - if (skb_copy_bits(skb, 0, nla_data(nla), data_len)) BUG(); } diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 7ff90325c97f..6395982e4d95 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -242,7 +242,7 @@ static int nft_pipapo_avx2_lookup_4b_2(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -319,7 +319,7 @@ static int nft_pipapo_avx2_lookup_4b_4(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -414,7 +414,7 @@ static int nft_pipapo_avx2_lookup_4b_8(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -505,7 +505,7 @@ static int nft_pipapo_avx2_lookup_4b_12(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -641,7 +641,7 @@ static int nft_pipapo_avx2_lookup_4b_32(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -699,7 +699,7 @@ static int nft_pipapo_avx2_lookup_8b_1(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -764,7 +764,7 @@ static int nft_pipapo_avx2_lookup_8b_2(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -839,7 +839,7 @@ static int nft_pipapo_avx2_lookup_8b_4(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -925,7 +925,7 @@ static int nft_pipapo_avx2_lookup_8b_6(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -1019,7 +1019,7 @@ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index fe8bd497d74a..737c339decd0 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -572,14 +572,12 @@ static struct nft_array *nft_array_alloc(u32 max_intervals) return array; } -#define NFT_ARRAY_EXTRA_SIZE 10240 - /* Similar to nft_rbtree_{u,k}size to hide details to userspace, but consider * packed representation coming from userspace for anonymous sets too. */ static u32 nft_array_elems(const struct nft_set *set) { - u32 nelems = atomic_read(&set->nelems); + u32 nelems = atomic_read(&set->nelems) - set->ndeact; /* Adjacent intervals are represented with a single start element in * anonymous sets, use the current element counter as is. @@ -595,27 +593,87 @@ static u32 nft_array_elems(const struct nft_set *set) return (nelems / 2) + 2; } -static int nft_array_may_resize(const struct nft_set *set) +#define NFT_ARRAY_INITIAL_SIZE 1024 +#define NFT_ARRAY_INITIAL_ANON_SIZE 16 +#define NFT_ARRAY_INITIAL_ANON_THRESH (8192U / sizeof(struct nft_array_interval)) + +static int nft_array_may_resize(const struct nft_set *set, bool flush) { - u32 nelems = nft_array_elems(set), new_max_intervals; + u32 initial_intervals, max_intervals, new_max_intervals, delta; + u32 shrinked_max_intervals, nelems = nft_array_elems(set); struct nft_rbtree *priv = nft_set_priv(set); struct nft_array *array; - if (!priv->array_next) { - array = nft_array_alloc(nelems + NFT_ARRAY_EXTRA_SIZE); - if (!array) - return -ENOMEM; + if (nft_set_is_anonymous(set)) + initial_intervals = NFT_ARRAY_INITIAL_ANON_SIZE; + else + initial_intervals = NFT_ARRAY_INITIAL_SIZE; + + if (priv->array_next) { + max_intervals = priv->array_next->max_intervals; + new_max_intervals = priv->array_next->max_intervals; + } else { + if (priv->array) { + max_intervals = priv->array->max_intervals; + new_max_intervals = priv->array->max_intervals; + } else { + max_intervals = 0; + new_max_intervals = initial_intervals; + } + } - priv->array_next = array; + if (nft_set_is_anonymous(set)) + goto maybe_grow; + + if (flush) { + /* Set flush just started, nelems still report elements.*/ + nelems = 0; + new_max_intervals = NFT_ARRAY_INITIAL_SIZE; + goto realloc_array; } - if (nelems < priv->array_next->max_intervals) - return 0; + if (check_add_overflow(new_max_intervals, new_max_intervals, + &shrinked_max_intervals)) + return -EOVERFLOW; + + shrinked_max_intervals = DIV_ROUND_UP(shrinked_max_intervals, 3); - new_max_intervals = priv->array_next->max_intervals + NFT_ARRAY_EXTRA_SIZE; - if (nft_array_intervals_alloc(priv->array_next, new_max_intervals) < 0) + if (shrinked_max_intervals > NFT_ARRAY_INITIAL_SIZE && + nelems < shrinked_max_intervals) { + new_max_intervals = shrinked_max_intervals; + goto realloc_array; + } +maybe_grow: + if (nelems > new_max_intervals) { + if (nft_set_is_anonymous(set) && + new_max_intervals < NFT_ARRAY_INITIAL_ANON_THRESH) { + new_max_intervals <<= 1; + } else { + delta = new_max_intervals >> 1; + if (check_add_overflow(new_max_intervals, delta, + &new_max_intervals)) + return -EOVERFLOW; + } + } + +realloc_array: + if (WARN_ON_ONCE(nelems > new_max_intervals)) return -ENOMEM; + if (priv->array_next) { + if (max_intervals == new_max_intervals) + return 0; + + if (nft_array_intervals_alloc(priv->array_next, new_max_intervals) < 0) + return -ENOMEM; + } else { + array = nft_array_alloc(new_max_intervals); + if (!array) + return -ENOMEM; + + priv->array_next = array; + } + return 0; } @@ -630,7 +688,7 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, nft_rbtree_maybe_reset_start_cookie(priv, tstamp); - if (nft_array_may_resize(set) < 0) + if (nft_array_may_resize(set, false) < 0) return -ENOMEM; do { @@ -741,7 +799,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set, nft_rbtree_interval_null(set, this)) priv->start_rbe_cookie = 0; - if (nft_array_may_resize(set) < 0) + if (nft_array_may_resize(set, false) < 0) return NULL; while (parent != NULL) { @@ -811,7 +869,7 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, switch (iter->type) { case NFT_ITER_UPDATE_CLONE: - if (nft_array_may_resize(set) < 0) { + if (nft_array_may_resize(set, true) < 0) { iter->err = -ENOMEM; break; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 43d871525dbc..5f46c4b5720f 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -579,8 +579,7 @@ static int nci_close_device(struct nci_dev *ndev) skb_queue_purge(&ndev->rx_q); skb_queue_purge(&ndev->tx_q); - /* Flush RX and TX wq */ - flush_workqueue(ndev->rx_wq); + /* Flush TX wq, RX wq flush can't be under the lock */ flush_workqueue(ndev->tx_wq); /* Reset device */ @@ -592,13 +591,13 @@ static int nci_close_device(struct nci_dev *ndev) msecs_to_jiffies(NCI_RESET_TIMEOUT)); /* After this point our queues are empty - * and no works are scheduled. + * rx work may be running but will see that NCI_UP was cleared */ ndev->ops->close(ndev); clear_bit(NCI_INIT, &ndev->flags); - /* Flush cmd wq */ + /* Flush cmd and tx wq */ flush_workqueue(ndev->cmd_wq); timer_delete_sync(&ndev->cmd_timer); @@ -613,6 +612,9 @@ static int nci_close_device(struct nci_dev *ndev) mutex_unlock(&ndev->req_lock); + /* rx_work may take req_lock via nci_deactivate_target */ + flush_workqueue(ndev->rx_wq); + return 0; } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 67fbf6e48a30..13052408a132 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2953,6 +2953,8 @@ static int validate_set(const struct nlattr *a, case OVS_KEY_ATTR_MPLS: if (!eth_p_mpls(eth_type)) return -EINVAL; + if (key_len != sizeof(struct ovs_key_mpls)) + return -EINVAL; break; case OVS_KEY_ATTR_SCTP: diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 6574f9bcdc02..12055af832dc 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -151,11 +151,15 @@ static void vport_netdev_free(struct rcu_head *rcu) void ovs_netdev_detach_dev(struct vport *vport) { ASSERT_RTNL(); - vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; netdev_rx_handler_unregister(vport->dev); netdev_upper_dev_unlink(vport->dev, netdev_master_upper_dev_get(vport->dev)); dev_set_promiscuity(vport->dev, -1); + + /* paired with smp_mb() in netdev_destroy() */ + smp_wmb(); + + vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; } static void netdev_destroy(struct vport *vport) @@ -174,6 +178,9 @@ static void netdev_destroy(struct vport *vport) rtnl_unlock(); } + /* paired with smp_wmb() in ovs_netdev_detach_dev() */ + smp_mb(); + call_rcu(&vport->rcu, vport_netdev_free); } @@ -189,8 +196,6 @@ void ovs_netdev_tunnel_destroy(struct vport *vport) */ if (vport->dev->reg_state == NETREG_REGISTERED) rtnl_delete_link(vport->dev, 0, NULL); - netdev_put(vport->dev, &vport->dev_tracker); - vport->dev = NULL; rtnl_unlock(); call_rcu(&vport->rcu, vport_netdev_free); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 72d0935139f0..bb2d88205e5a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3135,6 +3135,7 @@ static int packet_release(struct socket *sock) spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); + WRITE_ONCE(po->num, 0); packet_cached_dev_reset(po); if (po->prot_hook.dev) { diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index d833e36f7fd4..c1d9b923938d 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -135,9 +135,16 @@ out: sock_put(sk); } +static bool smc_rx_pipe_buf_get(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + /* smc_spd_priv in buf->private is not shareable; disallow cloning. */ + return false; +} + static const struct pipe_buf_operations smc_pipe_ops = { .release = smc_rx_pipe_buf_release, - .get = generic_pipe_buf_get + .get = smc_rx_pipe_buf_get, }; static void smc_rx_spd_release(struct splice_pipe_desc *spd, diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 5fe07f110fe8..dd9dda759bbb 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -246,6 +246,7 @@ static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); atomic_inc(&ctx->decrypt_pending); + __skb_queue_purge(&ctx->async_hold); return ctx->async_wait.err; } @@ -2225,7 +2226,6 @@ recv_end: /* Wait for all previously submitted records to be decrypted */ ret = tls_decrypt_async_wait(ctx); - __skb_queue_purge(&ctx->async_hold); if (ret) { if (err >= 0 || err == -EINPROGRESS) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 4ed346e682c7..dc1312ed5a09 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -75,7 +75,10 @@ int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo) spin_lock_bh(&xfrm_input_afinfo_lock); if (likely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family])) { - if (unlikely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family] != afinfo)) + const struct xfrm_input_afinfo *cur; + + cur = rcu_access_pointer(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family]); + if (unlikely(cur != afinfo)) err = -EINVAL; else RCU_INIT_POINTER(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family], NULL); diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c index 050a82101ca5..97bc979e55ba 100644 --- a/net/xfrm/xfrm_iptfs.c +++ b/net/xfrm/xfrm_iptfs.c @@ -901,6 +901,12 @@ static u32 iptfs_reassem_cont(struct xfrm_iptfs_data *xtfs, u64 seq, iptfs_skb_can_add_frags(newskb, fragwalk, data, copylen)) { iptfs_skb_add_frags(newskb, fragwalk, data, copylen); } else { + if (skb_linearize(newskb)) { + XFRM_INC_STATS(xs_net(xtfs->x), + LINUX_MIB_XFRMINBUFFERERROR); + goto abandon; + } + /* copy fragment data into newskb */ if (skb_copy_seq_read(st, data, skb_put(newskb, copylen), copylen)) { @@ -991,6 +997,11 @@ static bool __input_process_payload(struct xfrm_state *x, u32 data, iplen = be16_to_cpu(iph->tot_len); iphlen = iph->ihl << 2; + if (iplen < iphlen || iphlen < sizeof(*iph)) { + XFRM_INC_STATS(net, + LINUX_MIB_XFRMINHDRERROR); + goto done; + } protocol = cpu_to_be16(ETH_P_IP); XFRM_MODE_SKB_CB(skbseq->root_skb)->tos = iph->tos; } else if (iph->version == 0x6) { @@ -2653,9 +2664,6 @@ static int iptfs_clone_state(struct xfrm_state *x, struct xfrm_state *orig) if (!xtfs) return -ENOMEM; - x->mode_data = xtfs; - xtfs->x = x; - xtfs->ra_newskb = NULL; if (xtfs->cfg.reorder_win_size) { xtfs->w_saved = kzalloc_objs(*xtfs->w_saved, @@ -2666,6 +2674,9 @@ static int iptfs_clone_state(struct xfrm_state *x, struct xfrm_state *orig) } } + x->mode_data = xtfs; + xtfs->x = x; + return 0; } diff --git a/net/xfrm/xfrm_nat_keepalive.c b/net/xfrm/xfrm_nat_keepalive.c index ebf95d48e86c..1856beee0149 100644 --- a/net/xfrm/xfrm_nat_keepalive.c +++ b/net/xfrm/xfrm_nat_keepalive.c @@ -261,7 +261,7 @@ int __net_init xfrm_nat_keepalive_net_init(struct net *net) int xfrm_nat_keepalive_net_fini(struct net *net) { - cancel_delayed_work_sync(&net->xfrm.nat_keepalive_work); + disable_delayed_work_sync(&net->xfrm.nat_keepalive_work); return 0; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 9e1a522ab1c5..362939aa56cf 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -4156,7 +4156,7 @@ void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo) int i; for (i = 0; i < ARRAY_SIZE(xfrm_policy_afinfo); i++) { - if (xfrm_policy_afinfo[i] != afinfo) + if (rcu_access_pointer(xfrm_policy_afinfo[i]) != afinfo) continue; RCU_INIT_POINTER(xfrm_policy_afinfo[i], NULL); break; @@ -4242,7 +4242,7 @@ static int __net_init xfrm_policy_init(struct net *net) net->xfrm.policy_count[XFRM_POLICY_MAX + dir] = 0; htab = &net->xfrm.policy_bydst[dir]; - htab->table = xfrm_hash_alloc(sz); + rcu_assign_pointer(htab->table, xfrm_hash_alloc(sz)); if (!htab->table) goto out_bydst; htab->hmask = hmask; @@ -4269,7 +4269,7 @@ out_bydst: struct xfrm_policy_hash *htab; htab = &net->xfrm.policy_bydst[dir]; - xfrm_hash_free(htab->table, sz); + xfrm_hash_free(rcu_dereference_protected(htab->table, true), sz); } xfrm_hash_free(net->xfrm.policy_byidx, sz); out_byidx: @@ -4282,6 +4282,8 @@ static void xfrm_policy_fini(struct net *net) unsigned int sz; int dir; + disable_work_sync(&net->xfrm.policy_hthresh.work); + flush_work(&net->xfrm.policy_hash_work); #ifdef CONFIG_XFRM_SUB_POLICY xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false); @@ -4295,8 +4297,8 @@ static void xfrm_policy_fini(struct net *net) htab = &net->xfrm.policy_bydst[dir]; sz = (htab->hmask + 1) * sizeof(struct hlist_head); - WARN_ON(!hlist_empty(htab->table)); - xfrm_hash_free(htab->table, sz); + WARN_ON(!hlist_empty(rcu_dereference_protected(htab->table, true))); + xfrm_hash_free(rcu_dereference_protected(htab->table, true), sz); } sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 98b362d51836..1748d374abca 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -53,7 +53,7 @@ static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); static HLIST_HEAD(xfrm_state_gc_list); static HLIST_HEAD(xfrm_state_dev_gc_list); -static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x) +static inline bool xfrm_state_hold_rcu(struct xfrm_state *x) { return refcount_inc_not_zero(&x->refcnt); } @@ -870,7 +870,7 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; - hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) { if (xfrm_id_proto_match(x->id.proto, proto) && (err = security_xfrm_state_delete(x)) != 0) { xfrm_audit_state_delete(x, 0, task_valid); @@ -891,7 +891,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool struct xfrm_state *x; struct xfrm_dev_offload *xso; - hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) { xso = &x->xso; if (xso->dev == dev && @@ -931,7 +931,7 @@ int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; restart: - hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) { if (!xfrm_state_kern(x) && xfrm_id_proto_match(x->id.proto, proto)) { xfrm_state_hold(x); @@ -973,7 +973,7 @@ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_vali err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { restart: - hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) { xso = &x->xso; if (!xfrm_state_kern(x) && xso->dev == dev) { @@ -1563,23 +1563,23 @@ found: list_add(&x->km.all, &net->xfrm.state_all); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); XFRM_STATE_INSERT(bydst, &x->bydst, - net->xfrm.state_bydst + h, + xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, x->xso.type); h = xfrm_src_hash(net, daddr, saddr, encap_family); XFRM_STATE_INSERT(bysrc, &x->bysrc, - net->xfrm.state_bysrc + h, + xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h, x->xso.type); INIT_HLIST_NODE(&x->state_cache); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family); XFRM_STATE_INSERT(byspi, &x->byspi, - net->xfrm.state_byspi + h, + xfrm_state_deref_prot(net->xfrm.state_byspi, net) + h, x->xso.type); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); XFRM_STATE_INSERT(byseq, &x->byseq, - net->xfrm.state_byseq + h, + xfrm_state_deref_prot(net->xfrm.state_byseq, net) + h, x->xso.type); } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; @@ -1652,7 +1652,7 @@ xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, reqid, family); - hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) { if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && @@ -1703,18 +1703,12 @@ static struct xfrm_state *xfrm_state_lookup_spi_proto(struct net *net, __be32 sp struct xfrm_state *x; unsigned int i; - rcu_read_lock(); for (i = 0; i <= net->xfrm.state_hmask; i++) { - hlist_for_each_entry_rcu(x, &net->xfrm.state_byspi[i], byspi) { - if (x->id.spi == spi && x->id.proto == proto) { - if (!xfrm_state_hold_rcu(x)) - continue; - rcu_read_unlock(); + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_byspi, net) + i, byspi) { + if (x->id.spi == spi && x->id.proto == proto) return x; - } } } - rcu_read_unlock(); return NULL; } @@ -1730,25 +1724,29 @@ static void __xfrm_state_insert(struct xfrm_state *x) h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family); - XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, + XFRM_STATE_INSERT(bydst, &x->bydst, + xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, x->xso.type); h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family); - XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h, + XFRM_STATE_INSERT(bysrc, &x->bysrc, + xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h, x->xso.type); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); - XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, + XFRM_STATE_INSERT(byspi, &x->byspi, + xfrm_state_deref_prot(net->xfrm.state_byspi, net) + h, x->xso.type); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); - XFRM_STATE_INSERT(byseq, &x->byseq, net->xfrm.state_byseq + h, + XFRM_STATE_INSERT(byseq, &x->byseq, + xfrm_state_deref_prot(net->xfrm.state_byseq, net) + h, x->xso.type); } @@ -1775,7 +1773,7 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) u32 cpu_id = xnew->pcpu_num; h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family); - hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) { if (x->props.family == family && x->props.reqid == reqid && x->if_id == if_id && @@ -1811,7 +1809,7 @@ static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_state *x; u32 mark = m->v & m->m; - hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) { if (x->props.reqid != reqid || x->props.mode != mode || x->props.family != family || @@ -1868,10 +1866,12 @@ static struct xfrm_state *__find_acq_core(struct net *net, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL_SOFT); list_add(&x->km.all, &net->xfrm.state_all); - XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, + XFRM_STATE_INSERT(bydst, &x->bydst, + xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, x->xso.type); h = xfrm_src_hash(net, daddr, saddr, family); - XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h, + XFRM_STATE_INSERT(bysrc, &x->bysrc, + xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h, x->xso.type); net->xfrm.state_num++; @@ -2091,7 +2091,7 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n if (m->reqid) { h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr, m->reqid, m->old_family); - hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -2110,7 +2110,7 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n } else { h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr, m->old_family); - hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h, bysrc) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -2264,6 +2264,7 @@ out: err = 0; x->km.state = XFRM_STATE_DEAD; + xfrm_dev_state_delete(x); __xfrm_state_put(x); } @@ -2312,7 +2313,7 @@ void xfrm_state_update_stats(struct net *net) spin_lock_bh(&net->xfrm.xfrm_state_lock); for (i = 0; i <= net->xfrm.state_hmask; i++) { - hlist_for_each_entry(x, net->xfrm.state_bydst + i, bydst) + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) xfrm_dev_state_update_stats(x); } spin_unlock_bh(&net->xfrm.xfrm_state_lock); @@ -2503,7 +2504,7 @@ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 s unsigned int h = xfrm_seq_hash(net, seq); struct xfrm_state *x; - hlist_for_each_entry_rcu(x, net->xfrm.state_byseq + h, byseq) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_byseq, net) + h, byseq) { if (x->km.seq == seq && (mark & x->mark.m) == x->mark.v && x->pcpu_num == pcpu_num && @@ -2602,12 +2603,13 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high, if (!x0) { x->id.spi = newspi; h = xfrm_spi_hash(net, &x->id.daddr, newspi, x->id.proto, x->props.family); - XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, x->xso.type); + XFRM_STATE_INSERT(byspi, &x->byspi, + xfrm_state_deref_prot(net->xfrm.state_byspi, net) + h, + x->xso.type); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = 0; goto unlock; } - xfrm_state_put(x0); spin_unlock_bh(&net->xfrm.xfrm_state_lock); next: @@ -3258,6 +3260,7 @@ EXPORT_SYMBOL(xfrm_init_state); int __net_init xfrm_state_init(struct net *net) { + struct hlist_head *ndst, *nsrc, *nspi, *nseq; unsigned int sz; if (net_eq(net, &init_net)) @@ -3268,18 +3271,25 @@ int __net_init xfrm_state_init(struct net *net) sz = sizeof(struct hlist_head) * 8; - net->xfrm.state_bydst = xfrm_hash_alloc(sz); - if (!net->xfrm.state_bydst) + ndst = xfrm_hash_alloc(sz); + if (!ndst) goto out_bydst; - net->xfrm.state_bysrc = xfrm_hash_alloc(sz); - if (!net->xfrm.state_bysrc) + rcu_assign_pointer(net->xfrm.state_bydst, ndst); + + nsrc = xfrm_hash_alloc(sz); + if (!nsrc) goto out_bysrc; - net->xfrm.state_byspi = xfrm_hash_alloc(sz); - if (!net->xfrm.state_byspi) + rcu_assign_pointer(net->xfrm.state_bysrc, nsrc); + + nspi = xfrm_hash_alloc(sz); + if (!nspi) goto out_byspi; - net->xfrm.state_byseq = xfrm_hash_alloc(sz); - if (!net->xfrm.state_byseq) + rcu_assign_pointer(net->xfrm.state_byspi, nspi); + + nseq = xfrm_hash_alloc(sz); + if (!nseq) goto out_byseq; + rcu_assign_pointer(net->xfrm.state_byseq, nseq); net->xfrm.state_cache_input = alloc_percpu(struct hlist_head); if (!net->xfrm.state_cache_input) @@ -3295,17 +3305,19 @@ int __net_init xfrm_state_init(struct net *net) return 0; out_state_cache_input: - xfrm_hash_free(net->xfrm.state_byseq, sz); + xfrm_hash_free(nseq, sz); out_byseq: - xfrm_hash_free(net->xfrm.state_byspi, sz); + xfrm_hash_free(nspi, sz); out_byspi: - xfrm_hash_free(net->xfrm.state_bysrc, sz); + xfrm_hash_free(nsrc, sz); out_bysrc: - xfrm_hash_free(net->xfrm.state_bydst, sz); + xfrm_hash_free(ndst, sz); out_bydst: return -ENOMEM; } +#define xfrm_state_deref_netexit(table) \ + rcu_dereference_protected((table), true /* netns is going away */) void xfrm_state_fini(struct net *net) { unsigned int sz; @@ -3318,17 +3330,17 @@ 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)); + WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_byseq) + i)); + WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_byspi) + i)); + WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_bysrc) + i)); + WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_bydst) + i)); } sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head); - xfrm_hash_free(net->xfrm.state_byseq, sz); - xfrm_hash_free(net->xfrm.state_byspi, sz); - xfrm_hash_free(net->xfrm.state_bysrc, sz); - xfrm_hash_free(net->xfrm.state_bydst, sz); + xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_byseq), sz); + xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_byspi), sz); + xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_bysrc), sz); + xfrm_hash_free(xfrm_state_deref_netexit(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 403b5ecac2c5..1656b487f833 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -35,6 +35,15 @@ #endif #include <linux/unaligned.h> +static struct sock *xfrm_net_nlsk(const struct net *net, const struct sk_buff *skb) +{ + /* get the source of this request, see netlink_unicast_kernel */ + const struct sock *sk = NETLINK_CB(skb).sk; + + /* sk is refcounted, the netns stays alive and nlsk with it */ + return rcu_dereference_protected(net->xfrm.nlsk, sk->sk_net_refcnt); +} + static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type, struct netlink_ext_ack *extack) { @@ -1727,7 +1736,7 @@ static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh, err = build_spdinfo(r_skb, net, sportid, seq, *flags); BUG_ON(err < 0); - return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid); + return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, sportid); } static inline unsigned int xfrm_sadinfo_msgsize(void) @@ -1787,7 +1796,7 @@ static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh, err = build_sadinfo(r_skb, net, sportid, seq, *flags); BUG_ON(err < 0); - return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid); + return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, sportid); } static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -1807,7 +1816,7 @@ static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh, if (IS_ERR(resp_skb)) { err = PTR_ERR(resp_skb); } else { - err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid); + err = nlmsg_unicast(xfrm_net_nlsk(net, skb), resp_skb, NETLINK_CB(skb).portid); } xfrm_state_put(x); out_noput: @@ -1850,6 +1859,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]); if (pcpu_num >= num_possible_cpus()) { err = -EINVAL; + NL_SET_ERR_MSG(extack, "pCPU number too big"); goto out_noput; } } @@ -1897,7 +1907,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, } } - err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid); + err = nlmsg_unicast(xfrm_net_nlsk(net, skb), resp_skb, NETLINK_CB(skb).portid); out: xfrm_state_put(x); @@ -2542,7 +2552,7 @@ static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh, r_up->out = net->xfrm.policy_default[XFRM_POLICY_OUT]; nlmsg_end(r_skb, r_nlh); - return nlmsg_unicast(net->xfrm.nlsk, r_skb, portid); + return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, portid); } static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2608,7 +2618,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (IS_ERR(resp_skb)) { err = PTR_ERR(resp_skb); } else { - err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, + err = nlmsg_unicast(xfrm_net_nlsk(net, skb), resp_skb, NETLINK_CB(skb).portid); } } else { @@ -2781,7 +2791,7 @@ static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh, err = build_aevent(r_skb, x, &c); BUG_ON(err < 0); - err = nlmsg_unicast(net->xfrm.nlsk, r_skb, NETLINK_CB(skb).portid); + err = nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, NETLINK_CB(skb).portid); spin_unlock_bh(&x->lock); xfrm_state_put(x); return err; @@ -3001,8 +3011,10 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_SA_PCPU]) { x->pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]); err = -EINVAL; - if (x->pcpu_num >= num_possible_cpus()) + if (x->pcpu_num >= num_possible_cpus()) { + NL_SET_ERR_MSG(extack, "pCPU number too big"); goto free_state; + } } err = verify_newpolicy_info(&ua->policy, extack); @@ -3483,7 +3495,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, goto err; } - err = netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c); + err = netlink_dump_start(xfrm_net_nlsk(net, skb), skb, nlh, &c); goto err; } @@ -3673,7 +3685,7 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) } if (x->if_id) l += nla_total_size(sizeof(x->if_id)); - if (x->pcpu_num) + if (x->pcpu_num != UINT_MAX) l += nla_total_size(sizeof(x->pcpu_num)); /* Must count x->lastused as it may become non-zero behind our back. */ diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile index 45a3e7ad3dcb..02d6f51d5a06 100644 --- a/tools/testing/selftests/drivers/net/team/Makefile +++ b/tools/testing/selftests/drivers/net/team/Makefile @@ -3,6 +3,7 @@ TEST_PROGS := \ dev_addr_lists.sh \ + non_ether_header_ops.sh \ options.sh \ propagation.sh \ refleak.sh \ diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config index 558e1d0cf565..5d36a22ef080 100644 --- a/tools/testing/selftests/drivers/net/team/config +++ b/tools/testing/selftests/drivers/net/team/config @@ -1,7 +1,9 @@ +CONFIG_BONDING=y CONFIG_DUMMY=y CONFIG_IPV6=y CONFIG_MACVLAN=y CONFIG_NETDEVSIM=m +CONFIG_NET_IPGRE=y CONFIG_NET_TEAM=y CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=y CONFIG_NET_TEAM_MODE_LOADBALANCE=y diff --git a/tools/testing/selftests/drivers/net/team/non_ether_header_ops.sh b/tools/testing/selftests/drivers/net/team/non_ether_header_ops.sh new file mode 100755 index 000000000000..948a43576bdc --- /dev/null +++ b/tools/testing/selftests/drivers/net/team/non_ether_header_ops.sh @@ -0,0 +1,41 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# shellcheck disable=SC2154 +# +# Reproduce the non-Ethernet header_ops confusion scenario with: +# g0 (gre) -> b0 (bond) -> t0 (team) +# +# Before the fix, direct header_ops inheritance in this stack could call +# callbacks with the wrong net_device context and crash. + +lib_dir=$(dirname "$0") +source "$lib_dir"/../../../net/lib.sh + +trap cleanup_all_ns EXIT + +setup_ns ns1 + +ip -n "$ns1" link add d0 type dummy +ip -n "$ns1" addr add 10.10.10.1/24 dev d0 +ip -n "$ns1" link set d0 up + +ip -n "$ns1" link add g0 type gre local 10.10.10.1 +ip -n "$ns1" link add b0 type bond mode active-backup +ip -n "$ns1" link add t0 type team + +ip -n "$ns1" link set g0 master b0 +ip -n "$ns1" link set b0 master t0 + +ip -n "$ns1" link set g0 up +ip -n "$ns1" link set b0 up +ip -n "$ns1" link set t0 up + +# IPv6 address assignment triggers MLD join reports that call +# dev_hard_header() on t0, exercising the inherited header_ops path. +ip -n "$ns1" -6 addr add 2001:db8:1::1/64 dev t0 nodad +for i in $(seq 1 20); do + ip netns exec "$ns1" ping -6 -I t0 ff02::1 -c1 -W1 &>/dev/null || true +done + +echo "PASS: non-Ethernet header_ops stacking did not crash" +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index c5694cc4ddd2..829f72c8ee07 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -868,6 +868,64 @@ fib6_gc_test() check_rt_num 5 $($IP -6 route list |grep -v expires|grep 2001:20::|wc -l) log_test $ret 0 "ipv6 route garbage collection (replace with permanent)" + # Delete dummy_10 and remove all routes + $IP link del dev dummy_10 + + # rd6 is required for the next test. (ipv6toolkit) + if [ ! -x "$(command -v rd6)" ]; then + echo "SKIP: rd6 not found." + set +e + cleanup &> /dev/null + return + fi + + setup_ns ns2 + $IP link add veth1 type veth peer veth2 netns $ns2 + $IP link set veth1 up + ip -netns $ns2 link set veth2 up + $IP addr add fe80:dead::1/64 dev veth1 + ip -netns $ns2 addr add fe80:dead::2/64 dev veth2 + + # Add NTF_ROUTER neighbour to prevent rt6_age_examine_exception() + # from removing not-yet-expired exceptions. + ip -netns $ns2 link set veth2 address 00:11:22:33:44:55 + $IP neigh add fe80:dead::3 lladdr 00:11:22:33:44:55 dev veth1 router + + $NS_EXEC sysctl -wq net.ipv6.conf.veth1.accept_redirects=1 + $NS_EXEC sysctl -wq net.ipv6.conf.veth1.forwarding=0 + + # Temporary routes + for i in $(seq 1 5); do + # Expire route after $EXPIRE seconds + $IP -6 route add 2001:10::$i \ + via fe80:dead::2 dev veth1 expires $EXPIRE + + ip netns exec $ns2 rd6 -i veth2 \ + -s fe80:dead::2 -d fe80:dead::1 \ + -r 2001:10::$i -t fe80:dead::3 -p ICMP6 + done + + check_rt_num 5 $($IP -6 route list | grep expires | grep 2001:10:: | wc -l) + + # Promote to permanent routes by "prepend" (w/o NLM_F_EXCL and NLM_F_REPLACE) + for i in $(seq 1 5); do + # -EEXIST, but the temporary route becomes the permanent route. + $IP -6 route append 2001:10::$i \ + via fe80:dead::2 dev veth1 2>/dev/null || true + done + + check_rt_num 5 $($IP -6 route list | grep -v expires | grep 2001:10:: | wc -l) + check_rt_num 5 $($IP -6 route list cache | grep 2001:10:: | wc -l) + + # Trigger GC instead of waiting $GC_WAIT_TIME. + # rt6_nh_dump_exceptions() just skips expired exceptions. + $NS_EXEC sysctl -wq net.ipv6.route.flush=1 + check_rt_num 0 $($IP -6 route list cache | grep 2001:10:: | wc -l) + log_test $ret 0 "ipv6 route garbage collection (promote to permanent routes)" + + $IP neigh del fe80:dead::3 lladdr 00:11:22:33:44:55 dev veth1 router + $IP link del veth1 + # ra6 is required for the next test. (ipv6toolkit) if [ ! -x "$(command -v ra6)" ]; then echo "SKIP: ra6 not found." @@ -876,9 +934,6 @@ fib6_gc_test() return fi - # Delete dummy_10 and remove all routes - $IP link del dev dummy_10 - # Create a pair of veth devices to send a RA message from one # device to another. $IP link add veth1 type veth peer name veth2 diff --git a/tools/testing/selftests/net/netfilter/nft_concat_range.sh b/tools/testing/selftests/net/netfilter/nft_concat_range.sh index 394166f224a4..ffdc6ccc6511 100755 --- a/tools/testing/selftests/net/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/net/netfilter/nft_concat_range.sh @@ -29,7 +29,8 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto net6_port_net6_port net_port_mac_proto_net" # Reported bugs, also described by TYPE_ variables below -BUGS="flush_remove_add reload net_port_proto_match avx2_mismatch doublecreate insert_overlap" +BUGS="flush_remove_add reload net_port_proto_match avx2_mismatch doublecreate + insert_overlap load_flush_load4 load_flush_load8" # List of possible paths to pktgen script from kernel tree for performance tests PKTGEN_SCRIPT_PATHS=" @@ -432,6 +433,30 @@ race_repeat 0 perf_duration 0 " +TYPE_load_flush_load4=" +display reload with flush, 4bit groups +type_spec ipv4_addr . ipv4_addr +chain_spec ip saddr . ip daddr +dst addr4 +proto icmp + +race_repeat 0 + +perf_duration 0 +" + +TYPE_load_flush_load8=" +display reload with flush, 8bit groups +type_spec ipv4_addr . ipv4_addr +chain_spec ip saddr . ip daddr +dst addr4 +proto icmp + +race_repeat 0 + +perf_duration 0 +" + # Set template for all tests, types and rules are filled in depending on test set_template=' flush ruleset @@ -1997,6 +2022,49 @@ test_bug_insert_overlap() return 0 } +test_bug_load_flush_load4() +{ + local i + + setup veth send_"${proto}" set || return ${ksft_skip} + + for i in $(seq 0 255); do + local addelem="add element inet filter test" + local j + + for j in $(seq 0 20); do + echo "$addelem { 10.$j.0.$i . 10.$j.1.$i }" + echo "$addelem { 10.$j.0.$i . 10.$j.2.$i }" + done + done > "$tmp" + + nft -f "$tmp" || return 1 + + ( echo "flush set inet filter test";cat "$tmp") | nft -f - + [ $? -eq 0 ] || return 1 + + return 0 +} + +test_bug_load_flush_load8() +{ + local i + + setup veth send_"${proto}" set || return ${ksft_skip} + + for i in $(seq 1 100); do + echo "add element inet filter test { 10.0.0.$i . 10.0.1.$i }" + echo "add element inet filter test { 10.0.0.$i . 10.0.2.$i }" + done > "$tmp" + + nft -f "$tmp" || return 1 + + ( echo "flush set inet filter test";cat "$tmp") | nft -f - + [ $? -eq 0 ] || return 1 + + return 0 +} + test_reported_issues() { eval test_bug_"${subtest}" } |
