diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-05-19 05:50:29 -1000 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-05-19 05:50:29 -1000 |
commit | d904c8cc0302393640bc29ee62193f88ddc53126 (patch) | |
tree | a8c72d018d7bd0a9682a88d8e7199bfb306f52ae | |
parent | f993aed406eaf968ba3867a76bb46c95336a33d0 (diff) | |
parent | fbb3abdf2223cd0dfc07de85fe5a43ba7f435bdf (diff) |
Merge tag 'net-5.18-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni:
"Including fixes from can, xfrm and netfilter subtrees.
Notably this reverts a recent TCP/DCCP netns-related change to address
a possible UaF.
Current release - regressions:
- tcp: revert "tcp/dccp: get rid of inet_twsk_purge()"
- xfrm: set dst dev to blackhole_netdev instead of loopback_dev in
ifdown
Previous releases - regressions:
- netfilter: flowtable: fix TCP flow teardown
- can: revert "can: m_can: pci: use custom bit timings for Elkhart
Lake"
- xfrm: check encryption module availability consistency
- eth: vmxnet3: fix possible use-after-free bugs in
vmxnet3_rq_alloc_rx_buf()
- eth: mlx5: initialize flow steering during driver probe
- eth: ice: fix crash when writing timestamp on RX rings
Previous releases - always broken:
- mptcp: fix checksum byte order
- eth: lan966x: fix assignment of the MAC address
- eth: mlx5: remove HW-GRO from reported features
- eth: ftgmac100: disable hardware checksum on AST2600"
* tag 'net-5.18-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (50 commits)
net: bridge: Clear offload_fwd_mark when passing frame up bridge interface.
ptp: ocp: change sysfs attr group handling
selftests: forwarding: fix missing backslash
netfilter: nf_tables: disable expression reduction infra
netfilter: flowtable: move dst_check to packet path
netfilter: flowtable: fix TCP flow teardown
net: ftgmac100: Disable hardware checksum on AST2600
igb: skip phy status check where unavailable
nfc: pn533: Fix buggy cleanup order
mptcp: Do TCP fallback on early DSS checksum failure
mptcp: fix checksum byte order
net: af_key: check encryption module availability consistency
net: af_key: add check for pfkey_broadcast in function pfkey_process
net/mlx5: Drain fw_reset when removing device
net/mlx5e: CT: Fix setting flow_source for smfs ct tuples
net/mlx5e: CT: Fix support for GRE tuples
net/mlx5e: Remove HW-GRO from reported features
net/mlx5e: Properly block HW GRO when XDP is enabled
net/mlx5e: Properly block LRO when XDP is enabled
net/mlx5e: Block rx-gro-hw feature in switchdev mode
...
61 files changed, 694 insertions, 362 deletions
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index b3b5bc1c803b..088bb1bcf1ef 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1495,34 +1495,22 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) err = can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); if (err) return err; - cdev->can.bittiming_const = cdev->bit_timing ? - cdev->bit_timing : &m_can_bittiming_const_30X; - - cdev->can.data_bittiming_const = cdev->data_timing ? - cdev->data_timing : - &m_can_data_bittiming_const_30X; + cdev->can.bittiming_const = &m_can_bittiming_const_30X; + cdev->can.data_bittiming_const = &m_can_data_bittiming_const_30X; break; case 31: /* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.1.x */ err = can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); if (err) return err; - cdev->can.bittiming_const = cdev->bit_timing ? - cdev->bit_timing : &m_can_bittiming_const_31X; - - cdev->can.data_bittiming_const = cdev->data_timing ? - cdev->data_timing : - &m_can_data_bittiming_const_31X; + cdev->can.bittiming_const = &m_can_bittiming_const_31X; + cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X; break; case 32: case 33: /* Support both MCAN version v3.2.x and v3.3.0 */ - cdev->can.bittiming_const = cdev->bit_timing ? - cdev->bit_timing : &m_can_bittiming_const_31X; - - cdev->can.data_bittiming_const = cdev->data_timing ? - cdev->data_timing : - &m_can_data_bittiming_const_31X; + cdev->can.bittiming_const = &m_can_bittiming_const_31X; + cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X; cdev->can.ctrlmode_supported |= (m_can_niso_supported(cdev) ? diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index 2c5d40997168..d18b515e6ccc 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -85,9 +85,6 @@ struct m_can_classdev { struct sk_buff *tx_skb; struct phy *transceiver; - const struct can_bittiming_const *bit_timing; - const struct can_bittiming_const *data_timing; - struct m_can_ops *ops; int version; diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c index b56a54d6c5a9..8f184a852a0a 100644 --- a/drivers/net/can/m_can/m_can_pci.c +++ b/drivers/net/can/m_can/m_can_pci.c @@ -18,14 +18,9 @@ #define M_CAN_PCI_MMIO_BAR 0 +#define M_CAN_CLOCK_FREQ_EHL 200000000 #define CTL_CSR_INT_CTL_OFFSET 0x508 -struct m_can_pci_config { - const struct can_bittiming_const *bit_timing; - const struct can_bittiming_const *data_timing; - unsigned int clock_freq; -}; - struct m_can_pci_priv { struct m_can_classdev cdev; @@ -89,40 +84,9 @@ static struct m_can_ops m_can_pci_ops = { .read_fifo = iomap_read_fifo, }; -static const struct can_bittiming_const m_can_bittiming_const_ehl = { - .name = KBUILD_MODNAME, - .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ - .tseg1_max = 64, - .tseg2_min = 1, /* Time segment 2 = phase_seg2 */ - .tseg2_max = 128, - .sjw_max = 128, - .brp_min = 1, - .brp_max = 512, - .brp_inc = 1, -}; - -static const struct can_bittiming_const m_can_data_bittiming_const_ehl = { - .name = KBUILD_MODNAME, - .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ - .tseg1_max = 16, - .tseg2_min = 1, /* Time segment 2 = phase_seg2 */ - .tseg2_max = 8, - .sjw_max = 4, - .brp_min = 1, - .brp_max = 32, - .brp_inc = 1, -}; - -static const struct m_can_pci_config m_can_pci_ehl = { - .bit_timing = &m_can_bittiming_const_ehl, - .data_timing = &m_can_data_bittiming_const_ehl, - .clock_freq = 200000000, -}; - static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) { struct device *dev = &pci->dev; - const struct m_can_pci_config *cfg; struct m_can_classdev *mcan_class; struct m_can_pci_priv *priv; void __iomem *base; @@ -150,8 +114,6 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) if (!mcan_class) return -ENOMEM; - cfg = (const struct m_can_pci_config *)id->driver_data; - priv = cdev_to_priv(mcan_class); priv->base = base; @@ -163,9 +125,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) mcan_class->dev = &pci->dev; mcan_class->net->irq = pci_irq_vector(pci, 0); mcan_class->pm_clock_support = 1; - mcan_class->bit_timing = cfg->bit_timing; - mcan_class->data_timing = cfg->data_timing; - mcan_class->can.clock.freq = cfg->clock_freq; + mcan_class->can.clock.freq = id->driver_data; mcan_class->ops = &m_can_pci_ops; pci_set_drvdata(pci, mcan_class); @@ -218,8 +178,8 @@ static SIMPLE_DEV_PM_OPS(m_can_pci_pm_ops, m_can_pci_suspend, m_can_pci_resume); static const struct pci_device_id m_can_pci_id_table[] = { - { PCI_VDEVICE(INTEL, 0x4bc1), (kernel_ulong_t)&m_can_pci_ehl, }, - { PCI_VDEVICE(INTEL, 0x4bc2), (kernel_ulong_t)&m_can_pci_ehl, }, + { PCI_VDEVICE(INTEL, 0x4bc1), M_CAN_CLOCK_FREQ_EHL, }, + { PCI_VDEVICE(INTEL, 0x4bc2), M_CAN_CLOCK_FREQ_EHL, }, { } /* Terminating Entry */ }; MODULE_DEVICE_TABLE(pci, m_can_pci_id_table); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 60dde29974bf..df51be3cbe06 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2585,8 +2585,10 @@ static int bcm_sysport_probe(struct platform_device *pdev) device_set_wakeup_capable(&pdev->dev, 1); priv->wol_clk = devm_clk_get_optional(&pdev->dev, "sw_sysportwol"); - if (IS_ERR(priv->wol_clk)) - return PTR_ERR(priv->wol_clk); + if (IS_ERR(priv->wol_clk)) { + ret = PTR_ERR(priv->wol_clk); + goto err_deregister_fixed_link; + } /* Set the needed headroom once and for all */ BUILD_BUG_ON(sizeof(struct bcm_tsb) != 8); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index e475be29845c..61284baa0496 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1219,7 +1219,6 @@ static void gem_rx_refill(struct macb_queue *queue) /* Make hw descriptor updates visible to CPU */ rmb(); - queue->rx_prepared_head++; desc = macb_rx_desc(queue, entry); if (!queue->rx_skbuff[entry]) { @@ -1258,6 +1257,7 @@ static void gem_rx_refill(struct macb_queue *queue) dma_wmb(); desc->addr &= ~MACB_BIT(RX_USED); } + queue->rx_prepared_head++; } /* Make descriptor updates visible to hardware */ diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index caf48023f8ea..5231818943c6 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1928,6 +1928,11 @@ static int ftgmac100_probe(struct platform_device *pdev) /* AST2400 doesn't have working HW checksum generation */ if (np && (of_device_is_compatible(np, "aspeed,ast2400-mac"))) netdev->hw_features &= ~NETIF_F_HW_CSUM; + + /* AST2600 tx checksum with NCSI is broken */ + if (priv->use_ncsi && of_device_is_compatible(np, "aspeed,ast2600-mac")) + netdev->hw_features &= ~NETIF_F_HW_CSUM; + if (np && of_get_property(np, "no-hw-checksum", NULL)) netdev->hw_features &= ~(NETIF_F_HW_CSUM | NETIF_F_RXCSUM); netdev->features |= netdev->hw_features; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 6d19c58ccacd..454e01ae09b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -3043,8 +3043,8 @@ ice_vsi_rebuild_get_coalesce(struct ice_vsi *vsi, ice_for_each_q_vector(vsi, i) { struct ice_q_vector *q_vector = vsi->q_vectors[i]; - coalesce[i].itr_tx = q_vector->tx.itr_setting; - coalesce[i].itr_rx = q_vector->rx.itr_setting; + coalesce[i].itr_tx = q_vector->tx.itr_settings; + coalesce[i].itr_rx = q_vector->rx.itr_settings; coalesce[i].intrl = q_vector->intrl; if (i < vsi->num_txq) @@ -3100,21 +3100,21 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, */ if (i < vsi->alloc_rxq && coalesce[i].rx_valid) { rc = &vsi->q_vectors[i]->rx; - rc->itr_setting = coalesce[i].itr_rx; + rc->itr_settings = coalesce[i].itr_rx; ice_write_itr(rc, rc->itr_setting); } else if (i < vsi->alloc_rxq) { rc = &vsi->q_vectors[i]->rx; - rc->itr_setting = coalesce[0].itr_rx; + rc->itr_settings = coalesce[0].itr_rx; ice_write_itr(rc, rc->itr_setting); } if (i < vsi->alloc_txq && coalesce[i].tx_valid) { rc = &vsi->q_vectors[i]->tx; - rc->itr_setting = coalesce[i].itr_tx; + rc->itr_settings = coalesce[i].itr_tx; ice_write_itr(rc, rc->itr_setting); } else if (i < vsi->alloc_txq) { rc = &vsi->q_vectors[i]->tx; - rc->itr_setting = coalesce[0].itr_tx; + rc->itr_settings = coalesce[0].itr_tx; ice_write_itr(rc, rc->itr_setting); } @@ -3128,12 +3128,12 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, for (; i < vsi->num_q_vectors; i++) { /* transmit */ rc = &vsi->q_vectors[i]->tx; - rc->itr_setting = coalesce[0].itr_tx; + rc->itr_settings = coalesce[0].itr_tx; ice_write_itr(rc, rc->itr_setting); /* receive */ rc = &vsi->q_vectors[i]->rx; - rc->itr_setting = coalesce[0].itr_rx; + rc->itr_settings = coalesce[0].itr_rx; ice_write_itr(rc, rc->itr_setting); vsi->q_vectors[i]->intrl = coalesce[0].intrl; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 949669fed7d6..963a5f40e071 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -6172,9 +6172,10 @@ static int ice_up_complete(struct ice_vsi *vsi) ice_ptp_link_change(pf, pf->hw.pf_id, true); } - /* clear this now, and the first stats read will be used as baseline */ - vsi->stat_offsets_loaded = false; - + /* Perform an initial read of the statistics registers now to + * set the baseline so counters are ready when interface is up + */ + ice_update_eth_stats(vsi); ice_service_task_schedule(pf); return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index da025c204577..662947c882e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -500,12 +500,19 @@ ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) * This function must be called periodically to ensure that the cached value * is never more than 2 seconds old. It must also be called whenever the PHC * time has been changed. + * + * Return: + * * 0 - OK, successfully updated + * * -EAGAIN - PF was busy, need to reschedule the update */ -static void ice_ptp_update_cached_phctime(struct ice_pf *pf) +static int ice_ptp_update_cached_phctime(struct ice_pf *pf) { u64 systime; int i; + if (test_and_set_bit(ICE_CFG_BUSY, pf->state)) + return -EAGAIN; + /* Read the current PHC time */ systime = ice_ptp_read_src_clk_reg(pf, NULL); @@ -528,6 +535,9 @@ static void ice_ptp_update_cached_phctime(struct ice_pf *pf) WRITE_ONCE(vsi->rx_rings[j]->cached_phctime, systime); } } + clear_bit(ICE_CFG_BUSY, pf->state); + + return 0; } /** @@ -2330,17 +2340,18 @@ static void ice_ptp_periodic_work(struct kthread_work *work) { struct ice_ptp *ptp = container_of(work, struct ice_ptp, work.work); struct ice_pf *pf = container_of(ptp, struct ice_pf, ptp); + int err; if (!test_bit(ICE_FLAG_PTP, pf->flags)) return; - ice_ptp_update_cached_phctime(pf); + err = ice_ptp_update_cached_phctime(pf); ice_ptp_tx_tstamp_cleanup(&pf->hw, &pf->ptp.port.tx); - /* Run twice a second */ + /* Run twice a second or reschedule if phc update failed */ kthread_queue_delayed_work(ptp->kworker, &ptp->work, - msecs_to_jiffies(500)); + msecs_to_jiffies(err ? 10 : 500)); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index cead3eb149bd..ffb3f6a589da 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -384,9 +384,14 @@ struct ice_ring_container { /* this matches the maximum number of ITR bits, but in usec * values, so it is shifted left one bit (bit zero is ignored) */ - u16 itr_setting:13; - u16 itr_reserved:2; - u16 itr_mode:1; + union { + struct { + u16 itr_setting:13; + u16 itr_reserved:2; + u16 itr_mode:1; + }; + u16 itr_settings; + }; enum ice_container_type type; }; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 34b33b21e0dc..68be2976f539 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -5505,7 +5505,8 @@ static void igb_watchdog_task(struct work_struct *work) break; } - if (adapter->link_speed != SPEED_1000) + if (adapter->link_speed != SPEED_1000 || + !hw->phy.ops.read_reg) goto no_wait; /* wait for Remote receiver status OK */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c index 59988e24b704..bec9ed0103a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c @@ -23,7 +23,7 @@ struct mlx5_ct_fs_smfs_matcher { }; struct mlx5_ct_fs_smfs_matchers { - struct mlx5_ct_fs_smfs_matcher smfs_matchers[4]; + struct mlx5_ct_fs_smfs_matcher smfs_matchers[6]; struct list_head used; }; @@ -44,7 +44,8 @@ struct mlx5_ct_fs_smfs_rule { }; static inline void -mlx5_ct_fs_smfs_fill_mask(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, bool ipv4, bool tcp) +mlx5_ct_fs_smfs_fill_mask(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, bool ipv4, bool tcp, + bool gre) { void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, outer_headers); @@ -77,7 +78,7 @@ mlx5_ct_fs_smfs_fill_mask(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, bo MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, tcp_dport); MLX5_SET(fte_match_set_lyr_2_4, headers_c, tcp_flags, ntohs(MLX5_CT_TCP_FLAGS_MASK)); - } else { + } else if (!gre) { MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, udp_sport); MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, udp_dport); } @@ -87,7 +88,7 @@ mlx5_ct_fs_smfs_fill_mask(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, bo static struct mlx5dr_matcher * mlx5_ct_fs_smfs_matcher_create(struct mlx5_ct_fs *fs, struct mlx5dr_table *tbl, bool ipv4, - bool tcp, u32 priority) + bool tcp, bool gre, u32 priority) { struct mlx5dr_matcher *dr_matcher; struct mlx5_flow_spec *spec; @@ -96,7 +97,7 @@ mlx5_ct_fs_smfs_matcher_create(struct mlx5_ct_fs *fs, struct mlx5dr_table *tbl, if (!spec) return ERR_PTR(-ENOMEM); - mlx5_ct_fs_smfs_fill_mask(fs, spec, ipv4, tcp); + mlx5_ct_fs_smfs_fill_mask(fs, spec, ipv4, tcp, gre); spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2 | MLX5_MATCH_OUTER_HEADERS; dr_matcher = mlx5_smfs_matcher_create(tbl, priority, spec); @@ -108,7 +109,7 @@ mlx5_ct_fs_smfs_matcher_create(struct mlx5_ct_fs *fs, struct mlx5dr_table *tbl, } static struct mlx5_ct_fs_smfs_matcher * -mlx5_ct_fs_smfs_matcher_get(struct mlx5_ct_fs *fs, bool nat, bool ipv4, bool tcp) +mlx5_ct_fs_smfs_matcher_get(struct mlx5_ct_fs *fs, bool nat, bool ipv4, bool tcp, bool gre) { struct mlx5_ct_fs_smfs *fs_smfs = mlx5_ct_fs_priv(fs); struct mlx5_ct_fs_smfs_matcher *m, *smfs_matcher; @@ -119,7 +120,7 @@ mlx5_ct_fs_smfs_matcher_get(struct mlx5_ct_fs *fs, bool nat, bool ipv4, bool tcp int prio; matchers = nat ? &fs_smfs->matchers_nat : &fs_smfs->matchers; - smfs_matcher = &matchers->smfs_matchers[ipv4 * 2 + tcp]; + smfs_matcher = &matchers->smfs_matchers[ipv4 * 3 + tcp * 2 + gre]; if (refcount_inc_not_zero(&smfs_matcher->ref)) return smfs_matcher; @@ -145,11 +146,11 @@ mlx5_ct_fs_smfs_matcher_get(struct mlx5_ct_fs *fs, bool nat, bool ipv4, bool tcp } tbl = nat ? fs_smfs->ct_nat_tbl : fs_smfs->ct_tbl; - dr_matcher = mlx5_ct_fs_smfs_matcher_create(fs, tbl, ipv4, tcp, prio); + dr_matcher = mlx5_ct_fs_smfs_matcher_create(fs, tbl, ipv4, tcp, gre, prio); if (IS_ERR(dr_matcher)) { netdev_warn(fs->netdev, - "ct_fs_smfs: failed to create matcher (nat %d, ipv4 %d, tcp %d), err: %ld\n", - nat, ipv4, tcp, PTR_ERR(dr_matcher)); + "ct_fs_smfs: failed to create matcher (nat %d, ipv4 %d, tcp %d, gre %d), err: %ld\n", + nat, ipv4, tcp, gre, PTR_ERR(dr_matcher)); smfs_matcher = ERR_CAST(dr_matcher); goto out_unlock; @@ -222,16 +223,17 @@ mlx5_ct_fs_smfs_destroy(struct mlx5_ct_fs *fs) static inline bool mlx5_tc_ct_valid_used_dissector_keys(const u32 used_keys) { -#define DISSECTOR_BIT(name) BIT(FLOW_DISSECTOR_KEY_ ## name) - const u32 basic_keys = DISSECTOR_BIT(BASIC) | DISSECTOR_BIT(CONTROL) | - DISSECTOR_BIT(PORTS) | DISSECTOR_BIT(META); - const u32 ipv4_tcp = basic_keys | DISSECTOR_BIT(IPV4_ADDRS) | DISSECTOR_BIT(TCP); - const u32 ipv4_udp = basic_keys | DISSECTOR_BIT(IPV4_ADDRS); - const u32 ipv6_tcp = basic_keys | DISSECTOR_BIT(IPV6_ADDRS) | DISSECTOR_BIT(TCP); - const u32 ipv6_udp = basic_keys | DISSECTOR_BIT(IPV6_ADDRS); +#define DISS_BIT(name) BIT(FLOW_DISSECTOR_KEY_ ## name) + const u32 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) | DISS_BIT(META); + const u32 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) | DISS_BIT(PORTS) | DISS_BIT(TCP); + const u32 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) | DISS_BIT(PORTS) | DISS_BIT(TCP); + const u32 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) | DISS_BIT(PORTS); + const u32 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) | DISS_BIT(PORTS); + const u32 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS); + const u32 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS); return (used_keys == ipv4_tcp || used_keys == ipv4_udp || used_keys == ipv6_tcp || - used_keys == ipv6_udp); + used_keys == ipv6_udp || used_keys == ipv4_gre || used_keys == ipv6_gre); } static bool @@ -254,20 +256,24 @@ mlx5_ct_fs_smfs_ct_validate_flow_rule(struct mlx5_ct_fs *fs, struct flow_rule *f flow_rule_match_control(flow_rule, &control); flow_rule_match_ipv4_addrs(flow_rule, &ipv4_addrs); flow_rule_match_ipv6_addrs(flow_rule, &ipv6_addrs); - flow_rule_match_ports(flow_rule, &ports); - flow_rule_match_tcp(flow_rule, &tcp); + if (basic.key->ip_proto != IPPROTO_GRE) + flow_rule_match_ports(flow_rule, &ports); + if (basic.key->ip_proto == IPPROTO_TCP) + flow_rule_match_tcp(flow_rule, &tcp); if (basic.mask->n_proto != htons(0xFFFF) || (basic.key->n_proto != htons(ETH_P_IP) && basic.key->n_proto != htons(ETH_P_IPV6)) || basic.mask->ip_proto != 0xFF || - (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP)) { + (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP && + basic.key->ip_proto != IPPROTO_GRE)) { ct_dbg("rule uses unexpected basic match (n_proto 0x%04x/0x%04x, ip_proto 0x%02x/0x%02x)", ntohs(basic.key->n_proto), ntohs(basic.mask->n_proto), basic.key->ip_proto, basic.mask->ip_proto); return false; } - if (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF)) { + if (basic.key->ip_proto != IPPROTO_GRE && + (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF))) { ct_dbg("rule uses ports match (src 0x%04x, dst 0x%04x)", ports.mask->src, ports.mask->dst); return false; @@ -291,7 +297,7 @@ mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, struct mlx5dr_action *actions[5]; struct mlx5dr_rule *rule; int num_actions = 0, err; - bool nat, tcp, ipv4; + bool nat, tcp, ipv4, gre; if (!mlx5_ct_fs_smfs_ct_validate_flow_rule(fs, flow_rule)) return ERR_PTR(-EOPNOTSUPP); @@ -314,15 +320,17 @@ mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, ipv4 = mlx5e_tc_get_ip_version(spec, true) == 4; tcp = MLX5_GET(fte_match_param, spec->match_value, outer_headers.ip_protocol) == IPPROTO_TCP; + gre = MLX5_GET(fte_match_param, spec->match_value, + outer_headers.ip_protocol) == IPPROTO_GRE; - smfs_matcher = mlx5_ct_fs_smfs_matcher_get(fs, nat, ipv4, tcp); + smfs_matcher = mlx5_ct_fs_smfs_matcher_get(fs, nat, ipv4, tcp, gre); if (IS_ERR(smfs_matcher)) { err = PTR_ERR(smfs_matcher); goto err_matcher; } rule = mlx5_smfs_rule_create(smfs_matcher->dr_matcher, spec, num_actions, actions, - MLX5_FLOW_CONTEXT_FLOW_SOURCE_ANY_VPORT); + spec->flow_context.flow_source); if (!rule) { err = -EINVAL; goto err_create; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index a55b066746cb..857840ab1e91 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -14,19 +14,26 @@ static int mlx5e_trap_napi_poll(struct napi_struct *napi, int budget) bool busy = false; int work_done = 0; + rcu_read_lock(); + ch_stats->poll++; work_done = mlx5e_poll_rx_cq(&rq->cq, budget); busy |= work_done == budget; busy |= rq->post_wqes(rq); - if (busy) - return budget; + if (busy) { + work_done = budget; + goto out; + } if (unlikely(!napi_complete_done(napi, work_done))) - return work_done; + goto out; mlx5e_cq_arm(&rq->cq); + +out: + rcu_read_unlock(); return work_done; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2f1dedc721d1..fa229998606c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3864,6 +3864,10 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev if (netdev->features & NETIF_F_NTUPLE) netdev_warn(netdev, "Disabling ntuple, not supported in switchdev mode\n"); + features &= ~NETIF_F_GRO_HW; + if (netdev->features & NETIF_F_GRO_HW) + netdev_warn(netdev, "Disabling HW_GRO, not supported in switchdev mode\n"); + return features; } @@ -3896,6 +3900,25 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, } } + if (params->xdp_prog) { + if (features & NETIF_F_LRO) { + netdev_warn(netdev, "LRO is incompatible with XDP\n"); + features &= ~NETIF_F_LRO; + } + if (features & NETIF_F_GRO_HW) { + netdev_warn(netdev, "HW GRO is incompatible with XDP\n"); + features &= ~NETIF_F_GRO_HW; + } + } + + if (priv->xsk.refcnt) { + if (features & NETIF_F_GRO_HW) { + netdev_warn(netdev, "HW GRO is incompatible with AF_XDP (%u XSKs are active)\n", + priv->xsk.refcnt); + features &= ~NETIF_F_GRO_HW; + } + } + if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) { features &= ~NETIF_F_RXHASH; if (netdev->features & NETIF_F_RXHASH) @@ -4850,10 +4873,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_features |= NETIF_F_HW_VLAN_STAG_TX; - if (!!MLX5_CAP_GEN(mdev, shampo) && - mlx5e_check_fragmented_striding_rq_cap(mdev)) - netdev->hw_features |= NETIF_F_GRO_HW; - if (mlx5e_tunnel_any_tx_proto_supported(mdev)) { netdev->hw_enc_features |= NETIF_F_HW_CSUM; netdev->hw_enc_features |= NETIF_F_TSO; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 816d991f7621..3ad67e6b5586 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2663,28 +2663,6 @@ static void cleanup_root_ns(struct mlx5_flow_root_namespace *root_ns) clean_tree(&root_ns->ns.node); } -void mlx5_cleanup_fs(struct mlx5_core_dev *dev) -{ - struct mlx5_flow_steering *steering = dev->priv.steering; - - cleanup_root_ns(steering->root_ns); - cleanup_root_ns(steering->fdb_root_ns); - steering->fdb_root_ns = NULL; - kfree(steering->fdb_sub_ns); - steering->fdb_sub_ns = NULL; - cleanup_root_ns(steering->port_sel_root_ns); - cleanup_root_ns(steering->sniffer_rx_root_ns); - cleanup_root_ns(steering->sniffer_tx_root_ns); - cleanup_root_ns(steering->rdma_rx_root_ns); - cleanup_root_ns(steering->rdma_tx_root_ns); - cleanup_root_ns(steering->egress_root_ns); - mlx5_cleanup_fc_stats(dev); - kmem_cache_destroy(steering->ftes_cache); - kmem_cache_destroy(steering->fgs_cache); - mlx5_ft_pool_destroy(dev); - kfree(steering); -} - static int init_sniffer_tx_root_ns(struct mlx5_flow_steering *steering) { struct fs_prio *prio; @@ -3086,42 +3064,27 @@ cleanup: return err; } -int mlx5_init_fs(struct mlx5_core_dev *dev) +void mlx5_fs_core_cleanup(struct mlx5_core_dev *dev) { - struct mlx5_flow_steering *steering; - int err = 0; - - err = mlx5_init_fc_stats(dev); - if (err) - return err; - - err = mlx5_ft_pool_init(dev); - if (err) - return err; - - steering = kzalloc(sizeof(*steering), GFP_KERNEL); - if (!steering) { - err = -ENOMEM; - goto err; - } - - steering->dev = dev; - dev->priv.steering = steering; + struct mlx5_flow_steering *steering = dev->priv.steering; - if (mlx5_fs_dr_is_supported(dev)) - steering->mode = MLX5_FLOW_STEERING_MODE_SMFS; - else - steering->mode = MLX5_FLOW_STEERING_MODE_DMFS; + cleanup_root_ns(steering->root_ns); + cleanup_root_ns(steering->fdb_root_ns); + steering->fdb_root_ns = NULL; + kfree(steering->fdb_sub_ns); + steering->fdb_sub_ns = NULL; + cleanup_root_ns(steering->port_sel_root_ns); + cleanup_root_ns(steering->sniffer_rx_root_ns); + cleanup_root_ns(steering->sniffer_tx_root_ns); + cleanup_root_ns(steering->rdma_rx_root_ns); + cleanup_root_ns(steering->rdma_tx_root_ns); + cleanup_root_ns(steering->egress_root_ns); +} - steering->fgs_cache = kmem_cache_create("mlx5_fs_fgs", - sizeof(struct mlx5_flow_group), 0, - 0, NULL); - steering->ftes_cache = kmem_cache_create("mlx5_fs_ftes", sizeof(struct fs_fte), 0, - 0, NULL); - if (!steering->ftes_cache || !steering->fgs_cache) { - err = -ENOMEM; - goto err; - } +int mlx5_fs_core_init(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_steering *steering = dev->priv.steering; + int err = 0; if ((((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && (MLX5_CAP_GEN(dev, nic_flow_table))) || @@ -3180,8 +3143,64 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) } return 0; + +err: + mlx5_fs_core_cleanup(dev); + return err; +} + +void mlx5_fs_core_free(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_steering *steering = dev->priv.steering; + + kmem_cache_destroy(steering->ftes_cache); + kmem_cache_destroy(steering->fgs_cache); + kfree(steering); + mlx5_ft_pool_destroy(dev); + mlx5_cleanup_fc_stats(dev); +} + +int mlx5_fs_core_alloc(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_steering *steering; + int err = 0; + + err = mlx5_init_fc_stats(dev); + if (err) + return err; + + err = mlx5_ft_pool_init(dev); + if (err) + goto err; + + steering = kzalloc(sizeof(*steering), GFP_KERNEL); + if (!steering) { + err = -ENOMEM; + goto err; + } + + steering->dev = dev; + dev->priv.steering = steering; + + if (mlx5_fs_dr_is_supported(dev)) + steering->mode = MLX5_FLOW_STEERING_MODE_SMFS; + else + steering->mode = MLX5_FLOW_STEERING_MODE_DMFS; + + steering->fgs_cache = kmem_cache_create("mlx5_fs_fgs", + sizeof(struct mlx5_flow_group), 0, + 0, NULL); + steering->ftes_cache = kmem_cache_create("mlx5_fs_ftes", sizeof(struct fs_fte), 0, + 0, NULL); + if (!steering->ftes_cache || !steering->fgs_cache) { + err = -ENOMEM; + goto err; + } + + return 0; + err: - mlx5_cleanup_fs(dev); + mlx5_fs_core_free(dev); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index c488a7c5b07e..3f20523e514f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -298,8 +298,10 @@ int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns, enum mlx5_flow_steering_mode mode); -int mlx5_init_fs(struct mlx5_core_dev *dev); -void mlx5_cleanup_fs(struct mlx5_core_dev *dev); +int mlx5_fs_core_alloc(struct mlx5_core_dev *dev); +void mlx5_fs_core_free(struct mlx5_core_dev *dev); +int mlx5_fs_core_init(struct mlx5_core_dev *dev); +void mlx5_fs_core_cleanup(struct mlx5_core_dev *dev); int mlx5_fs_egress_acls_init(struct mlx5_core_dev *dev, int total_vports); void mlx5_fs_egress_acls_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index ca1aba845dd6..81eb67fb95b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -8,7 +8,8 @@ enum { MLX5_FW_RESET_FLAGS_RESET_REQUESTED, MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, - MLX5_FW_RESET_FLAGS_PENDING_COMP + MLX5_FW_RESET_FLAGS_PENDING_COMP, + MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS }; struct mlx5_fw_reset { @@ -208,7 +209,10 @@ static void poll_sync_reset(struct timer_list *t) if (fatal_error) { mlx5_core_warn(dev, "Got Device Reset\n"); - queue_work(fw_reset->wq, &fw_reset->reset_reload_work); + if (!test_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags)) + queue_work(fw_reset->wq, &fw_reset->reset_reload_work); + else + mlx5_core_err(dev, "Device is being removed, Drop new reset work\n"); return; } @@ -433,9 +437,12 @@ static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long acti struct mlx5_fw_reset *fw_reset = mlx5_nb_cof(nb, struct mlx5_fw_reset, nb); struct mlx5_eqe *eqe = data; + if (test_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags)) + return NOTIFY_DONE; + switch (eqe->sub_type) { case MLX5_GENERAL_SUBTYPE_FW_LIVE_PATCH_EVENT: - queue_work(fw_reset->wq, &fw_reset->fw_live_patch_work); + queue_work(fw_reset->wq, &fw_reset->fw_live_patch_work); break; case MLX5_GENERAL_SUBTYPE_PCI_SYNC_FOR_FW_UPDATE_EVENT: mlx5_sync_reset_events_handle(fw_reset, eqe); @@ -479,6 +486,18 @@ void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev) mlx5_eq_notifier_unregister(dev, &dev->priv.fw_reset->nb); } +void mlx5_drain_fw_reset(struct mlx5_core_dev *dev) +{ + struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + + set_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags); + cancel_work_sync(&fw_reset->fw_live_patch_work); + cancel_work_sync(&fw_reset->reset_request_work); + cancel_work_sync(&fw_reset->reset_reload_work); + cancel_work_sync(&fw_reset->reset_now_work); + cancel_work_sync(&fw_reset->reset_abort_work); +} + int mlx5_fw_reset_init(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h index 694fc7cb2684..dc141c7e641a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h @@ -16,6 +16,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev); int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev); void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev); void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev); +void mlx5_drain_fw_reset(struct mlx5_core_dev *dev); int mlx5_fw_reset_init(struct mlx5_core_dev *dev); void mlx5_fw_reset_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 2589e39eb9c7..ef196cb764e2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -938,6 +938,12 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) goto err_sf_table_cleanup; } + err = mlx5_fs_core_alloc(dev); + if (err) { + mlx5_core_err(dev, "Failed to alloc flow steering\n"); + goto err_fs; + } + dev->dm = mlx5_dm_create(dev); if (IS_ERR(dev->dm)) mlx5_core_warn(dev, "Failed to init device memory%d\n", err); @@ -948,6 +954,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) return 0; +err_fs: + mlx5_sf_table_cleanup(dev); err_sf_table_cleanup: mlx5_sf_hw_table_cleanup(dev); err_sf_hw_table_cleanup: @@ -985,6 +993,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_hv_vhca_destroy(dev->hv_vhca); mlx5_fw_tracer_destroy(dev->tracer); mlx5_dm_cleanup(dev); + mlx5_fs_core_free(dev); mlx5_sf_table_cleanup(dev); mlx5_sf_hw_table_cleanup(dev); mlx5_vhca_event_cleanup(dev); @@ -1191,7 +1200,7 @@ static int mlx5_load(struct mlx5_core_dev *dev) goto err_tls_start; } - err = mlx5_init_fs(dev); + err = mlx5_fs_core_init(dev); if (err) { mlx5_core_err(dev, "Failed to init flow steering\n"); goto err_fs; @@ -1236,7 +1245,7 @@ err_ec: err_vhca: mlx5_vhca_event_stop(dev); err_set_hca: - mlx5_cleanup_fs(dev); + mlx5_fs_core_cleanup(dev); err_fs: mlx5_accel_tls_cleanup(dev); err_tls_start: @@ -1265,7 +1274,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev) mlx5_ec_cleanup(dev); mlx5_sf_hw_table_destroy(dev); mlx5_vhca_event_stop(dev); - mlx5_cleanup_fs(dev); + mlx5_fs_core_cleanup(dev); mlx5_accel_ipsec_cleanup(dev); mlx5_accel_tls_cleanup(dev); mlx5_fpga_device_stop(dev); @@ -1618,6 +1627,10 @@ static void remove_one(struct pci_dev *pdev) struct mlx5_core_dev *dev = pci_get_drvdata(pdev); struct devlink *devlink = priv_to_devlink(dev); + /* mlx5_drain_fw_reset() is using devlink APIs. Hence, we must drain + * fw_reset before unregistering the devlink. + */ + mlx5_drain_fw_reset(dev); devlink_unregister(devlink); mlx5_sriov_disable(pdev); mlx5_crdump_disable(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 850937cd8bf9..1383550f44c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -530,6 +530,37 @@ static int dr_action_handle_cs_recalc(struct mlx5dr_domain *dmn, return 0; } +static void dr_action_modify_ttl_adjust(struct mlx5dr_domain *dmn, + struct mlx5dr_ste_actions_attr *attr, + bool rx_rule, + bool *recalc_cs_required) +{ + *recalc_cs_required = false; + + /* if device supports csum recalculation - no adjustment needed */ + if (mlx5dr_ste_supp_ttl_cs_recalc(&dmn->info.caps)) + return; + + /* no adjustment needed on TX rules */ + if (!rx_rule) + return; + + if (!MLX5_CAP_ESW_FLOWTABLE(dmn->mdev, fdb_ipv4_ttl_modify)) { + /* Ignore the modify TTL action. + * It is always kept as last HW action. + */ + attr->modify_actions--; + return; + } + + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB) + /* Due to a HW bug on some devices, modifying TTL on RX flows + * will cause an incorrect checksum calculation. In such cases + * we will use a FW table to recalculate the checksum. + */ + *recalc_cs_required = true; +} + static void dr_action_print_sequence(struct mlx5dr_domain *dmn, struct mlx5dr_action *actions[], int last_idx) @@ -650,8 +681,9 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, case DR_ACTION_TYP_MODIFY_HDR: attr.modify_index = action->rewrite->index; attr.modify_actions = action->rewrite->num_of_actions; - recalc_cs_required = action->rewrite->modify_ttl && - !mlx5dr_ste_supp_ttl_cs_recalc(&dmn->info.caps); + if (action->rewrite->modify_ttl) + dr_action_modify_ttl_adjust(dmn, &attr, rx_rule, + &recalc_cs_required); break; case DR_ACTION_TYP_L2_TO_TNL_L2: case DR_ACTION_TYP_L2_TO_TNL_L3: @@ -732,12 +764,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, *new_hw_ste_arr_sz = nic_matcher->num_of_builders; last_ste = ste_arr + DR_STE_SIZE * (nic_matcher->num_of_builders - 1); - /* Due to a HW bug in some devices, modifying TTL on RX flows will - * cause an incorrect checksum calculation. In this case we will - * use a FW table to recalculate. - */ - if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB && - rx_rule && recalc_cs_required && dest_action) { + if (recalc_cs_required && dest_action) { ret = dr_action_handle_cs_recalc(dmn, dest_action, &attr.final_icm_addr); if (ret) { mlx5dr_err(dmn, @@ -842,7 +869,8 @@ struct mlx5dr_action * mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, struct mlx5dr_action_dest *dests, u32 num_of_dests, - bool ignore_flow_level) + bool ignore_flow_level, + u32 flow_source) { struct mlx5dr_cmd_flow_destination_hw_info *hw_dests; struct mlx5dr_action **ref_actions; @@ -914,7 +942,8 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, reformat_req, &action->dest_tbl->fw_tbl.id, &action->dest_tbl->fw_tbl.group_id, - ignore_flow_level); + ignore_flow_level, + flow_source); if (ret) goto free_action; @@ -1556,12 +1585,6 @@ dr_action_modify_check_is_ttl_modify(const void *sw_action) return sw_field == MLX5_ACTION_IN_FIELD_OUT_IP_TTL; } -static bool dr_action_modify_ttl_ignore(struct mlx5dr_domain *dmn) -{ - return !mlx5dr_ste_supp_ttl_cs_recalc(&dmn->info.caps) && - !MLX5_CAP_ESW_FLOWTABLE(dmn->mdev, fdb_ipv4_ttl_modify); -} - static int dr_actions_convert_modify_header(struct mlx5dr_action *action, u32 max_hw_actions, u32 num_sw_actions, @@ -1573,6 +1596,7 @@ static int dr_actions_convert_modify_header(struct mlx5dr_action *action, const struct mlx5dr_ste_action_modify_field *hw_dst_action_info; const struct mlx5dr_ste_action_modify_field *hw_src_action_info; struct mlx5dr_domain *dmn = action->rewrite->dmn; + __be64 *modify_ttl_sw_action = NULL; int ret, i, hw_idx = 0; __be64 *sw_action; __be64 hw_action; @@ -1585,8 +1609,14 @@ static int dr_actions_convert_modify_header(struct mlx5dr_action *action, action->rewrite->allow_rx = 1; action->rewrite->allow_tx = 1; - for (i = 0; i < num_sw_actions; i++) { - sw_action = &sw_actions[i]; + for (i = 0; i < num_sw_actions || modify_ttl_sw_action; i++) { + /* modify TTL is handled separately, as a last action */ + if (i == num_sw_actions) { + sw_action = modify_ttl_sw_action; + modify_ttl_sw_action = NULL; + } else { + sw_action = &sw_actions[i]; + } ret = dr_action_modify_check_field_limitation(action, sw_action); @@ -1595,10 +1625,9 @@ static int dr_actions_convert_modify_header(struct mlx5dr_action *action, if (!(*modify_ttl) && dr_action_modify_check_is_ttl_modify(sw_action)) { - if (dr_action_modify_ttl_ignore(dmn)) - continue; - + modify_ttl_sw_action = sw_action; *modify_ttl = true; + continue; } /* Convert SW action to HW action */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c index 68a4c32d5f34..f05ef0cd54ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c @@ -104,7 +104,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, bool reformat_req, u32 *tbl_id, u32 *group_id, - bool ignore_flow_level) + bool ignore_flow_level, + u32 flow_source) { struct mlx5dr_cmd_create_flow_table_attr ft_attr = {}; struct mlx5dr_cmd_fte_info fte_info = {}; @@ -139,6 +140,7 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, fte_info.val = val; fte_info.dest_arr = dest; fte_info.ignore_flow_level = ignore_flow_level; + fte_info.flow_context.flow_source = flow_source; ret = mlx5dr_cmd_set_fte(dmn->mdev, 0, 0, &ft_info, *group_id, &fte_info); if (ret) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c index 5a322335f204..2010d4ac6519 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c @@ -420,7 +420,7 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn, * encapsulation. The reason for that is that we support * modify headers for outer headers only */ - if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR] && attr->modify_actions) { dr_ste_v0_set_entry_type(last_ste, DR_STE_TYPE_MODIFY_PKT); dr_ste_v0_set_rewrite_actions(last_ste, attr->modify_actions, @@ -513,7 +513,7 @@ dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn, } } - if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR] && attr->modify_actions) { if (dr_ste_v0_get_entry_type(last_ste) == DR_STE_TYPE_MODIFY_PKT) dr_ste_v0_arr_init_next(&last_ste, added_stes, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 46866a5fc5ca..98320e3945ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -1461,7 +1461,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, bool reformat_req, u32 *tbl_id, u32 *group_id, - bool ignore_flow_level); + bool ignore_flow_level, + u32 flow_source); void mlx5dr_fw_destroy_md_tbl(struct mlx5dr_domain *dmn, u32 tbl_id, u32 group_id); #endif /* _DR_TYPES_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 045b0cf90063..728f81882589 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -520,6 +520,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, } else if (num_term_actions > 1) { bool ignore_flow_level = !!(fte->action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL); + u32 flow_source = fte->flow_context.flow_source; if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || fs_dr_num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { @@ -529,7 +530,8 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, tmp_action = mlx5dr_action_create_mult_dest_tbl(domain, term_actions, num_term_actions, - ignore_flow_level); + ignore_flow_level, + flow_source); if (!tmp_action) { err = -EOPNOTSUPP; goto free_actions; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index ec5cbec0d455..7626c85643b1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -99,7 +99,8 @@ struct mlx5dr_action * mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, struct mlx5dr_action_dest *dests, u32 num_of_dests, - bool ignore_flow_level); + bool ignore_flow_level, + u32 flow_source); struct mlx5dr_action *mlx5dr_action_create_drop(void); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 95830e3e2b1f..05f6dcc9dfd5 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -103,6 +103,24 @@ static int lan966x_create_targets(struct platform_device *pdev, return 0; } +static bool lan966x_port_unique_address(struct net_device *dev) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + int p; + + for (p = 0; p < lan966x->num_phys_ports; ++p) { + port = lan966x->ports[p]; + if (!port || port->dev == dev) + continue; + + if (ether_addr_equal(dev->dev_addr, port->dev->dev_addr)) + return false; + } + + return true; +} + static int lan966x_port_set_mac_address(struct net_device *dev, void *p) { struct lan966x_port *port = netdev_priv(dev); @@ -110,16 +128,26 @@ static int lan966x_port_set_mac_address(struct net_device *dev, void *p) const struct sockaddr *addr = p; int ret; + if (ether_addr_equal(addr->sa_data, dev->dev_addr)) + return 0; + /* Learn the new net device MAC address in the mac table. */ ret = lan966x_mac_cpu_learn(lan966x, addr->sa_data, HOST_PVID); if (ret) return ret; + /* If there is another port with the same address as the dev, then don't + * delete it from the MAC table + */ + if (!lan966x_port_unique_address(dev)) + goto out; + /* Then forget the previous one. */ ret = lan966x_mac_cpu_forget(lan966x, dev->dev_addr, HOST_PVID); if (ret) return ret; +out: eth_hw_addr_set(dev, addr->sa_data); return ret; } diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index b30589a135c2..06f4d9a9e938 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -3614,7 +3614,8 @@ static void ql_reset_work(struct work_struct *work) qdev->mem_map_registers; unsigned long hw_flags; - if (test_bit((QL_RESET_PER_SCSI | QL_RESET_START), &qdev->flags)) { + if (test_bit(QL_RESET_PER_SCSI, &qdev->flags) || + test_bit(QL_RESET_START, &qdev->flags)) { clear_bit(QL_LINK_MASTER, &qdev->flags); /* diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index bc981043cc80..a701178a1d13 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -1367,9 +1367,10 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) struct gsi_event *event_done; struct gsi_event *event; struct gsi_trans *trans; + u32 trans_count = 0; u32 byte_count = 0; - u32 old_index; u32 event_avail; + u32 old_index; trans_info = &channel->trans_info; @@ -1390,6 +1391,7 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) do { trans->len = __le16_to_cpu(event->len); byte_count += trans->len; + trans_count++; /* Move on to the next event and transaction */ if (--event_avail) @@ -1401,7 +1403,7 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) /* We record RX bytes when they are received */ channel->byte_count += byte_count; - channel->trans_count++; + channel->trans_count += trans_count; } /* Initialize a ring, including allocating DMA memory for its entries */ diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 888e94278a84..cea7b2e2ce96 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -1150,13 +1150,12 @@ static void ipa_endpoint_skb_copy(struct ipa_endpoint *endpoint, return; skb = __dev_alloc_skb(len, GFP_ATOMIC); - if (!skb) - return; - - /* Copy the data into the socket buffer and receive it */ - skb_put(skb, len); - memcpy(skb->data, data, len); - skb->truesize += extra; + if (skb) { + /* Copy the data into the socket buffer and receive it */ + skb_put(skb, len); + memcpy(skb->data, data, len); + skb->truesize += extra; + } ipa_modem_skb_rx(endpoint->netdev, skb); } diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c index 90f3aec55b36..ec010cf2e816 100644 --- a/drivers/net/ipa/ipa_qmi.c +++ b/drivers/net/ipa/ipa_qmi.c @@ -125,7 +125,7 @@ static void ipa_qmi_indication(struct ipa_qmi *ipa_qmi) */ static void ipa_qmi_ready(struct ipa_qmi *ipa_qmi) { - struct ipa *ipa = container_of(ipa_qmi, struct ipa, qmi); + struct ipa *ipa; int ret; /* We aren't ready until the modem and microcontroller are */ diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 3619520340b7..e172743948ed 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -988,6 +988,7 @@ static int pppoe_fill_forward_path(struct net_device_path_ctx *ctx, path->encap.proto = htons(ETH_P_PPP_SES); path->encap.id = be16_to_cpu(po->num); memcpy(path->encap.h_dest, po->pppoe_pa.remote, ETH_ALEN); + memcpy(ctx->daddr, po->pppoe_pa.remote, ETH_ALEN); path->dev = ctx->dev; ctx->dev = dev; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index d9d90baac72a..93e8d119d45f 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -589,6 +589,7 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, if (dma_mapping_error(&adapter->pdev->dev, rbi->dma_addr)) { dev_kfree_skb_any(rbi->skb); + rbi->skb = NULL; rq->stats.rx_buf_alloc_failure++; break; } @@ -613,6 +614,7 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, if (dma_mapping_error(&adapter->pdev->dev, rbi->dma_addr)) { put_page(rbi->page); + rbi->page = NULL; rq->stats.rx_buf_alloc_failure++; break; } @@ -1666,6 +1668,10 @@ vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq, u32 i, ring_idx; struct Vmxnet3_RxDesc *rxd; + /* ring has already been cleaned up */ + if (!rq->rx_ring[0].base) + return; + for (ring_idx = 0; ring_idx < 2; ring_idx++) { for (i = 0; i < rq->rx_ring[ring_idx].size; i++) { #ifdef __BIG_ENDIAN_BITFIELD diff --git a/drivers/nfc/pn533/pn533.c b/drivers/nfc/pn533/pn533.c index a491db46e3bd..d9f6367b9993 100644 --- a/drivers/nfc/pn533/pn533.c +++ b/drivers/nfc/pn533/pn533.c @@ -2787,13 +2787,14 @@ void pn53x_common_clean(struct pn533 *priv) { struct pn533_cmd *cmd, *n; + /* delete the timer before cleanup the worker */ + del_timer_sync(&priv->listen_timer); + flush_delayed_work(&priv->poll_work); destroy_workqueue(priv->wq); skb_queue_purge(&priv->resp_q); - del_timer(&priv->listen_timer); - list_for_each_entry_safe(cmd, n, &priv->cmd_queue, queue) { list_del(&cmd->queue); kfree(cmd); diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index dd45471f6780..860672d6a03c 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -300,7 +300,7 @@ struct ptp_ocp { struct platform_device *spi_flash; struct clk_hw *i2c_clk; struct timer_list watchdog; - const struct ocp_attr_group *attr_tbl; + const struct attribute_group **attr_group; const struct ptp_ocp_eeprom_map *eeprom_map; struct dentry *debug_root; time64_t gnss_lost; @@ -841,7 +841,7 @@ __ptp_ocp_adjtime_locked(struct ptp_ocp *bp, u32 adj_val) } static void -ptp_ocp_adjtime_coarse(struct ptp_ocp *bp, u64 delta_ns) +ptp_ocp_adjtime_coarse(struct ptp_ocp *bp, s64 delta_ns) { struct timespec64 ts; unsigned long flags; @@ -850,7 +850,8 @@ ptp_ocp_adjtime_coarse(struct ptp_ocp *bp, u64 delta_ns) spin_lock_irqsave(&bp->lock, flags); err = __ptp_ocp_gettime_locked(bp, &ts, NULL); if (likely(!err)) { - timespec64_add_ns(&ts, delta_ns); + set_normalized_timespec64(&ts, ts.tv_sec, + ts.tv_nsec + delta_ns); __ptp_ocp_settime_locked(bp, &ts); } spin_unlock_irqrestore(&bp->lock, flags); @@ -1836,6 +1837,42 @@ ptp_ocp_signal_init(struct ptp_ocp *bp) } static void +ptp_ocp_attr_group_del(struct ptp_ocp *bp) +{ + sysfs_remove_groups(&bp->dev.kobj, bp->attr_group); + kfree(bp->attr_group); +} + +static int +ptp_ocp_attr_group_add(struct ptp_ocp *bp, + const struct ocp_attr_group *attr_tbl) +{ + int count, i; + int err; + + count = 0; + for (i = 0; attr_tbl[i].cap; i++) + if (attr_tbl[i].cap & bp->fw_cap) + count++; + + bp->attr_group = kcalloc(count + 1, sizeof(struct attribute_group *), + GFP_KERNEL); + if (!bp->attr_group) + return -ENOMEM; + + count = 0; + for (i = 0; attr_tbl[i].cap; i++) + if (attr_tbl[i].cap & bp->fw_cap) + bp->attr_group[count++] = attr_tbl[i].group; + + err = sysfs_create_groups(&bp->dev.kobj, bp->attr_group); + if (err) + bp->attr_group[0] = NULL; + + return err; +} + +static void ptp_ocp_sma_init(struct ptp_ocp *bp) { u32 reg; @@ -1904,7 +1941,6 @@ ptp_ocp_fb_board_init(struct ptp_ocp *bp, struct ocp_resource *r) bp->flash_start = 1024 * 4096; bp->eeprom_map = fb_eeprom_map; bp->fw_version = ioread32(&bp->image->version); - bp->attr_tbl = fb_timecard_groups; bp->fw_cap = OCP_CAP_BASIC; ver = bp->fw_version & 0xffff; @@ -1918,6 +1954,10 @@ ptp_ocp_fb_board_init(struct ptp_ocp *bp, struct ocp_resource *r) ptp_ocp_sma_init(bp); ptp_ocp_signal_init(bp); + err = ptp_ocp_attr_group_add(bp, fb_timecard_groups); + if (err) + return err; + err = ptp_ocp_fb_set_pins(bp); if (err) return err; @@ -3388,7 +3428,6 @@ ptp_ocp_complete(struct ptp_ocp *bp) { struct pps_device *pps; char buf[32]; - int i, err; if (bp->gnss_port != -1) { sprintf(buf, "ttyS%d", bp->gnss_port); @@ -3413,14 +3452,6 @@ ptp_ocp_complete(struct ptp_ocp *bp) if (pps) ptp_ocp_symlink(bp, pps->dev, "pps"); - for (i = 0; bp->attr_tbl[i].cap; i++) { - if (!(bp->attr_tbl[i].cap & bp->fw_cap)) - continue; - err = sysfs_create_group(&bp->dev.kobj, bp->attr_tbl[i].group); - if (err) - return err; - } - ptp_ocp_debugfs_add_device(bp); return 0; @@ -3492,15 +3523,11 @@ static void ptp_ocp_detach_sysfs(struct ptp_ocp *bp) { struct device *dev = &bp->dev; - int i; sysfs_remove_link(&dev->kobj, "ttyGNSS"); sysfs_remove_link(&dev->kobj, "ttyMAC"); sysfs_remove_link(&dev->kobj, "ptp"); sysfs_remove_link(&dev->kobj, "pps"); - if (bp->attr_tbl) - for (i = 0; bp->attr_tbl[i].cap; i++) - sysfs_remove_group(&dev->kobj, bp->attr_tbl[i].group); } static void @@ -3510,6 +3537,7 @@ ptp_ocp_detach(struct ptp_ocp *bp) ptp_ocp_debugfs_remove_device(bp); ptp_ocp_detach_sysfs(bp); + ptp_ocp_attr_group_del(bp); if (timer_pending(&bp->watchdog)) del_timer_sync(&bp->watchdog); if (bp->ts0) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b1fbe21650bb..f736c020cde2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -900,7 +900,7 @@ struct net_device_path_stack { struct net_device_path_ctx { const struct net_device *dev; - const u8 *daddr; + u8 daddr[ETH_ALEN]; int num_vlans; struct { diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 463ae5d33eb0..5b47545f22d3 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -71,7 +71,6 @@ struct inet_timewait_sock { tw_tos : 8; u32 tw_txhash; u32 tw_priority; - u32 tw_bslot; /* bind bucket slot */ struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; }; @@ -110,6 +109,8 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); +void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family); + static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { diff --git a/include/net/ip.h b/include/net/ip.h index 3984f2c39c4b..0161137914cf 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -56,6 +56,7 @@ struct inet_skb_parm { #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) #define IPSKB_L3SLAVE BIT(7) +#define IPSKB_NOPOLICY BIT(8) u16 frag_max_size; }; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6fb899ff5afc..d2efddce65d4 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1093,6 +1093,18 @@ static inline bool __xfrm_check_nopolicy(struct net *net, struct sk_buff *skb, return false; } +static inline bool __xfrm_check_dev_nopolicy(struct sk_buff *skb, + int dir, unsigned short family) +{ + if (dir != XFRM_POLICY_OUT && family == AF_INET) { + /* same dst may be used for traffic originating from + * devices with different policy settings. + */ + return IPCB(skb)->flags & IPSKB_NOPOLICY; + } + return skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY); +} + static inline int __xfrm_policy_check2(struct sock *sk, int dir, struct sk_buff *skb, unsigned int family, int reverse) @@ -1104,7 +1116,7 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, return __xfrm_policy_check(sk, ndir, skb, family); return __xfrm_check_nopolicy(net, skb, dir) || - (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || + __xfrm_check_dev_nopolicy(skb, dir, family) || __xfrm_policy_check(sk, ndir, skb, family); } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 196417859c4a..68b3e850bcb9 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -39,6 +39,13 @@ static int br_pass_frame_up(struct sk_buff *skb) dev_sw_netstats_rx_add(brdev, skb->len); vg = br_vlan_group_rcu(br); + + /* Reset the offload_fwd_mark because there could be a stacked + * bridge above, and it should not think this bridge it doing + * that bridge's work forwarding out its ports. + */ + br_switchdev_frame_unmark(skb); + /* Bridge is just like any other port. Make sure the * packet is allowed except in promisc mode when someone * may be running packet capture. diff --git a/net/core/dev.c b/net/core/dev.c index 1461c2d9dec8..2771fd22dc6a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -681,11 +681,11 @@ int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, const struct net_device *last_dev; struct net_device_path_ctx ctx = { .dev = dev, - .daddr = daddr, }; struct net_device_path *path; int ret = 0; + memcpy(ctx.daddr, daddr, sizeof(ctx.daddr)); stack->num_paths = 0; while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) { last_dev = ctx.dev; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index ae662567a6cb..0ea29270d7e5 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -1030,9 +1030,15 @@ static void __net_exit dccp_v4_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v4_ctl_sk); } +static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&dccp_hashinfo, AF_INET); +} + static struct pernet_operations dccp_v4_ops = { .init = dccp_v4_init_net, .exit = dccp_v4_exit_net, + .exit_batch = dccp_v4_exit_batch, .id = &dccp_v4_pernet_id, .size = sizeof(struct dccp_v4_pernet), }; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index eab3bd1ee9a0..fa663518fa0e 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1115,9 +1115,15 @@ static void __net_exit dccp_v6_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v6_ctl_sk); } +static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&dccp_hashinfo, AF_INET6); +} + static struct pernet_operations dccp_v6_ops = { .init = dccp_v6_init_net, .exit = dccp_v6_exit_net, + .exit_batch = dccp_v6_exit_batch, .id = &dccp_v6_pernet_id, .size = sizeof(struct dccp_v6_pernet), }; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 9e0bbd026560..0ec501845cb3 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -52,7 +52,8 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) spin_unlock(lock); /* Disassociate with bind bucket. */ - bhead = &hashinfo->bhash[tw->tw_bslot]; + bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num, + hashinfo->bhash_size)]; spin_lock(&bhead->lock); inet_twsk_bind_unhash(tw, hashinfo); @@ -111,12 +112,8 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, Note, that any socket with inet->num != 0 MUST be bound in binding cache, even if it is closed. */ - /* Cache inet_bhashfn(), because 'struct net' might be no longer - * available later in inet_twsk_kill(). - */ - tw->tw_bslot = inet_bhashfn(twsk_net(tw), inet->inet_num, - hashinfo->bhash_size); - bhead = &hashinfo->bhash[tw->tw_bslot]; + bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, + hashinfo->bhash_size)]; spin_lock(&bhead->lock); tw->tw_tb = icsk->icsk_bind_hash; WARN_ON(!icsk->icsk_bind_hash); @@ -257,3 +254,50 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) } } EXPORT_SYMBOL_GPL(__inet_twsk_schedule); + +void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) +{ + struct inet_timewait_sock *tw; + struct sock *sk; + struct hlist_nulls_node *node; + unsigned int slot; + + for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { + struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; +restart_rcu: + cond_resched(); + rcu_read_lock(); +restart: + sk_nulls_for_each_rcu(sk, node, &head->chain) { + if (sk->sk_state != TCP_TIME_WAIT) + continue; + tw = inet_twsk(sk); + if ((tw->tw_family != family) || + refcount_read(&twsk_net(tw)->ns.count)) + continue; + + if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) + continue; + + if (unlikely((tw->tw_family != family) || + refcount_read(&twsk_net(tw)->ns.count))) { + inet_twsk_put(tw); + goto restart; + } + + rcu_read_unlock(); + local_bh_disable(); + inet_twsk_deschedule_put(tw); + local_bh_enable(); + goto restart_rcu; + } + /* If the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto restart; + rcu_read_unlock(); + } +} +EXPORT_SYMBOL_GPL(inet_twsk_purge); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 57abd27e842c..ed01063d8f30 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1726,6 +1726,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct in_device *in_dev = __in_dev_get_rcu(dev); unsigned int flags = RTCF_MULTICAST; struct rtable *rth; + bool no_policy; u32 itag = 0; int err; @@ -1736,8 +1737,12 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (our) flags |= RTCF_LOCAL; + no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY); + if (no_policy) + IPCB(skb)->flags |= IPSKB_NOPOLICY; + rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, - IN_DEV_ORCONF(in_dev, NOPOLICY), false); + no_policy, false); if (!rth) return -ENOBUFS; @@ -1796,7 +1801,7 @@ static int __mkroute_input(struct sk_buff *skb, struct rtable *rth; int err; struct in_device *out_dev; - bool do_cache; + bool do_cache, no_policy; u32 itag = 0; /* get a working reference to the output device */ @@ -1841,6 +1846,10 @@ static int __mkroute_input(struct sk_buff *skb, } } + no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY); + if (no_policy) + IPCB(skb)->flags |= IPSKB_NOPOLICY; + fnhe = find_exception(nhc, daddr); if (do_cache) { if (fnhe) @@ -1853,8 +1862,7 @@ static int __mkroute_input(struct sk_buff *skb, } } - rth = rt_dst_alloc(out_dev->dev, 0, res->type, - IN_DEV_ORCONF(in_dev, NOPOLICY), + rth = rt_dst_alloc(out_dev->dev, 0, res->type, no_policy, IN_DEV_ORCONF(out_dev, NOXFRM)); if (!rth) { err = -ENOBUFS; @@ -2229,6 +2237,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct rtable *rth; struct flowi4 fl4; bool do_cache = true; + bool no_policy; /* IP on this device is disabled. */ @@ -2347,6 +2356,10 @@ brd_input: RT_CACHE_STAT_INC(in_brd); local_input: + no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY); + if (no_policy) + IPCB(skb)->flags |= IPSKB_NOPOLICY; + do_cache &= res->fi && !itag; if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); @@ -2361,7 +2374,7 @@ local_input: rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, - IN_DEV_ORCONF(in_dev, NOPOLICY), false); + no_policy, false); if (!rth) goto e_nobufs; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f9cec624068d..457f5b5d5d4a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3173,6 +3173,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; + inet_twsk_purge(&tcp_hashinfo, AF_INET); + list_for_each_entry(net, net_exit_list, exit_list) tcp_fastopen_ctx_destroy(net); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 13678d3908fa..faaddaf43c90 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2207,9 +2207,15 @@ static void __net_exit tcpv6_net_exit(struct net *net) inet_ctl_sock_destroy(net->ipv6.tcp_sk); } +static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&tcp_hashinfo, AF_INET6); +} + static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, + .exit_batch = tcpv6_net_exit_batch, }; int __init tcpv6_init(void) diff --git a/net/key/af_key.c b/net/key/af_key.c index fd51db3be91c..339d95df19d3 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2826,8 +2826,10 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb void *ext_hdrs[SADB_EXT_MAX]; int err; - pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, - BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); + err = pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, + BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); + if (err) + return err; memset(ext_hdrs, 0, sizeof(ext_hdrs)); err = parse_exthdrs(skb, hdr, ext_hdrs); @@ -2898,7 +2900,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t) break; if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg)) + if (aalg_tmpl_set(t, aalg) && aalg->available) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); @@ -2916,7 +2918,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!ealg->pfkey_supported) continue; - if (!(ealg_tmpl_set(t, ealg))) + if (!(ealg_tmpl_set(t, ealg) && ealg->available)) continue; for (k = 1; ; k++) { @@ -2927,7 +2929,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg)) + if (aalg_tmpl_set(t, aalg) && aalg->available) sz += sizeof(struct sadb_comb); } } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 325383646f5c..b548cec86c9d 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -107,7 +107,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 2; } if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) { - mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + mp_opt->csum = get_unaligned((__force __sum16 *)ptr); mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; ptr += 2; } @@ -221,7 +221,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) { mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; - mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + mp_opt->csum = get_unaligned((__force __sum16 *)ptr); ptr += 2; } @@ -1240,7 +1240,7 @@ static void mptcp_set_rwin(const struct tcp_sock *tp) WRITE_ONCE(msk->rcv_wnd_sent, ack_seq); } -u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) +__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) { struct csum_pseudo_header header; __wsum csum; @@ -1256,15 +1256,25 @@ u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) header.csum = 0; csum = csum_partial(&header, sizeof(header), sum); - return (__force u16)csum_fold(csum); + return csum_fold(csum); } -static u16 mptcp_make_csum(const struct mptcp_ext *mpext) +static __sum16 mptcp_make_csum(const struct mptcp_ext *mpext) { return __mptcp_make_csum(mpext->data_seq, mpext->subflow_seq, mpext->data_len, ~csum_unfold(mpext->csum)); } +static void put_len_csum(u16 len, __sum16 csum, void *data) +{ + __sum16 *sumptr = data + 2; + __be16 *ptr = data; + + put_unaligned_be16(len, ptr); + + put_unaligned(csum, sumptr); +} + void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { @@ -1340,8 +1350,9 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, put_unaligned_be32(mpext->subflow_seq, ptr); ptr += 1; if (opts->csum_reqd) { - put_unaligned_be32(mpext->data_len << 16 | - mptcp_make_csum(mpext), ptr); + put_len_csum(mpext->data_len, + mptcp_make_csum(mpext), + ptr); } else { put_unaligned_be32(mpext->data_len << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); @@ -1392,11 +1403,12 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, goto mp_capable_done; if (opts->csum_reqd) { - put_unaligned_be32(opts->data_len << 16 | - __mptcp_make_csum(opts->data_seq, - opts->subflow_seq, - opts->data_len, - ~csum_unfold(opts->csum)), ptr); + put_len_csum(opts->data_len, + __mptcp_make_csum(opts->data_seq, + opts->subflow_seq, + opts->data_len, + ~csum_unfold(opts->csum)), + ptr); } else { put_unaligned_be32(opts->data_len << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 01809eef29b4..aa51b100e033 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -178,14 +178,13 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk, struct mptcp_pm_data *pm = &msk->pm; bool update_subflows; - update_subflows = (ssk->sk_state == TCP_CLOSE) && - (subflow->request_join || subflow->mp_join); + update_subflows = subflow->request_join || subflow->mp_join; if (!READ_ONCE(pm->work_pending) && !update_subflows) return; spin_lock_bh(&pm->lock); if (update_subflows) - pm->subflows--; + __mptcp_pm_close_subflow(msk); /* Even if this subflow is not really established, tell the PM to try * to pick the next ones, if possible. diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3c1a3036550f..5655a63aa6a8 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -443,7 +443,8 @@ struct mptcp_subflow_context { can_ack : 1, /* only after processing the remote a key */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ - local_id_valid : 1; /* local_id is correctly initialized */ + local_id_valid : 1, /* local_id is correctly initialized */ + valid_csum_seen : 1; /* at least one csum validated */ enum mptcp_data_avail data_avail; u32 remote_nonce; u64 thmac; @@ -723,7 +724,7 @@ void mptcp_token_destroy(struct mptcp_sock *msk); void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn); void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac); -u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum); +__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum); void __init mptcp_pm_init(void); void mptcp_pm_data_init(struct mptcp_sock *msk); @@ -833,6 +834,20 @@ unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk); +/* called under PM lock */ +static inline void __mptcp_pm_close_subflow(struct mptcp_sock *msk) +{ + if (--msk->pm.subflows < mptcp_pm_get_subflows_max(msk)) + WRITE_ONCE(msk->pm.accept_subflow, true); +} + +static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk) +{ + spin_lock_bh(&msk->pm.lock); + __mptcp_pm_close_subflow(msk); + spin_unlock_bh(&msk->pm.lock); +} + void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk); void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index aba260f547da..be76ada89d96 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -888,7 +888,7 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff * { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); u32 offset, seq, delta; - u16 csum; + __sum16 csum; int len; if (!csum_reqd) @@ -955,11 +955,14 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff * subflow->map_data_csum); if (unlikely(csum)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR); - subflow->send_mp_fail = 1; - MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX); + if (subflow->mp_join || subflow->valid_csum_seen) { + subflow->send_mp_fail = 1; + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX); + } return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY; } + subflow->valid_csum_seen = 1; return MAPPING_OK; } @@ -1141,6 +1144,18 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss } } +static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) +{ + struct mptcp_sock *msk = mptcp_sk(subflow->conn); + + if (subflow->mp_join) + return false; + else if (READ_ONCE(msk->csum_enabled)) + return !subflow->valid_csum_seen; + else + return !subflow->fully_established; +} + static bool subflow_check_data_avail(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -1218,7 +1233,7 @@ fallback: return true; } - if (subflow->mp_join || subflow->fully_established) { + if (!subflow_can_fallback(subflow)) { /* fatal protocol error, close the socket. * subflow_error_report() will introduce the appropriate barriers */ @@ -1422,20 +1437,20 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, struct sockaddr_storage addr; int remote_id = remote->id; int local_id = loc->id; + int err = -ENOTCONN; struct socket *sf; struct sock *ssk; u32 remote_token; int addrlen; int ifindex; u8 flags; - int err; if (!mptcp_is_fully_established(sk)) - return -ENOTCONN; + goto err_out; err = mptcp_subflow_create_socket(sk, &sf); if (err) - return err; + goto err_out; ssk = sf->sk; subflow = mptcp_subflow_ctx(ssk); @@ -1492,6 +1507,12 @@ failed_unlink: failed: subflow->disposable = 1; sock_release(sf); + +err_out: + /* we account subflows before the creation, and this failures will not + * be caught by sk_state_change() + */ + mptcp_pm_close_subflow(msk); return err; } diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 3db256da919b..f2def06d1070 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -179,12 +179,11 @@ EXPORT_SYMBOL_GPL(flow_offload_route_init); static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) { - tcp->state = TCP_CONNTRACK_ESTABLISHED; tcp->seen[0].td_maxwin = 0; tcp->seen[1].td_maxwin = 0; } -static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) +static void flow_offload_fixup_ct(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); int l4num = nf_ct_protonum(ct); @@ -193,7 +192,9 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) if (l4num == IPPROTO_TCP) { struct nf_tcp_net *tn = nf_tcp_pernet(net); - timeout = tn->timeouts[TCP_CONNTRACK_ESTABLISHED]; + flow_offload_fixup_tcp(&ct->proto.tcp); + + timeout = tn->timeouts[ct->proto.tcp.state]; timeout -= tn->offload_timeout; } else if (l4num == IPPROTO_UDP) { struct nf_udp_net *tn = nf_udp_pernet(net); @@ -211,18 +212,6 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout); } -static void flow_offload_fixup_ct_state(struct nf_conn *ct) -{ - if (nf_ct_protonum(ct) == IPPROTO_TCP) - flow_offload_fixup_tcp(&ct->proto.tcp); -} - -static void flow_offload_fixup_ct(struct nf_conn *ct) -{ - flow_offload_fixup_ct_state(ct); - flow_offload_fixup_ct_timeout(ct); -} - static void flow_offload_route_release(struct flow_offload *flow) { nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL); @@ -335,8 +324,10 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, u32 timeout; timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); - if (READ_ONCE(flow->timeout) != timeout) + if (timeout - READ_ONCE(flow->timeout) > HZ) WRITE_ONCE(flow->timeout, timeout); + else + return; if (likely(!nf_flowtable_hw_offload(flow_table))) return; @@ -359,22 +350,14 @@ static void flow_offload_del(struct nf_flowtable *flow_table, rhashtable_remove_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node, nf_flow_offload_rhash_params); - - clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status); - - if (nf_flow_has_expired(flow)) - flow_offload_fixup_ct(flow->ct); - else - flow_offload_fixup_ct_timeout(flow->ct); - flow_offload_free(flow); } void flow_offload_teardown(struct flow_offload *flow) { + clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status); set_bit(NF_FLOW_TEARDOWN, &flow->flags); - - flow_offload_fixup_ct_state(flow->ct); + flow_offload_fixup_ct(flow->ct); } EXPORT_SYMBOL_GPL(flow_offload_teardown); @@ -438,33 +421,12 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table, return err; } -static bool flow_offload_stale_dst(struct flow_offload_tuple *tuple) -{ - struct dst_entry *dst; - - if (tuple->xmit_type == FLOW_OFFLOAD_XMIT_NEIGH || - tuple->xmit_type == FLOW_OFFLOAD_XMIT_XFRM) { - dst = tuple->dst_cache; - if (!dst_check(dst, tuple->dst_cookie)) - return true; - } - - return false; -} - -static bool nf_flow_has_stale_dst(struct flow_offload *flow) -{ - return flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple) || - flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple); -} - static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { if (nf_flow_has_expired(flow) || - nf_ct_is_dying(flow->ct) || - nf_flow_has_stale_dst(flow)) - set_bit(NF_FLOW_TEARDOWN, &flow->flags); + nf_ct_is_dying(flow->ct)) + flow_offload_teardown(flow); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { if (test_bit(NF_FLOW_HW, &flow->flags)) { diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 32c0eb1b4821..b350fe9d00b0 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -248,6 +248,15 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) return true; } +static inline bool nf_flow_dst_check(struct flow_offload_tuple *tuple) +{ + if (tuple->xmit_type != FLOW_OFFLOAD_XMIT_NEIGH && + tuple->xmit_type != FLOW_OFFLOAD_XMIT_XFRM) + return true; + + return dst_check(tuple->dst_cache, tuple->dst_cookie); +} + static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, const struct nf_hook_state *state, struct dst_entry *dst) @@ -367,6 +376,11 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (nf_flow_state_check(flow, iph->protocol, skb, thoff)) return NF_ACCEPT; + if (!nf_flow_dst_check(&tuplehash->tuple)) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } + if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; @@ -624,6 +638,11 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (nf_flow_state_check(flow, ip6h->nexthdr, skb, thoff)) return NF_ACCEPT; + if (!nf_flow_dst_check(&tuplehash->tuple)) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } + if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 16c3a39689f4..a096b9fbbbdf 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8342,16 +8342,7 @@ EXPORT_SYMBOL_GPL(nf_tables_trans_destroy_flush_work); static bool nft_expr_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { - if (!expr->ops->reduce) { - pr_warn_once("missing reduce for expression %s ", - expr->ops->type->name); - return false; - } - - if (nft_reduce_is_readonly(expr)) - return false; - - return expr->ops->reduce(track, expr); + return false; } static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *chain) diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 900d48c810a1..6f0b07fe648d 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -36,6 +36,15 @@ static void nft_default_forward_path(struct nf_flow_route *route, route->tuple[dir].xmit_type = nft_xmit_type(dst_cache); } +static bool nft_is_valid_ether_device(const struct net_device *dev) +{ + if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || + dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) + return false; + + return true; +} + static int nft_dev_fill_forward_path(const struct nf_flow_route *route, const struct dst_entry *dst_cache, const struct nf_conn *ct, @@ -47,6 +56,9 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route, struct neighbour *n; u8 nud_state; + if (!nft_is_valid_ether_device(dev)) + goto out; + n = dst_neigh_lookup(dst_cache, daddr); if (!n) return -1; @@ -60,6 +72,7 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route, if (!(nud_state & NUD_VALID)) return -1; +out: return dev_fill_forward_path(dev, ha, stack); } @@ -78,15 +91,6 @@ struct nft_forward_info { enum flow_offload_xmit_type xmit_type; }; -static bool nft_is_valid_ether_device(const struct net_device *dev) -{ - if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || - dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) - return false; - - return true; -} - static void nft_dev_path_info(const struct net_device_path_stack *stack, struct nft_forward_info *info, unsigned char *ha, struct nf_flowtable *flowtable) @@ -119,7 +123,8 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack, info->indev = NULL; break; } - info->outdev = path->dev; + if (!info->outdev) + info->outdev = path->dev; info->encap[info->num_encaps].id = path->encap.id; info->encap[info->num_encaps].proto = path->encap.proto; info->num_encaps++; @@ -293,7 +298,8 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, case IPPROTO_TCP: tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(_tcph), &_tcph); - if (unlikely(!tcph || tcph->fin || tcph->rst)) + if (unlikely(!tcph || tcph->fin || tcph->rst || + !nf_conntrack_tcp_established(ct))) goto out; break; case IPPROTO_UDP: diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index 6055dc9a82aa..aa5e712adf07 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -118,7 +118,7 @@ static int nci_queue_tx_data_frags(struct nci_dev *ndev, skb_frag = nci_skb_alloc(ndev, (NCI_DATA_HDR_SIZE + frag_len), - GFP_KERNEL); + GFP_ATOMIC); if (skb_frag == NULL) { rc = -ENOMEM; goto free_exit; diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index 19703a649b5a..78c4b6addf15 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -153,7 +153,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, i = 0; skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + - NCI_DATA_HDR_SIZE, GFP_KERNEL); + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM; @@ -184,7 +184,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, if (i < data_len) { skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + - NCI_DATA_HDR_SIZE, GFP_KERNEL); + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 0eaaf1f45de1..211c757bfc3c 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -232,6 +232,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, for (i = 0; i < p->tcfp_nkeys; ++i) { u32 cur = p->tcfp_keys[i].off; + /* sanitize the shift value for any later use */ + p->tcfp_keys[i].shift = min_t(size_t, BITS_PER_TYPE(int) - 1, + p->tcfp_keys[i].shift); + /* The AT option can read a single byte, we can bound the actual * value with uchar max. */ diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 00bd0ecff5a1..f1876ea61fdc 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3744,7 +3744,7 @@ static int stale_bundle(struct dst_entry *dst) void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) { - dst->dev = dev_net(dev)->loopback_dev; + dst->dev = blackhole_netdev; dev_hold(dst->dev); dev_put(dev); } diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index c87e674b61b1..e811090f7748 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -86,7 +86,7 @@ TEST_PROGS = bridge_igmp.sh \ vxlan_bridge_1d_port_8472.sh \ vxlan_bridge_1d.sh \ vxlan_bridge_1q_ipv6.sh \ - vxlan_bridge_1q_port_8472_ipv6.sh + vxlan_bridge_1q_port_8472_ipv6.sh \ vxlan_bridge_1q_port_8472.sh \ vxlan_bridge_1q.sh \ vxlan_symmetric_ipv6.sh \ diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 7314257d248a..48ef112f42c2 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1444,6 +1444,33 @@ chk_prio_nr() [ "${dump_stats}" = 1 ] && dump_stats } +chk_subflow_nr() +{ + local need_title="$1" + local msg="$2" + local subflow_nr=$3 + local cnt1 + local cnt2 + + if [ -n "${need_title}" ]; then + printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" + else + printf "%-${nr_blank}s %s" " " "${msg}" + fi + + cnt1=$(ss -N $ns1 -tOni | grep -c token) + cnt2=$(ss -N $ns2 -tOni | grep -c token) + if [ "$cnt1" != "$subflow_nr" -o "$cnt2" != "$subflow_nr" ]; then + echo "[fail] got $cnt1:$cnt2 subflows expected $subflow_nr" + fail_test + dump_stats=1 + else + echo "[ ok ]" + fi + + [ "${dump_stats}" = 1 ] && ( ss -N $ns1 -tOni ; ss -N $ns1 -tOni | grep token; ip -n $ns1 mptcp endpoint ) +} + chk_link_usage() { local ns=$1 @@ -2556,7 +2583,7 @@ fastclose_tests() fi } -implicit_tests() +endpoint_tests() { # userspace pm type prevents add_addr if reset "implicit EP"; then @@ -2578,6 +2605,23 @@ implicit_tests() $ns2 10.0.2.2 id 1 flags signal wait fi + + if reset "delete and re-add"; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 4 0 0 slow & + + wait_mpj $ns2 + pm_nl_del_endpoint $ns2 2 10.0.2.2 + sleep 0.5 + chk_subflow_nr needtitle "after delete" 1 + + pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow + wait_mpj $ns2 + chk_subflow_nr "" "after re-add" 2 + wait + fi } # [$1: error message] @@ -2624,7 +2668,7 @@ all_tests_sorted=( d@deny_join_id0_tests m@fullmesh_tests z@fastclose_tests - I@implicit_tests + I@endpoint_tests ) all_tests_args="" |