diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-11-24 22:19:20 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-11-24 22:19:20 +0300 |
commit | 08ad43d554bacb9769c6a69d5f771f02f5ba411c (patch) | |
tree | b0e5a5d8ffdf637963ba1c382abbfc343958acdf | |
parent | cd89db60e22824b82f9458753fa6cb770cca8bde (diff) | |
parent | 661e5ebbafd26d9d2e3c749f5cf591e55c7364f5 (diff) | |
download | linux-08ad43d554bacb9769c6a69d5f771f02f5ba411c.tar.xz |
Merge tag 'net-6.1-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni:
"Including fixes from rxrpc, netfilter and xfrm.
Current release - regressions:
- dccp/tcp: fix bhash2 issues related to WARN_ON() in
inet_csk_get_port()
- l2tp: don't sleep and disable BH under writer-side sk_callback_lock
- eth: ice: fix handling of burst tx timestamps
Current release - new code bugs:
- xfrm: squelch kernel warning in case XFRM encap type is not
available
- eth: mlx5e: fix possible race condition in macsec extended packet
number update routine
Previous releases - regressions:
- neigh: decrement the family specific qlen
- netfilter: fix ipset regression
- rxrpc: fix race between conn bundle lookup and bundle removal
[ZDI-CAN-15975]
- eth: iavf: do not restart tx queues after reset task failure
- eth: nfp: add port from netdev validation for EEPROM access
- eth: mtk_eth_soc: fix potential memory leak in mtk_rx_alloc()
Previous releases - always broken:
- tipc: set con sock in tipc_conn_alloc
- nfc:
- fix potential memory leaks
- fix incorrect sizing calculations in EVT_TRANSACTION
- eth: octeontx2-af: fix pci device refcount leak
- eth: bonding: fix ICMPv6 header handling when receiving IPv6
messages
- eth: prestera: add missing unregister_netdev() in
prestera_port_create()
- eth: tsnep: fix rotten packets
Misc:
- usb: qmi_wwan: add support for LARA-L6"
* tag 'net-6.1-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (95 commits)
net: thunderx: Fix the ACPI memory leak
octeontx2-af: Fix reference count issue in rvu_sdp_init()
net: altera_tse: release phylink resources in tse_shutdown()
virtio_net: Fix probe failed when modprobe virtio_net
net: wwan: t7xx: Fix the ACPI memory leak
octeontx2-pf: Add check for devm_kcalloc
net: enetc: preserve TX ring priority across reconfiguration
net: marvell: prestera: add missing unregister_netdev() in prestera_port_create()
nfc: st-nci: fix incorrect sizing calculations in EVT_TRANSACTION
nfc: st-nci: fix memory leaks in EVT_TRANSACTION
nfc: st-nci: fix incorrect validating logic in EVT_TRANSACTION
Documentation: networking: Update generic_netlink_howto URL
net/cdc_ncm: Fix multicast RX support for CDC NCM devices with ZLP
net: usb: qmi_wwan: add u-blox 0x1342 composition
l2tp: Don't sleep and disable BH under writer-side sk_callback_lock
net: dm9051: Fix missing dev_kfree_skb() in dm9051_loop_rx()
arcnet: fix potential memory leak in com20020_probe()
ipv4: Fix error return code in fib_table_insert()
net: ethernet: mtk_eth_soc: fix memory leak in error path
net: ethernet: mtk_eth_soc: fix resource leak in error path
...
119 files changed, 917 insertions, 483 deletions
diff --git a/Documentation/networking/generic_netlink.rst b/Documentation/networking/generic_netlink.rst index 59e04ccf80c1..d960dbd7e80e 100644 --- a/Documentation/networking/generic_netlink.rst +++ b/Documentation/networking/generic_netlink.rst @@ -6,4 +6,4 @@ Generic Netlink A wiki document on how to use Generic Netlink can be found here: - * http://www.linuxfoundation.org/collaborate/workgroups/networking/generic_netlink_howto + * https://wiki.linuxfoundation.org/networking/generic_netlink_howto diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c index 24150c933fcb..dc3253b318da 100644 --- a/drivers/net/arcnet/com20020_cs.c +++ b/drivers/net/arcnet/com20020_cs.c @@ -113,6 +113,7 @@ static int com20020_probe(struct pcmcia_device *p_dev) struct com20020_dev *info; struct net_device *dev; struct arcnet_local *lp; + int ret = -ENOMEM; dev_dbg(&p_dev->dev, "com20020_attach()\n"); @@ -142,12 +143,18 @@ static int com20020_probe(struct pcmcia_device *p_dev) info->dev = dev; p_dev->priv = info; - return com20020_config(p_dev); + ret = com20020_config(p_dev); + if (ret) + goto fail_config; + + return 0; +fail_config: + free_arcdev(dev); fail_alloc_dev: kfree(info); fail_alloc_info: - return -ENOMEM; + return ret; } /* com20020_attach */ static void com20020_detach(struct pcmcia_device *link) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e84c49bf4d0c..f298b9b3eb77 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3231,16 +3231,23 @@ static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { struct slave *curr_active_slave, *curr_arp_slave; - struct icmp6hdr *hdr = icmp6_hdr(skb); struct in6_addr *saddr, *daddr; + struct { + struct ipv6hdr ip6; + struct icmp6hdr icmp6; + } *combined, _combined; if (skb->pkt_type == PACKET_OTHERHOST || - skb->pkt_type == PACKET_LOOPBACK || - hdr->icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT) + skb->pkt_type == PACKET_LOOPBACK) + goto out; + + combined = skb_header_pointer(skb, 0, sizeof(_combined), &_combined); + if (!combined || combined->ip6.nexthdr != NEXTHDR_ICMP || + combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT) goto out; - saddr = &ipv6_hdr(skb)->saddr; - daddr = &ipv6_hdr(skb)->daddr; + saddr = &combined->ip6.saddr; + daddr = &combined->ip6.saddr; slave_dbg(bond->dev, slave->dev, "%s: %s/%d av %d sv %d sip %pI6c tip %pI6c\n", __func__, slave->dev->name, bond_slave_state(slave), diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c index 215dd17ca790..4059fcc8c832 100644 --- a/drivers/net/dsa/sja1105/sja1105_mdio.c +++ b/drivers/net/dsa/sja1105/sja1105_mdio.c @@ -256,6 +256,9 @@ static int sja1105_base_tx_mdio_read(struct mii_bus *bus, int phy, int reg) u32 tmp; int rc; + if (reg & MII_ADDR_C45) + return -EOPNOTSUPP; + rc = sja1105_xfer_u32(priv, SPI_READ, regs->mdio_100base_tx + reg, &tmp, NULL); if (rc < 0) @@ -272,6 +275,9 @@ static int sja1105_base_tx_mdio_write(struct mii_bus *bus, int phy, int reg, const struct sja1105_regs *regs = priv->info->regs; u32 tmp = val; + if (reg & MII_ADDR_C45) + return -EOPNOTSUPP; + return sja1105_xfer_u32(priv, SPI_WRITE, regs->mdio_100base_tx + reg, &tmp, NULL); } diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 7633b227b2ca..711d5b5a4c49 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -990,6 +990,7 @@ static int tse_shutdown(struct net_device *dev) int ret; phylink_stop(priv->phylink); + phylink_disconnect_phy(priv->phylink); netif_stop_queue(dev); napi_disable(&priv->napi); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 11d15cd03600..77d4cb4ad782 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -795,16 +795,20 @@ static void bnx2x_vf_enable_traffic(struct bnx2x *bp, struct bnx2x_virtf *vf) static u8 bnx2x_vf_is_pcie_pending(struct bnx2x *bp, u8 abs_vfid) { - struct pci_dev *dev; struct bnx2x_virtf *vf = bnx2x_vf_by_abs_fid(bp, abs_vfid); + struct pci_dev *dev; + bool pending; if (!vf) return false; dev = pci_get_domain_bus_and_slot(vf->domain, vf->bus, vf->devfn); - if (dev) - return bnx2x_is_pcie_pending(dev); - return false; + if (!dev) + return false; + pending = bnx2x_is_pcie_pending(dev); + pci_dev_put(dev); + + return pending; } int bnx2x_vf_flr_clnup_epilog(struct bnx2x *bp, u8 abs_vfid) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 75771825c3f9..98793b2ac2c7 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1794,7 +1794,7 @@ static int liquidio_open(struct net_device *netdev) ifstate_set(lio, LIO_IFSTATE_RUNNING); - if (!OCTEON_CN23XX_PF(oct) || (OCTEON_CN23XX_PF(oct) && !oct->msix_on)) { + if (!OCTEON_CN23XX_PF(oct) || !oct->msix_on) { ret = setup_tx_poll_fn(netdev); if (ret) goto err_poll; @@ -1824,7 +1824,7 @@ static int liquidio_open(struct net_device *netdev) return 0; err_rx_ctrl: - if (!OCTEON_CN23XX_PF(oct) || (OCTEON_CN23XX_PF(oct) && !oct->msix_on)) + if (!OCTEON_CN23XX_PF(oct) || !oct->msix_on) cleanup_tx_poll_fn(netdev); err_poll: if (lio->ptp_clock) { diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 2f6484dc186a..7eb2ddbe9bad 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1436,8 +1436,10 @@ static acpi_status bgx_acpi_match_id(acpi_handle handle, u32 lvl, return AE_OK; } - if (strncmp(string.pointer, bgx_sel, 4)) + if (strncmp(string.pointer, bgx_sel, 4)) { + kfree(string.pointer); return AE_OK; + } acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1, bgx_acpi_register_phy, NULL, bgx, NULL); diff --git a/drivers/net/ethernet/davicom/dm9051.c b/drivers/net/ethernet/davicom/dm9051.c index a523ddda7609..de7105a84747 100644 --- a/drivers/net/ethernet/davicom/dm9051.c +++ b/drivers/net/ethernet/davicom/dm9051.c @@ -798,8 +798,10 @@ static int dm9051_loop_rx(struct board_info *db) } ret = dm9051_stop_mrcmd(db); - if (ret) + if (ret) { + dev_kfree_skb(skb); return ret; + } skb->protocol = eth_type_trans(skb, db->ndev); if (db->ndev->features & NETIF_F_RXCSUM) diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index 48fb391951dd..13d5ff4e0e02 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -542,6 +542,27 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget) return (budget != 0); } +static bool tsnep_tx_pending(struct tsnep_tx *tx) +{ + unsigned long flags; + struct tsnep_tx_entry *entry; + bool pending = false; + + spin_lock_irqsave(&tx->lock, flags); + + if (tx->read != tx->write) { + entry = &tx->entry[tx->read]; + if ((__le32_to_cpu(entry->desc_wb->properties) & + TSNEP_TX_DESC_OWNER_MASK) == + (entry->properties & TSNEP_TX_DESC_OWNER_MASK)) + pending = true; + } + + spin_unlock_irqrestore(&tx->lock, flags); + + return pending; +} + static int tsnep_tx_open(struct tsnep_adapter *adapter, void __iomem *addr, int queue_index, struct tsnep_tx *tx) { @@ -821,6 +842,19 @@ static int tsnep_rx_poll(struct tsnep_rx *rx, struct napi_struct *napi, return done; } +static bool tsnep_rx_pending(struct tsnep_rx *rx) +{ + struct tsnep_rx_entry *entry; + + entry = &rx->entry[rx->read]; + if ((__le32_to_cpu(entry->desc_wb->properties) & + TSNEP_DESC_OWNER_COUNTER_MASK) == + (entry->properties & TSNEP_DESC_OWNER_COUNTER_MASK)) + return true; + + return false; +} + static int tsnep_rx_open(struct tsnep_adapter *adapter, void __iomem *addr, int queue_index, struct tsnep_rx *rx) { @@ -866,6 +900,17 @@ static void tsnep_rx_close(struct tsnep_rx *rx) tsnep_rx_ring_cleanup(rx); } +static bool tsnep_pending(struct tsnep_queue *queue) +{ + if (queue->tx && tsnep_tx_pending(queue->tx)) + return true; + + if (queue->rx && tsnep_rx_pending(queue->rx)) + return true; + + return false; +} + static int tsnep_poll(struct napi_struct *napi, int budget) { struct tsnep_queue *queue = container_of(napi, struct tsnep_queue, @@ -886,9 +931,19 @@ static int tsnep_poll(struct napi_struct *napi, int budget) if (!complete) return budget; - if (likely(napi_complete_done(napi, done))) + if (likely(napi_complete_done(napi, done))) { tsnep_enable_irq(queue->adapter, queue->irq_mask); + /* reschedule if work is already pending, prevent rotten packets + * which are transmitted or received after polling but before + * interrupt enable + */ + if (tsnep_pending(queue)) { + tsnep_disable_irq(queue->adapter, queue->irq_mask); + napi_schedule(napi); + } + } + return min(done, budget - 1); } diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index f8c06c3f9464..8671591cb750 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2058,7 +2058,7 @@ static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) /* enable Tx ints by setting pkt thr to 1 */ enetc_txbdr_wr(hw, idx, ENETC_TBICR0, ENETC_TBICR0_ICEN | 0x1); - tbmr = ENETC_TBMR_EN; + tbmr = ENETC_TBMR_EN | ENETC_TBMR_SET_PRIO(tx_ring->prio); if (tx_ring->ndev->features & NETIF_F_HW_VLAN_CTAG_TX) tbmr |= ENETC_TBMR_VIH; @@ -2461,7 +2461,8 @@ int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) /* Reset all ring priorities to 0 */ for (i = 0; i < priv->num_tx_rings; i++) { tx_ring = priv->tx_ring[i]; - enetc_set_bdr_prio(hw, tx_ring->index, 0); + tx_ring->prio = 0; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); } return 0; @@ -2480,7 +2481,8 @@ int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) */ for (i = 0; i < num_tc; i++) { tx_ring = priv->tx_ring[i]; - enetc_set_bdr_prio(hw, tx_ring->index, i); + tx_ring->prio = i; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); } /* Reset the number of netdev queues based on the TC count */ diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 161930a65f61..c6d8cc15c270 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -95,6 +95,7 @@ struct enetc_bdr { void __iomem *rcir; }; u16 index; + u16 prio; int bd_count; /* # of BDs */ int next_to_use; int next_to_clean; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index a842e1999122..fcebb54224c0 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -137,6 +137,7 @@ int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data) struct tc_taprio_qopt_offload *taprio = type_data; struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_hw *hw = &priv->si->hw; + struct enetc_bdr *tx_ring; int err; int i; @@ -145,16 +146,20 @@ int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data) if (priv->tx_ring[i]->tsd_enable) return -EBUSY; - for (i = 0; i < priv->num_tx_rings; i++) - enetc_set_bdr_prio(hw, priv->tx_ring[i]->index, - taprio->enable ? i : 0); + for (i = 0; i < priv->num_tx_rings; i++) { + tx_ring = priv->tx_ring[i]; + tx_ring->prio = taprio->enable ? i : 0; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + } err = enetc_setup_taprio(ndev, taprio); - - if (err) - for (i = 0; i < priv->num_tx_rings; i++) - enetc_set_bdr_prio(hw, priv->tx_ring[i]->index, - taprio->enable ? 0 : i); + if (err) { + for (i = 0; i < priv->num_tx_rings; i++) { + tx_ring = priv->tx_ring[i]; + tx_ring->prio = taprio->enable ? 0 : i; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + } + } return err; } diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 3f6187c16424..0d1bab4ac1b0 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -298,7 +298,6 @@ struct iavf_adapter { #define IAVF_FLAG_QUEUES_DISABLED BIT(17) #define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) #define IAVF_FLAG_REINIT_MSIX_NEEDED BIT(20) -#define IAVF_FLAG_INITIAL_MAC_SET BIT(23) /* duplicates for common code */ #define IAVF_FLAG_DCB_ENABLED 0 /* flags for admin queue service task */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 3fc572341781..d7465296f650 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1087,12 +1087,6 @@ static int iavf_set_mac(struct net_device *netdev, void *p) if (ret) return ret; - /* If this is an initial set MAC during VF spawn do not wait */ - if (adapter->flags & IAVF_FLAG_INITIAL_MAC_SET) { - adapter->flags &= ~IAVF_FLAG_INITIAL_MAC_SET; - return 0; - } - ret = wait_event_interruptible_timeout(adapter->vc_waitqueue, iavf_is_mac_set_handled(netdev, addr->sa_data), msecs_to_jiffies(2500)); @@ -2605,8 +2599,6 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } - adapter->flags |= IAVF_FLAG_INITIAL_MAC_SET; - adapter->tx_desc_count = IAVF_DEFAULT_TXD; adapter->rx_desc_count = IAVF_DEFAULT_RXD; err = iavf_init_interrupt_scheme(adapter); @@ -2921,7 +2913,6 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) iavf_free_queues(adapter); memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE); iavf_shutdown_adminq(&adapter->hw); - adapter->netdev->flags &= ~IFF_UP; adapter->flags &= ~IAVF_FLAG_RESET_PENDING; iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); @@ -3021,6 +3012,11 @@ static void iavf_reset_task(struct work_struct *work) iavf_disable_vf(adapter); mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); + if (netif_running(netdev)) { + rtnl_lock(); + dev_close(netdev); + rtnl_unlock(); + } return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -3033,6 +3029,7 @@ continue_reset: if (running) { netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); adapter->link_up = false; iavf_napi_disable_all(adapter); } @@ -3172,6 +3169,16 @@ reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); + + if (netif_running(netdev)) { + /* Close device to ensure that Tx queues will not be started + * during netif_device_attach() at the end of the reset task. + */ + rtnl_lock(); + dev_close(netdev); + rtnl_unlock(); + } + dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); reset_finish: rtnl_lock(); @@ -5035,23 +5042,21 @@ static int __maybe_unused iavf_resume(struct device *dev_d) static void iavf_remove(struct pci_dev *pdev) { struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); - struct net_device *netdev = adapter->netdev; struct iavf_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; + struct iavf_cloud_filter *cf, *cftmp; struct iavf_adv_rss *rss, *rsstmp; struct iavf_mac_filter *f, *ftmp; - struct iavf_cloud_filter *cf, *cftmp; - struct iavf_hw *hw = &adapter->hw; + struct net_device *netdev; + struct iavf_hw *hw; int err; - /* When reboot/shutdown is in progress no need to do anything - * as the adapter is already REMOVE state that was set during - * iavf_shutdown() callback. - */ - if (adapter->state == __IAVF_REMOVE) + netdev = adapter->netdev; + hw = &adapter->hw; + + if (test_and_set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) return; - set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section); /* Wait until port initialization is complete. * There are flows where register/unregister netdev may race. */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 0f6718719453..ca2898467dcb 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3145,15 +3145,15 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) */ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data) { - irqreturn_t ret = IRQ_HANDLED; struct ice_pf *pf = data; - bool irq_handled; - irq_handled = ice_ptp_process_ts(pf); - if (!irq_handled) - ret = IRQ_WAKE_THREAD; + if (ice_is_reset_in_progress(pf->state)) + return IRQ_HANDLED; - return ret; + while (!ice_ptp_process_ts(pf)) + usleep_range(50, 100); + + return IRQ_HANDLED; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 011b727ab190..0f668468d141 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -614,11 +614,14 @@ static u64 ice_ptp_extend_40b_ts(struct ice_pf *pf, u64 in_tstamp) * 2) extend the 40b timestamp value to get a 64bit timestamp * 3) send that timestamp to the stack * - * After looping, if we still have waiting SKBs, return true. This may cause us - * effectively poll even when not strictly necessary. We do this because it's - * possible a new timestamp was requested around the same time as the interrupt. - * In some cases hardware might not interrupt us again when the timestamp is - * captured. + * Returns true if all timestamps were handled, and false if any slots remain + * without a timestamp. + * + * After looping, if we still have waiting SKBs, return false. This may cause + * us effectively poll even when not strictly necessary. We do this because + * it's possible a new timestamp was requested around the same time as the + * interrupt. In some cases hardware might not interrupt us again when the + * timestamp is captured. * * Note that we only take the tracking lock when clearing the bit and when * checking if we need to re-queue this task. The only place where bits can be @@ -641,7 +644,7 @@ static bool ice_ptp_tx_tstamp(struct ice_ptp_tx *tx) u8 idx; if (!tx->init) - return false; + return true; ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); @@ -2381,10 +2384,7 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) */ bool ice_ptp_process_ts(struct ice_pf *pf) { - if (pf->ptp.port.tx.init) - return ice_ptp_tx_tstamp(&pf->ptp.port.tx); - - return false; + return ice_ptp_tx_tstamp(&pf->ptp.port.tx); } static void ice_ptp_periodic_work(struct kthread_work *work) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index eb0fb8128096..b399bdb1ca36 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -7350,6 +7350,7 @@ static int mvpp2_get_sram(struct platform_device *pdev, struct mvpp2 *priv) { struct resource *res; + void __iomem *base; res = platform_get_resource(pdev, IORESOURCE_MEM, 2); if (!res) { @@ -7360,9 +7361,12 @@ static int mvpp2_get_sram(struct platform_device *pdev, return 0; } - priv->cm3_base = devm_ioremap_resource(&pdev->dev, res); + base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); - return PTR_ERR_OR_ZERO(priv->cm3_base); + priv->cm3_base = base; + return 0; } static int mvpp2_probe(struct platform_device *pdev) diff --git a/drivers/net/ethernet/marvell/octeontx2/Kconfig b/drivers/net/ethernet/marvell/octeontx2/Kconfig index 6b4f640163f7..993ac180a5db 100644 --- a/drivers/net/ethernet/marvell/octeontx2/Kconfig +++ b/drivers/net/ethernet/marvell/octeontx2/Kconfig @@ -32,7 +32,6 @@ config OCTEONTX2_PF tristate "Marvell OcteonTX2 NIC Physical Function driver" select OCTEONTX2_MBOX select NET_DEVLINK - depends on MACSEC || !MACSEC depends on (64BIT && COMPILE_TEST) || ARM64 select DIMLIB depends on PCI diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c index 4a343f853b28..c0bedf402da9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c @@ -951,7 +951,7 @@ static void mcs_bbe_intr_handler(struct mcs *mcs, u64 intr, enum mcs_direction d else event.intr_mask = (dir == MCS_RX) ? MCS_BBE_RX_PLFIFO_OVERFLOW_INT : - MCS_BBE_RX_PLFIFO_OVERFLOW_INT; + MCS_BBE_TX_PLFIFO_OVERFLOW_INT; /* Notify the lmac_id info which ran into BBE fatal error */ event.lmac_id = i & 0x3ULL; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index a1970ebedf95..f66dde2b0f92 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -880,6 +880,8 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused) sprintf(lmac, "LMAC%d", lmac_id); seq_printf(filp, "%s\t0x%x\t\tNIX%d\t\t%s\t%s\n", dev_name(&pdev->dev), pcifunc, blkid, cgx, lmac); + + pci_dev_put(pdev); } return 0; } @@ -2566,6 +2568,7 @@ static int cgx_print_dmac_flt(struct seq_file *s, int lmac_id) } } + pci_dev_put(pdev); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 7646bb2ec89b..a62c1b322012 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4985,6 +4985,8 @@ static int nix_setup_ipolicers(struct rvu *rvu, ipolicer->ref_count = devm_kcalloc(rvu->dev, ipolicer->band_prof.max, sizeof(u16), GFP_KERNEL); + if (!ipolicer->ref_count) + return -ENOMEM; } /* Set policer timeunit to 2us ie (19 + 1) * 100 nsec = 2us */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c index b04fb226f708..ae50d56258ec 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c @@ -62,15 +62,18 @@ int rvu_sdp_init(struct rvu *rvu) pfvf->sdp_info = devm_kzalloc(rvu->dev, sizeof(struct sdp_node_info), GFP_KERNEL); - if (!pfvf->sdp_info) + if (!pfvf->sdp_info) { + pci_dev_put(pdev); return -ENOMEM; + } dev_info(rvu->dev, "SDP PF number:%d\n", sdp_pf_num[i]); - put_device(&pdev->dev); i++; } + pci_dev_put(pdev); + return 0; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 24f9d6024745..47796e4d900c 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -746,6 +746,7 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) return 0; err_sfp_bind: + unregister_netdev(dev); err_register_netdev: prestera_port_list_del(port); err_port_init: diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 7cd381530aa4..1d36619c5ec9 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2378,8 +2378,10 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) data + NET_SKB_PAD + eth->ip_align, ring->buf_size, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(eth->dma_dev, - dma_addr))) + dma_addr))) { + skb_free_frag(data); return -ENOMEM; + } } rxd->rxd1 = (unsigned int)dma_addr; ring->data[i] = data; @@ -2996,8 +2998,10 @@ static int mtk_open(struct net_device *dev) int i; err = mtk_start_dma(eth); - if (err) + if (err) { + phylink_disconnect_phy(mac->phylink); return err; + } for (i = 0; i < ARRAY_SIZE(eth->ppe); i++) mtk_ppe_start(eth->ppe[i]); @@ -4143,13 +4147,13 @@ static int mtk_probe(struct platform_device *pdev) eth->soc->offload_version, i); if (!eth->ppe[i]) { err = -ENOMEM; - goto err_free_dev; + goto err_deinit_ppe; } } err = mtk_eth_offload_init(eth); if (err) - goto err_free_dev; + goto err_deinit_ppe; } for (i = 0; i < MTK_MAX_DEVS; i++) { @@ -4159,7 +4163,7 @@ static int mtk_probe(struct platform_device *pdev) err = register_netdev(eth->netdev[i]); if (err) { dev_err(eth->dev, "error bringing up device\n"); - goto err_deinit_mdio; + goto err_deinit_ppe; } else netif_info(eth, probe, eth->netdev[i], "mediatek frame engine at 0x%08lx, irq %d\n", @@ -4177,7 +4181,8 @@ static int mtk_probe(struct platform_device *pdev) return 0; -err_deinit_mdio: +err_deinit_ppe: + mtk_ppe_deinit(eth); mtk_mdio_cleanup(eth); err_free_dev: mtk_free_dev(eth); diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index 2d8ca99f2467..784ecb2dc9fb 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -737,7 +737,7 @@ struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, MTK_PPE_ENTRIES * soc->foe_entry_size, &ppe->foe_phys, GFP_KERNEL); if (!foe) - return NULL; + goto err_free_l2_flows; ppe->foe_table = foe; @@ -745,11 +745,26 @@ struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, sizeof(*ppe->foe_flow); ppe->foe_flow = devm_kzalloc(dev, foe_flow_size, GFP_KERNEL); if (!ppe->foe_flow) - return NULL; + goto err_free_l2_flows; mtk_ppe_debugfs_init(ppe, index); return ppe; + +err_free_l2_flows: + rhashtable_destroy(&ppe->l2_flows); + return NULL; +} + +void mtk_ppe_deinit(struct mtk_eth *eth) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(eth->ppe); i++) { + if (!eth->ppe[i]) + return; + rhashtable_destroy(ð->ppe[i]->l2_flows); + } } static void mtk_ppe_init_foe_table(struct mtk_ppe *ppe) diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h index 0b7a67a958e4..a09c32539bcc 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.h +++ b/drivers/net/ethernet/mediatek/mtk_ppe.h @@ -304,6 +304,7 @@ struct mtk_ppe { struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, int version, int index); +void mtk_ppe_deinit(struct mtk_eth *eth); void mtk_ppe_start(struct mtk_ppe *ppe); int mtk_ppe_stop(struct mtk_ppe *ppe); diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index b149e601f673..48cfaa7eaf50 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -697,7 +697,8 @@ static int mlx4_create_zones(struct mlx4_dev *dev, err = mlx4_bitmap_init(*bitmap + k, 1, MLX4_QP_TABLE_RAW_ETH_SIZE - 1, 0, 0); - mlx4_bitmap_alloc_range(*bitmap + k, 1, 1, 0); + if (!err) + mlx4_bitmap_alloc_range(*bitmap + k, 1, 1, 0); } if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 2e0d59ca62b5..74bd05e5dda2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -45,6 +45,8 @@ #include "mlx5_core.h" #include "lib/eq.h" #include "lib/tout.h" +#define CREATE_TRACE_POINTS +#include "diag/cmd_tracepoint.h" enum { CMD_IF_REV = 5, @@ -785,27 +787,14 @@ EXPORT_SYMBOL(mlx5_cmd_out_err); static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out) { u16 opcode, op_mod; - u32 syndrome; - u8 status; u16 uid; - int err; - - syndrome = MLX5_GET(mbox_out, out, syndrome); - status = MLX5_GET(mbox_out, out, status); opcode = MLX5_GET(mbox_in, in, opcode); op_mod = MLX5_GET(mbox_in, in, op_mod); uid = MLX5_GET(mbox_in, in, uid); - err = cmd_status_to_err(status); - if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY) mlx5_cmd_out_err(dev, opcode, op_mod, out); - else - mlx5_core_dbg(dev, - "%s(0x%x) op_mod(0x%x) uid(%d) failed, status %s(0x%x), syndrome (0x%x), err(%d)\n", - mlx5_command_str(opcode), opcode, op_mod, uid, - cmd_status_str(status), status, syndrome, err); } int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out) @@ -1016,6 +1005,7 @@ static void cmd_work_handler(struct work_struct *work) cmd_ent_get(ent); set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); + cmd_ent_get(ent); /* for the _real_ FW event on completion */ /* Skip sending command to fw if internal error */ if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, ent->op)) { ent->ret = -ENXIO; @@ -1023,7 +1013,6 @@ static void cmd_work_handler(struct work_struct *work) return; } - cmd_ent_get(ent); /* for the _real_ FW event on completion */ /* ring doorbell after the descriptor is valid */ mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx); wmb(); @@ -1672,8 +1661,8 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force cmd_ent_put(ent); /* timeout work was canceled */ if (!forced || /* Real FW completion */ - pci_channel_offline(dev->pdev) || /* FW is inaccessible */ - dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + mlx5_cmd_is_down(dev) || /* No real FW completion is expected */ + !opcode_allowed(cmd, ent->op)) cmd_ent_put(ent); ent->ts2 = ktime_get_ns(); @@ -1892,6 +1881,16 @@ out_in: return err; } +static void mlx5_cmd_err_trace(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod, void *out) +{ + u32 syndrome = MLX5_GET(mbox_out, out, syndrome); + u8 status = MLX5_GET(mbox_out, out, status); + + trace_mlx5_cmd(mlx5_command_str(opcode), opcode, op_mod, + cmd_status_str(status), status, syndrome, + cmd_status_to_err(status)); +} + static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, u32 syndrome, int err) { @@ -1914,7 +1913,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, } /* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */ -static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void *out) +static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, u16 op_mod, void *out) { u32 syndrome = MLX5_GET(mbox_out, out, syndrome); u8 status = MLX5_GET(mbox_out, out, status); @@ -1922,8 +1921,10 @@ static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void * if (err == -EREMOTEIO) /* -EREMOTEIO is preserved */ err = -EIO; - if (!err && status != MLX5_CMD_STAT_OK) + if (!err && status != MLX5_CMD_STAT_OK) { err = -EREMOTEIO; + mlx5_cmd_err_trace(dev, opcode, op_mod, out); + } cmd_status_log(dev, opcode, status, syndrome, err); return err; @@ -1951,9 +1952,9 @@ int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false); u16 opcode = MLX5_GET(mbox_in, in, opcode); + u16 op_mod = MLX5_GET(mbox_in, in, op_mod); - err = cmd_status_err(dev, err, opcode, out); - return err; + return cmd_status_err(dev, err, opcode, op_mod, out); } EXPORT_SYMBOL(mlx5_cmd_do); @@ -1997,8 +1998,9 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true); u16 opcode = MLX5_GET(mbox_in, in, opcode); + u16 op_mod = MLX5_GET(mbox_in, in, op_mod); - err = cmd_status_err(dev, err, opcode, out); + err = cmd_status_err(dev, err, opcode, op_mod, out); return mlx5_cmd_check(dev, err, in, out); } EXPORT_SYMBOL(mlx5_cmd_exec_polling); @@ -2034,7 +2036,7 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work) struct mlx5_async_ctx *ctx; ctx = work->ctx; - status = cmd_status_err(ctx->dev, status, work->opcode, work->out); + status = cmd_status_err(ctx->dev, status, work->opcode, work->op_mod, work->out); work->user_callback(status, work); if (atomic_dec_and_test(&ctx->num_inflight)) complete(&ctx->inflight_done); @@ -2049,6 +2051,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, work->ctx = ctx; work->user_callback = callback; work->opcode = MLX5_GET(mbox_in, in, opcode); + work->op_mod = MLX5_GET(mbox_in, in, op_mod); work->out = out; if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight))) return -EIO; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/cmd_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/cmd_tracepoint.h new file mode 100644 index 000000000000..406ebe17405f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/cmd_tracepoint.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlx5 + +#if !defined(_MLX5_CMD_TP_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _MLX5_CMD_TP_H_ + +#include <linux/tracepoint.h> +#include <linux/trace_seq.h> + +TRACE_EVENT(mlx5_cmd, + TP_PROTO(const char *command_str, u16 opcode, u16 op_mod, + const char *status_str, u8 status, u32 syndrome, int err), + TP_ARGS(command_str, opcode, op_mod, status_str, status, syndrome, err), + TP_STRUCT__entry(__string(command_str, command_str) + __field(u16, opcode) + __field(u16, op_mod) + __string(status_str, status_str) + __field(u8, status) + __field(u32, syndrome) + __field(int, err) + ), + TP_fast_assign(__assign_str(command_str, command_str); + __entry->opcode = opcode; + __entry->op_mod = op_mod; + __assign_str(status_str, status_str); + __entry->status = status; + __entry->syndrome = syndrome; + __entry->err = err; + ), + TP_printk("%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x), err(%d)", + __get_str(command_str), __entry->opcode, __entry->op_mod, + __get_str(status_str), __entry->status, __entry->syndrome, + __entry->err) +); + +#endif /* _MLX5_CMD_TP_H_ */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ./diag +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE cmd_tracepoint +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 978a2bb8e122..21831386b26e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -638,7 +638,7 @@ static void mlx5_tracer_handle_timestamp_trace(struct mlx5_fw_tracer *tracer, trace_timestamp = (timestamp_event.timestamp & MASK_52_7) | (str_frmt->timestamp & MASK_6_0); else - trace_timestamp = ((timestamp_event.timestamp & MASK_52_7) - 1) | + trace_timestamp = ((timestamp_event.timestamp - 1) & MASK_52_7) | (str_frmt->timestamp & MASK_6_0); mlx5_tracer_print_trace(str_frmt, dev, trace_timestamp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 5aff97914367..ff73d25bc6eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -224,15 +224,16 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, list_for_each_entry(flow, flow_list, tmp_list) { if (!mlx5e_is_offloaded_flow(flow) || flow_flag_test(flow, SLOW)) continue; - spec = &flow->attr->parse_attr->spec; - - /* update from encap rule to slow path rule */ - rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec); attr = mlx5e_tc_get_encap_attr(flow); esw_attr = attr->esw_attr; /* mark the flow's encap dest as non-valid */ esw_attr->dests[flow->tmp_entry_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID; + esw_attr->dests[flow->tmp_entry_index].pkt_reformat = NULL; + + /* update from encap rule to slow path rule */ + spec = &flow->attr->parse_attr->spec; + rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec); if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -251,6 +252,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, /* we know that the encap is valid */ e->flags &= ~MLX5_ENCAP_ENTRY_VALID; mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat); + e->pkt_reformat = NULL; } static void mlx5e_take_tmp_flow(struct mlx5e_tc_flow *flow, @@ -762,8 +764,7 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, struct net_device *mirred_dev, int out_index, struct netlink_ext_ack *extack, - struct net_device **encap_dev, - bool *encap_valid) + struct net_device **encap_dev) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; @@ -878,9 +879,8 @@ attach_flow: if (e->flags & MLX5_ENCAP_ENTRY_VALID) { attr->esw_attr->dests[out_index].pkt_reformat = e->pkt_reformat; attr->esw_attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; - *encap_valid = true; } else { - *encap_valid = false; + flow_flag_set(flow, SLOW); } mutex_unlock(&esw->offloads.encap_tbl_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h index d542b8476491..8ad273dde40e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h @@ -17,8 +17,7 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, struct net_device *mirred_dev, int out_index, struct netlink_ext_ack *extack, - struct net_device **encap_dev, - bool *encap_valid); + struct net_device **encap_dev); int mlx5e_attach_decap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index 2ef36cb9555a..3dc6c987b8da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -368,15 +368,15 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx, obj_attrs.aso_pdn = macsec->aso.pdn; obj_attrs.epn_state = sa->epn_state; - if (is_tx) { - obj_attrs.ssci = cpu_to_be32((__force u32)ctx->sa.tx_sa->ssci); - key = &ctx->sa.tx_sa->key; - } else { - obj_attrs.ssci = cpu_to_be32((__force u32)ctx->sa.rx_sa->ssci); - key = &ctx->sa.rx_sa->key; + key = (is_tx) ? &ctx->sa.tx_sa->key : &ctx->sa.rx_sa->key; + + if (sa->epn_state.epn_enabled) { + obj_attrs.ssci = (is_tx) ? cpu_to_be32((__force u32)ctx->sa.tx_sa->ssci) : + cpu_to_be32((__force u32)ctx->sa.rx_sa->ssci); + + memcpy(&obj_attrs.salt, &key->salt, sizeof(key->salt)); } - memcpy(&obj_attrs.salt, &key->salt, sizeof(key->salt)); obj_attrs.replay_window = ctx->secy->replay_window; obj_attrs.replay_protect = ctx->secy->replay_protect; @@ -1155,7 +1155,7 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx, continue; if (rx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, rx_sa, false, false); + err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false); if (err) goto out; } @@ -1536,6 +1536,8 @@ static void macsec_async_event(struct work_struct *work) async_work = container_of(work, struct mlx5e_macsec_async_work, work); macsec = async_work->macsec; + mutex_lock(&macsec->lock); + mdev = async_work->mdev; obj_id = async_work->obj_id; macsec_sa = get_macsec_tx_sa_from_obj_id(macsec, obj_id); @@ -1557,6 +1559,7 @@ static void macsec_async_event(struct work_struct *work) out_async_work: kfree(async_work); + mutex_unlock(&macsec->lock); } static int macsec_obj_change_event(struct notifier_block *nb, unsigned long event, void *data) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 24aa25da482b..1728e197558d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -35,7 +35,6 @@ #include "en.h" #include "en/port.h" #include "en/params.h" -#include "en/xsk/pool.h" #include "en/ptp.h" #include "lib/clock.h" #include "en/fs_ethtool.h" @@ -412,15 +411,8 @@ void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv, struct ethtool_channels *ch) { mutex_lock(&priv->state_lock); - ch->max_combined = priv->max_nch; ch->combined_count = priv->channels.params.num_channels; - if (priv->xsk.refcnt) { - /* The upper half are XSK queues. */ - ch->max_combined *= 2; - ch->combined_count *= 2; - } - mutex_unlock(&priv->state_lock); } @@ -454,16 +446,6 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, mutex_lock(&priv->state_lock); - /* Don't allow changing the number of channels if there is an active - * XSK, because the numeration of the XSK and regular RQs will change. - */ - if (priv->xsk.refcnt) { - err = -EINVAL; - netdev_err(priv->netdev, "%s: AF_XDP is active, cannot change the number of channels\n", - __func__); - goto out; - } - /* Don't allow changing the number of channels if HTB offload is active, * because the numeration of the QoS SQs will change, while per-queue * qdiscs are attached. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index e3a4f01bcceb..5e41dfdf79c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -206,10 +206,11 @@ static void mlx5e_disable_blocking_events(struct mlx5e_priv *priv) static u16 mlx5e_mpwrq_umr_octowords(u32 entries, enum mlx5e_mpwrq_umr_mode umr_mode) { u8 umr_entry_size = mlx5e_mpwrq_umr_entry_size(umr_mode); + u32 sz; - WARN_ON_ONCE(entries * umr_entry_size % MLX5_OCTWORD); + sz = ALIGN(entries * umr_entry_size, MLX5_UMR_MTT_ALIGNMENT); - return entries * umr_entry_size / MLX5_OCTWORD; + return sz / MLX5_OCTWORD; } static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 5a6aa61ec82a..bd9936af4582 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1634,7 +1634,6 @@ set_encap_dests(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, struct netlink_ext_ack *extack, - bool *encap_valid, bool *vf_tun) { struct mlx5e_tc_flow_parse_attr *parse_attr; @@ -1651,7 +1650,6 @@ set_encap_dests(struct mlx5e_priv *priv, parse_attr = attr->parse_attr; esw_attr = attr->esw_attr; *vf_tun = false; - *encap_valid = true; for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { struct net_device *out_dev; @@ -1668,7 +1666,7 @@ set_encap_dests(struct mlx5e_priv *priv, goto out; } err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index, - extack, &encap_dev, encap_valid); + extack, &encap_dev); dev_put(out_dev); if (err) goto out; @@ -1732,8 +1730,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct mlx5_esw_flow_attr *esw_attr; - bool vf_tun, encap_valid; u32 max_prio, max_chain; + bool vf_tun; int err = 0; parse_attr = attr->parse_attr; @@ -1823,7 +1821,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr->int_port = int_port; } - err = set_encap_dests(priv, flow, attr, extack, &encap_valid, &vf_tun); + err = set_encap_dests(priv, flow, attr, extack, &vf_tun); if (err) goto err_out; @@ -1853,7 +1851,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, * (1) there's no error * (2) there's an encap action and we don't have valid neigh */ - if (!encap_valid || flow_flag_test(flow, SLOW)) + if (flow_flag_test(flow, SLOW)) flow->rule[0] = mlx5e_tc_offload_to_slow_path(esw, flow, &parse_attr->spec); else flow->rule[0] = mlx5e_tc_offload_fdb_rules(esw, flow, &parse_attr->spec, attr); @@ -3759,7 +3757,7 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) struct mlx5e_post_act *post_act = get_post_action(flow->priv); struct mlx5_flow_attr *attr, *next_attr = NULL; struct mlx5e_post_act_handle *handle; - bool vf_tun, encap_valid = true; + bool vf_tun; int err; /* This is going in reverse order as needed. @@ -3781,13 +3779,10 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) if (list_is_last(&attr->list, &flow->attrs)) break; - err = set_encap_dests(flow->priv, flow, attr, extack, &encap_valid, &vf_tun); + err = set_encap_dests(flow->priv, flow, attr, extack, &vf_tun); if (err) goto out_free; - if (!encap_valid) - flow_flag_set(flow, SLOW); - err = actions_prepare_mod_hdr_actions(flow->priv, flow, attr, extack); if (err) goto out_free; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 728ca9f2bb9d..3fda75fe168c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -433,7 +433,7 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f mlx5_lag_mpesw_is_activated(esw->dev)) dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_UPLINK; } - if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP) { + if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP_VALID) { if (pkt_reformat) { flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; flow_act->pkt_reformat = esw_attr->dests[attr_idx].pkt_reformat; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 9d908a0ccfef..1e46f9afa40e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -9,7 +9,8 @@ enum { MLX5_FW_RESET_FLAGS_RESET_REQUESTED, MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, MLX5_FW_RESET_FLAGS_PENDING_COMP, - MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS + MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, + MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED }; struct mlx5_fw_reset { @@ -406,7 +407,7 @@ static void mlx5_sync_reset_now_event(struct work_struct *work) err = mlx5_pci_link_toggle(dev); if (err) { mlx5_core_warn(dev, "mlx5_pci_link_toggle failed, no reset done, err %d\n", err); - goto done; + set_bit(MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, &fw_reset->reset_flags); } mlx5_enter_error_state(dev, true); @@ -482,6 +483,10 @@ int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev) goto out; } err = fw_reset->ret; + if (test_and_clear_bit(MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, &fw_reset->reset_flags)) { + mlx5_unload_one_devl_locked(dev); + mlx5_load_one_devl_locked(dev, false); + } out: clear_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags); return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index a9f4ede4a9bf..be1307a63e6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -228,9 +228,8 @@ static void mlx5_ldev_free(struct kref *ref) if (ldev->nb.notifier_call) unregister_netdevice_notifier_net(&init_net, &ldev->nb); mlx5_lag_mp_cleanup(ldev); - mlx5_lag_mpesw_cleanup(ldev); - cancel_work_sync(&ldev->mpesw_work); destroy_workqueue(ldev->wq); + mlx5_lag_mpesw_cleanup(ldev); mutex_destroy(&ldev->lock); kfree(ldev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h index ce2ce8ccbd70..f30ac2de639f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h @@ -50,6 +50,19 @@ struct lag_tracker { enum netdev_lag_hash hash_type; }; +enum mpesw_op { + MLX5_MPESW_OP_ENABLE, + MLX5_MPESW_OP_DISABLE, +}; + +struct mlx5_mpesw_work_st { + struct work_struct work; + struct mlx5_lag *lag; + enum mpesw_op op; + struct completion comp; + int result; +}; + /* LAG data of a ConnectX card. * It serves both its phys functions. */ @@ -66,7 +79,6 @@ struct mlx5_lag { struct lag_tracker tracker; struct workqueue_struct *wq; struct delayed_work bond_work; - struct work_struct mpesw_work; struct notifier_block nb; struct lag_mp lag_mp; struct mlx5_lag_port_sel port_sel; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index f643202b29c6..c17e8f1ec914 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -7,63 +7,95 @@ #include "eswitch.h" #include "lib/mlx5.h" -void mlx5_mpesw_work(struct work_struct *work) +static int add_mpesw_rule(struct mlx5_lag *ldev) { - struct mlx5_lag *ldev = container_of(work, struct mlx5_lag, mpesw_work); + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + int err; - mutex_lock(&ldev->lock); - mlx5_disable_lag(ldev); - mutex_unlock(&ldev->lock); -} + if (atomic_add_return(1, &ldev->lag_mpesw.mpesw_rule_count) != 1) + return 0; -static void mlx5_lag_disable_mpesw(struct mlx5_core_dev *dev) -{ - struct mlx5_lag *ldev = dev->priv.lag; + if (ldev->mode != MLX5_LAG_MODE_NONE) { + err = -EINVAL; + goto out_err; + } - if (!queue_work(ldev->wq, &ldev->mpesw_work)) - mlx5_core_warn(dev, "failed to queue work\n"); + err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, false); + if (err) { + mlx5_core_warn(dev, "Failed to create LAG in MPESW mode (%d)\n", err); + goto out_err; + } + + return 0; + +out_err: + atomic_dec(&ldev->lag_mpesw.mpesw_rule_count); + return err; } -void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev) +static void del_mpesw_rule(struct mlx5_lag *ldev) { - struct mlx5_lag *ldev = dev->priv.lag; + if (!atomic_dec_return(&ldev->lag_mpesw.mpesw_rule_count) && + ldev->mode == MLX5_LAG_MODE_MPESW) + mlx5_disable_lag(ldev); +} - if (!ldev) - return; +static void mlx5_mpesw_work(struct work_struct *work) +{ + struct mlx5_mpesw_work_st *mpesww = container_of(work, struct mlx5_mpesw_work_st, work); + struct mlx5_lag *ldev = mpesww->lag; mutex_lock(&ldev->lock); - if (!atomic_dec_return(&ldev->lag_mpesw.mpesw_rule_count) && - ldev->mode == MLX5_LAG_MODE_MPESW) - mlx5_lag_disable_mpesw(dev); + if (mpesww->op == MLX5_MPESW_OP_ENABLE) + mpesww->result = add_mpesw_rule(ldev); + else if (mpesww->op == MLX5_MPESW_OP_DISABLE) + del_mpesw_rule(ldev); mutex_unlock(&ldev->lock); + + complete(&mpesww->comp); } -int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev) +static int mlx5_lag_mpesw_queue_work(struct mlx5_core_dev *dev, + enum mpesw_op op) { struct mlx5_lag *ldev = dev->priv.lag; + struct mlx5_mpesw_work_st *work; int err = 0; if (!ldev) return 0; - mutex_lock(&ldev->lock); - if (atomic_add_return(1, &ldev->lag_mpesw.mpesw_rule_count) != 1) - goto out; + work = kzalloc(sizeof(*work), GFP_KERNEL); + if (!work) + return -ENOMEM; - if (ldev->mode != MLX5_LAG_MODE_NONE) { + INIT_WORK(&work->work, mlx5_mpesw_work); + init_completion(&work->comp); + work->op = op; + work->lag = ldev; + + if (!queue_work(ldev->wq, &work->work)) { + mlx5_core_warn(dev, "failed to queue mpesw work\n"); err = -EINVAL; goto out; } - - err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, false); - if (err) - mlx5_core_warn(dev, "Failed to create LAG in MPESW mode (%d)\n", err); - + wait_for_completion(&work->comp); + err = work->result; out: - mutex_unlock(&ldev->lock); + kfree(work); return err; } +void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev) +{ + mlx5_lag_mpesw_queue_work(dev, MLX5_MPESW_OP_DISABLE); +} + +int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev) +{ + return mlx5_lag_mpesw_queue_work(dev, MLX5_MPESW_OP_ENABLE); +} + int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev) { struct mlx5_lag *ldev = mdev->priv.lag; @@ -71,12 +103,9 @@ int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev) if (!netif_is_bond_master(out_dev) || !ldev) return 0; - mutex_lock(&ldev->lock); - if (ldev->mode == MLX5_LAG_MODE_MPESW) { - mutex_unlock(&ldev->lock); + if (ldev->mode == MLX5_LAG_MODE_MPESW) return -EOPNOTSUPP; - } - mutex_unlock(&ldev->lock); + return 0; } @@ -90,11 +119,10 @@ bool mlx5_lag_mpesw_is_activated(struct mlx5_core_dev *dev) void mlx5_lag_mpesw_init(struct mlx5_lag *ldev) { - INIT_WORK(&ldev->mpesw_work, mlx5_mpesw_work); atomic_set(&ldev->lag_mpesw.mpesw_rule_count, 0); } void mlx5_lag_mpesw_cleanup(struct mlx5_lag *ldev) { - cancel_delayed_work_sync(&ldev->bond_work); + WARN_ON(atomic_read(&ldev->lag_mpesw.mpesw_rule_count)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h index be4abcb8fcd5..88e8daffcf92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h @@ -12,7 +12,6 @@ struct lag_mpesw { atomic_t mpesw_rule_count; }; -void mlx5_mpesw_work(struct work_struct *work); int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev); bool mlx5_lag_mpesw_is_activated(struct mlx5_core_dev *dev); #if IS_ENABLED(CONFIG_MLX5_ESWITCH) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 283c4cc28944..e58775a7d955 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1798,7 +1798,8 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, res = state == pci_channel_io_perm_failure ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET; - mlx5_pci_trace(dev, "Exit, result = %d, %s\n", res, result2str(res)); + mlx5_core_info(dev, "%s Device state = %d pci_status: %d. Exit, result = %d, %s\n", + __func__, dev->state, dev->pci_status, res, result2str(res)); return res; } @@ -1837,7 +1838,8 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) struct mlx5_core_dev *dev = pci_get_drvdata(pdev); int err; - mlx5_pci_trace(dev, "Enter\n"); + mlx5_core_info(dev, "%s Device state = %d pci_status: %d. Enter\n", + __func__, dev->state, dev->pci_status); err = mlx5_pci_enable_device(dev); if (err) { @@ -1859,7 +1861,8 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) res = PCI_ERS_RESULT_RECOVERED; out: - mlx5_pci_trace(dev, "Exit, err = %d, result = %d, %s\n", err, res, result2str(res)); + mlx5_core_info(dev, "%s Device state = %d pci_status: %d. Exit, err = %d, result = %d, %s\n", + __func__, dev->state, dev->pci_status, err, res, result2str(res)); return res; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c index 7da012ff0d41..8e2abbab05f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -18,6 +18,10 @@ struct mlx5_sf_dev_table { phys_addr_t base_address; u64 sf_bar_length; struct notifier_block nb; + struct mutex table_lock; /* Serializes sf life cycle and vhca state change handler */ + struct workqueue_struct *active_wq; + struct work_struct work; + u8 stop_active_wq:1; struct mlx5_core_dev *dev; }; @@ -168,6 +172,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_ return 0; sf_index = event->function_id - base_id; + mutex_lock(&table->table_lock); sf_dev = xa_load(&table->devices, sf_index); switch (event->new_vhca_state) { case MLX5_VHCA_STATE_INVALID: @@ -191,6 +196,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_ default: break; } + mutex_unlock(&table->table_lock); return 0; } @@ -215,6 +221,78 @@ static int mlx5_sf_dev_vhca_arm_all(struct mlx5_sf_dev_table *table) return 0; } +static void mlx5_sf_dev_add_active_work(struct work_struct *work) +{ + struct mlx5_sf_dev_table *table = container_of(work, struct mlx5_sf_dev_table, work); + u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {}; + struct mlx5_core_dev *dev = table->dev; + u16 max_functions; + u16 function_id; + u16 sw_func_id; + int err = 0; + u8 state; + int i; + + max_functions = mlx5_sf_max_functions(dev); + function_id = MLX5_CAP_GEN(dev, sf_base_id); + for (i = 0; i < max_functions; i++, function_id++) { + if (table->stop_active_wq) + return; + err = mlx5_cmd_query_vhca_state(dev, function_id, out, sizeof(out)); + if (err) + /* A failure of specific vhca doesn't mean others will + * fail as well. + */ + continue; + state = MLX5_GET(query_vhca_state_out, out, vhca_state_context.vhca_state); + if (state != MLX5_VHCA_STATE_ACTIVE) + continue; + + sw_func_id = MLX5_GET(query_vhca_state_out, out, vhca_state_context.sw_function_id); + mutex_lock(&table->table_lock); + /* Don't probe device which is already probe */ + if (!xa_load(&table->devices, i)) + mlx5_sf_dev_add(dev, i, function_id, sw_func_id); + /* There is a race where SF got inactive after the query + * above. e.g.: the query returns that the state of the + * SF is active, and after that the eswitch manager set it to + * inactive. + * This case cannot be managed in SW, since the probing of the + * SF is on one system, and the inactivation is on a different + * system. + * If the inactive is done after the SF perform init_hca(), + * the SF will fully probe and then removed. If it was + * done before init_hca(), the SF probe will fail. + */ + mutex_unlock(&table->table_lock); + } +} + +/* In case SFs are generated externally, probe active SFs */ +static int mlx5_sf_dev_queue_active_work(struct mlx5_sf_dev_table *table) +{ + if (MLX5_CAP_GEN(table->dev, eswitch_manager)) + return 0; /* the table is local */ + + /* Use a workqueue to probe active SFs, which are in large + * quantity and may take up to minutes to probe. + */ + table->active_wq = create_singlethread_workqueue("mlx5_active_sf"); + if (!table->active_wq) + return -ENOMEM; + INIT_WORK(&table->work, &mlx5_sf_dev_add_active_work); + queue_work(table->active_wq, &table->work); + return 0; +} + +static void mlx5_sf_dev_destroy_active_work(struct mlx5_sf_dev_table *table) +{ + if (table->active_wq) { + table->stop_active_wq = true; + destroy_workqueue(table->active_wq); + } +} + void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) { struct mlx5_sf_dev_table *table; @@ -240,11 +318,17 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) table->base_address = pci_resource_start(dev->pdev, 2); table->max_sfs = max_sfs; xa_init(&table->devices); + mutex_init(&table->table_lock); dev->priv.sf_dev_table = table; err = mlx5_vhca_event_notifier_register(dev, &table->nb); if (err) goto vhca_err; + + err = mlx5_sf_dev_queue_active_work(table); + if (err) + goto add_active_err; + err = mlx5_sf_dev_vhca_arm_all(table); if (err) goto arm_err; @@ -252,6 +336,8 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) return; arm_err: + mlx5_sf_dev_destroy_active_work(table); +add_active_err: mlx5_vhca_event_notifier_unregister(dev, &table->nb); vhca_err: table->max_sfs = 0; @@ -279,7 +365,9 @@ void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev) if (!table) return; + mlx5_sf_dev_destroy_active_work(table); mlx5_vhca_event_notifier_unregister(dev, &table->nb); + mutex_destroy(&table->table_lock); /* Now that event handler is not running, it is safe to destroy * the sf device without race. diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c index 19516ccad533..d078156581d5 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c @@ -104,7 +104,7 @@ static int sparx5_port_open(struct net_device *ndev) err = phylink_of_phy_connect(port->phylink, port->of_node, 0); if (err) { netdev_err(ndev, "Could not attach to PHY\n"); - return err; + goto err_connect; } phylink_start(port->phylink); @@ -116,10 +116,20 @@ static int sparx5_port_open(struct net_device *ndev) err = sparx5_serdes_set(port->sparx5, port, &port->conf); else err = phy_power_on(port->serdes); - if (err) + if (err) { netdev_err(ndev, "%s failed\n", __func__); + goto out_power; + } } + return 0; + +out_power: + phylink_stop(port->phylink); + phylink_disconnect_phy(port->phylink); +err_connect: + sparx5_port_enable(port, false); + return err; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c index e05429c751ee..dc2c3756e3a2 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c @@ -90,13 +90,10 @@ static int sparx5_tc_setup_qdisc_ets(struct net_device *ndev, } } - sparx5_tc_ets_add(port, params); - break; + return sparx5_tc_ets_add(port, params); case TC_ETS_DESTROY: - sparx5_tc_ets_del(port); - - break; + return sparx5_tc_ets_del(port); case TC_ETS_GRAFT: return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index 405786c00334..cb08d7bf9524 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -341,7 +341,7 @@ int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port) return ret; attrs.split = eth_port.is_split; - attrs.splittable = !attrs.split; + attrs.splittable = eth_port.port_lanes > 1 && !attrs.split; attrs.lanes = eth_port.port_lanes; attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; attrs.phys.port_number = eth_port.label_port; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 1775997f9c69..991059d6cb32 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -1432,6 +1432,9 @@ nfp_port_get_module_info(struct net_device *netdev, u8 data; port = nfp_port_from_netdev(netdev); + if (!port) + return -EOPNOTSUPP; + /* update port state to get latest interface */ set_bit(NFP_PORT_CHANGED, &port->flags); eth_port = nfp_port_get_eth_port(port); diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 3f2c30184752..28b7cec485ef 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -1143,6 +1143,7 @@ static void pch_gbe_tx_queue(struct pch_gbe_adapter *adapter, buffer_info->dma = 0; buffer_info->time_stamp = 0; tx_ring->next_to_use = ring_num; + dev_kfree_skb_any(skb); return; } buffer_info->mapped = true; @@ -2459,6 +2460,7 @@ static void pch_gbe_remove(struct pci_dev *pdev) unregister_netdev(netdev); pch_gbe_phy_hw_reset(&adapter->hw); + pci_dev_put(adapter->ptp_pdev); free_netdev(netdev); } @@ -2533,7 +2535,7 @@ static int pch_gbe_probe(struct pci_dev *pdev, /* setup the private structure */ ret = pch_gbe_sw_init(adapter); if (ret) - goto err_free_netdev; + goto err_put_dev; /* Initialize PHY */ ret = pch_gbe_init_phy(adapter); @@ -2591,6 +2593,8 @@ static int pch_gbe_probe(struct pci_dev *pdev, err_free_adapter: pch_gbe_phy_hw_reset(&adapter->hw); +err_put_dev: + pci_dev_put(adapter->ptp_pdev); err_free_netdev: free_netdev(netdev); return ret; diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 76072f8c3d2f..0d57ffcedf0c 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -2471,6 +2471,7 @@ static netdev_tx_t ql3xxx_send(struct sk_buff *skb, skb_shinfo(skb)->nr_frags); if (tx_cb->seg_count == -1) { netdev_err(ndev, "%s: invalid segment count!\n", __func__); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c index 88fa29572e23..ddcc325ed570 100644 --- a/drivers/net/ethernet/sfc/ef100_netdev.c +++ b/drivers/net/ethernet/sfc/ef100_netdev.c @@ -218,6 +218,7 @@ netdev_tx_t __ef100_hard_start_xmit(struct sk_buff *skb, skb->len, skb->data_len, channel->channel); if (!efx->n_channels || !efx->n_tx_channels || !channel) { netif_stop_queue(net_dev); + dev_kfree_skb_any(skb); goto err; } diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index de94921cbef9..025e0c19ec25 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -98,6 +98,7 @@ struct ipvl_port { struct sk_buff_head backlog; int count; struct ida ida; + netdevice_tracker dev_tracker; }; struct ipvl_skb_cb { diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 54c94a69c2bb..796a38f9d7b2 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -83,6 +83,7 @@ static int ipvlan_port_create(struct net_device *dev) if (err) goto err; + netdev_hold(dev, &port->dev_tracker, GFP_KERNEL); return 0; err: @@ -95,6 +96,7 @@ static void ipvlan_port_destroy(struct net_device *dev) struct ipvl_port *port = ipvlan_port_get_rtnl(dev); struct sk_buff *skb; + netdev_put(dev, &port->dev_tracker); if (port->mode == IPVLAN_MODE_L3S) ipvlan_l3s_unregister(port); netdev_rx_handler_unregister(dev); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 85376d2f24ca..f41f67b583db 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3835,7 +3835,6 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[], if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; - int ret; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 349b7b1dbbf2..d49965907561 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -870,8 +870,10 @@ static int at803x_probe(struct phy_device *phydev) .wolopts = 0, }; - if (ccr < 0) + if (ccr < 0) { + ret = ccr; goto err; + } mode_cfg = ccr & AT803X_MODE_CFG_MASK; switch (mode_cfg) { diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 8d5cbda33f66..0897fdb6254b 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -1915,6 +1915,7 @@ static const struct driver_info cdc_ncm_zlp_info = { .status = cdc_ncm_status, .rx_fixup = cdc_ncm_rx_fixup, .tx_fixup = cdc_ncm_tx_fixup, + .set_rx_mode = usbnet_cdc_update_filter, }; /* Same as cdc_ncm_info, but with FLAG_WWAN */ diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index afd6faa4c2ec..554d4e2a84a4 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1423,6 +1423,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ + {QMI_QUIRK_SET_DTR(0x1546, 0x1342, 4)}, /* u-blox LARA-L6 */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 7106932c6f88..86e52454b5b5 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3949,12 +3949,11 @@ static int virtnet_probe(struct virtio_device *vdev) return 0; free_unregister_netdev: - virtio_reset_device(vdev); - unregister_netdev(dev); free_failover: net_failover_destroy(vi->failover); free_vqs: + virtio_reset_device(vdev); cancel_delayed_work_sync(&vi->refill); free_receive_page_frags(vi); virtnet_del_vqs(vi); diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c index d3d34d1c4704..5bf5a93937c9 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c @@ -249,7 +249,7 @@ static enum ipc_pcie_sleep_state ipc_pcie_read_bios_cfg(struct device *dev) if (object->integer.value == 3) sleep_state = IPC_PCIE_D3L2; - kfree(object); + ACPI_FREE(object); default_ret: return sleep_state; diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.c b/drivers/net/wwan/t7xx/t7xx_modem_ops.c index 3458af31e864..7d0f5e4f0a78 100644 --- a/drivers/net/wwan/t7xx/t7xx_modem_ops.c +++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.c @@ -165,6 +165,8 @@ static int t7xx_acpi_reset(struct t7xx_pci_dev *t7xx_dev, char *fn_name) return -EFAULT; } + kfree(buffer.pointer); + #endif return 0; } diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index 24436c9e54c9..97600826af69 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -112,8 +112,10 @@ static int nfcmrvl_i2c_nci_send(struct nfcmrvl_private *priv, struct nfcmrvl_i2c_drv_data *drv_data = priv->drv_data; int ret; - if (test_bit(NFCMRVL_PHY_ERROR, &priv->flags)) + if (test_bit(NFCMRVL_PHY_ERROR, &priv->flags)) { + kfree_skb(skb); return -EREMOTEIO; + } ret = i2c_master_send(drv_data->i2c, skb->data, skb->len); diff --git a/drivers/nfc/nxp-nci/core.c b/drivers/nfc/nxp-nci/core.c index 580cb6ecffee..66b198663387 100644 --- a/drivers/nfc/nxp-nci/core.c +++ b/drivers/nfc/nxp-nci/core.c @@ -73,11 +73,15 @@ static int nxp_nci_send(struct nci_dev *ndev, struct sk_buff *skb) struct nxp_nci_info *info = nci_get_drvdata(ndev); int r; - if (!info->phy_ops->write) + if (!info->phy_ops->write) { + kfree_skb(skb); return -EOPNOTSUPP; + } - if (info->mode != NXP_NCI_MODE_NCI) + if (info->mode != NXP_NCI_MODE_NCI) { + kfree_skb(skb); return -EINVAL; + } r = info->phy_ops->write(info->phy_id, skb); if (r < 0) { diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c index 0270e05b68df..aec356880adf 100644 --- a/drivers/nfc/s3fwrn5/core.c +++ b/drivers/nfc/s3fwrn5/core.c @@ -105,6 +105,7 @@ static int s3fwrn5_nci_send(struct nci_dev *ndev, struct sk_buff *skb) mutex_lock(&info->mutex); if (s3fwrn5_get_mode(info) != S3FWRN5_MODE_NCI) { + kfree_skb(skb); mutex_unlock(&info->mutex); return -EINVAL; } diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index 7764b1a4c3cf..ec87dd21e054 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -312,6 +312,8 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev, int r = 0; struct device *dev = &ndev->nfc_dev->dev; struct nfc_evt_transaction *transaction; + u32 aid_len; + u8 params_len; pr_debug("connectivity gate event: %x\n", event); @@ -325,26 +327,47 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev, * Description Tag Length * AID 81 5 to 16 * PARAMETERS 82 0 to 255 + * + * The key differences are aid storage length is variably sized + * in the packet, but fixed in nfc_evt_transaction, and that + * the aid_len is u8 in the packet, but u32 in the structure, + * and the tags in the packet are not included in + * nfc_evt_transaction. + * + * size(b): 1 1 5-16 1 1 0-255 + * offset: 0 1 2 aid_len + 2 aid_len + 3 aid_len + 4 + * mem name: aid_tag(M) aid_len aid params_tag(M) params_len params + * example: 0x81 5-16 X 0x82 0-255 X */ - if (skb->len < NFC_MIN_AID_LENGTH + 2 && - skb->data[0] != NFC_EVT_TRANSACTION_AID_TAG) + if (skb->len < 2 || skb->data[0] != NFC_EVT_TRANSACTION_AID_TAG) return -EPROTO; - transaction = devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); - if (!transaction) - return -ENOMEM; + aid_len = skb->data[1]; - transaction->aid_len = skb->data[1]; - memcpy(transaction->aid, &skb->data[2], transaction->aid_len); + if (skb->len < aid_len + 4 || + aid_len > sizeof(transaction->aid)) + return -EPROTO; - /* Check next byte is PARAMETERS tag (82) */ - if (skb->data[transaction->aid_len + 2] != - NFC_EVT_TRANSACTION_PARAMS_TAG) + params_len = skb->data[aid_len + 3]; + + /* Verify PARAMETERS tag is (82), and final check that there is + * enough space in the packet to read everything. + */ + if (skb->data[aid_len + 2] != NFC_EVT_TRANSACTION_PARAMS_TAG || + skb->len < aid_len + 4 + params_len) return -EPROTO; - transaction->params_len = skb->data[transaction->aid_len + 3]; - memcpy(transaction->params, skb->data + - transaction->aid_len + 4, transaction->params_len); + transaction = devm_kzalloc(dev, sizeof(*transaction) + + params_len, GFP_KERNEL); + if (!transaction) + return -ENOMEM; + + transaction->aid_len = aid_len; + transaction->params_len = params_len; + + memcpy(transaction->aid, &skb->data[2], aid_len); + memcpy(transaction->params, &skb->data[aid_len + 4], + params_len); r = nfc_se_transaction(ndev->nfc_dev, host, transaction); break; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index af2ceb4160bc..06cbad166225 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -981,6 +981,7 @@ struct mlx5_async_work { struct mlx5_async_ctx *ctx; mlx5_async_cbk_t user_callback; u16 opcode; /* cmd opcode */ + u16 op_mod; /* cmd op_mod */ void *out; /* pointer to the cmd output buffer */ }; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 3af1e927247d..69174093078f 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -281,7 +281,8 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in * sk_v6_rcv_saddr (ipv6) changes after it has been binded. The socket's * rcv_saddr field should already have been updated when this is called. */ -int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk); +int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family); +void inet_bhash2_reset_saddr(struct sock *sk); void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, struct inet_bind2_bucket *tb2, unsigned short port); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 20745cf7ae1a..2f2a6023fb0e 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -83,7 +83,7 @@ struct neigh_parms { struct rcu_head rcu_head; int reachable_time; - int qlen; + u32 qlen; int data[NEIGH_VAR_DATA_MAX]; DECLARE_BITMAP(data_state, NEIGH_VAR_DATA_MAX); }; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 25cd35f5922e..007730412947 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -296,7 +296,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb, key->ct_zone = ct->zone.id; #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - key->ct_mark = ct->mark; + key->ct_mark = READ_ONCE(ct->mark); #endif cl = nf_ct_labels_find(ct); diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 6fac2f0ef074..711cd3b4347a 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -48,9 +48,11 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) return "RPL"; case LWTUNNEL_ENCAP_IOAM6: return "IOAM6"; + case LWTUNNEL_ENCAP_XFRM: + /* module autoload not supported for encap type */ + return NULL; case LWTUNNEL_ENCAP_IP6: case LWTUNNEL_ENCAP_IP: - case LWTUNNEL_ENCAP_XFRM: case LWTUNNEL_ENCAP_NONE: case __LWTUNNEL_ENCAP_MAX: /* should not have got here */ diff --git a/net/core/neighbour.c b/net/core/neighbour.c index a77a85e357e0..952a54763358 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -307,7 +307,31 @@ static int neigh_del_timer(struct neighbour *n) return 0; } -static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) +static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, + int family) +{ + switch (family) { + case AF_INET: + return __in_dev_arp_parms_get_rcu(dev); + case AF_INET6: + return __in6_dev_nd_parms_get_rcu(dev); + } + return NULL; +} + +static void neigh_parms_qlen_dec(struct net_device *dev, int family) +{ + struct neigh_parms *p; + + rcu_read_lock(); + p = neigh_get_dev_parms_rcu(dev, family); + if (p) + p->qlen--; + rcu_read_unlock(); +} + +static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net, + int family) { struct sk_buff_head tmp; unsigned long flags; @@ -321,13 +345,7 @@ static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) struct net_device *dev = skb->dev; if (net == NULL || net_eq(dev_net(dev), net)) { - struct in_device *in_dev; - - rcu_read_lock(); - in_dev = __in_dev_get_rcu(dev); - if (in_dev) - in_dev->arp_parms->qlen--; - rcu_read_unlock(); + neigh_parms_qlen_dec(dev, family); __skb_unlink(skb, list); __skb_queue_tail(&tmp, skb); } @@ -409,7 +427,8 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); pneigh_ifdown_and_unlock(tbl, dev); - pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL); + pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL, + tbl->family); if (skb_queue_empty_lockless(&tbl->proxy_queue)) del_timer_sync(&tbl->proxy_timer); return 0; @@ -1621,13 +1640,8 @@ static void neigh_proxy_process(struct timer_list *t) if (tdif <= 0) { struct net_device *dev = skb->dev; - struct in_device *in_dev; - rcu_read_lock(); - in_dev = __in_dev_get_rcu(dev); - if (in_dev) - in_dev->arp_parms->qlen--; - rcu_read_unlock(); + neigh_parms_qlen_dec(dev, tbl->family); __skb_unlink(skb, &tbl->proxy_queue); if (tbl->proxy_redo && netif_running(dev)) { @@ -1821,7 +1835,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) cancel_delayed_work_sync(&tbl->managed_work); cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); - pneigh_queue_purge(&tbl->proxy_queue, NULL); + pneigh_queue_purge(&tbl->proxy_queue, NULL, tbl->family); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) pr_crit("neighbour leakage\n"); @@ -3539,18 +3553,6 @@ static int proc_unres_qlen(struct ctl_table *ctl, int write, return ret; } -static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, - int family) -{ - switch (family) { - case AF_INET: - return __in_dev_arp_parms_get_rcu(dev); - case AF_INET6: - return __in6_dev_nd_parms_get_rcu(dev); - } - return NULL; -} - static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, int index) { diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 713b7b8dad7e..b780827f5e0a 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -45,11 +45,10 @@ static unsigned int dccp_v4_pernet_id __read_mostly; int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - __be32 daddr, nexthop, prev_sk_rcv_saddr; struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); __be16 orig_sport, orig_dport; + __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; @@ -91,26 +90,13 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) daddr = fl4->daddr; if (inet->inet_saddr == 0) { - if (inet_csk(sk)->icsk_bind2_hash) { - prev_addr_hashbucket = - inet_bhashfn_portaddr(&dccp_hashinfo, sk, - sock_net(sk), - inet->inet_num); - prev_sk_rcv_saddr = sk->sk_rcv_saddr; - } - inet->inet_saddr = fl4->saddr; - } - - sk_rcv_saddr_set(sk, inet->inet_saddr); - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { - inet->inet_saddr = 0; - sk_rcv_saddr_set(sk, prev_sk_rcv_saddr); ip_rt_put(rt); return err; } + } else { + sk_rcv_saddr_set(sk, inet->inet_saddr); } inet->inet_dport = usin->sin_port; @@ -157,6 +143,7 @@ failure: * This unhashes the socket and releases the local port, if necessary. */ dccp_set_state(sk, DCCP_CLOSED); + inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index e57b43006074..602f3432d80b 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -934,26 +934,11 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, } if (saddr == NULL) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - struct in6_addr prev_v6_rcv_saddr; - - if (icsk->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(&dccp_hashinfo, - sk, sock_net(sk), - inet->inet_num); - prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - } - saddr = &fl6.saddr; - sk->sk_v6_rcv_saddr = *saddr; - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); - if (err) { - sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr; - goto failure; - } - } + + err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); + if (err) + goto failure; } /* set the source address */ @@ -985,6 +970,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: dccp_set_state(sk, DCCP_CLOSED); + inet_bhash2_reset_saddr(sk); __sk_dst_reset(sk); failure: inet->inet_dport = 0; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index c548ca3e9b0e..85e35c5e8890 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -279,8 +279,7 @@ int dccp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 4728087c42a5..0da679411330 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1230,7 +1230,6 @@ EXPORT_SYMBOL(inet_unregister_protosw); static int inet_sk_reselect_saddr(struct sock *sk) { - struct inet_bind_hashbucket *prev_addr_hashbucket; struct inet_sock *inet = inet_sk(sk); __be32 old_saddr = inet->inet_saddr; __be32 daddr = inet->inet_daddr; @@ -1260,16 +1259,8 @@ static int inet_sk_reselect_saddr(struct sock *sk) return 0; } - prev_addr_hashbucket = - inet_bhashfn_portaddr(tcp_or_dccp_get_hashinfo(sk), sk, - sock_net(sk), inet->inet_num); - - inet->inet_saddr = inet->inet_rcv_saddr = new_saddr; - - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &new_saddr, AF_INET); if (err) { - inet->inet_saddr = old_saddr; - inet->inet_rcv_saddr = old_saddr; ip_rt_put(rt); return err; } diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 170152772d33..3969fa805679 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -314,6 +314,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ xo->seq.low += skb_shinfo(skb)->gso_segs; } + if (xo->seq.low < seq) + xo->seq.hi++; + esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32)); ip_hdr(skb)->tot_len = htons(skb->len); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 452ff177e4da..74d403dbd2b4 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -126,7 +126,7 @@ struct key_vector { /* This list pointer if valid if (pos | bits) == 0 (LEAF) */ struct hlist_head leaf; /* This array is valid if (pos | bits) > 0 (TNODE) */ - struct key_vector __rcu *tnode[0]; + DECLARE_FLEX_ARRAY(struct key_vector __rcu *, tnode); }; }; @@ -1381,8 +1381,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb, /* The alias was already inserted, so the node must exist. */ l = l ? l : fib_find_node(t, &tp, key); - if (WARN_ON_ONCE(!l)) + if (WARN_ON_ONCE(!l)) { + err = -ENOENT; goto out_free_new_fa; + } if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 033bf3c2538f..3cec471a2cd2 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -858,34 +858,80 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; } -int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk) +static void inet_update_saddr(struct sock *sk, void *saddr, int family) +{ + if (family == AF_INET) { + inet_sk(sk)->inet_saddr = *(__be32 *)saddr; + sk_rcv_saddr_set(sk, inet_sk(sk)->inet_saddr); + } +#if IS_ENABLED(CONFIG_IPV6) + else { + sk->sk_v6_rcv_saddr = *(struct in6_addr *)saddr; + } +#endif +} + +static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2, *new_tb2; int l3mdev = inet_sk_bound_l3mdev(sk); - struct inet_bind_hashbucket *head2; int port = inet_sk(sk)->inet_num; struct net *net = sock_net(sk); + int bhash; + + if (!inet_csk(sk)->icsk_bind2_hash) { + /* Not bind()ed before. */ + if (reset) + inet_reset_saddr(sk); + else + inet_update_saddr(sk, saddr, family); + + return 0; + } /* Allocate a bind2 bucket ahead of time to avoid permanently putting * the bhash2 table in an inconsistent state if a new tb2 bucket * allocation fails. */ new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC); - if (!new_tb2) + if (!new_tb2) { + if (reset) { + /* The (INADDR_ANY, port) bucket might have already + * been freed, then we cannot fixup icsk_bind2_hash, + * so we give up and unlink sk from bhash/bhash2 not + * to leave inconsistency in bhash2. + */ + inet_put_port(sk); + inet_reset_saddr(sk); + } + return -ENOMEM; + } + bhash = inet_bhashfn(net, port, hinfo->bhash_size); + head = &hinfo->bhash[bhash]; head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); - if (prev_saddr) { - spin_lock_bh(&prev_saddr->lock); - __sk_del_bind2_node(sk); - inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, - inet_csk(sk)->icsk_bind2_hash); - spin_unlock_bh(&prev_saddr->lock); - } + /* If we change saddr locklessly, another thread + * iterating over bhash might see corrupted address. + */ + spin_lock_bh(&head->lock); - spin_lock_bh(&head2->lock); + spin_lock(&head2->lock); + __sk_del_bind2_node(sk); + inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash); + spin_unlock(&head2->lock); + + if (reset) + inet_reset_saddr(sk); + else + inet_update_saddr(sk, saddr, family); + + head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); + + spin_lock(&head2->lock); tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); if (!tb2) { tb2 = new_tb2; @@ -893,15 +939,29 @@ int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct soc } sk_add_bind2_node(sk, &tb2->owners); inet_csk(sk)->icsk_bind2_hash = tb2; - spin_unlock_bh(&head2->lock); + spin_unlock(&head2->lock); + + spin_unlock_bh(&head->lock); if (tb2 != new_tb2) kmem_cache_free(hinfo->bind2_bucket_cachep, new_tb2); return 0; } + +int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) +{ + return __inet_bhash2_update_saddr(sk, saddr, family, false); +} EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr); +void inet_bhash2_reset_saddr(struct sock *sk) +{ + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + __inet_bhash2_update_saddr(sk, NULL, 0, true); +} +EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr); + /* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 1b512390b3cf..e880ce77322a 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -366,6 +366,11 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, iph->tos, dev); if (unlikely(err)) goto drop_error; + } else { + struct in_device *in_dev = __in_dev_get_rcu(dev); + + if (in_dev && IN_DEV_ORCONF(in_dev, NOPOLICY)) + IPCB(skb)->flags |= IPSKB_NOPOLICY; } #ifdef CONFIG_IP_ROUTE_CLASSID diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index f8e176c77d1c..b3cc416ed292 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -435,7 +435,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) switch (ctinfo) { case IP_CT_NEW: - ct->mark = hash; + WRITE_ONCE(ct->mark, hash); break; case IP_CT_RELATED: case IP_CT_RELATED_REPLY: @@ -452,7 +452,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) #ifdef DEBUG nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); #endif - pr_debug("hash=%u ct_hash=%u ", hash, ct->mark); + pr_debug("hash=%u ct_hash=%u ", hash, READ_ONCE(ct->mark)); if (!clusterip_responsible(cipinfo->config, hash)) { pr_debug("not responsible\n"); return NF_DROP; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 54836a6b81d6..4f2205756cfe 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3114,8 +3114,7 @@ int tcp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 87d440f47a70..da46357f501b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -199,15 +199,14 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_timewait_death_row *tcp_death_row; - __be32 daddr, nexthop, prev_sk_rcv_saddr; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct ip_options_rcu *inet_opt; struct net *net = sock_net(sk); __be16 orig_sport, orig_dport; + __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; @@ -251,24 +250,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!inet->inet_saddr) { - if (inet_csk(sk)->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo, - sk, net, inet->inet_num); - prev_sk_rcv_saddr = sk->sk_rcv_saddr; - } - inet->inet_saddr = fl4->saddr; - } - - sk_rcv_saddr_set(sk, inet->inet_saddr); - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { - inet->inet_saddr = 0; - sk_rcv_saddr_set(sk, prev_sk_rcv_saddr); ip_rt_put(rt); return err; } + } else { + sk_rcv_saddr_set(sk, inet->inet_saddr); } if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { @@ -343,6 +331,7 @@ failure: * if necessary. */ tcp_set_state(sk, TCP_CLOSE); + inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 79d43548279c..242f4295940e 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -346,6 +346,9 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features xo->seq.low += skb_shinfo(skb)->gso_segs; } + if (xo->seq.low < seq) + xo->seq.hi++; + esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32)); len = skb->len - sizeof(struct ipv6hdr); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2a3f9296df1e..f0548dbcabd2 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -292,24 +292,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!saddr) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - struct in6_addr prev_v6_rcv_saddr; - - if (icsk->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo, - sk, net, inet->inet_num); - prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - } saddr = &fl6.saddr; - sk->sk_v6_rcv_saddr = *saddr; - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); - if (err) { - sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr; - goto failure; - } - } + err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); + if (err) + goto failure; } /* set the source address */ @@ -359,6 +346,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: tcp_set_state(sk, TCP_CLOSE); + inet_bhash2_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 4a4b0e49ec92..ea435eba3053 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -287,9 +287,13 @@ int __init xfrm6_init(void) if (ret) goto out_state; - register_pernet_subsys(&xfrm6_net_ops); + ret = register_pernet_subsys(&xfrm6_net_ops); + if (ret) + goto out_protocol; out: return ret; +out_protocol: + xfrm6_protocol_fini(); out_state: xfrm6_state_fini(); out_policy: diff --git a/net/key/af_key.c b/net/key/af_key.c index c85df5b958d2..95edcbedf6ef 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2905,7 +2905,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t) break; if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); @@ -2923,7 +2923,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!ealg->pfkey_supported) continue; - if (!(ealg_tmpl_set(t, ealg) && ealg->available)) + if (!(ealg_tmpl_set(t, ealg))) continue; for (k = 1; ; k++) { @@ -2934,16 +2934,17 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } } return sz + sizeof(struct sadb_prop); } -static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i; p = skb_put(skb, sizeof(struct sadb_prop)); @@ -2971,13 +2972,17 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); } -static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i, k; p = skb_put(skb, sizeof(struct sadb_prop)); @@ -3019,8 +3024,11 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); } static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c) @@ -3150,6 +3158,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int ctx_size = 0; + int alg_size = 0; sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) @@ -3161,16 +3170,16 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct sizeof(struct sadb_x_policy); if (x->id.proto == IPPROTO_AH) - size += count_ah_combs(t); + alg_size = count_ah_combs(t); else if (x->id.proto == IPPROTO_ESP) - size += count_esp_combs(t); + alg_size = count_esp_combs(t); if ((xfrm_ctx = x->security)) { ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); size += sizeof(struct sadb_x_sec_ctx) + ctx_size; } - skb = alloc_skb(size + 16, GFP_ATOMIC); + skb = alloc_skb(size + alg_size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; @@ -3224,10 +3233,13 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct pol->sadb_x_policy_priority = xp->priority; /* Set sadb_comb's. */ + alg_size = 0; if (x->id.proto == IPPROTO_AH) - dump_ah_combs(skb, t); + alg_size = dump_ah_combs(skb, t); else if (x->id.proto == IPPROTO_ESP) - dump_esp_combs(skb, t); + alg_size = dump_esp_combs(skb, t); + + hdr->sadb_msg_len += alg_size / 8; /* security context */ if (xfrm_ctx) { @@ -3382,7 +3394,7 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, hdr->sadb_msg_len = size / sizeof(uint64_t); hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; - hdr->sadb_msg_seq = x->km.seq = get_acqseq(); + hdr->sadb_msg_seq = x->km.seq; hdr->sadb_msg_pid = 0; /* SA */ diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 754fdda8a5f5..9a1415fe3fa7 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1474,11 +1474,12 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, } sk = sock->sk; - write_lock(&sk->sk_callback_lock); - + write_lock_bh(&sk->sk_callback_lock); ret = l2tp_validate_socket(sk, net, tunnel->encap); if (ret < 0) - goto err_sock; + goto err_inval_sock; + rcu_assign_sk_user_data(sk, tunnel); + write_unlock_bh(&sk->sk_callback_lock); tunnel->l2tp_net = net; pn = l2tp_pernet(net); @@ -1507,8 +1508,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, }; setup_udp_tunnel_sock(net, sock, &udp_cfg); - } else { - rcu_assign_sk_user_data(sk, tunnel); } tunnel->old_sk_destruct = sk->sk_destruct; @@ -1522,16 +1521,18 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, if (tunnel->fd >= 0) sockfd_put(sock); - write_unlock(&sk->sk_callback_lock); return 0; err_sock: + write_lock_bh(&sk->sk_callback_lock); + rcu_assign_sk_user_data(sk, NULL); +err_inval_sock: + write_unlock_bh(&sk->sk_callback_lock); + if (tunnel->fd < 0) sock_release(sock); else sockfd_put(sock); - - write_unlock(&sk->sk_callback_lock); err: return ret; } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 3adc291d9ce1..7499192af586 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -916,7 +916,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, #ifdef IP_SET_HASH_WITH_MULTI if (h->bucketsize >= AHASH_MAX_TUNED) goto set_full; - else if (h->bucketsize < multi) + else if (h->bucketsize <= multi) h->bucketsize += AHASH_INIT_SIZE; #endif if (n->size >= AHASH_MAX(h)) { diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index dd30c03d5a23..75d556d71652 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -151,18 +151,16 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE) return -ERANGE; - if (retried) { + if (retried) ip = ntohl(h->next.ip); - e.ip = htonl(ip); - } for (; ip <= ip_to;) { + e.ip = htonl(ip); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ip += hosts; - e.ip = htonl(ip); - if (e.ip == 0) + if (ip == 0) return 0; ret = 0; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index f97bda06d2a9..2692139ce417 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1781,7 +1781,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, } #ifdef CONFIG_NF_CONNTRACK_MARK - ct->mark = exp->master->mark; + ct->mark = READ_ONCE(exp->master->mark); #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK ct->secmark = exp->master->secmark; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 7562b215b932..d71150a40fb0 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -328,9 +328,9 @@ nla_put_failure: } #ifdef CONFIG_NF_CONNTRACK_MARK -static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) +static int ctnetlink_dump_mark(struct sk_buff *skb, u32 mark) { - if (nla_put_be32(skb, CTA_MARK, htonl(ct->mark))) + if (nla_put_be32(skb, CTA_MARK, htonl(mark))) goto nla_put_failure; return 0; @@ -543,7 +543,7 @@ static int ctnetlink_dump_extinfo(struct sk_buff *skb, static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) { if (ctnetlink_dump_status(skb, ct) < 0 || - ctnetlink_dump_mark(skb, ct) < 0 || + ctnetlink_dump_mark(skb, READ_ONCE(ct->mark)) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || @@ -722,6 +722,7 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) struct sk_buff *skb; unsigned int type; unsigned int flags = 0, group; + u32 mark; int err; if (events & (1 << IPCT_DESTROY)) { @@ -826,8 +827,9 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) } #ifdef CONFIG_NF_CONNTRACK_MARK - if ((events & (1 << IPCT_MARK) || ct->mark) - && ctnetlink_dump_mark(skb, ct) < 0) + mark = READ_ONCE(ct->mark); + if ((events & (1 << IPCT_MARK) || mark) && + ctnetlink_dump_mark(skb, mark) < 0) goto nla_put_failure; #endif nlmsg_end(skb, nlh); @@ -1154,7 +1156,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) } #ifdef CONFIG_NF_CONNTRACK_MARK - if ((ct->mark & filter->mark.mask) != filter->mark.val) + if ((READ_ONCE(ct->mark) & filter->mark.mask) != filter->mark.val) goto ignore_entry; #endif status = (u32)READ_ONCE(ct->status); @@ -2002,9 +2004,9 @@ static void ctnetlink_change_mark(struct nf_conn *ct, mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK])); mark = ntohl(nla_get_be32(cda[CTA_MARK])); - newmark = (ct->mark & mask) ^ mark; - if (newmark != ct->mark) - ct->mark = newmark; + newmark = (READ_ONCE(ct->mark) & mask) ^ mark; + if (newmark != READ_ONCE(ct->mark)) + WRITE_ONCE(ct->mark, newmark); } #endif @@ -2669,6 +2671,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) { const struct nf_conntrack_zone *zone; struct nlattr *nest_parms; + u32 mark; zone = nf_ct_zone(ct); @@ -2730,7 +2733,8 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_MARK - if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0) + mark = READ_ONCE(ct->mark); + if (mark && ctnetlink_dump_mark(skb, mark) < 0) goto nla_put_failure; #endif if (ctnetlink_dump_labels(skb, ct) < 0) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 4ffe84c5a82c..bca839ab1ae8 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -366,7 +366,7 @@ static int ct_seq_show(struct seq_file *s, void *v) goto release; #if defined(CONFIG_NF_CONNTRACK_MARK) - seq_printf(s, "mark=%u ", ct->mark); + seq_printf(s, "mark=%u ", READ_ONCE(ct->mark)); #endif ct_show_secctx(s, ct); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index b04645ced89b..00b522890d77 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -1098,6 +1098,7 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, struct flow_block_cb *block_cb, *next; int err = 0; + down_write(&flowtable->flow_block_lock); switch (cmd) { case FLOW_BLOCK_BIND: list_splice(&bo->cb_list, &flowtable->flow_block.cb_list); @@ -1112,6 +1113,7 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, WARN_ON_ONCE(1); err = -EOPNOTSUPP; } + up_write(&flowtable->flow_block_lock); return err; } @@ -1168,7 +1170,9 @@ static int nf_flow_table_offload_cmd(struct flow_block_offload *bo, nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable, extack); + down_write(&flowtable->flow_block_lock); err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, bo); + up_write(&flowtable->flow_block_lock); if (err < 0) return err; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e7152d599d73..7a09421f19e1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5958,7 +5958,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, &timeout); if (err) return err; - } else if (set->flags & NFT_SET_TIMEOUT) { + } else if (set->flags & NFT_SET_TIMEOUT && + !(flags & NFT_SET_ELEM_INTERVAL_END)) { timeout = set->timeout; } @@ -6024,7 +6025,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = -EOPNOTSUPP; goto err_set_elem_expr; } - } else if (set->num_exprs > 0) { + } else if (set->num_exprs > 0 && + !(flags & NFT_SET_ELEM_INTERVAL_END)) { err = nft_set_elem_expr_clone(ctx, set, expr_array); if (err < 0) goto err_set_elem_expr_clone; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index a3f01f209a53..641dc21f92b4 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -98,7 +98,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, return; #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: - *dest = ct->mark; + *dest = READ_ONCE(ct->mark); return; #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK @@ -297,8 +297,8 @@ static void nft_ct_set_eval(const struct nft_expr *expr, switch (priv->key) { #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: - if (ct->mark != value) { - ct->mark = value; + if (READ_ONCE(ct->mark) != value) { + WRITE_ONCE(ct->mark, value); nf_conntrack_event_cache(IPCT_MARK, ct); } break; diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index e5ebc0810675..ad3c033db64e 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -30,6 +30,7 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) u_int32_t new_targetmark; struct nf_conn *ct; u_int32_t newmark; + u_int32_t oldmark; ct = nf_ct_get(skb, &ctinfo); if (ct == NULL) @@ -37,14 +38,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) switch (info->mode) { case XT_CONNMARK_SET: - newmark = (ct->mark & ~info->ctmask) ^ info->ctmark; + oldmark = READ_ONCE(ct->mark); + newmark = (oldmark & ~info->ctmask) ^ info->ctmark; if (info->shift_dir == D_SHIFT_RIGHT) newmark >>= info->shift_bits; else newmark <<= info->shift_bits; - if (ct->mark != newmark) { - ct->mark = newmark; + if (READ_ONCE(ct->mark) != newmark) { + WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; @@ -55,15 +57,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) else new_targetmark <<= info->shift_bits; - newmark = (ct->mark & ~info->ctmask) ^ + newmark = (READ_ONCE(ct->mark) & ~info->ctmask) ^ new_targetmark; - if (ct->mark != newmark) { - ct->mark = newmark; + if (READ_ONCE(ct->mark) != newmark) { + WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_RESTORE: - new_targetmark = (ct->mark & info->ctmask); + new_targetmark = (READ_ONCE(ct->mark) & info->ctmask); if (info->shift_dir == D_SHIFT_RIGHT) new_targetmark >>= info->shift_bits; else @@ -126,7 +128,7 @@ connmark_mt(const struct sk_buff *skb, struct xt_action_param *par) if (ct == NULL) return false; - return ((ct->mark & info->mask) == info->mark) ^ info->invert; + return ((READ_ONCE(ct->mark) & info->mask) == info->mark) ^ info->invert; } static int connmark_mt_check(const struct xt_mtchk_param *par) diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 6a193cce2a75..4ffdf2f45c44 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -542,7 +542,7 @@ static int nci_open_device(struct nci_dev *ndev) skb_queue_purge(&ndev->tx_q); ndev->ops->close(ndev); - ndev->flags = 0; + ndev->flags &= BIT(NCI_UNREG); } done: diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index aa5e712adf07..3d36ea5701f0 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -279,8 +279,10 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb) nci_plen(skb->data)); conn_info = nci_get_conn_info_by_conn_id(ndev, nci_conn_id(skb->data)); - if (!conn_info) + if (!conn_info) { + kfree_skb(skb); return; + } /* strip the nci data header */ skb_pull(skb, NCI_DATA_HDR_SIZE); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c7b10234cf7c..c8eaf4234b2e 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -152,7 +152,7 @@ static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo) static u32 ovs_ct_get_mark(const struct nf_conn *ct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - return ct ? ct->mark : 0; + return ct ? READ_ONCE(ct->mark) : 0; #else return 0; #endif @@ -340,9 +340,9 @@ static int ovs_ct_set_mark(struct nf_conn *ct, struct sw_flow_key *key, #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) u32 new_mark; - new_mark = ct_mark | (ct->mark & ~(mask)); - if (ct->mark != new_mark) { - ct->mark = new_mark; + new_mark = ct_mark | (READ_ONCE(ct->mark) & ~(mask)); + if (READ_ONCE(ct->mark) != new_mark) { + WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); key->ct.mark = new_mark; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 1ad0ec5afb50..8499ceb7719c 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -399,6 +399,7 @@ enum rxrpc_conn_proto_state { struct rxrpc_bundle { struct rxrpc_conn_parameters params; refcount_t ref; + atomic_t active; /* Number of active users */ unsigned int debug_id; bool try_upgrade; /* True if the bundle is attempting upgrade */ bool alloc_conn; /* True if someone's getting a conn */ diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 3c9eeb5b750c..bdb335cb2d05 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -40,6 +40,8 @@ __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ; DEFINE_IDR(rxrpc_client_conn_ids); static DEFINE_SPINLOCK(rxrpc_conn_id_lock); +static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); + /* * Get a connection ID and epoch for a client connection from the global pool. * The connection struct pointer is then recorded in the idr radix tree. The @@ -123,6 +125,7 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, bundle->params = *cp; rxrpc_get_peer(bundle->params.peer); refcount_set(&bundle->ref, 1); + atomic_set(&bundle->active, 1); spin_lock_init(&bundle->channel_lock); INIT_LIST_HEAD(&bundle->waiting_calls); } @@ -149,7 +152,7 @@ void rxrpc_put_bundle(struct rxrpc_bundle *bundle) dead = __refcount_dec_and_test(&bundle->ref, &r); - _debug("PUT B=%x %d", d, r); + _debug("PUT B=%x %d", d, r - 1); if (dead) rxrpc_free_bundle(bundle); } @@ -338,6 +341,7 @@ found_bundle_free: rxrpc_free_bundle(candidate); found_bundle: rxrpc_get_bundle(bundle); + atomic_inc(&bundle->active); spin_unlock(&local->client_bundles_lock); _leave(" = %u [found]", bundle->debug_id); return bundle; @@ -435,6 +439,7 @@ static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp) if (old) trace_rxrpc_client(old, -1, rxrpc_client_replace); candidate->bundle_shift = shift; + atomic_inc(&bundle->active); bundle->conns[i] = candidate; for (j = 0; j < RXRPC_MAXCALLS; j++) set_bit(shift + j, &bundle->avail_chans); @@ -725,6 +730,7 @@ granted_channel: smp_rmb(); out_put_bundle: + rxrpc_deactivate_bundle(bundle); rxrpc_put_bundle(bundle); out: _leave(" = %d", ret); @@ -900,9 +906,8 @@ out: static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) { struct rxrpc_bundle *bundle = conn->bundle; - struct rxrpc_local *local = bundle->params.local; unsigned int bindex; - bool need_drop = false, need_put = false; + bool need_drop = false; int i; _enter("C=%x", conn->debug_id); @@ -921,15 +926,22 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) } spin_unlock(&bundle->channel_lock); - /* If there are no more connections, remove the bundle */ - if (!bundle->avail_chans) { - _debug("maybe unbundle"); - spin_lock(&local->client_bundles_lock); + if (need_drop) { + rxrpc_deactivate_bundle(bundle); + rxrpc_put_connection(conn); + } +} - for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) - if (bundle->conns[i]) - break; - if (i == ARRAY_SIZE(bundle->conns) && !bundle->params.exclusive) { +/* + * Drop the active count on a bundle. + */ +static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) +{ + struct rxrpc_local *local = bundle->params.local; + bool need_put = false; + + if (atomic_dec_and_lock(&bundle->active, &local->client_bundles_lock)) { + if (!bundle->params.exclusive) { _debug("erase bundle"); rb_erase(&bundle->local_node, &local->client_bundles); need_put = true; @@ -939,10 +951,6 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) if (need_put) rxrpc_put_bundle(bundle); } - - if (need_drop) - rxrpc_put_connection(conn); - _leave(""); } /* diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 1e8ab4749c6c..4662a6ce8a7e 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -976,7 +976,7 @@ config NET_ACT_TUNNEL_KEY config NET_ACT_CT tristate "connection tracking tc action" - depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT && NF_FLOW_TABLE + depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE help Say Y here to allow sending the packets to conntrack module. diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 66b143bb04ac..d41002e4613f 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -61,7 +61,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, c = nf_ct_get(skb, &ctinfo); if (c) { - skb->mark = c->mark; + skb->mark = READ_ONCE(c->mark); /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; goto out; @@ -81,7 +81,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, c = nf_ct_tuplehash_to_ctrack(thash); /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; - skb->mark = c->mark; + skb->mark = READ_ONCE(c->mark); nf_ct_put(c); out: diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b38d91d6b249..4c7f7861ea96 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -178,7 +178,7 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, entry = tcf_ct_flow_table_flow_action_get_next(action); entry->id = FLOW_ACTION_CT_METADATA; #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - entry->ct_metadata.mark = ct->mark; + entry->ct_metadata.mark = READ_ONCE(ct->mark); #endif ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED : IP_CT_ESTABLISHED_REPLY; @@ -936,9 +936,9 @@ static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask) if (!mask) return; - new_mark = mark | (ct->mark & ~(mask)); - if (ct->mark != new_mark) { - ct->mark = new_mark; + new_mark = mark | (READ_ONCE(ct->mark) & ~(mask)); + if (READ_ONCE(ct->mark) != new_mark) { + WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); } diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index d4102f0a9abd..eaa02f098d1c 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -32,7 +32,7 @@ static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca, { u8 dscp, newdscp; - newdscp = (((ct->mark & cp->dscpmask) >> cp->dscpmaskshift) << 2) & + newdscp = (((READ_ONCE(ct->mark) & cp->dscpmask) >> cp->dscpmaskshift) << 2) & ~INET_ECN_MASK; switch (proto) { @@ -72,7 +72,7 @@ static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca, struct sk_buff *skb) { ca->stats_cpmark_set++; - skb->mark = ct->mark & cp->cpmarkmask; + skb->mark = READ_ONCE(ct->mark) & cp->cpmarkmask; } static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, @@ -130,7 +130,7 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, } if (cp->mode & CTINFO_MODE_DSCP) - if (!cp->dscpstatemask || (ct->mark & cp->dscpstatemask)) + if (!cp->dscpstatemask || (READ_ONCE(ct->mark) & cp->dscpstatemask)) tcf_ctinfo_dscp_set(ct, ca, cp, skb, wlen, proto); if (cp->mode & CTINFO_MODE_CPMARK) diff --git a/net/tipc/discover.c b/net/tipc/discover.c index e8630707901e..e8dcdf267c0c 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -211,7 +211,10 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, u32 self; int err; - skb_linearize(skb); + if (skb_linearize(skb)) { + kfree_skb(skb); + return; + } hdr = buf_msg(skb); if (caps & TIPC_NODE_ID128) diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index d92ec92f0b71..e3b427a70398 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -176,7 +176,7 @@ static void tipc_conn_close(struct tipc_conn *con) conn_put(con); } -static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) +static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s, struct socket *sock) { struct tipc_conn *con; int ret; @@ -202,10 +202,12 @@ static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) } con->conid = ret; s->idr_in_use++; - spin_unlock_bh(&s->idr_lock); set_bit(CF_CONNECTED, &con->flags); con->server = s; + con->sock = sock; + conn_get(con); + spin_unlock_bh(&s->idr_lock); return con; } @@ -467,7 +469,7 @@ static void tipc_topsrv_accept(struct work_struct *work) ret = kernel_accept(lsock, &newsock, O_NONBLOCK); if (ret < 0) return; - con = tipc_conn_alloc(srv); + con = tipc_conn_alloc(srv, newsock); if (IS_ERR(con)) { ret = PTR_ERR(con); sock_release(newsock); @@ -479,11 +481,11 @@ static void tipc_topsrv_accept(struct work_struct *work) newsk->sk_data_ready = tipc_conn_data_ready; newsk->sk_write_space = tipc_conn_write_space; newsk->sk_user_data = con; - con->sock = newsock; write_unlock_bh(&newsk->sk_callback_lock); /* Wake up receive process in case of 'SYN+' message */ newsk->sk_data_ready(newsk); + conn_put(con); } } @@ -577,17 +579,17 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, sub.filter = filter; *(u64 *)&sub.usr_handle = (u64)port; - con = tipc_conn_alloc(tipc_topsrv(net)); + con = tipc_conn_alloc(tipc_topsrv(net), NULL); if (IS_ERR(con)) return false; *conid = con->conid; - con->sock = NULL; rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub); - if (rc >= 0) - return true; + if (rc) + conn_put(con); + conn_put(con); - return false; + return !rc; } void tipc_topsrv_kern_unsubscr(struct net *net, int conid) diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 5f5aafd418af..21269e8f2db4 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -97,6 +97,18 @@ static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb) } } +static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb) +{ + struct xfrm_offload *xo = xfrm_offload(skb); + __u32 seq = xo->seq.low; + + seq += skb_shinfo(skb)->gso_segs; + if (unlikely(seq < xo->seq.low)) + return true; + + return false; +} + struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { int err; @@ -134,7 +146,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } - if (skb_is_gso(skb) && unlikely(x->xso.dev != dev)) { + if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || + unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 9f4d42eb090f..ce56d659c55a 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -714,7 +714,7 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff oseq += skb_shinfo(skb)->gso_segs; } - if (unlikely(oseq < replay_esn->oseq)) { + if (unlikely(xo->seq.low < replay_esn->oseq)) { XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi; xo->seq.hi = oseq_hi; replay_esn->oseq_hi = oseq_hi; diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 31c3b6ebd388..21ca91473c09 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -4196,10 +4196,13 @@ elif [ "$TESTS" = "ipv6" ]; then TESTS="$TESTS_IPV6" fi -which nettest >/dev/null -if [ $? -ne 0 ]; then - echo "'nettest' command not found; skipping tests" - exit $ksft_skip +# nettest can be run from PATH or from same directory as this selftest +if ! which nettest >/dev/null; then + PATH=$PWD:$PATH + if ! which nettest >/dev/null; then + echo "'nettest' command not found; skipping tests" + exit $ksft_skip + fi fi declare -i nfail=0 diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index f3dd5f2a0272..2eeaf4aca644 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2152,7 +2152,7 @@ remove_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 slow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 speed_10 chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 2 2 @@ -2165,7 +2165,7 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.4.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 speed_10 chk_join_nr 3 3 3 chk_add_nr 3 3 chk_rm_nr 3 3 invert @@ -2178,7 +2178,7 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.14.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 speed_10 chk_join_nr 1 1 1 chk_add_nr 3 3 chk_rm_nr 3 1 invert diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 0879da915014..80d36f7cfee8 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -35,8 +35,9 @@ init() ns1="ns1-$rndh" ns2="ns2-$rndh" + ns_sbox="ns_sbox-$rndh" - for netns in "$ns1" "$ns2";do + for netns in "$ns1" "$ns2" "$ns_sbox";do ip netns add $netns || exit $ksft_skip ip -net $netns link set lo up ip netns exec $netns sysctl -q net.mptcp.enabled=1 @@ -73,7 +74,7 @@ init() cleanup() { - for netns in "$ns1" "$ns2"; do + for netns in "$ns1" "$ns2" "$ns_sbox"; do ip netns del $netns done rm -f "$cin" "$cout" @@ -243,7 +244,7 @@ do_mptcp_sockopt_tests() { local lret=0 - ./mptcp_sockopt + ip netns exec "$ns_sbox" ./mptcp_sockopt lret=$? if [ $lret -ne 0 ]; then @@ -252,7 +253,7 @@ do_mptcp_sockopt_tests() return fi - ./mptcp_sockopt -6 + ip netns exec "$ns_sbox" ./mptcp_sockopt -6 lret=$? if [ $lret -ne 0 ]; then diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index ffa13a957a36..40aeb5a71a2a 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -247,9 +247,10 @@ run_test() tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 - # time is measured in ms, account for transfer size, affegated link speed + # time is measured in ms, account for transfer size, aggregated link speed # and header overhead (10%) - local time=$((size * 8 * 1000 * 10 / (( $rate1 + $rate2) * 1024 *1024 * 9) )) + # ms byte -> bit 10% mbit -> kbit -> bit 10% + local time=$((1000 * size * 8 * 10 / ((rate1 + rate2) * 1000 * 1000 * 9) )) # mptcp_connect will do some sleeps to allow the mp_join handshake # completion (see mptcp_connect): 200ms on each side, add some slack diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 736e358dc549..dfe3d287f01d 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -686,10 +686,12 @@ setup_xfrm() { } setup_nettest_xfrm() { - which nettest >/dev/null - if [ $? -ne 0 ]; then - echo "'nettest' command not found; skipping tests" - return 1 + if ! which nettest >/dev/null; then + PATH=$PWD:$PATH + if ! which nettest >/dev/null; then + echo "'nettest' command not found; skipping tests" + return 1 + fi fi [ ${1} -eq 6 ] && proto="-6" || proto="" diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index 6a443ca3cd3a..0c743752669a 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -5,6 +5,8 @@ readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" +BPF_FILE="../bpf/xdp_dummy.bpf.o" + # set global exit status, but never reset nonzero one. check_err() { @@ -34,7 +36,7 @@ cfg_veth() { ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24 ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad ip -netns "${PEER_NS}" link set dev veth1 up - ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp + ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp } run_one() { @@ -195,8 +197,8 @@ run_all() { return $ret } -if [ ! -f ../bpf/xdp_dummy.o ]; then - echo "Missing xdp_dummy helper. Build bpf selftest first" +if [ ! -f ${BPF_FILE} ]; then + echo "Missing ${BPF_FILE}. Build bpf selftest first" exit -1 fi diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh index 8a1109a545db..894972877e8b 100755 --- a/tools/testing/selftests/net/udpgro_bench.sh +++ b/tools/testing/selftests/net/udpgro_bench.sh @@ -5,6 +5,8 @@ readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" +BPF_FILE="../bpf/xdp_dummy.bpf.o" + cleanup() { local -r jobs="$(jobs -p)" local -r ns="$(ip netns list|grep $PEER_NS)" @@ -34,7 +36,7 @@ run_one() { ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad ip -netns "${PEER_NS}" link set dev veth1 up - ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp + ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r & @@ -80,8 +82,8 @@ run_all() { run_udp "${ipv6_args}" } -if [ ! -f ../bpf/xdp_dummy.o ]; then - echo "Missing xdp_dummy helper. Build bpf selftest first" +if [ ! -f ${BPF_FILE} ]; then + echo "Missing ${BPF_FILE}. Build bpf selftest first" exit -1 fi diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh index 7fe85ba51075..c9c4b9d65839 100755 --- a/tools/testing/selftests/net/udpgro_frglist.sh +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -5,6 +5,8 @@ readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" +BPF_FILE="../bpf/xdp_dummy.bpf.o" + cleanup() { local -r jobs="$(jobs -p)" local -r ns="$(ip netns list|grep $PEER_NS)" @@ -36,7 +38,7 @@ run_one() { ip netns exec "${PEER_NS}" ethtool -K veth1 rx-gro-list on - ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp + ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp tc -n "${PEER_NS}" qdisc add dev veth1 clsact tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file ../bpf/nat6to4.o section schedcls/ingress6/nat_6 direct-action tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file ../bpf/nat6to4.o section schedcls/egress4/snat4 direct-action @@ -81,8 +83,8 @@ run_all() { run_udp "${ipv6_args}" } -if [ ! -f ../bpf/xdp_dummy.o ]; then - echo "Missing xdp_dummy helper. Build bpf selftest first" +if [ ! -f ${BPF_FILE} ]; then + echo "Missing ${BPF_FILE}. Build bpf selftest first" exit -1 fi diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index 1bcd82e1f662..c079565add39 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +BPF_FILE="../bpf/xdp_dummy.bpf.o" readonly BASE="ns-$(mktemp -u XXXXXX)" readonly SRC=2 readonly DST=1 @@ -46,7 +47,7 @@ create_ns() { ip -n $BASE$ns addr add dev veth$ns $BM_NET_V4$ns/24 ip -n $BASE$ns addr add dev veth$ns $BM_NET_V6$ns/64 nodad done - ip -n $NS_DST link set veth$DST xdp object ../bpf/xdp_dummy.o section xdp 2>/dev/null + ip -n $NS_DST link set veth$DST xdp object ${BPF_FILE} section xdp 2>/dev/null } create_vxlan_endpoint() { diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh index 430895d1a2b6..2d073595c620 100755 --- a/tools/testing/selftests/net/veth.sh +++ b/tools/testing/selftests/net/veth.sh @@ -1,6 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 +BPF_FILE="../bpf/xdp_dummy.bpf.o" readonly STATS="$(mktemp -p /tmp ns-XXXXXX)" readonly BASE=`basename $STATS` readonly SRC=2 @@ -216,8 +217,8 @@ while getopts "hs:" option; do esac done -if [ ! -f ../bpf/xdp_dummy.o ]; then - echo "Missing xdp_dummy helper. Build bpf selftest first" +if [ ! -f ${BPF_FILE} ]; then + echo "Missing ${BPF_FILE}. Build bpf selftest first" exit 1 fi @@ -288,14 +289,14 @@ if [ $CPUS -gt 1 ]; then ip netns exec $NS_DST ethtool -L veth$DST rx 1 tx 2 2>/dev/null ip netns exec $NS_SRC ethtool -L veth$SRC rx 1 tx 2 2>/dev/null printf "%-60s" "bad setting: XDP with RX nr less than TX" - ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o \ + ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} \ section xdp 2>/dev/null &&\ echo "fail - set operation successful ?!?" || echo " ok " # the following tests will run with multiple channels active ip netns exec $NS_SRC ethtool -L veth$SRC rx 2 ip netns exec $NS_DST ethtool -L veth$DST rx 2 - ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o \ + ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} \ section xdp 2>/dev/null printf "%-60s" "bad setting: reducing RX nr below peer TX with XDP set" ip netns exec $NS_DST ethtool -L veth$DST rx 1 2>/dev/null &&\ @@ -311,7 +312,7 @@ if [ $CPUS -gt 2 ]; then chk_channels "setting invalid channels nr" $DST 2 2 fi -ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o section xdp 2>/dev/null +ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} section xdp 2>/dev/null chk_gro_flag "with xdp attached - gro flag" $DST on chk_gro_flag " - peer gro flag" $SRC off chk_tso_flag " - tso flag" $SRC off |