diff options
189 files changed, 2944 insertions, 1094 deletions
diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 7ca8df5451d4..68b21395a743 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -1458,11 +1458,22 @@ unprivileged_bpf_disabled ========================= Writing 1 to this entry will disable unprivileged calls to ``bpf()``; -once disabled, calling ``bpf()`` without ``CAP_SYS_ADMIN`` will return -``-EPERM``. +once disabled, calling ``bpf()`` without ``CAP_SYS_ADMIN`` or ``CAP_BPF`` +will return ``-EPERM``. Once set to 1, this can't be cleared from the +running kernel anymore. -Once set, this can't be cleared. +Writing 2 to this entry will also disable unprivileged calls to ``bpf()``, +however, an admin can still change this setting later on, if needed, by +writing 0 or 1 to this entry. +If ``BPF_UNPRIV_DEFAULT_OFF`` is enabled in the kernel config, then this +entry will default to 2 instead of 0. + += ============================================================= +0 Unprivileged calls to ``bpf()`` are enabled +1 Unprivileged calls to ``bpf()`` are disabled without recovery +2 Unprivileged calls to ``bpf()`` are disabled += ============================================================= watchdog ======== diff --git a/Documentation/devicetree/bindings/net/renesas,ether.yaml b/Documentation/devicetree/bindings/net/renesas,ether.yaml index 8ce5ed8a58dd..c101a1ec846e 100644 --- a/Documentation/devicetree/bindings/net/renesas,ether.yaml +++ b/Documentation/devicetree/bindings/net/renesas,ether.yaml @@ -10,7 +10,7 @@ allOf: - $ref: ethernet-controller.yaml# maintainers: - - Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> + - Sergei Shtylyov <sergei.shtylyov@gmail.com> properties: compatible: diff --git a/MAINTAINERS b/MAINTAINERS index 04babfa8fc76..8696ead91480 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4138,6 +4138,14 @@ S: Odd Fixes F: Documentation/devicetree/bindings/arm/cavium-thunder2.txt F: arch/arm64/boot/dts/cavium/thunder2-99xx* +CBS/ETF/TAPRIO QDISCS +M: Vinicius Costa Gomes <vinicius.gomes@intel.com> +S: Maintained +L: netdev@vger.kernel.org +F: net/sched/sch_cbs.c +F: net/sched/sch_etf.c +F: net/sched/sch_taprio.c + CC2520 IEEE-802.15.4 RADIO DRIVER M: Varka Bhadram <varkabhadram@gmail.com> L: linux-wpan@vger.kernel.org @@ -5569,7 +5577,6 @@ F: drivers/soc/fsl/dpio DPAA2 ETHERNET DRIVER M: Ioana Ciornei <ioana.ciornei@nxp.com> -M: Ioana Radulescu <ruxandra.radulescu@nxp.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/device_drivers/ethernet/freescale/dpaa2/ethernet-driver.rst @@ -12681,9 +12688,9 @@ F: drivers/rtc/rtc-ntxec.c F: include/linux/mfd/ntxec.h NETRONOME ETHERNET DRIVERS -M: Simon Horman <simon.horman@netronome.com> +M: Simon Horman <simon.horman@corigine.com> R: Jakub Kicinski <kuba@kernel.org> -L: oss-drivers@netronome.com +L: oss-drivers@corigine.com S: Maintained F: drivers/net/ethernet/netronome/ @@ -12710,7 +12717,6 @@ M: "David S. Miller" <davem@davemloft.net> M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org S: Maintained -W: http://www.linuxfoundation.org/en/Net Q: https://patchwork.kernel.org/project/netdevbpf/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git @@ -12755,7 +12761,6 @@ M: "David S. Miller" <davem@davemloft.net> M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org S: Maintained -W: http://www.linuxfoundation.org/en/Net Q: https://patchwork.kernel.org/project/netdevbpf/list/ B: mailto:netdev@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git @@ -12897,8 +12902,10 @@ F: include/uapi/linux/nexthop.h F: net/ipv4/nexthop.c NFC SUBSYSTEM +M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +L: linux-nfc@lists.01.org (moderated for non-subscribers) L: netdev@vger.kernel.org -S: Orphan +S: Maintained F: Documentation/devicetree/bindings/net/nfc/ F: drivers/nfc/ F: include/linux/platform_data/nfcmrvl.h @@ -13206,7 +13213,6 @@ F: Documentation/devicetree/bindings/sound/tfa9879.txt F: sound/soc/codecs/tfa9879* NXP-NCI NFC DRIVER -M: Clément Perrochaud <clement.perrochaud@effinnov.com> R: Charles Gorand <charles.gorand@effinnov.com> L: linux-nfc@lists.01.org (moderated for non-subscribers) S: Supported @@ -15945,6 +15951,7 @@ S390 IUCV NETWORK LAYER M: Julian Wiedmann <jwi@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> L: linux-s390@vger.kernel.org +L: netdev@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ F: drivers/s390/net/*iucv* @@ -15955,6 +15962,7 @@ S390 NETWORK DRIVERS M: Julian Wiedmann <jwi@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> L: linux-s390@vger.kernel.org +L: netdev@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ F: drivers/s390/net/ diff --git a/arch/arm64/Kbuild b/arch/arm64/Kbuild index d6465823b281..7b393cfec071 100644 --- a/arch/arm64/Kbuild +++ b/arch/arm64/Kbuild @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y += kernel/ mm/ -obj-$(CONFIG_NET) += net/ +obj-y += kernel/ mm/ net/ obj-$(CONFIG_KVM) += kvm/ obj-$(CONFIG_XEN) += xen/ obj-$(CONFIG_CRYPTO) += crypto/ diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 4388afeff251..9662cd39c7ff 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -743,10 +743,10 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev) ent->xlt = (1 << ent->order) * sizeof(struct mlx5_mtt) / MLX5_IB_UMR_OCTOWORD; ent->access_mode = MLX5_MKC_ACCESS_MODE_MTT; - if ((dev->mdev->profile->mask & MLX5_PROF_MASK_MR_CACHE) && + if ((dev->mdev->profile.mask & MLX5_PROF_MASK_MR_CACHE) && !dev->is_rep && mlx5_core_is_pf(dev->mdev) && mlx5_ib_can_load_pas_with_umr(dev, 0)) - ent->limit = dev->mdev->profile->mr_cache[i].limit; + ent->limit = dev->mdev->profile.mr_cache[i].limit; else ent->limit = 0; spin_lock_irq(&ent->lock); diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c index ee925b58bbce..2a1ddd47a096 100644 --- a/drivers/isdn/hardware/mISDN/netjet.c +++ b/drivers/isdn/hardware/mISDN/netjet.c @@ -1100,7 +1100,6 @@ nj_probe(struct pci_dev *pdev, const struct pci_device_id *ent) card->typ = NETJET_S_TJ300; card->base = pci_resource_start(pdev, 0); - card->irq = pdev->irq; pci_set_drvdata(pdev, card); err = setup_instance(card); if (err) diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c index ba8e70a8e312..6b12ce822e51 100644 --- a/drivers/net/appletalk/cops.c +++ b/drivers/net/appletalk/cops.c @@ -327,6 +327,8 @@ static int __init cops_probe1(struct net_device *dev, int ioaddr) break; } + dev->base_addr = ioaddr; + /* Reserve any actual interrupt. */ if (dev->irq) { retval = request_irq(dev->irq, cops_interrupt, 0, dev->name, dev); @@ -334,8 +336,6 @@ static int __init cops_probe1(struct net_device *dev, int ioaddr) goto err_out; } - dev->base_addr = ioaddr; - lp = netdev_priv(dev); spin_lock_init(&lp->lock); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 20bbda1b36e1..c5a646d06102 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1526,6 +1526,7 @@ static struct slave *bond_alloc_slave(struct bonding *bond, slave->bond = bond; slave->dev = slave_dev; + INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work); if (bond_kobj_init(slave)) return NULL; @@ -1538,7 +1539,6 @@ static struct slave *bond_alloc_slave(struct bonding *bond, return NULL; } } - INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work); return slave; } diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 9150038b60cb..3b018fcf4412 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -821,11 +821,9 @@ static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port, bcm_sf2_sw_mac_link_set(ds, port, interface, true); if (port != core_readl(priv, CORE_IMP0_PRT_ID)) { - u32 reg_rgmii_ctrl; + u32 reg_rgmii_ctrl = 0; u32 reg, offset; - reg_rgmii_ctrl = bcm_sf2_reg_rgmii_cntrl(priv, port); - if (priv->type == BCM4908_DEVICE_ID || priv->type == BCM7445_DEVICE_ID) offset = CORE_STS_OVERRIDE_GMIIP_PORT(port); @@ -836,6 +834,7 @@ static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port, interface == PHY_INTERFACE_MODE_RGMII_TXID || interface == PHY_INTERFACE_MODE_MII || interface == PHY_INTERFACE_MODE_REVMII) { + reg_rgmii_ctrl = bcm_sf2_reg_rgmii_cntrl(priv, port); reg = reg_readl(priv, reg_rgmii_ctrl); reg &= ~(RX_PAUSE_EN | TX_PAUSE_EN); diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 55e5d479acce..854e25f43fa7 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -1530,6 +1530,7 @@ static const struct ksz_chip_data ksz9477_switch_chips[] = { .num_statics = 16, .cpu_ports = 0x7F, /* can be configured as cpu port */ .port_cnt = 7, /* total physical port count */ + .phy_errata_9477 = true, }, }; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 96f7c9eede35..9b90f3d3a8f5 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1262,14 +1262,6 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port) { struct mt7530_priv *priv = ds->priv; - /* The real fabric path would be decided on the membership in the - * entry of VLAN table. PCR_MATRIX set up here with ALL_MEMBERS - * means potential VLAN can be consisting of certain subset of all - * ports. - */ - mt7530_rmw(priv, MT7530_PCR_P(port), - PCR_MATRIX_MASK, PCR_MATRIX(MT7530_ALL_MEMBERS)); - /* Trapped into security mode allows packet forwarding through VLAN * table lookup. CPU port is set to fallback mode to let untagged * frames pass through. diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 2473bebe48e6..f966a253d1c7 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1227,12 +1227,17 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port, if (taprio->num_entries > VSC9959_TAS_GCL_ENTRY_MAX) return -ERANGE; - /* Set port num and disable ALWAYS_GUARD_BAND_SCH_Q, which means set - * guard band to be implemented for nonschedule queues to schedule - * queues transition. + /* Enable guard band. The switch will schedule frames without taking + * their length into account. Thus we'll always need to enable the + * guard band which reserves the time of a maximum sized frame at the + * end of the time window. + * + * Although the ALWAYS_GUARD_BAND_SCH_Q bit is global for all ports, we + * need to set PORT_NUM, because subsequent writes to PARAM_CFG_REG_n + * operate on the port number. */ - ocelot_rmw(ocelot, - QSYS_TAS_PARAM_CFG_CTRL_PORT_NUM(port), + ocelot_rmw(ocelot, QSYS_TAS_PARAM_CFG_CTRL_PORT_NUM(port) | + QSYS_TAS_PARAM_CFG_CTRL_ALWAYS_GUARD_BAND_SCH_Q, QSYS_TAS_PARAM_CFG_CTRL_PORT_NUM_M | QSYS_TAS_PARAM_CFG_CTRL_ALWAYS_GUARD_BAND_SCH_Q, QSYS_TAS_PARAM_CFG_CTRL); diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c index b777d3f37573..12cd04b56803 100644 --- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c +++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c @@ -167,9 +167,10 @@ enum sja1105_hostcmd { SJA1105_HOSTCMD_INVALIDATE = 4, }; +/* Command and entry overlap */ static void -sja1105_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, - enum packing_op op) +sja1105et_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) { const int size = SJA1105_SIZE_DYN_CMD; @@ -179,6 +180,20 @@ sja1105_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, sja1105_packing(buf, &cmd->index, 9, 0, size, op); } +/* Command and entry are separate */ +static void +sja1105pqrs_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105_SIZE_VL_LOOKUP_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->errors, 30, 30, size, op); + sja1105_packing(p, &cmd->rdwrset, 29, 29, size, op); + sja1105_packing(p, &cmd->index, 9, 0, size, op); +} + static size_t sja1105et_vl_lookup_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -641,7 +656,7 @@ static size_t sja1105pqrs_cbs_entry_packing(void *buf, void *entry_ptr, const struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = { [BLK_IDX_VL_LOOKUP] = { .entry_packing = sja1105et_vl_lookup_entry_packing, - .cmd_packing = sja1105_vl_lookup_cmd_packing, + .cmd_packing = sja1105et_vl_lookup_cmd_packing, .access = OP_WRITE, .max_entry_count = SJA1105_MAX_VL_LOOKUP_COUNT, .packed_size = SJA1105ET_SIZE_VL_LOOKUP_DYN_CMD, @@ -725,7 +740,7 @@ const struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = { const struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN] = { [BLK_IDX_VL_LOOKUP] = { .entry_packing = sja1105_vl_lookup_entry_packing, - .cmd_packing = sja1105_vl_lookup_cmd_packing, + .cmd_packing = sja1105pqrs_vl_lookup_cmd_packing, .access = (OP_READ | OP_WRITE), .max_entry_count = SJA1105_MAX_VL_LOOKUP_COUNT, .packed_size = SJA1105PQRS_SIZE_VL_LOOKUP_DYN_CMD, diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 405024b637d6..b88d9ef45a1f 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -26,6 +26,7 @@ #include "sja1105_tas.h" #define SJA1105_UNKNOWN_MULTICAST 0x010000000000ull +#define SJA1105_DEFAULT_VLAN (VLAN_N_VID - 1) static const struct dsa_switch_ops sja1105_switch_ops; @@ -207,6 +208,7 @@ static int sja1105_init_mii_settings(struct sja1105_private *priv, default: dev_err(dev, "Unsupported PHY mode %s!\n", phy_modes(ports[i].phy_mode)); + return -EINVAL; } /* Even though the SerDes port is able to drive SGMII autoneg @@ -321,6 +323,13 @@ static int sja1105_init_l2_lookup_params(struct sja1105_private *priv) return 0; } +/* Set up a default VLAN for untagged traffic injected from the CPU + * using management routes (e.g. STP, PTP) as opposed to tag_8021q. + * All DT-defined ports are members of this VLAN, and there are no + * restrictions on forwarding (since the CPU selects the destination). + * Frames from this VLAN will always be transmitted as untagged, and + * neither the bridge nor the 8021q module cannot create this VLAN ID. + */ static int sja1105_init_static_vlan(struct sja1105_private *priv) { struct sja1105_table *table; @@ -330,17 +339,13 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) .vmemb_port = 0, .vlan_bc = 0, .tag_port = 0, - .vlanid = 1, + .vlanid = SJA1105_DEFAULT_VLAN, }; struct dsa_switch *ds = priv->ds; int port; table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP]; - /* The static VLAN table will only contain the initial pvid of 1. - * All other VLANs are to be configured through dynamic entries, - * and kept in the static configuration table as backing memory. - */ if (table->entry_count) { kfree(table->entries); table->entry_count = 0; @@ -353,9 +358,6 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) table->entry_count = 1; - /* VLAN 1: all DT-defined ports are members; no restrictions on - * forwarding; always transmit as untagged. - */ for (port = 0; port < ds->num_ports; port++) { struct sja1105_bridge_vlan *v; @@ -366,15 +368,12 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) pvid.vlan_bc |= BIT(port); pvid.tag_port &= ~BIT(port); - /* Let traffic that don't need dsa_8021q (e.g. STP, PTP) be - * transmitted as untagged. - */ v = kzalloc(sizeof(*v), GFP_KERNEL); if (!v) return -ENOMEM; v->port = port; - v->vid = 1; + v->vid = SJA1105_DEFAULT_VLAN; v->untagged = true; if (dsa_is_cpu_port(ds, port)) v->pvid = true; @@ -2817,11 +2816,22 @@ static int sja1105_vlan_add_one(struct dsa_switch *ds, int port, u16 vid, bool pvid = flags & BRIDGE_VLAN_INFO_PVID; struct sja1105_bridge_vlan *v; - list_for_each_entry(v, vlan_list, list) - if (v->port == port && v->vid == vid && - v->untagged == untagged && v->pvid == pvid) + list_for_each_entry(v, vlan_list, list) { + if (v->port == port && v->vid == vid) { /* Already added */ - return 0; + if (v->untagged == untagged && v->pvid == pvid) + /* Nothing changed */ + return 0; + + /* It's the same VLAN, but some of the flags changed + * and the user did not bother to delete it first. + * Update it and trigger sja1105_build_vlan_table. + */ + v->untagged = untagged; + v->pvid = pvid; + return 1; + } + } v = kzalloc(sizeof(*v), GFP_KERNEL); if (!v) { @@ -2976,13 +2986,13 @@ static int sja1105_setup(struct dsa_switch *ds) rc = sja1105_static_config_load(priv, ports); if (rc < 0) { dev_err(ds->dev, "Failed to load static config: %d\n", rc); - return rc; + goto out_ptp_clock_unregister; } /* Configure the CGU (PHY link modes and speeds) */ rc = sja1105_clocking_setup(priv); if (rc < 0) { dev_err(ds->dev, "Failed to configure MII clocking: %d\n", rc); - return rc; + goto out_static_config_free; } /* On SJA1105, VLAN filtering per se is always enabled in hardware. * The only thing we can do to disable it is lie about what the 802.1Q @@ -3003,7 +3013,7 @@ static int sja1105_setup(struct dsa_switch *ds) rc = sja1105_devlink_setup(ds); if (rc < 0) - return rc; + goto out_static_config_free; /* The DSA/switchdev model brings up switch ports in standalone mode by * default, and that means vlan_filtering is 0 since they're not under @@ -3012,6 +3022,17 @@ static int sja1105_setup(struct dsa_switch *ds) rtnl_lock(); rc = sja1105_setup_8021q_tagging(ds, true); rtnl_unlock(); + if (rc) + goto out_devlink_teardown; + + return 0; + +out_devlink_teardown: + sja1105_devlink_teardown(ds); +out_ptp_clock_unregister: + sja1105_ptp_clock_unregister(ds); +out_static_config_free: + sja1105_static_config_free(&priv->static_config); return rc; } @@ -3646,8 +3667,10 @@ static int sja1105_probe(struct spi_device *spi) priv->cbs = devm_kcalloc(dev, priv->info->num_cbs_shapers, sizeof(struct sja1105_cbs_entry), GFP_KERNEL); - if (!priv->cbs) - return -ENOMEM; + if (!priv->cbs) { + rc = -ENOMEM; + goto out_unregister_switch; + } } /* Connections between dsa_port and sja1105_port */ @@ -3672,7 +3695,7 @@ static int sja1105_probe(struct spi_device *spi) dev_err(ds->dev, "failed to create deferred xmit thread: %d\n", rc); - goto out; + goto out_destroy_workers; } skb_queue_head_init(&sp->xmit_queue); sp->xmit_tpid = ETH_P_SJA1105; @@ -3682,7 +3705,8 @@ static int sja1105_probe(struct spi_device *spi) } return 0; -out: + +out_destroy_workers: while (port-- > 0) { struct sja1105_port *sp = &priv->ports[port]; @@ -3691,6 +3715,10 @@ out: kthread_destroy_worker(sp->xmit_worker); } + +out_unregister_switch: + dsa_unregister_switch(ds); + return rc; } diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index c0986096c701..5bace8a93d73 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -8247,9 +8247,9 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev) BNX2_WR(bp, PCI_COMMAND, reg); } else if ((BNX2_CHIP_ID(bp) == BNX2_CHIP_ID_5706_A1) && !(bp->flags & BNX2_FLAG_PCIX)) { - dev_err(&pdev->dev, "5706 A1 can only be used in a PCIX bus, aborting\n"); + rc = -EPERM; goto err_out_unmap; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index d21f085044cd..27943b0446c2 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1223,8 +1223,10 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param, goto failed; /* SR-IOV capability was enabled but there are no VFs*/ - if (iov->total == 0) + if (iov->total == 0) { + err = -EINVAL; goto failed; + } iov->nr_virtfn = min_t(u16, iov->total, num_vfs_param); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 2985844634c8..fcc729d52b17 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -282,7 +282,8 @@ static bool bnxt_vf_pciid(enum board_idx idx) { return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF || idx == NETXTREME_S_VF || idx == NETXTREME_C_VF_HV || - idx == NETXTREME_E_VF_HV || idx == NETXTREME_E_P5_VF); + idx == NETXTREME_E_VF_HV || idx == NETXTREME_E_P5_VF || + idx == NETXTREME_E_P5_VF_HV); } #define DB_CP_REARM_FLAGS (DB_KEY_CP | DB_IDX_VALID) @@ -6932,17 +6933,10 @@ ctx_err: static void bnxt_hwrm_set_pg_attr(struct bnxt_ring_mem_info *rmem, u8 *pg_attr, __le64 *pg_dir) { - u8 pg_size = 0; - if (!rmem->nr_pages) return; - if (BNXT_PAGE_SHIFT == 13) - pg_size = 1 << 4; - else if (BNXT_PAGE_SIZE == 16) - pg_size = 2 << 4; - - *pg_attr = pg_size; + BNXT_SET_CTX_PAGE_ATTR(*pg_attr); if (rmem->depth >= 1) { if (rmem->depth == 2) *pg_attr |= 2; @@ -10785,37 +10779,125 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) return rc; } +static bool bnxt_exthdr_check(struct bnxt *bp, struct sk_buff *skb, int nw_off, + u8 **nextp) +{ + struct ipv6hdr *ip6h = (struct ipv6hdr *)(skb->data + nw_off); + int hdr_count = 0; + u8 *nexthdr; + int start; + + /* Check that there are at most 2 IPv6 extension headers, no + * fragment header, and each is <= 64 bytes. + */ + start = nw_off + sizeof(*ip6h); + nexthdr = &ip6h->nexthdr; + while (ipv6_ext_hdr(*nexthdr)) { + struct ipv6_opt_hdr *hp; + int hdrlen; + + if (hdr_count >= 3 || *nexthdr == NEXTHDR_NONE || + *nexthdr == NEXTHDR_FRAGMENT) + return false; + hp = __skb_header_pointer(NULL, start, sizeof(*hp), skb->data, + skb_headlen(skb), NULL); + if (!hp) + return false; + if (*nexthdr == NEXTHDR_AUTH) + hdrlen = ipv6_authlen(hp); + else + hdrlen = ipv6_optlen(hp); + + if (hdrlen > 64) + return false; + nexthdr = &hp->nexthdr; + start += hdrlen; + hdr_count++; + } + if (nextp) { + /* Caller will check inner protocol */ + if (skb->encapsulation) { + *nextp = nexthdr; + return true; + } + *nextp = NULL; + } + /* Only support TCP/UDP for non-tunneled ipv6 and inner ipv6 */ + return *nexthdr == IPPROTO_TCP || *nexthdr == IPPROTO_UDP; +} + +/* For UDP, we can only handle 1 Vxlan port and 1 Geneve port. */ +static bool bnxt_udp_tunl_check(struct bnxt *bp, struct sk_buff *skb) +{ + struct udphdr *uh = udp_hdr(skb); + __be16 udp_port = uh->dest; + + if (udp_port != bp->vxlan_port && udp_port != bp->nge_port) + return false; + if (skb->inner_protocol_type == ENCAP_TYPE_ETHER) { + struct ethhdr *eh = inner_eth_hdr(skb); + + switch (eh->h_proto) { + case htons(ETH_P_IP): + return true; + case htons(ETH_P_IPV6): + return bnxt_exthdr_check(bp, skb, + skb_inner_network_offset(skb), + NULL); + } + } + return false; +} + +static bool bnxt_tunl_check(struct bnxt *bp, struct sk_buff *skb, u8 l4_proto) +{ + switch (l4_proto) { + case IPPROTO_UDP: + return bnxt_udp_tunl_check(bp, skb); + case IPPROTO_IPIP: + return true; + case IPPROTO_GRE: { + switch (skb->inner_protocol) { + default: + return false; + case htons(ETH_P_IP): + return true; + case htons(ETH_P_IPV6): + fallthrough; + } + } + case IPPROTO_IPV6: + /* Check ext headers of inner ipv6 */ + return bnxt_exthdr_check(bp, skb, skb_inner_network_offset(skb), + NULL); + } + return false; +} + static netdev_features_t bnxt_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { - struct bnxt *bp; - __be16 udp_port; - u8 l4_proto = 0; + struct bnxt *bp = netdev_priv(dev); + u8 *l4_proto; features = vlan_features_check(skb, features); - if (!skb->encapsulation) - return features; - switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): - l4_proto = ip_hdr(skb)->protocol; + if (!skb->encapsulation) + return features; + l4_proto = &ip_hdr(skb)->protocol; + if (bnxt_tunl_check(bp, skb, *l4_proto)) + return features; break; case htons(ETH_P_IPV6): - l4_proto = ipv6_hdr(skb)->nexthdr; + if (!bnxt_exthdr_check(bp, skb, skb_network_offset(skb), + &l4_proto)) + break; + if (!l4_proto || bnxt_tunl_check(bp, skb, *l4_proto)) + return features; break; - default: - return features; } - - if (l4_proto != IPPROTO_UDP) - return features; - - bp = netdev_priv(dev); - /* For UDP, we can only handle 1 Vxlan port and 1 Geneve port. */ - udp_port = udp_hdr(skb)->dest; - if (udp_port == bp->vxlan_port || udp_port == bp->nge_port) - return features; return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 98e0cef4532c..30e47ea343f9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1457,6 +1457,16 @@ struct bnxt_ctx_pg_info { #define BNXT_BACKING_STORE_CFG_LEGACY_LEN 256 +#define BNXT_SET_CTX_PAGE_ATTR(attr) \ +do { \ + if (BNXT_PAGE_SIZE == 0x2000) \ + attr = FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8K; \ + else if (BNXT_PAGE_SIZE == 0x10000) \ + attr = FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_64K; \ + else \ + attr = FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_4K; \ +} while (0) + struct bnxt_ctx_mem_info { u32 qp_max_entries; u16 qp_min_qp1_entries; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 6bc7d41d519b..a0c7b1167dbb 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -2867,6 +2867,9 @@ static struct net_device_stats *gem_get_stats(struct macb *bp) struct gem_stats *hwstat = &bp->hw_stats.gem; struct net_device_stats *nstat = &bp->dev->stats; + if (!netif_running(bp->dev)) + return nstat; + gem_update_stats(bp); nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors + diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index bc581b149b11..22c9ac922eba 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -1042,7 +1042,7 @@ void clear_all_filters(struct adapter *adapter) cxgb4_del_filter(dev, f->tid, &f->fs); } - sb = t4_read_reg(adapter, LE_DB_SRVR_START_INDEX_A); + sb = adapter->tids.stid_base; for (i = 0; i < sb; i++) { f = (struct filter_entry *)adapter->tids.tid_tab[i]; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 6264bc66a4fc..421bd9b88028 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -6480,9 +6480,9 @@ static void cxgb4_ktls_dev_del(struct net_device *netdev, adap->uld[CXGB4_ULD_KTLS].tlsdev_ops->tls_dev_del(netdev, tls_ctx, direction); - cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE); out_unlock: + cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE); mutex_unlock(&uld_mutex); } diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c index ef3f1e92632f..59683f79959c 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c @@ -59,6 +59,7 @@ static int chcr_get_nfrags_to_send(struct sk_buff *skb, u32 start, u32 len) } static int chcr_init_tcb_fields(struct chcr_ktls_info *tx_info); +static void clear_conn_resources(struct chcr_ktls_info *tx_info); /* * chcr_ktls_save_keys: calculate and save crypto keys. * @tx_info - driver specific tls info. @@ -364,10 +365,14 @@ static void chcr_ktls_dev_del(struct net_device *netdev, chcr_get_ktls_tx_context(tls_ctx); struct chcr_ktls_info *tx_info = tx_ctx->chcr_info; struct ch_ktls_port_stats_debug *port_stats; + struct chcr_ktls_uld_ctx *u_ctx; if (!tx_info) return; + u_ctx = tx_info->adap->uld[CXGB4_ULD_KTLS].handle; + if (u_ctx && u_ctx->detach) + return; /* clear l2t entry */ if (tx_info->l2te) cxgb4_l2t_release(tx_info->l2te); @@ -384,6 +389,8 @@ static void chcr_ktls_dev_del(struct net_device *netdev, if (tx_info->tid != -1) { cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan, tx_info->tid, tx_info->ip_family); + + xa_erase(&u_ctx->tid_list, tx_info->tid); } port_stats = &tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id]; @@ -411,6 +418,7 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk, struct tls_context *tls_ctx = tls_get_ctx(sk); struct ch_ktls_port_stats_debug *port_stats; struct chcr_ktls_ofld_ctx_tx *tx_ctx; + struct chcr_ktls_uld_ctx *u_ctx; struct chcr_ktls_info *tx_info; struct dst_entry *dst; struct adapter *adap; @@ -425,6 +433,7 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk, adap = pi->adapter; port_stats = &adap->ch_ktls_stats.ktls_port[pi->port_id]; atomic64_inc(&port_stats->ktls_tx_connection_open); + u_ctx = adap->uld[CXGB4_ULD_KTLS].handle; if (direction == TLS_OFFLOAD_CTX_DIR_RX) { pr_err("not expecting for RX direction\n"); @@ -434,6 +443,9 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk, if (tx_ctx->chcr_info) goto out; + if (u_ctx && u_ctx->detach) + goto out; + tx_info = kvzalloc(sizeof(*tx_info), GFP_KERNEL); if (!tx_info) goto out; @@ -569,6 +581,8 @@ free_tid: cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan, tx_info->tid, tx_info->ip_family); + xa_erase(&u_ctx->tid_list, tx_info->tid); + put_module: /* release module refcount */ module_put(THIS_MODULE); @@ -633,8 +647,12 @@ static int chcr_ktls_cpl_act_open_rpl(struct adapter *adap, { const struct cpl_act_open_rpl *p = (void *)input; struct chcr_ktls_info *tx_info = NULL; + struct chcr_ktls_ofld_ctx_tx *tx_ctx; + struct chcr_ktls_uld_ctx *u_ctx; unsigned int atid, tid, status; + struct tls_context *tls_ctx; struct tid_info *t; + int ret = 0; tid = GET_TID(p); status = AOPEN_STATUS_G(ntohl(p->atid_status)); @@ -666,14 +684,29 @@ static int chcr_ktls_cpl_act_open_rpl(struct adapter *adap, if (!status) { tx_info->tid = tid; cxgb4_insert_tid(t, tx_info, tx_info->tid, tx_info->ip_family); + /* Adding tid */ + tls_ctx = tls_get_ctx(tx_info->sk); + tx_ctx = chcr_get_ktls_tx_context(tls_ctx); + u_ctx = adap->uld[CXGB4_ULD_KTLS].handle; + if (u_ctx) { + ret = xa_insert_bh(&u_ctx->tid_list, tid, tx_ctx, + GFP_NOWAIT); + if (ret < 0) { + pr_err("%s: Failed to allocate tid XA entry = %d\n", + __func__, tx_info->tid); + tx_info->open_state = CH_KTLS_OPEN_FAILURE; + goto out; + } + } tx_info->open_state = CH_KTLS_OPEN_SUCCESS; } else { tx_info->open_state = CH_KTLS_OPEN_FAILURE; } +out: spin_unlock(&tx_info->lock); complete(&tx_info->completion); - return 0; + return ret; } /* @@ -2090,6 +2123,8 @@ static void *chcr_ktls_uld_add(const struct cxgb4_lld_info *lldi) goto out; } u_ctx->lldi = *lldi; + u_ctx->detach = false; + xa_init_flags(&u_ctx->tid_list, XA_FLAGS_LOCK_BH); out: return u_ctx; } @@ -2123,6 +2158,45 @@ static int chcr_ktls_uld_rx_handler(void *handle, const __be64 *rsp, return 0; } +static void clear_conn_resources(struct chcr_ktls_info *tx_info) +{ + /* clear l2t entry */ + if (tx_info->l2te) + cxgb4_l2t_release(tx_info->l2te); + +#if IS_ENABLED(CONFIG_IPV6) + /* clear clip entry */ + if (tx_info->ip_family == AF_INET6) + cxgb4_clip_release(tx_info->netdev, (const u32 *) + &tx_info->sk->sk_v6_rcv_saddr, + 1); +#endif + + /* clear tid */ + if (tx_info->tid != -1) + cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan, + tx_info->tid, tx_info->ip_family); +} + +static void ch_ktls_reset_all_conn(struct chcr_ktls_uld_ctx *u_ctx) +{ + struct ch_ktls_port_stats_debug *port_stats; + struct chcr_ktls_ofld_ctx_tx *tx_ctx; + struct chcr_ktls_info *tx_info; + unsigned long index; + + xa_for_each(&u_ctx->tid_list, index, tx_ctx) { + tx_info = tx_ctx->chcr_info; + clear_conn_resources(tx_info); + port_stats = &tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id]; + atomic64_inc(&port_stats->ktls_tx_connection_close); + kvfree(tx_info); + tx_ctx->chcr_info = NULL; + /* release module refcount */ + module_put(THIS_MODULE); + } +} + static int chcr_ktls_uld_state_change(void *handle, enum cxgb4_state new_state) { struct chcr_ktls_uld_ctx *u_ctx = handle; @@ -2139,7 +2213,10 @@ static int chcr_ktls_uld_state_change(void *handle, enum cxgb4_state new_state) case CXGB4_STATE_DETACH: pr_info("%s: Down\n", pci_name(u_ctx->lldi.pdev)); mutex_lock(&dev_mutex); + u_ctx->detach = true; list_del(&u_ctx->entry); + ch_ktls_reset_all_conn(u_ctx); + xa_destroy(&u_ctx->tid_list); mutex_unlock(&dev_mutex); break; default: @@ -2178,6 +2255,7 @@ static void __exit chcr_ktls_exit(void) adap = pci_get_drvdata(u_ctx->lldi.pdev); memset(&adap->ch_ktls_stats, 0, sizeof(adap->ch_ktls_stats)); list_del(&u_ctx->entry); + xa_destroy(&u_ctx->tid_list); kfree(u_ctx); } mutex_unlock(&dev_mutex); diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h index 18b3b1f02415..10572dc55365 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h @@ -75,6 +75,8 @@ struct chcr_ktls_ofld_ctx_tx { struct chcr_ktls_uld_ctx { struct list_head entry; struct cxgb4_lld_info lldi; + struct xarray tid_list; + bool detach; }; static inline struct chcr_ktls_ofld_ctx_tx * diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c index 188d871f6b8c..c320cc8ca68d 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c @@ -1564,8 +1564,10 @@ found_ok_skb: cerr = put_cmsg(msg, SOL_TLS, TLS_GET_RECORD_TYPE, sizeof(thdr->type), &thdr->type); - if (cerr && thdr->type != TLS_RECORD_TYPE_DATA) - return -EIO; + if (cerr && thdr->type != TLS_RECORD_TYPE_DATA) { + copied = -EIO; + break; + } /* don't send tls header, skip copy */ goto skip_copy; } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index f2065f9d02e6..ad82cffc6f3f 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1662,7 +1662,7 @@ static int fec_enet_rx_napi(struct napi_struct *napi, int budget) } /* ------------------------------------------------------------------------- */ -static void fec_get_mac(struct net_device *ndev) +static int fec_get_mac(struct net_device *ndev) { struct fec_enet_private *fep = netdev_priv(ndev); unsigned char *iap, tmpaddr[ETH_ALEN]; @@ -1685,6 +1685,8 @@ static void fec_get_mac(struct net_device *ndev) ret = of_get_mac_address(np, tmpaddr); if (!ret) iap = tmpaddr; + else if (ret == -EPROBE_DEFER) + return ret; } } @@ -1723,7 +1725,7 @@ static void fec_get_mac(struct net_device *ndev) eth_hw_addr_random(ndev); dev_info(&fep->pdev->dev, "Using random MAC address: %pM\n", ndev->dev_addr); - return; + return 0; } memcpy(ndev->dev_addr, iap, ETH_ALEN); @@ -1731,6 +1733,8 @@ static void fec_get_mac(struct net_device *ndev) /* Adjust MAC if using macaddr */ if (iap == macaddr) ndev->dev_addr[ETH_ALEN-1] = macaddr[ETH_ALEN-1] + fep->dev_id; + + return 0; } /* ------------------------------------------------------------------------- */ @@ -3290,7 +3294,9 @@ static int fec_enet_init(struct net_device *ndev) return ret; } - fec_enet_alloc_queue(ndev); + ret = fec_enet_alloc_queue(ndev); + if (ret) + return ret; bd_size = (fep->total_tx_ring_size + fep->total_rx_ring_size) * dsize; @@ -3298,11 +3304,15 @@ static int fec_enet_init(struct net_device *ndev) cbd_base = dmam_alloc_coherent(&fep->pdev->dev, bd_size, &bd_dma, GFP_KERNEL); if (!cbd_base) { - return -ENOMEM; + ret = -ENOMEM; + goto free_queue_mem; } /* Get the Ethernet address */ - fec_get_mac(ndev); + ret = fec_get_mac(ndev); + if (ret) + goto free_queue_mem; + /* make sure MAC we just acquired is programmed into the hw */ fec_set_mac_address(ndev, NULL); @@ -3376,6 +3386,10 @@ static int fec_enet_init(struct net_device *ndev) fec_enet_update_ethtool_stats(ndev); return 0; + +free_queue_mem: + fec_enet_free_queue(ndev); + return ret; } #ifdef CONFIG_OF diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 7302498c6df3..bbc423e93122 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -180,7 +180,7 @@ static int gve_napi_poll(struct napi_struct *napi, int budget) /* Double check we have no extra work. * Ensure unmask synchronizes with checking for work. */ - dma_rmb(); + mb(); if (block->tx) reschedule |= gve_tx_poll(block, -1); if (block->rx) @@ -220,6 +220,7 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv) int vecs_left = new_num_ntfy_blks % 2; priv->num_ntfy_blks = new_num_ntfy_blks; + priv->mgmt_msix_idx = priv->num_ntfy_blks; priv->tx_cfg.max_queues = min_t(int, priv->tx_cfg.max_queues, vecs_per_type); priv->rx_cfg.max_queues = min_t(int, priv->rx_cfg.max_queues, @@ -300,20 +301,22 @@ static void gve_free_notify_blocks(struct gve_priv *priv) { int i; - /* Free the irqs */ - for (i = 0; i < priv->num_ntfy_blks; i++) { - struct gve_notify_block *block = &priv->ntfy_blocks[i]; - int msix_idx = i; + if (priv->msix_vectors) { + /* Free the irqs */ + for (i = 0; i < priv->num_ntfy_blks; i++) { + struct gve_notify_block *block = &priv->ntfy_blocks[i]; + int msix_idx = i; - irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector, - NULL); - free_irq(priv->msix_vectors[msix_idx].vector, block); + irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector, + NULL); + free_irq(priv->msix_vectors[msix_idx].vector, block); + } + free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv); } dma_free_coherent(&priv->pdev->dev, priv->num_ntfy_blks * sizeof(*priv->ntfy_blocks), priv->ntfy_blocks, priv->ntfy_block_bus); priv->ntfy_blocks = NULL; - free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv); pci_disable_msix(priv->pdev); kvfree(priv->msix_vectors); priv->msix_vectors = NULL; diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 6938f3a939d6..3e04a3973d68 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -212,10 +212,11 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) tx->dev = &priv->pdev->dev; if (!tx->raw_addressing) { tx->tx_fifo.qpl = gve_assign_tx_qpl(priv); - + if (!tx->tx_fifo.qpl) + goto abort_with_desc; /* map Tx FIFO */ if (gve_tx_fifo_init(priv, &tx->tx_fifo)) - goto abort_with_desc; + goto abort_with_qpl; } tx->q_resources = @@ -236,6 +237,9 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) abort_with_fifo: if (!tx->raw_addressing) gve_tx_fifo_release(priv, &tx->tx_fifo); +abort_with_qpl: + if (!tx->raw_addressing) + gve_unassign_qpl(priv, tx->tx_fifo.qpl->id); abort_with_desc: dma_free_coherent(hdev, bytes, tx->desc, tx->bus); tx->desc = NULL; @@ -589,7 +593,7 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev) struct gve_tx_ring *tx; int nsegs; - WARN(skb_get_queue_mapping(skb) > priv->tx_cfg.num_queues, + WARN(skb_get_queue_mapping(skb) >= priv->tx_cfg.num_queues, "skb queue index out of range"); tx = &priv->tx[skb_get_queue_mapping(skb)]; if (unlikely(gve_maybe_stop_tx(tx, skb))) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index da48c05435ea..7e62dcff2426 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -192,7 +192,7 @@ static int hns_nic_get_link_ksettings(struct net_device *net_dev, } /** - *hns_nic_set_link_settings - implement ethtool set link ksettings + *hns_nic_set_link_ksettings - implement ethtool set link ksettings *@net_dev: net_device *@cmd: ethtool_link_ksettings *retuen 0 - success , negative --fail @@ -827,7 +827,7 @@ hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch) } /** - * get_ethtool_stats - get detail statistics. + * hns_get_ethtool_stats - get detail statistics. * @netdev: net device * @stats: statistics info. * @data: statistics data. @@ -885,7 +885,7 @@ static void hns_get_ethtool_stats(struct net_device *netdev, } /** - * get_strings: Return a set of strings that describe the requested objects + * hns_get_strings: Return a set of strings that describe the requested objects * @netdev: net device * @stringset: string set ID. * @data: objects data. diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 783fdaf8f8d6..026558f8e04b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -264,22 +264,17 @@ static void hns3_vector_coalesce_init(struct hns3_enet_tqp_vector *tqp_vector, struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev); struct hns3_enet_coalesce *tx_coal = &tqp_vector->tx_group.coal; struct hns3_enet_coalesce *rx_coal = &tqp_vector->rx_group.coal; + struct hns3_enet_coalesce *ptx_coal = &priv->tx_coal; + struct hns3_enet_coalesce *prx_coal = &priv->rx_coal; - /* initialize the configuration for interrupt coalescing. - * 1. GL (Interrupt Gap Limiter) - * 2. RL (Interrupt Rate Limiter) - * 3. QL (Interrupt Quantity Limiter) - * - * Default: enable interrupt coalescing self-adaptive and GL - */ - tx_coal->adapt_enable = 1; - rx_coal->adapt_enable = 1; + tx_coal->adapt_enable = ptx_coal->adapt_enable; + rx_coal->adapt_enable = prx_coal->adapt_enable; - tx_coal->int_gl = HNS3_INT_GL_50K; - rx_coal->int_gl = HNS3_INT_GL_50K; + tx_coal->int_gl = ptx_coal->int_gl; + rx_coal->int_gl = prx_coal->int_gl; - rx_coal->flow_level = HNS3_FLOW_LOW; - tx_coal->flow_level = HNS3_FLOW_LOW; + rx_coal->flow_level = prx_coal->flow_level; + tx_coal->flow_level = ptx_coal->flow_level; /* device version above V3(include V3), GL can configure 1us * unit, so uses 1us unit. @@ -294,8 +289,8 @@ static void hns3_vector_coalesce_init(struct hns3_enet_tqp_vector *tqp_vector, rx_coal->ql_enable = 1; tx_coal->int_ql_max = ae_dev->dev_specs.int_ql_max; rx_coal->int_ql_max = ae_dev->dev_specs.int_ql_max; - tx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG; - rx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG; + tx_coal->int_ql = ptx_coal->int_ql; + rx_coal->int_ql = prx_coal->int_ql; } } @@ -846,8 +841,6 @@ static bool hns3_tunnel_csum_bug(struct sk_buff *skb) l4.udp->dest == htons(4790)))) return false; - skb_checksum_help(skb); - return true; } @@ -924,8 +917,7 @@ static int hns3_set_l2l3l4(struct sk_buff *skb, u8 ol4_proto, /* the stack computes the IP header already, * driver calculate l4 checksum when not TSO. */ - skb_checksum_help(skb); - return 0; + return skb_checksum_help(skb); } hns3_set_outer_l2l3l4(skb, ol4_proto, ol_type_vlan_len_msec); @@ -970,7 +962,7 @@ static int hns3_set_l2l3l4(struct sk_buff *skb, u8 ol4_proto, break; case IPPROTO_UDP: if (hns3_tunnel_csum_bug(skb)) - break; + return skb_checksum_help(skb); hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1); hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S, @@ -995,8 +987,7 @@ static int hns3_set_l2l3l4(struct sk_buff *skb, u8 ol4_proto, /* the stack computes the IP header already, * driver calculate l4 checksum when not TSO. */ - skb_checksum_help(skb); - return 0; + return skb_checksum_help(skb); } return 0; @@ -3844,6 +3835,34 @@ map_ring_fail: return ret; } +static void hns3_nic_init_coal_cfg(struct hns3_nic_priv *priv) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev); + struct hns3_enet_coalesce *tx_coal = &priv->tx_coal; + struct hns3_enet_coalesce *rx_coal = &priv->rx_coal; + + /* initialize the configuration for interrupt coalescing. + * 1. GL (Interrupt Gap Limiter) + * 2. RL (Interrupt Rate Limiter) + * 3. QL (Interrupt Quantity Limiter) + * + * Default: enable interrupt coalescing self-adaptive and GL + */ + tx_coal->adapt_enable = 1; + rx_coal->adapt_enable = 1; + + tx_coal->int_gl = HNS3_INT_GL_50K; + rx_coal->int_gl = HNS3_INT_GL_50K; + + rx_coal->flow_level = HNS3_FLOW_LOW; + tx_coal->flow_level = HNS3_FLOW_LOW; + + if (ae_dev->dev_specs.int_ql_max) { + tx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG; + rx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG; + } +} + static int hns3_nic_alloc_vector_data(struct hns3_nic_priv *priv) { struct hnae3_handle *h = priv->ae_handle; @@ -4295,6 +4314,8 @@ static int hns3_client_init(struct hnae3_handle *handle) goto out_get_ring_cfg; } + hns3_nic_init_coal_cfg(priv); + ret = hns3_nic_alloc_vector_data(priv); if (ret) { ret = -ENOMEM; @@ -4317,12 +4338,6 @@ static int hns3_client_init(struct hnae3_handle *handle) if (ret) goto out_init_phy; - ret = register_netdev(netdev); - if (ret) { - dev_err(priv->dev, "probe register netdev fail!\n"); - goto out_reg_netdev_fail; - } - /* the device can work without cpu rmap, only aRFS needs it */ ret = hns3_set_rx_cpu_rmap(netdev); if (ret) @@ -4355,17 +4370,23 @@ static int hns3_client_init(struct hnae3_handle *handle) if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3) set_bit(HNAE3_PFLAG_LIMIT_PROMISC, &handle->supported_pflags); + ret = register_netdev(netdev); + if (ret) { + dev_err(priv->dev, "probe register netdev fail!\n"); + goto out_reg_netdev_fail; + } + if (netif_msg_drv(handle)) hns3_info_show(priv); return ret; +out_reg_netdev_fail: + hns3_dbg_uninit(handle); out_client_start: hns3_free_rx_cpu_rmap(netdev); hns3_nic_uninit_irq(priv); out_init_irq_fail: - unregister_netdev(netdev); -out_reg_netdev_fail: hns3_uninit_phy(netdev); out_init_phy: hns3_uninit_all_ring(priv); @@ -4571,31 +4592,6 @@ int hns3_nic_reset_all_ring(struct hnae3_handle *h) return 0; } -static void hns3_store_coal(struct hns3_nic_priv *priv) -{ - /* ethtool only support setting and querying one coal - * configuration for now, so save the vector 0' coal - * configuration here in order to restore it. - */ - memcpy(&priv->tx_coal, &priv->tqp_vector[0].tx_group.coal, - sizeof(struct hns3_enet_coalesce)); - memcpy(&priv->rx_coal, &priv->tqp_vector[0].rx_group.coal, - sizeof(struct hns3_enet_coalesce)); -} - -static void hns3_restore_coal(struct hns3_nic_priv *priv) -{ - u16 vector_num = priv->vector_num; - int i; - - for (i = 0; i < vector_num; i++) { - memcpy(&priv->tqp_vector[i].tx_group.coal, &priv->tx_coal, - sizeof(struct hns3_enet_coalesce)); - memcpy(&priv->tqp_vector[i].rx_group.coal, &priv->rx_coal, - sizeof(struct hns3_enet_coalesce)); - } -} - static int hns3_reset_notify_down_enet(struct hnae3_handle *handle) { struct hnae3_knic_private_info *kinfo = &handle->kinfo; @@ -4654,8 +4650,6 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle) if (ret) goto err_put_ring; - hns3_restore_coal(priv); - ret = hns3_nic_init_vector_data(priv); if (ret) goto err_dealloc_vector; @@ -4721,8 +4715,6 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle) hns3_nic_uninit_vector_data(priv); - hns3_store_coal(priv); - hns3_nic_dealloc_vector_data(priv); hns3_uninit_all_ring(priv); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index b48faf769b1c..c1ea403d2b56 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -1134,50 +1134,32 @@ static void hns3_get_channels(struct net_device *netdev, h->ae_algo->ops->get_channels(h, ch); } -static int hns3_get_coalesce_per_queue(struct net_device *netdev, u32 queue, - struct ethtool_coalesce *cmd) +static int hns3_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *cmd) { - struct hns3_enet_tqp_vector *tx_vector, *rx_vector; struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hns3_enet_coalesce *tx_coal = &priv->tx_coal; + struct hns3_enet_coalesce *rx_coal = &priv->rx_coal; struct hnae3_handle *h = priv->ae_handle; - u16 queue_num = h->kinfo.num_tqps; if (hns3_nic_resetting(netdev)) return -EBUSY; - if (queue >= queue_num) { - netdev_err(netdev, - "Invalid queue value %u! Queue max id=%u\n", - queue, queue_num - 1); - return -EINVAL; - } - - tx_vector = priv->ring[queue].tqp_vector; - rx_vector = priv->ring[queue_num + queue].tqp_vector; + cmd->use_adaptive_tx_coalesce = tx_coal->adapt_enable; + cmd->use_adaptive_rx_coalesce = rx_coal->adapt_enable; - cmd->use_adaptive_tx_coalesce = - tx_vector->tx_group.coal.adapt_enable; - cmd->use_adaptive_rx_coalesce = - rx_vector->rx_group.coal.adapt_enable; - - cmd->tx_coalesce_usecs = tx_vector->tx_group.coal.int_gl; - cmd->rx_coalesce_usecs = rx_vector->rx_group.coal.int_gl; + cmd->tx_coalesce_usecs = tx_coal->int_gl; + cmd->rx_coalesce_usecs = rx_coal->int_gl; cmd->tx_coalesce_usecs_high = h->kinfo.int_rl_setting; cmd->rx_coalesce_usecs_high = h->kinfo.int_rl_setting; - cmd->tx_max_coalesced_frames = tx_vector->tx_group.coal.int_ql; - cmd->rx_max_coalesced_frames = rx_vector->rx_group.coal.int_ql; + cmd->tx_max_coalesced_frames = tx_coal->int_ql; + cmd->rx_max_coalesced_frames = rx_coal->int_ql; return 0; } -static int hns3_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *cmd) -{ - return hns3_get_coalesce_per_queue(netdev, 0, cmd); -} - static int hns3_check_gl_coalesce_para(struct net_device *netdev, struct ethtool_coalesce *cmd) { @@ -1292,19 +1274,7 @@ static int hns3_check_coalesce_para(struct net_device *netdev, return ret; } - ret = hns3_check_ql_coalesce_param(netdev, cmd); - if (ret) - return ret; - - if (cmd->use_adaptive_tx_coalesce == 1 || - cmd->use_adaptive_rx_coalesce == 1) { - netdev_info(netdev, - "adaptive-tx=%u and adaptive-rx=%u, tx_usecs or rx_usecs will changed dynamically.\n", - cmd->use_adaptive_tx_coalesce, - cmd->use_adaptive_rx_coalesce); - } - - return 0; + return hns3_check_ql_coalesce_param(netdev, cmd); } static void hns3_set_coalesce_per_queue(struct net_device *netdev, @@ -1350,6 +1320,9 @@ static int hns3_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *cmd) { struct hnae3_handle *h = hns3_get_handle(netdev); + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hns3_enet_coalesce *tx_coal = &priv->tx_coal; + struct hns3_enet_coalesce *rx_coal = &priv->rx_coal; u16 queue_num = h->kinfo.num_tqps; int ret; int i; @@ -1364,6 +1337,15 @@ static int hns3_set_coalesce(struct net_device *netdev, h->kinfo.int_rl_setting = hns3_rl_round_down(cmd->rx_coalesce_usecs_high); + tx_coal->adapt_enable = cmd->use_adaptive_tx_coalesce; + rx_coal->adapt_enable = cmd->use_adaptive_rx_coalesce; + + tx_coal->int_gl = cmd->tx_coalesce_usecs; + rx_coal->int_gl = cmd->rx_coalesce_usecs; + + tx_coal->int_ql = cmd->tx_max_coalesced_frames; + rx_coal->int_ql = cmd->rx_max_coalesced_frames; + for (i = 0; i < queue_num; i++) hns3_set_coalesce_per_queue(netdev, cmd, i); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 8e5f9dc8791d..f1c9f4ada348 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -710,7 +710,6 @@ void hclge_mbx_handler(struct hclge_dev *hdev) unsigned int flag; int ret = 0; - memset(&resp_msg, 0, sizeof(resp_msg)); /* handle all the mailbox requests in the queue */ while (!hclge_cmd_crq_empty(&hdev->hw)) { if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) { @@ -738,6 +737,9 @@ void hclge_mbx_handler(struct hclge_dev *hdev) trace_hclge_pf_mbx_get(hdev, req); + /* clear the resp_msg before processing every mailbox message */ + memset(&resp_msg, 0, sizeof(resp_msg)); + switch (req->msg.code) { case HCLGE_MBX_MAP_RING_TO_VECTOR: ret = hclge_map_unmap_ring_to_vf_vector(vport, true, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 988db46bff0e..214a38de3f41 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -467,12 +467,16 @@ static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, return err; } -static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) +static int ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 max_frame, u32 vf) { struct ixgbe_hw *hw = &adapter->hw; - int max_frame = msgbuf[1]; u32 max_frs; + if (max_frame < ETH_MIN_MTU || max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE) { + e_err(drv, "VF max_frame %d out of range\n", max_frame); + return -EINVAL; + } + /* * For 82599EB we have to keep all PFs and VFs operating with * the same max_frame value in order to avoid sending an oversize @@ -533,12 +537,6 @@ static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) } } - /* MTU < 68 is an error and causes problems on some kernels */ - if (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE) { - e_err(drv, "VF max_frame %d out of range\n", max_frame); - return -EINVAL; - } - /* pull current max frame size from hardware */ max_frs = IXGBE_READ_REG(hw, IXGBE_MAXFRS); max_frs &= IXGBE_MHADD_MFS_MASK; @@ -1249,7 +1247,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) retval = ixgbe_set_vf_vlan_msg(adapter, msgbuf, vf); break; case IXGBE_VF_SET_LPE: - retval = ixgbe_set_vf_lpe(adapter, msgbuf, vf); + retval = ixgbe_set_vf_lpe(adapter, msgbuf[1], vf); break; case IXGBE_VF_SET_MACVLAN: retval = ixgbe_set_vf_macvlan_msg(adapter, msgbuf, vf); diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c index 6f987a7ffcb3..b30a45725374 100644 --- a/drivers/net/ethernet/korina.c +++ b/drivers/net/ethernet/korina.c @@ -1315,23 +1315,23 @@ static int korina_probe(struct platform_device *pdev) lp->tx_irq = platform_get_irq_byname(pdev, "tx"); p = devm_platform_ioremap_resource_byname(pdev, "emac"); - if (!p) { + if (IS_ERR(p)) { printk(KERN_ERR DRV_NAME ": cannot remap registers\n"); - return -ENOMEM; + return PTR_ERR(p); } lp->eth_regs = p; p = devm_platform_ioremap_resource_byname(pdev, "dma_rx"); - if (!p) { + if (IS_ERR(p)) { printk(KERN_ERR DRV_NAME ": cannot remap Rx DMA registers\n"); - return -ENOMEM; + return PTR_ERR(p); } lp->rx_dma_regs = p; p = devm_platform_ioremap_resource_byname(pdev, "dma_tx"); - if (!p) { + if (IS_ERR(p)) { printk(KERN_ERR DRV_NAME ": cannot remap Tx DMA registers\n"); - return -ENOMEM; + return PTR_ERR(p); } lp->tx_dma_regs = p; diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 41c2ad210bc9..36dc3e5f6218 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -154,6 +154,7 @@ static int xrx200_close(struct net_device *net_dev) static int xrx200_alloc_skb(struct xrx200_chan *ch) { + dma_addr_t mapping; int ret = 0; ch->skb[ch->dma.desc] = netdev_alloc_skb_ip_align(ch->priv->net_dev, @@ -163,16 +164,17 @@ static int xrx200_alloc_skb(struct xrx200_chan *ch) goto skip; } - ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(ch->priv->dev, - ch->skb[ch->dma.desc]->data, XRX200_DMA_DATA_LEN, - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(ch->priv->dev, - ch->dma.desc_base[ch->dma.desc].addr))) { + mapping = dma_map_single(ch->priv->dev, ch->skb[ch->dma.desc]->data, + XRX200_DMA_DATA_LEN, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(ch->priv->dev, mapping))) { dev_kfree_skb_any(ch->skb[ch->dma.desc]); ret = -ENOMEM; goto skip; } + ch->dma.desc_base[ch->dma.desc].addr = mapping; + /* Make sure the address is written before we give it to HW */ + wmb(); skip: ch->dma.desc_base[ch->dma.desc].ctl = LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | @@ -196,6 +198,8 @@ static int xrx200_hw_receive(struct xrx200_chan *ch) ch->dma.desc %= LTQ_DESC_NUM; if (ret) { + ch->skb[ch->dma.desc] = skb; + net_dev->stats.rx_dropped++; netdev_err(net_dev, "failed to allocate new rx buffer\n"); return ret; } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 8edba5ea90f0..4a61c90003b5 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -993,6 +993,14 @@ enum mvpp22_ptp_packet_format { #define MVPP2_DESC_DMA_MASK DMA_BIT_MASK(40) +/* Buffer header info bits */ +#define MVPP2_B_HDR_INFO_MC_ID_MASK 0xfff +#define MVPP2_B_HDR_INFO_MC_ID(info) ((info) & MVPP2_B_HDR_INFO_MC_ID_MASK) +#define MVPP2_B_HDR_INFO_LAST_OFFS 12 +#define MVPP2_B_HDR_INFO_LAST_MASK BIT(12) +#define MVPP2_B_HDR_INFO_IS_LAST(info) \ + (((info) & MVPP2_B_HDR_INFO_LAST_MASK) >> MVPP2_B_HDR_INFO_LAST_OFFS) + struct mvpp2_tai; /* Definitions */ @@ -1002,6 +1010,20 @@ struct mvpp2_rss_table { u32 indir[MVPP22_RSS_TABLE_ENTRIES]; }; +struct mvpp2_buff_hdr { + __le32 next_phys_addr; + __le32 next_dma_addr; + __le16 byte_count; + __le16 info; + __le16 reserved1; /* bm_qset (for future use, BM) */ + u8 next_phys_addr_high; + u8 next_dma_addr_high; + __le16 reserved2; + __le16 reserved3; + __le16 reserved4; + __le16 reserved5; +}; + /* Shared Packet Processor resources */ struct mvpp2 { /* Shared registers' base addresses */ diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index ec706d614cac..d39c7639cdba 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3839,6 +3839,35 @@ mvpp2_run_xdp(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq, return ret; } +static void mvpp2_buff_hdr_pool_put(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc, + int pool, u32 rx_status) +{ + phys_addr_t phys_addr, phys_addr_next; + dma_addr_t dma_addr, dma_addr_next; + struct mvpp2_buff_hdr *buff_hdr; + + phys_addr = mvpp2_rxdesc_dma_addr_get(port, rx_desc); + dma_addr = mvpp2_rxdesc_cookie_get(port, rx_desc); + + do { + buff_hdr = (struct mvpp2_buff_hdr *)phys_to_virt(phys_addr); + + phys_addr_next = le32_to_cpu(buff_hdr->next_phys_addr); + dma_addr_next = le32_to_cpu(buff_hdr->next_dma_addr); + + if (port->priv->hw_version >= MVPP22) { + phys_addr_next |= ((u64)buff_hdr->next_phys_addr_high << 32); + dma_addr_next |= ((u64)buff_hdr->next_dma_addr_high << 32); + } + + mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr); + + phys_addr = phys_addr_next; + dma_addr = dma_addr_next; + + } while (!MVPP2_B_HDR_INFO_IS_LAST(le16_to_cpu(buff_hdr->info))); +} + /* Main rx processing */ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, int rx_todo, struct mvpp2_rx_queue *rxq) @@ -3885,14 +3914,6 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, MVPP2_RXD_BM_POOL_ID_OFFS; bm_pool = &port->priv->bm_pools[pool]; - /* In case of an error, release the requested buffer pointer - * to the Buffer Manager. This request process is controlled - * by the hardware, and the information about the buffer is - * comprised by the RX descriptor. - */ - if (rx_status & MVPP2_RXD_ERR_SUMMARY) - goto err_drop_frame; - if (port->priv->percpu_pools) { pp = port->priv->page_pool[pool]; dma_dir = page_pool_get_dma_dir(pp); @@ -3904,6 +3925,18 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, rx_bytes + MVPP2_MH_SIZE, dma_dir); + /* Buffer header not supported */ + if (rx_status & MVPP2_RXD_BUF_HDR) + goto err_drop_frame; + + /* In case of an error, release the requested buffer pointer + * to the Buffer Manager. This request process is controlled + * by the hardware, and the information about the buffer is + * comprised by the RX descriptor. + */ + if (rx_status & MVPP2_RXD_ERR_SUMMARY) + goto err_drop_frame; + /* Prefetch header */ prefetch(data); @@ -3985,7 +4018,10 @@ err_drop_frame: dev->stats.rx_errors++; mvpp2_rx_error(port, rx_desc); /* Return the buffer to the pool */ - mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr); + if (rx_status & MVPP2_RXD_BUF_HDR) + mvpp2_buff_hdr_pool_put(port, rx_desc, pool, rx_status); + else + mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr); } rcu_read_unlock(); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index f4962a97a075..9d9a2e438acf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -786,6 +786,10 @@ static int otx2_set_rxfh_context(struct net_device *dev, const u32 *indir, if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) return -EOPNOTSUPP; + if (*rss_context != ETH_RXFH_CONTEXT_ALLOC && + *rss_context >= MAX_RSS_GROUPS) + return -EINVAL; + rss = &pfvf->hw.rss_info; if (!rss->enable) { diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index ed4eacef17ce..64adfd24e134 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -681,32 +681,53 @@ static int mtk_set_mac_address(struct net_device *dev, void *p) void mtk_stats_update_mac(struct mtk_mac *mac) { struct mtk_hw_stats *hw_stats = mac->hw_stats; - unsigned int base = MTK_GDM1_TX_GBCNT; - u64 stats; - - base += hw_stats->reg_offset; + struct mtk_eth *eth = mac->hw; u64_stats_update_begin(&hw_stats->syncp); - hw_stats->rx_bytes += mtk_r32(mac->hw, base); - stats = mtk_r32(mac->hw, base + 0x04); - if (stats) - hw_stats->rx_bytes += (stats << 32); - hw_stats->rx_packets += mtk_r32(mac->hw, base + 0x08); - hw_stats->rx_overflow += mtk_r32(mac->hw, base + 0x10); - hw_stats->rx_fcs_errors += mtk_r32(mac->hw, base + 0x14); - hw_stats->rx_short_errors += mtk_r32(mac->hw, base + 0x18); - hw_stats->rx_long_errors += mtk_r32(mac->hw, base + 0x1c); - hw_stats->rx_checksum_errors += mtk_r32(mac->hw, base + 0x20); - hw_stats->rx_flow_control_packets += - mtk_r32(mac->hw, base + 0x24); - hw_stats->tx_skip += mtk_r32(mac->hw, base + 0x28); - hw_stats->tx_collisions += mtk_r32(mac->hw, base + 0x2c); - hw_stats->tx_bytes += mtk_r32(mac->hw, base + 0x30); - stats = mtk_r32(mac->hw, base + 0x34); - if (stats) - hw_stats->tx_bytes += (stats << 32); - hw_stats->tx_packets += mtk_r32(mac->hw, base + 0x38); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + hw_stats->tx_packets += mtk_r32(mac->hw, MT7628_SDM_TPCNT); + hw_stats->tx_bytes += mtk_r32(mac->hw, MT7628_SDM_TBCNT); + hw_stats->rx_packets += mtk_r32(mac->hw, MT7628_SDM_RPCNT); + hw_stats->rx_bytes += mtk_r32(mac->hw, MT7628_SDM_RBCNT); + hw_stats->rx_checksum_errors += + mtk_r32(mac->hw, MT7628_SDM_CS_ERR); + } else { + unsigned int offs = hw_stats->reg_offset; + u64 stats; + + hw_stats->rx_bytes += mtk_r32(mac->hw, + MTK_GDM1_RX_GBCNT_L + offs); + stats = mtk_r32(mac->hw, MTK_GDM1_RX_GBCNT_H + offs); + if (stats) + hw_stats->rx_bytes += (stats << 32); + hw_stats->rx_packets += + mtk_r32(mac->hw, MTK_GDM1_RX_GPCNT + offs); + hw_stats->rx_overflow += + mtk_r32(mac->hw, MTK_GDM1_RX_OERCNT + offs); + hw_stats->rx_fcs_errors += + mtk_r32(mac->hw, MTK_GDM1_RX_FERCNT + offs); + hw_stats->rx_short_errors += + mtk_r32(mac->hw, MTK_GDM1_RX_SERCNT + offs); + hw_stats->rx_long_errors += + mtk_r32(mac->hw, MTK_GDM1_RX_LENCNT + offs); + hw_stats->rx_checksum_errors += + mtk_r32(mac->hw, MTK_GDM1_RX_CERCNT + offs); + hw_stats->rx_flow_control_packets += + mtk_r32(mac->hw, MTK_GDM1_RX_FCCNT + offs); + hw_stats->tx_skip += + mtk_r32(mac->hw, MTK_GDM1_TX_SKIPCNT + offs); + hw_stats->tx_collisions += + mtk_r32(mac->hw, MTK_GDM1_TX_COLCNT + offs); + hw_stats->tx_bytes += + mtk_r32(mac->hw, MTK_GDM1_TX_GBCNT_L + offs); + stats = mtk_r32(mac->hw, MTK_GDM1_TX_GBCNT_H + offs); + if (stats) + hw_stats->tx_bytes += (stats << 32); + hw_stats->tx_packets += + mtk_r32(mac->hw, MTK_GDM1_TX_GPCNT + offs); + } + u64_stats_update_end(&hw_stats->syncp); } @@ -2423,7 +2444,8 @@ static void mtk_dim_rx(struct work_struct *work) val |= cur << MTK_PDMA_DELAY_RX_PINT_SHIFT; mtk_w32(eth, val, MTK_PDMA_DELAY_INT); - mtk_w32(eth, val, MTK_QDMA_DELAY_INT); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + mtk_w32(eth, val, MTK_QDMA_DELAY_INT); spin_unlock_bh(ð->dim_lock); @@ -2452,7 +2474,8 @@ static void mtk_dim_tx(struct work_struct *work) val |= cur << MTK_PDMA_DELAY_TX_PINT_SHIFT; mtk_w32(eth, val, MTK_PDMA_DELAY_INT); - mtk_w32(eth, val, MTK_QDMA_DELAY_INT); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + mtk_w32(eth, val, MTK_QDMA_DELAY_INT); spin_unlock_bh(ð->dim_lock); @@ -2480,6 +2503,10 @@ static int mtk_hw_init(struct mtk_eth *eth) goto err_disable_pm; } + /* set interrupt delays based on current Net DIM sample */ + mtk_dim_rx(ð->rx_dim.work); + mtk_dim_tx(ð->tx_dim.work); + /* disable delay and normal interrupt */ mtk_tx_irq_disable(eth, ~0); mtk_rx_irq_disable(eth, ~0); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 11331b44ba07..5ef70dd8b49c 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -278,8 +278,21 @@ /* QDMA FQ Free Page Buffer Length Register */ #define MTK_QDMA_FQ_BLEN 0x1B2C -/* GMA1 Received Good Byte Count Register */ -#define MTK_GDM1_TX_GBCNT 0x2400 +/* GMA1 counter / statics register */ +#define MTK_GDM1_RX_GBCNT_L 0x2400 +#define MTK_GDM1_RX_GBCNT_H 0x2404 +#define MTK_GDM1_RX_GPCNT 0x2408 +#define MTK_GDM1_RX_OERCNT 0x2410 +#define MTK_GDM1_RX_FERCNT 0x2414 +#define MTK_GDM1_RX_SERCNT 0x2418 +#define MTK_GDM1_RX_LENCNT 0x241c +#define MTK_GDM1_RX_CERCNT 0x2420 +#define MTK_GDM1_RX_FCCNT 0x2424 +#define MTK_GDM1_TX_SKIPCNT 0x2428 +#define MTK_GDM1_TX_COLCNT 0x242c +#define MTK_GDM1_TX_GBCNT_L 0x2430 +#define MTK_GDM1_TX_GBCNT_H 0x2434 +#define MTK_GDM1_TX_GPCNT 0x2438 #define MTK_STAT_OFFSET 0x40 /* QDMA descriptor txd4 */ @@ -502,6 +515,13 @@ #define MT7628_SDM_MAC_ADRL (MT7628_SDM_OFFSET + 0x0c) #define MT7628_SDM_MAC_ADRH (MT7628_SDM_OFFSET + 0x10) +/* Counter / stat register */ +#define MT7628_SDM_TPCNT (MT7628_SDM_OFFSET + 0x100) +#define MT7628_SDM_TBCNT (MT7628_SDM_OFFSET + 0x104) +#define MT7628_SDM_RPCNT (MT7628_SDM_OFFSET + 0x108) +#define MT7628_SDM_RBCNT (MT7628_SDM_OFFSET + 0x10c) +#define MT7628_SDM_CS_ERR (MT7628_SDM_OFFSET + 0x110) + struct mtk_rx_dma { unsigned int rxd1; unsigned int rxd2; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 1434df66fcf2..3616b77caa0a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -2027,8 +2027,6 @@ static int mlx4_en_set_tunable(struct net_device *dev, return ret; } -#define MLX4_EEPROM_PAGE_LEN 256 - static int mlx4_en_get_module_info(struct net_device *dev, struct ethtool_modinfo *modinfo) { @@ -2063,7 +2061,7 @@ static int mlx4_en_get_module_info(struct net_device *dev, break; case MLX4_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; - modinfo->eeprom_len = MLX4_EEPROM_PAGE_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; break; default: return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index ba6ac31a339d..256a06b3c096 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -1973,6 +1973,7 @@ EXPORT_SYMBOL(mlx4_get_roce_gid_from_slave); #define I2C_ADDR_LOW 0x50 #define I2C_ADDR_HIGH 0x51 #define I2C_PAGE_SIZE 256 +#define I2C_HIGH_PAGE_SIZE 128 /* Module Info Data */ struct mlx4_cable_info { @@ -2026,6 +2027,88 @@ static inline const char *cable_info_mad_err_str(u16 mad_status) return "Unknown Error"; } +static int mlx4_get_module_id(struct mlx4_dev *dev, u8 port, u8 *module_id) +{ + struct mlx4_cmd_mailbox *inbox, *outbox; + struct mlx4_mad_ifc *inmad, *outmad; + struct mlx4_cable_info *cable_info; + int ret; + + inbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(inbox)) + return PTR_ERR(inbox); + + outbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(outbox)) { + mlx4_free_cmd_mailbox(dev, inbox); + return PTR_ERR(outbox); + } + + inmad = (struct mlx4_mad_ifc *)(inbox->buf); + outmad = (struct mlx4_mad_ifc *)(outbox->buf); + + inmad->method = 0x1; /* Get */ + inmad->class_version = 0x1; + inmad->mgmt_class = 0x1; + inmad->base_version = 0x1; + inmad->attr_id = cpu_to_be16(0xFF60); /* Module Info */ + + cable_info = (struct mlx4_cable_info *)inmad->data; + cable_info->dev_mem_address = 0; + cable_info->page_num = 0; + cable_info->i2c_addr = I2C_ADDR_LOW; + cable_info->size = cpu_to_be16(1); + + ret = mlx4_cmd_box(dev, inbox->dma, outbox->dma, port, 3, + MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C, + MLX4_CMD_NATIVE); + if (ret) + goto out; + + if (be16_to_cpu(outmad->status)) { + /* Mad returned with bad status */ + ret = be16_to_cpu(outmad->status); + mlx4_warn(dev, + "MLX4_CMD_MAD_IFC Get Module ID attr(%x) port(%d) i2c_addr(%x) offset(%d) size(%d): Response Mad Status(%x) - %s\n", + 0xFF60, port, I2C_ADDR_LOW, 0, 1, ret, + cable_info_mad_err_str(ret)); + ret = -ret; + goto out; + } + cable_info = (struct mlx4_cable_info *)outmad->data; + *module_id = cable_info->data[0]; +out: + mlx4_free_cmd_mailbox(dev, inbox); + mlx4_free_cmd_mailbox(dev, outbox); + return ret; +} + +static void mlx4_sfp_eeprom_params_set(u8 *i2c_addr, u8 *page_num, u16 *offset) +{ + *i2c_addr = I2C_ADDR_LOW; + *page_num = 0; + + if (*offset < I2C_PAGE_SIZE) + return; + + *i2c_addr = I2C_ADDR_HIGH; + *offset -= I2C_PAGE_SIZE; +} + +static void mlx4_qsfp_eeprom_params_set(u8 *i2c_addr, u8 *page_num, u16 *offset) +{ + /* Offsets 0-255 belong to page 0. + * Offsets 256-639 belong to pages 01, 02, 03. + * For example, offset 400 is page 02: 1 + (400 - 256) / 128 = 2 + */ + if (*offset < I2C_PAGE_SIZE) + *page_num = 0; + else + *page_num = 1 + (*offset - I2C_PAGE_SIZE) / I2C_HIGH_PAGE_SIZE; + *i2c_addr = I2C_ADDR_LOW; + *offset -= *page_num * I2C_HIGH_PAGE_SIZE; +} + /** * mlx4_get_module_info - Read cable module eeprom data * @dev: mlx4_dev. @@ -2045,12 +2128,30 @@ int mlx4_get_module_info(struct mlx4_dev *dev, u8 port, struct mlx4_cmd_mailbox *inbox, *outbox; struct mlx4_mad_ifc *inmad, *outmad; struct mlx4_cable_info *cable_info; - u16 i2c_addr; + u8 module_id, i2c_addr, page_num; int ret; if (size > MODULE_INFO_MAX_READ) size = MODULE_INFO_MAX_READ; + ret = mlx4_get_module_id(dev, port, &module_id); + if (ret) + return ret; + + switch (module_id) { + case MLX4_MODULE_ID_SFP: + mlx4_sfp_eeprom_params_set(&i2c_addr, &page_num, &offset); + break; + case MLX4_MODULE_ID_QSFP: + case MLX4_MODULE_ID_QSFP_PLUS: + case MLX4_MODULE_ID_QSFP28: + mlx4_qsfp_eeprom_params_set(&i2c_addr, &page_num, &offset); + break; + default: + mlx4_err(dev, "Module ID not recognized: %#x\n", module_id); + return -EINVAL; + } + inbox = mlx4_alloc_cmd_mailbox(dev); if (IS_ERR(inbox)) return PTR_ERR(inbox); @@ -2076,11 +2177,9 @@ int mlx4_get_module_info(struct mlx4_dev *dev, u8 port, */ size -= offset + size - I2C_PAGE_SIZE; - i2c_addr = I2C_ADDR_LOW; - cable_info = (struct mlx4_cable_info *)inmad->data; cable_info->dev_mem_address = cpu_to_be16(offset); - cable_info->page_num = 0; + cable_info->page_num = page_num; cable_info->i2c_addr = i2c_addr; cable_info->size = cpu_to_be16(size); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c index 95f2b26a3ee3..9c076aa20306 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c @@ -223,6 +223,8 @@ static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *pt rpriv = priv->ppriv; fwd_vport_num = rpriv->rep->vport; lag_dev = netdev_master_upper_dev_get(netdev); + if (!lag_dev) + return; netdev_dbg(netdev, "lag_dev(%s)'s slave vport(%d) is txable(%d)\n", lag_dev->name, fwd_vport_num, net_lag_port_dev_txable(netdev)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 6cdc52d50a48..311382261840 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -626,7 +626,7 @@ static bool mlx5e_restore_skb(struct sk_buff *skb, u32 chain, u32 reg_c1, struct mlx5_eswitch *esw; u32 zone_restore_id; - tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); + tc_skb_ext = tc_skb_ext_alloc(skb); if (!tc_skb_ext) { WARN_ON(1); return false; 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 593503bc4d07..f1fb11680d20 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 @@ -1505,7 +1505,7 @@ mlx5e_init_fib_work_ipv4(struct mlx5e_priv *priv, fen_info = container_of(info, struct fib_entry_notifier_info, info); fib_dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev; - if (fib_dev->netdev_ops != &mlx5e_netdev_ops || + if (!fib_dev || fib_dev->netdev_ops != &mlx5e_netdev_ops || fen_info->dst_len != 32) return NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 0d571a0c76d9..0b75fab41ae8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -35,6 +35,7 @@ #include <linux/ipv6.h> #include <linux/tcp.h> #include <linux/mlx5/fs.h> +#include <linux/mlx5/mpfs.h> #include "en.h" #include "en_rep.h" #include "lib/mpfs.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index bca832cdc4cb..ad0f69480b9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -889,10 +889,13 @@ err_free_rq: void mlx5e_activate_rq(struct mlx5e_rq *rq) { set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); - if (rq->icosq) + if (rq->icosq) { mlx5e_trigger_irq(rq->icosq); - else + } else { + local_bh_disable(); napi_schedule(rq->cq.napi); + local_bh_enable(); + } } void mlx5e_deactivate_rq(struct mlx5e_rq *rq) @@ -2697,7 +2700,7 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv) int err; old_num_txqs = netdev->real_num_tx_queues; - old_ntc = netdev->num_tc; + old_ntc = netdev->num_tc ? : 1; nch = priv->channels.params.num_channels; ntc = priv->channels.params.num_tc; @@ -5229,6 +5232,11 @@ static void mlx5e_update_features(struct net_device *netdev) rtnl_unlock(); } +static void mlx5e_reset_channels(struct net_device *netdev) +{ + netdev_reset_tc(netdev); +} + int mlx5e_attach_netdev(struct mlx5e_priv *priv) { const bool take_rtnl = priv->netdev->reg_state == NETREG_REGISTERED; @@ -5283,6 +5291,7 @@ err_cleanup_tx: profile->cleanup_tx(priv); out: + mlx5e_reset_channels(priv->netdev); set_bit(MLX5E_STATE_DESTROYING, &priv->state); cancel_work_sync(&priv->update_stats_work); return err; @@ -5300,6 +5309,7 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv) profile->cleanup_rx(priv); profile->cleanup_tx(priv); + mlx5e_reset_channels(priv->netdev); cancel_work_sync(&priv->update_stats_work); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 47a9c49b25fd..2c776e7a7692 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1322,10 +1322,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct net_device *out_dev, *encap_dev = NULL; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; bool vf_tun = false, encap_valid = true; + struct net_device *encap_dev = NULL; struct mlx5_esw_flow_attr *esw_attr; struct mlx5_fc *counter = NULL; struct mlx5e_rep_priv *rpriv; @@ -1371,16 +1371,22 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr = attr->esw_attr; for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + struct net_device *out_dev; int mirred_ifindex; if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) continue; mirred_ifindex = parse_attr->mirred_ifindex[out_index]; - out_dev = __dev_get_by_index(dev_net(priv->netdev), - mirred_ifindex); + out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); + if (!out_dev) { + NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); + err = -ENODEV; + goto err_out; + } err = mlx5e_attach_encap(priv, flow, out_dev, out_index, extack, &encap_dev, &encap_valid); + dev_put(out_dev); if (err) goto err_out; @@ -1393,6 +1399,12 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr->dests[out_index].mdev = out_priv->mdev; } + if (vf_tun && esw_attr->out_count > 1) { + NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported"); + err = -EOPNOTSUPP; + goto err_out; + } + err = mlx5_eswitch_add_vlan_action(esw, attr); if (err) goto err_out; @@ -3526,8 +3538,12 @@ static int add_vlan_push_action(struct mlx5e_priv *priv, if (err) return err; - *out_dev = dev_get_by_index_rcu(dev_net(vlan_dev), - dev_get_iflink(vlan_dev)); + rcu_read_lock(); + *out_dev = dev_get_by_index_rcu(dev_net(vlan_dev), dev_get_iflink(vlan_dev)); + rcu_read_unlock(); + if (!*out_dev) + return -ENODEV; + if (is_vlan_dev(*out_dev)) err = add_vlan_push_action(priv, attr, out_dev, action); @@ -5074,7 +5090,7 @@ bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, if (mapped_obj.type == MLX5_MAPPED_OBJ_CHAIN) { chain = mapped_obj.chain; - tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); + tc_skb_ext = tc_skb_ext_alloc(skb); if (WARN_ON(!tc_skb_ext)) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 570f2280823c..b88705a3a1a8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -35,6 +35,7 @@ #include <linux/mlx5/mlx5_ifc.h> #include <linux/mlx5/vport.h> #include <linux/mlx5/fs.h> +#include <linux/mlx5/mpfs.h> #include "esw/acl/lgcy.h" #include "esw/legacy.h" #include "mlx5_core.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index a81ece94f599..b45954905845 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -65,7 +65,7 @@ mlx5_eswitch_termtbl_create(struct mlx5_core_dev *dev, { struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_flow_namespace *root_ns; - int err; + int err, err2; root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); if (!root_ns) { @@ -76,33 +76,34 @@ mlx5_eswitch_termtbl_create(struct mlx5_core_dev *dev, /* As this is the terminating action then the termination table is the * same prio as the slow path */ - ft_attr.flags = MLX5_FLOW_TABLE_TERMINATION | + ft_attr.flags = MLX5_FLOW_TABLE_TERMINATION | MLX5_FLOW_TABLE_UNMANAGED | MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; - ft_attr.prio = FDB_SLOW_PATH; + ft_attr.prio = FDB_TC_OFFLOAD; ft_attr.max_fte = 1; + ft_attr.level = 1; ft_attr.autogroup.max_num_groups = 1; tt->termtbl = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr); if (IS_ERR(tt->termtbl)) { - esw_warn(dev, "Failed to create termination table (error %d)\n", - IS_ERR(tt->termtbl)); - return -EOPNOTSUPP; + err = PTR_ERR(tt->termtbl); + esw_warn(dev, "Failed to create termination table, err %pe\n", tt->termtbl); + return err; } tt->rule = mlx5_add_flow_rules(tt->termtbl, NULL, flow_act, &tt->dest, 1); if (IS_ERR(tt->rule)) { - esw_warn(dev, "Failed to create termination table rule (error %d)\n", - IS_ERR(tt->rule)); + err = PTR_ERR(tt->rule); + esw_warn(dev, "Failed to create termination table rule, err %pe\n", tt->rule); goto add_flow_err; } return 0; add_flow_err: - err = mlx5_destroy_flow_table(tt->termtbl); - if (err) - esw_warn(dev, "Failed to destroy termination table\n"); + err2 = mlx5_destroy_flow_table(tt->termtbl); + if (err2) + esw_warn(dev, "Failed to destroy termination table, err %d\n", err2); - return -EOPNOTSUPP; + return err; } static struct mlx5_termtbl_handle * @@ -172,19 +173,6 @@ mlx5_eswitch_termtbl_put(struct mlx5_eswitch *esw, } } -static bool mlx5_eswitch_termtbl_is_encap_reformat(struct mlx5_pkt_reformat *rt) -{ - switch (rt->reformat_type) { - case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: - case MLX5_REFORMAT_TYPE_L2_TO_NVGRE: - case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: - case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: - return true; - default: - return false; - } -} - static void mlx5_eswitch_termtbl_actions_move(struct mlx5_flow_act *src, struct mlx5_flow_act *dst) @@ -202,14 +190,6 @@ mlx5_eswitch_termtbl_actions_move(struct mlx5_flow_act *src, memset(&src->vlan[1], 0, sizeof(src->vlan[1])); } } - - if (src->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT && - mlx5_eswitch_termtbl_is_encap_reformat(src->pkt_reformat)) { - src->action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - dst->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - dst->pkt_reformat = src->pkt_reformat; - src->pkt_reformat = NULL; - } } static bool mlx5_eswitch_offload_is_uplink_port(const struct mlx5_eswitch *esw, @@ -238,6 +218,7 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw, int i; if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, termination_table) || + !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level) || attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH || !mlx5_eswitch_offload_is_uplink_port(esw, spec)) return false; @@ -279,12 +260,19 @@ mlx5_eswitch_add_termtbl_rule(struct mlx5_eswitch *esw, if (dest[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT) continue; + if (attr->dests[num_vport_dests].flags & MLX5_ESW_DEST_ENCAP) { + term_tbl_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + term_tbl_act.pkt_reformat = attr->dests[num_vport_dests].pkt_reformat; + } else { + term_tbl_act.action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + term_tbl_act.pkt_reformat = NULL; + } + /* get the terminating table for the action list */ tt = mlx5_eswitch_termtbl_get_create(esw, &term_tbl_act, &dest[i], attr); if (IS_ERR(tt)) { - esw_warn(esw->dev, "Failed to get termination table (error %d)\n", - IS_ERR(tt)); + esw_warn(esw->dev, "Failed to get termination table, err %pe\n", tt); goto revert_changes; } attr->dests[num_vport_dests].termtbl = tt; @@ -301,6 +289,9 @@ mlx5_eswitch_add_termtbl_rule(struct mlx5_eswitch *esw, goto revert_changes; /* create the FTE */ + flow_act->action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + flow_act->pkt_reformat = NULL; + flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; rule = mlx5_add_flow_rules(fdb, spec, flow_act, dest, num_dest); if (IS_ERR(rule)) goto revert_changes; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index 2c41a6920264..fd6196b5e163 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -307,6 +307,11 @@ int mlx5_lag_mp_init(struct mlx5_lag *ldev) struct lag_mp *mp = &ldev->lag_mp; int err; + /* always clear mfi, as it might become stale when a route delete event + * has been missed + */ + mp->mfi = NULL; + if (mp->fib_nb.notifier_call) return 0; @@ -335,4 +340,5 @@ void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) unregister_fib_notifier(&init_net, &mp->fib_nb); destroy_workqueue(mp->wq); mp->fib_nb.notifier_call = NULL; + mp->mfi = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c index fd8449ff9e17..839a01da110f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -33,6 +33,7 @@ #include <linux/etherdevice.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/mlx5_ifc.h> +#include <linux/mlx5/mpfs.h> #include <linux/mlx5/eswitch.h> #include "mlx5_core.h" #include "lib/mpfs.h" @@ -175,6 +176,7 @@ out: mutex_unlock(&mpfs->lock); return err; } +EXPORT_SYMBOL(mlx5_mpfs_add_mac); int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { @@ -206,3 +208,4 @@ unlock: mutex_unlock(&mpfs->lock); return err; } +EXPORT_SYMBOL(mlx5_mpfs_del_mac); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h index 4a7b2c3203a7..4a293542a7aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h @@ -84,12 +84,9 @@ struct l2addr_node { #ifdef CONFIG_MLX5_MPFS int mlx5_mpfs_init(struct mlx5_core_dev *dev); void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev); -int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac); -int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac); #else /* #ifndef CONFIG_MLX5_MPFS */ static inline int mlx5_mpfs_init(struct mlx5_core_dev *dev) { return 0; } static inline void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) {} -static inline int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } -static inline int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } #endif + #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c114365eb126..a1d67bd7fb43 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -503,7 +503,7 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) { - struct mlx5_profile *prof = dev->profile; + struct mlx5_profile *prof = &dev->profile; void *set_hca_cap; int err; @@ -524,11 +524,11 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) to_fw_pkey_sz(dev, 128)); /* Check log_max_qp from HCA caps to set in current profile */ - if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < profile[prof_sel].log_max_qp) { + if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < prof->log_max_qp) { mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n", - profile[prof_sel].log_max_qp, + prof->log_max_qp, MLX5_CAP_GEN_MAX(dev, log_max_qp)); - profile[prof_sel].log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp); + prof->log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp); } if (prof->mask & MLX5_PROF_MASK_QP_SIZE) MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp, @@ -1381,8 +1381,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) struct mlx5_priv *priv = &dev->priv; int err; - dev->profile = &profile[profile_idx]; - + memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile)); INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); mutex_init(&dev->intf_state_mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 1f907df5b3a2..c3373fb1cd7f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -95,9 +95,10 @@ int mlx5_get_default_msix_vec_count(struct mlx5_core_dev *dev, int num_vfs) int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, int msix_vec_count) { - int sz = MLX5_ST_SZ_BYTES(set_hca_cap_in); + int query_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out); + int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in); + void *hca_cap = NULL, *query_cap = NULL, *cap; int num_vf_msix, min_msix, max_msix; - void *hca_cap, *cap; int ret; num_vf_msix = MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix); @@ -116,11 +117,20 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, if (msix_vec_count > max_msix) return -EOVERFLOW; - hca_cap = kzalloc(sz, GFP_KERNEL); - if (!hca_cap) - return -ENOMEM; + query_cap = kzalloc(query_sz, GFP_KERNEL); + hca_cap = kzalloc(set_sz, GFP_KERNEL); + if (!hca_cap || !query_cap) { + ret = -ENOMEM; + goto out; + } + + ret = mlx5_vport_get_other_func_cap(dev, function_id, query_cap); + if (ret) + goto out; cap = MLX5_ADDR_OF(set_hca_cap_in, hca_cap, capability); + memcpy(cap, MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability), + MLX5_UN_SZ_BYTES(hca_cap_union)); MLX5_SET(cmd_hca_cap, cap, dynamic_msix_table_size, msix_vec_count); MLX5_SET(set_hca_cap_in, hca_cap, opcode, MLX5_CMD_OP_SET_HCA_CAP); @@ -130,7 +140,9 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, MLX5_SET(set_hca_cap_in, hca_cap, op_mod, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1); ret = mlx5_cmd_exec_in(dev, set_hca_cap, hca_cap); +out: kfree(hca_cap); + kfree(query_cap); return ret; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index a8e73c9ed1ea..1be048769309 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -136,10 +136,10 @@ static enum devlink_port_fn_state mlx5_sf_to_devlink_state(u8 hw_state) switch (hw_state) { case MLX5_VHCA_STATE_ACTIVE: case MLX5_VHCA_STATE_IN_USE: - case MLX5_VHCA_STATE_TEARDOWN_REQUEST: return DEVLINK_PORT_FN_STATE_ACTIVE; case MLX5_VHCA_STATE_INVALID: case MLX5_VHCA_STATE_ALLOCATED: + case MLX5_VHCA_STATE_TEARDOWN_REQUEST: default: return DEVLINK_PORT_FN_STATE_INACTIVE; } @@ -192,14 +192,17 @@ sf_err: return err; } -static int mlx5_sf_activate(struct mlx5_core_dev *dev, struct mlx5_sf *sf) +static int mlx5_sf_activate(struct mlx5_core_dev *dev, struct mlx5_sf *sf, + struct netlink_ext_ack *extack) { int err; if (mlx5_sf_is_active(sf)) return 0; - if (sf->hw_state != MLX5_VHCA_STATE_ALLOCATED) - return -EINVAL; + if (sf->hw_state != MLX5_VHCA_STATE_ALLOCATED) { + NL_SET_ERR_MSG_MOD(extack, "SF is inactivated but it is still attached"); + return -EBUSY; + } err = mlx5_cmd_sf_enable_hca(dev, sf->hw_fn_id); if (err) @@ -226,7 +229,8 @@ static int mlx5_sf_deactivate(struct mlx5_core_dev *dev, struct mlx5_sf *sf) static int mlx5_sf_state_set(struct mlx5_core_dev *dev, struct mlx5_sf_table *table, struct mlx5_sf *sf, - enum devlink_port_fn_state state) + enum devlink_port_fn_state state, + struct netlink_ext_ack *extack) { int err = 0; @@ -234,7 +238,7 @@ static int mlx5_sf_state_set(struct mlx5_core_dev *dev, struct mlx5_sf_table *ta if (state == mlx5_sf_to_devlink_state(sf->hw_state)) goto out; if (state == DEVLINK_PORT_FN_STATE_ACTIVE) - err = mlx5_sf_activate(dev, sf); + err = mlx5_sf_activate(dev, sf, extack); else if (state == DEVLINK_PORT_FN_STATE_INACTIVE) err = mlx5_sf_deactivate(dev, sf); else @@ -265,7 +269,7 @@ int mlx5_devlink_sf_port_fn_state_set(struct devlink *devlink, struct devlink_po goto out; } - err = mlx5_sf_state_set(dev, table, sf, state); + err = mlx5_sf_state_set(dev, table, sf, state, extack); out: mlx5_sf_table_put(table); return err; diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c index 3658c4ae3c37..ee921a99e439 100644 --- a/drivers/net/ethernet/microchip/encx24j600.c +++ b/drivers/net/ethernet/microchip/encx24j600.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/** +/* * Microchip ENCX24J600 ethernet driver * * Copyright (C) 2015 Gridpoint diff --git a/drivers/net/ethernet/microchip/encx24j600_hw.h b/drivers/net/ethernet/microchip/encx24j600_hw.h index f604a260ede7..fac61a8fbd02 100644 --- a/drivers/net/ethernet/microchip/encx24j600_hw.h +++ b/drivers/net/ethernet/microchip/encx24j600_hw.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/** +/* * encx24j600_hw.h: Register definitions * */ diff --git a/drivers/net/ethernet/pensando/Kconfig b/drivers/net/ethernet/pensando/Kconfig index 5f8b0bb3af6e..202973a82712 100644 --- a/drivers/net/ethernet/pensando/Kconfig +++ b/drivers/net/ethernet/pensando/Kconfig @@ -20,6 +20,7 @@ if NET_VENDOR_PENSANDO config IONIC tristate "Pensando Ethernet IONIC Support" depends on 64BIT && PCI + depends on PTP_1588_CLOCK || !PTP_1588_CLOCK select NET_DEVLINK select DIMLIB help diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 214e347097a7..2376b2729633 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -114,7 +114,7 @@ static int ql_sem_spinlock(struct ql3_adapter *qdev, value = readl(&port_regs->CommonRegs.semaphoreReg); if ((value & (sem_mask >> 16)) == sem_bits) return 0; - ssleep(1); + mdelay(1000); } while (--seconds); return -1; } diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c index d1e908846f5d..22fbb0ae77fb 100644 --- a/drivers/net/ethernet/sfc/nic.c +++ b/drivers/net/ethernet/sfc/nic.c @@ -90,6 +90,7 @@ int efx_nic_init_interrupt(struct efx_nic *efx) efx->pci_dev->irq); goto fail1; } + efx->irqs_hooked = true; return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 345b4c6d1fd4..5d956a553434 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1196,7 +1196,6 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv) */ static int stmmac_init_phy(struct net_device *dev) { - struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; struct stmmac_priv *priv = netdev_priv(dev); struct device_node *node; int ret; @@ -1222,8 +1221,12 @@ static int stmmac_init_phy(struct net_device *dev) ret = phylink_connect_phy(priv->phylink, phydev); } - phylink_ethtool_get_wol(priv->phylink, &wol); - device_set_wakeup_capable(priv->device, !!wol.supported); + if (!priv->plat->pmt) { + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; + + phylink_ethtool_get_wol(priv->phylink, &wol); + device_set_wakeup_capable(priv->device, !!wol.supported); + } return ret; } @@ -5888,12 +5891,21 @@ static int stmmac_set_mac_address(struct net_device *ndev, void *addr) struct stmmac_priv *priv = netdev_priv(ndev); int ret = 0; + ret = pm_runtime_get_sync(priv->device); + if (ret < 0) { + pm_runtime_put_noidle(priv->device); + return ret; + } + ret = eth_mac_addr(ndev, addr); if (ret) - return ret; + goto set_mac_error; stmmac_set_umac_addr(priv, priv->hw, ndev->dev_addr, 0); +set_mac_error: + pm_runtime_put(priv->device); + return ret; } @@ -6188,12 +6200,6 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid bool is_double = false; int ret; - ret = pm_runtime_get_sync(priv->device); - if (ret < 0) { - pm_runtime_put_noidle(priv->device); - return ret; - } - if (be16_to_cpu(proto) == ETH_P_8021AD) is_double = true; @@ -6219,6 +6225,12 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi bool is_double = false; int ret; + ret = pm_runtime_get_sync(priv->device); + if (ret < 0) { + pm_runtime_put_noidle(priv->device); + return ret; + } + if (be16_to_cpu(proto) == ETH_P_8021AD) is_double = true; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 9030e619e543..97942b0e3897 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1350,8 +1350,8 @@ int netcp_txpipe_open(struct netcp_tx_pipe *tx_pipe) tx_pipe->dma_queue = knav_queue_open(name, tx_pipe->dma_queue_id, KNAV_QUEUE_SHARED); if (IS_ERR(tx_pipe->dma_queue)) { - dev_err(dev, "Could not open DMA queue for channel \"%s\": %d\n", - name, ret); + dev_err(dev, "Could not open DMA queue for channel \"%s\": %pe\n", + name, tx_pipe->dma_queue); ret = PTR_ERR(tx_pipe->dma_queue); goto err; } diff --git a/drivers/net/ipa/ipa.h b/drivers/net/ipa/ipa.h index e7ff376cb5b7..744406832a77 100644 --- a/drivers/net/ipa/ipa.h +++ b/drivers/net/ipa/ipa.h @@ -58,6 +58,7 @@ enum ipa_flag { * @mem_virt: Virtual address of IPA-local memory space * @mem_offset: Offset from @mem_virt used for access to IPA memory * @mem_size: Total size (bytes) of memory at @mem_virt + * @mem_count: Number of entries in the mem array * @mem: Array of IPA-local memory region descriptors * @imem_iova: I/O virtual address of IPA region in IMEM * @imem_size: Size of IMEM region @@ -103,6 +104,7 @@ struct ipa { void *mem_virt; u32 mem_offset; u32 mem_size; + u32 mem_count; const struct ipa_mem *mem; unsigned long imem_iova; diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c index c5c3b1b7e67d..1624125e7459 100644 --- a/drivers/net/ipa/ipa_mem.c +++ b/drivers/net/ipa/ipa_mem.c @@ -180,7 +180,7 @@ int ipa_mem_config(struct ipa *ipa) * for the region, write "canary" values in the space prior to * the region's base address. */ - for (mem_id = 0; mem_id < IPA_MEM_COUNT; mem_id++) { + for (mem_id = 0; mem_id < ipa->mem_count; mem_id++) { const struct ipa_mem *mem = &ipa->mem[mem_id]; u16 canary_count; __le32 *canary; @@ -487,6 +487,7 @@ int ipa_mem_init(struct ipa *ipa, const struct ipa_mem_data *mem_data) ipa->mem_size = resource_size(res); /* The ipa->mem[] array is indexed by enum ipa_mem_id values */ + ipa->mem_count = mem_data->local_count; ipa->mem = mem_data->local; ret = ipa_imem_init(ipa, mem_data->imem_addr, mem_data->imem_size); diff --git a/drivers/net/mdio/mdio-octeon.c b/drivers/net/mdio/mdio-octeon.c index 8ce99c4888e1..e096e68ac667 100644 --- a/drivers/net/mdio/mdio-octeon.c +++ b/drivers/net/mdio/mdio-octeon.c @@ -71,7 +71,6 @@ static int octeon_mdiobus_probe(struct platform_device *pdev) return 0; fail_register: - mdiobus_free(bus->mii_bus); smi_en.u64 = 0; oct_mdio_writeq(smi_en.u64, bus->register_base + SMI_EN); return err; @@ -85,7 +84,6 @@ static int octeon_mdiobus_remove(struct platform_device *pdev) bus = platform_get_drvdata(pdev); mdiobus_unregister(bus->mii_bus); - mdiobus_free(bus->mii_bus); smi_en.u64 = 0; oct_mdio_writeq(smi_en.u64, bus->register_base + SMI_EN); return 0; diff --git a/drivers/net/mdio/mdio-thunder.c b/drivers/net/mdio/mdio-thunder.c index cb1761693b69..822d2cdd2f35 100644 --- a/drivers/net/mdio/mdio-thunder.c +++ b/drivers/net/mdio/mdio-thunder.c @@ -126,7 +126,6 @@ static void thunder_mdiobus_pci_remove(struct pci_dev *pdev) continue; mdiobus_unregister(bus->mii_bus); - mdiobus_free(bus->mii_bus); oct_mdio_writeq(0, bus->register_base + SMI_EN); } pci_release_regions(pdev); diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index dadf75ff3ab9..6045ad3def12 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -607,7 +607,8 @@ void mdiobus_unregister(struct mii_bus *bus) struct mdio_device *mdiodev; int i; - BUG_ON(bus->state != MDIOBUS_REGISTERED); + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) + return; bus->state = MDIOBUS_UNREGISTERED; for (i = 0; i < PHY_MAX_ADDR; i++) { diff --git a/drivers/net/usb/cdc_eem.c b/drivers/net/usb/cdc_eem.c index 0eeec80bec31..2e60bc1b9a6b 100644 --- a/drivers/net/usb/cdc_eem.c +++ b/drivers/net/usb/cdc_eem.c @@ -26,7 +26,7 @@ * for transport over USB using a simpler USB device model than the * previous CDC "Ethernet Control Model" (ECM, or "CDC Ethernet"). * - * For details, see www.usb.org/developers/devclass_docs/CDC_EEM10.pdf + * For details, see https://usb.org/sites/default/files/CDC_EEM10.pdf * * This version has been tested with GIGAntIC WuaoW SIM Smart Card on 2.6.24, * 2.6.27 and 2.6.30rc2 kernel. diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 3ef4b2841402..5c779cc0ea11 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -1689,7 +1689,7 @@ static int hso_serial_tiocmset(struct tty_struct *tty, spin_unlock_irqrestore(&serial->serial_lock, flags); return usb_control_msg(serial->parent->usb, - usb_rcvctrlpipe(serial->parent->usb, 0), 0x22, + usb_sndctrlpipe(serial->parent->usb, 0), 0x22, 0x21, val, if_num, NULL, 0, USB_CTRL_SET_TIMEOUT); } @@ -2436,7 +2436,7 @@ static int hso_rfkill_set_block(void *data, bool blocked) if (hso_dev->usb_gone) rv = 0; else - rv = usb_control_msg(hso_dev->usb, usb_rcvctrlpipe(hso_dev->usb, 0), + rv = usb_control_msg(hso_dev->usb, usb_sndctrlpipe(hso_dev->usb, 0), enabled ? 0x82 : 0x81, 0x40, 0, 0, NULL, 0, USB_CTRL_SET_TIMEOUT); mutex_unlock(&hso_dev->mutex); @@ -2618,32 +2618,31 @@ static struct hso_device *hso_create_bulk_serial_device( num_urbs = 2; serial->tiocmget = kzalloc(sizeof(struct hso_tiocmget), GFP_KERNEL); + if (!serial->tiocmget) + goto exit; serial->tiocmget->serial_state_notification = kzalloc(sizeof(struct hso_serial_state_notification), GFP_KERNEL); - /* it isn't going to break our heart if serial->tiocmget - * allocation fails don't bother checking this. - */ - if (serial->tiocmget && serial->tiocmget->serial_state_notification) { - tiocmget = serial->tiocmget; - tiocmget->endp = hso_get_ep(interface, - USB_ENDPOINT_XFER_INT, - USB_DIR_IN); - if (!tiocmget->endp) { - dev_err(&interface->dev, "Failed to find INT IN ep\n"); - goto exit; - } - - tiocmget->urb = usb_alloc_urb(0, GFP_KERNEL); - if (tiocmget->urb) { - mutex_init(&tiocmget->mutex); - init_waitqueue_head(&tiocmget->waitq); - } else - hso_free_tiomget(serial); + if (!serial->tiocmget->serial_state_notification) + goto exit; + tiocmget = serial->tiocmget; + tiocmget->endp = hso_get_ep(interface, + USB_ENDPOINT_XFER_INT, + USB_DIR_IN); + if (!tiocmget->endp) { + dev_err(&interface->dev, "Failed to find INT IN ep\n"); + goto exit; } - } - else + + tiocmget->urb = usb_alloc_urb(0, GFP_KERNEL); + if (!tiocmget->urb) + goto exit; + + mutex_init(&tiocmget->mutex); + init_waitqueue_head(&tiocmget->waitq); + } else { num_urbs = 1; + } if (hso_serial_common_create(serial, num_urbs, BULK_URB_RX_SIZE, BULK_URB_TX_SIZE)) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 6acc5e904518..02bce40a67e5 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1645,6 +1645,7 @@ static const struct ethtool_ops lan78xx_ethtool_ops = { .get_strings = lan78xx_get_strings, .get_wol = lan78xx_get_wol, .set_wol = lan78xx_set_wol, + .get_ts_info = ethtool_op_get_ts_info, .get_eee = lan78xx_get_eee, .set_eee = lan78xx_set_eee, .get_pauseparam = lan78xx_get_pause, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 136ea06540ff..f6abb2fbf972 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -8107,6 +8107,37 @@ static void r8156b_init(struct r8152 *tp) tp->coalesce = 15000; /* 15 us */ } +static bool rtl_check_vendor_ok(struct usb_interface *intf) +{ + struct usb_host_interface *alt = intf->cur_altsetting; + struct usb_endpoint_descriptor *in, *out, *intr; + + if (usb_find_common_endpoints(alt, &in, &out, &intr, NULL) < 0) { + dev_err(&intf->dev, "Expected endpoints are not found\n"); + return false; + } + + /* Check Rx endpoint address */ + if (usb_endpoint_num(in) != 1) { + dev_err(&intf->dev, "Invalid Rx endpoint address\n"); + return false; + } + + /* Check Tx endpoint address */ + if (usb_endpoint_num(out) != 2) { + dev_err(&intf->dev, "Invalid Tx endpoint address\n"); + return false; + } + + /* Check interrupt endpoint address */ + if (usb_endpoint_num(intr) != 3) { + dev_err(&intf->dev, "Invalid interrupt endpoint address\n"); + return false; + } + + return true; +} + static bool rtl_vendor_mode(struct usb_interface *intf) { struct usb_host_interface *alt = intf->cur_altsetting; @@ -8115,12 +8146,15 @@ static bool rtl_vendor_mode(struct usb_interface *intf) int i, num_configs; if (alt->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC) - return true; + return rtl_check_vendor_ok(intf); /* The vendor mode is not always config #1, so to find it out. */ udev = interface_to_usbdev(intf); c = udev->config; num_configs = udev->descriptor.bNumConfigurations; + if (num_configs < 2) + return false; + for (i = 0; i < num_configs; (i++, c++)) { struct usb_interface_descriptor *desc = NULL; @@ -8135,7 +8169,8 @@ static bool rtl_vendor_mode(struct usb_interface *intf) } } - WARN_ON_ONCE(i == num_configs); + if (i == num_configs) + dev_err(&intf->dev, "Unexpected Device\n"); return false; } @@ -9381,9 +9416,6 @@ static int rtl8152_probe(struct usb_interface *intf, if (!rtl_vendor_mode(intf)) return -ENODEV; - if (intf->cur_altsetting->desc.bNumEndpoints < 3) - return -ENODEV; - usb_reset_device(udev); netdev = alloc_etherdev(sizeof(struct r8152)); if (!netdev) { diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index f8cdabb9ef5a..b286993da67c 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -1483,7 +1483,7 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) ret = smsc75xx_wait_ready(dev, 0); if (ret < 0) { netdev_warn(dev->net, "device not ready in smsc75xx_bind\n"); - return ret; + goto err; } smsc75xx_init_mac_address(dev); @@ -1492,7 +1492,7 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) ret = smsc75xx_reset(dev); if (ret < 0) { netdev_warn(dev->net, "smsc75xx_reset error %d\n", ret); - return ret; + goto err; } dev->net->netdev_ops = &smsc75xx_netdev_ops; @@ -1502,6 +1502,10 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; dev->net->max_mtu = MAX_SINGLE_PACKET_SIZE; return 0; + +err: + kfree(pdata); + return ret; } static void smsc75xx_unbind(struct usbnet *dev, struct usb_interface *intf) diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h index 956157946106..dbc8aef82a65 100644 --- a/drivers/net/wireless/ath/ath10k/htt.h +++ b/drivers/net/wireless/ath/ath10k/htt.h @@ -845,6 +845,7 @@ enum htt_security_types { #define ATH10K_HTT_TXRX_PEER_SECURITY_MAX 2 #define ATH10K_TXRX_NUM_EXT_TIDS 19 +#define ATH10K_TXRX_NON_QOS_TID 16 enum htt_security_flags { #define HTT_SECURITY_TYPE_MASK 0x7F diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index 1a08156d5011..7ffb5d5b2a70 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -1746,16 +1746,97 @@ static void ath10k_htt_rx_h_csum_offload(struct sk_buff *msdu) msdu->ip_summed = ath10k_htt_rx_get_csum_state(msdu); } +static u64 ath10k_htt_rx_h_get_pn(struct ath10k *ar, struct sk_buff *skb, + u16 offset, + enum htt_rx_mpdu_encrypt_type enctype) +{ + struct ieee80211_hdr *hdr; + u64 pn = 0; + u8 *ehdr; + + hdr = (struct ieee80211_hdr *)(skb->data + offset); + ehdr = skb->data + offset + ieee80211_hdrlen(hdr->frame_control); + + if (enctype == HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2) { + pn = ehdr[0]; + pn |= (u64)ehdr[1] << 8; + pn |= (u64)ehdr[4] << 16; + pn |= (u64)ehdr[5] << 24; + pn |= (u64)ehdr[6] << 32; + pn |= (u64)ehdr[7] << 40; + } + return pn; +} + +static bool ath10k_htt_rx_h_frag_multicast_check(struct ath10k *ar, + struct sk_buff *skb, + u16 offset) +{ + struct ieee80211_hdr *hdr; + + hdr = (struct ieee80211_hdr *)(skb->data + offset); + return !is_multicast_ether_addr(hdr->addr1); +} + +static bool ath10k_htt_rx_h_frag_pn_check(struct ath10k *ar, + struct sk_buff *skb, + u16 peer_id, + u16 offset, + enum htt_rx_mpdu_encrypt_type enctype) +{ + struct ath10k_peer *peer; + union htt_rx_pn_t *last_pn, new_pn = {0}; + struct ieee80211_hdr *hdr; + bool more_frags; + u8 tid, frag_number; + u32 seq; + + peer = ath10k_peer_find_by_id(ar, peer_id); + if (!peer) { + ath10k_dbg(ar, ATH10K_DBG_HTT, "invalid peer for frag pn check\n"); + return false; + } + + hdr = (struct ieee80211_hdr *)(skb->data + offset); + if (ieee80211_is_data_qos(hdr->frame_control)) + tid = ieee80211_get_tid(hdr); + else + tid = ATH10K_TXRX_NON_QOS_TID; + + last_pn = &peer->frag_tids_last_pn[tid]; + new_pn.pn48 = ath10k_htt_rx_h_get_pn(ar, skb, offset, enctype); + more_frags = ieee80211_has_morefrags(hdr->frame_control); + frag_number = le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_FRAG; + seq = (__le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_SEQ) >> 4; + + if (frag_number == 0) { + last_pn->pn48 = new_pn.pn48; + peer->frag_tids_seq[tid] = seq; + } else { + if (seq != peer->frag_tids_seq[tid]) + return false; + + if (new_pn.pn48 != last_pn->pn48 + 1) + return false; + + last_pn->pn48 = new_pn.pn48; + } + + return true; +} + static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, struct sk_buff_head *amsdu, struct ieee80211_rx_status *status, bool fill_crypt_header, u8 *rx_hdr, - enum ath10k_pkt_rx_err *err) + enum ath10k_pkt_rx_err *err, + u16 peer_id, + bool frag) { struct sk_buff *first; struct sk_buff *last; - struct sk_buff *msdu; + struct sk_buff *msdu, *temp; struct htt_rx_desc *rxd; struct ieee80211_hdr *hdr; enum htt_rx_mpdu_encrypt_type enctype; @@ -1768,6 +1849,7 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, bool is_decrypted; bool is_mgmt; u32 attention; + bool frag_pn_check = true, multicast_check = true; if (skb_queue_empty(amsdu)) return; @@ -1866,7 +1948,37 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, } skb_queue_walk(amsdu, msdu) { + if (frag && !fill_crypt_header && is_decrypted && + enctype == HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2) + frag_pn_check = ath10k_htt_rx_h_frag_pn_check(ar, + msdu, + peer_id, + 0, + enctype); + + if (frag) + multicast_check = ath10k_htt_rx_h_frag_multicast_check(ar, + msdu, + 0); + + if (!frag_pn_check || !multicast_check) { + /* Discard the fragment with invalid PN or multicast DA + */ + temp = msdu->prev; + __skb_unlink(msdu, amsdu); + dev_kfree_skb_any(msdu); + msdu = temp; + frag_pn_check = true; + multicast_check = true; + continue; + } + ath10k_htt_rx_h_csum_offload(msdu); + + if (frag && !fill_crypt_header && + enctype == HTT_RX_MPDU_ENCRYPT_TKIP_WPA) + status->flag &= ~RX_FLAG_MMIC_STRIPPED; + ath10k_htt_rx_h_undecap(ar, msdu, status, first_hdr, enctype, is_decrypted); @@ -1884,6 +1996,11 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, hdr = (void *)msdu->data; hdr->frame_control &= ~__cpu_to_le16(IEEE80211_FCTL_PROTECTED); + + if (frag && !fill_crypt_header && + enctype == HTT_RX_MPDU_ENCRYPT_TKIP_WPA) + status->flag &= ~RX_FLAG_IV_STRIPPED & + ~RX_FLAG_MMIC_STRIPPED; } } @@ -1991,14 +2108,62 @@ static void ath10k_htt_rx_h_unchain(struct ath10k *ar, ath10k_unchain_msdu(amsdu, unchain_cnt); } +static bool ath10k_htt_rx_validate_amsdu(struct ath10k *ar, + struct sk_buff_head *amsdu) +{ + u8 *subframe_hdr; + struct sk_buff *first; + bool is_first, is_last; + struct htt_rx_desc *rxd; + struct ieee80211_hdr *hdr; + size_t hdr_len, crypto_len; + enum htt_rx_mpdu_encrypt_type enctype; + int bytes_aligned = ar->hw_params.decap_align_bytes; + + first = skb_peek(amsdu); + + rxd = (void *)first->data - sizeof(*rxd); + hdr = (void *)rxd->rx_hdr_status; + + is_first = !!(rxd->msdu_end.common.info0 & + __cpu_to_le32(RX_MSDU_END_INFO0_FIRST_MSDU)); + is_last = !!(rxd->msdu_end.common.info0 & + __cpu_to_le32(RX_MSDU_END_INFO0_LAST_MSDU)); + + /* Return in case of non-aggregated msdu */ + if (is_first && is_last) + return true; + + /* First msdu flag is not set for the first msdu of the list */ + if (!is_first) + return false; + + enctype = MS(__le32_to_cpu(rxd->mpdu_start.info0), + RX_MPDU_START_INFO0_ENCRYPT_TYPE); + + hdr_len = ieee80211_hdrlen(hdr->frame_control); + crypto_len = ath10k_htt_rx_crypto_param_len(ar, enctype); + + subframe_hdr = (u8 *)hdr + round_up(hdr_len, bytes_aligned) + + crypto_len; + + /* Validate if the amsdu has a proper first subframe. + * There are chances a single msdu can be received as amsdu when + * the unauthenticated amsdu flag of a QoS header + * gets flipped in non-SPP AMSDU's, in such cases the first + * subframe has llc/snap header in place of a valid da. + * return false if the da matches rfc1042 pattern + */ + if (ether_addr_equal(subframe_hdr, rfc1042_header)) + return false; + + return true; +} + static bool ath10k_htt_rx_amsdu_allowed(struct ath10k *ar, struct sk_buff_head *amsdu, struct ieee80211_rx_status *rx_status) { - /* FIXME: It might be a good idea to do some fuzzy-testing to drop - * invalid/dangerous frames. - */ - if (!rx_status->freq) { ath10k_dbg(ar, ATH10K_DBG_HTT, "no channel configured; ignoring frame(s)!\n"); return false; @@ -2009,6 +2174,11 @@ static bool ath10k_htt_rx_amsdu_allowed(struct ath10k *ar, return false; } + if (!ath10k_htt_rx_validate_amsdu(ar, amsdu)) { + ath10k_dbg(ar, ATH10K_DBG_HTT, "invalid amsdu received\n"); + return false; + } + return true; } @@ -2071,7 +2241,8 @@ static int ath10k_htt_rx_handle_amsdu(struct ath10k_htt *htt) ath10k_htt_rx_h_unchain(ar, &amsdu, &drop_cnt, &unchain_cnt); ath10k_htt_rx_h_filter(ar, &amsdu, rx_status, &drop_cnt_filter); - ath10k_htt_rx_h_mpdu(ar, &amsdu, rx_status, true, first_hdr, &err); + ath10k_htt_rx_h_mpdu(ar, &amsdu, rx_status, true, first_hdr, &err, 0, + false); msdus_to_queue = skb_queue_len(&amsdu); ath10k_htt_rx_h_enqueue(ar, &amsdu, rx_status); @@ -2204,6 +2375,11 @@ static bool ath10k_htt_rx_proc_rx_ind_hl(struct ath10k_htt *htt, fw_desc = &rx->fw_desc; rx_desc_len = fw_desc->len; + if (fw_desc->u.bits.discard) { + ath10k_dbg(ar, ATH10K_DBG_HTT, "htt discard mpdu\n"); + goto err; + } + /* I have not yet seen any case where num_mpdu_ranges > 1. * qcacld does not seem handle that case either, so we introduce the * same limitiation here as well. @@ -2509,6 +2685,13 @@ static bool ath10k_htt_rx_proc_rx_frag_ind_hl(struct ath10k_htt *htt, rx_desc = (struct htt_hl_rx_desc *)(skb->data + tot_hdr_len); rx_desc_info = __le32_to_cpu(rx_desc->info); + hdr = (struct ieee80211_hdr *)((u8 *)rx_desc + rx_hl->fw_desc.len); + + if (is_multicast_ether_addr(hdr->addr1)) { + /* Discard the fragment with multicast DA */ + goto err; + } + if (!MS(rx_desc_info, HTT_RX_DESC_HL_INFO_ENCRYPTED)) { spin_unlock_bh(&ar->data_lock); return ath10k_htt_rx_proc_rx_ind_hl(htt, &resp->rx_ind_hl, skb, @@ -2516,8 +2699,6 @@ static bool ath10k_htt_rx_proc_rx_frag_ind_hl(struct ath10k_htt *htt, HTT_RX_NON_TKIP_MIC); } - hdr = (struct ieee80211_hdr *)((u8 *)rx_desc + rx_hl->fw_desc.len); - if (ieee80211_has_retry(hdr->frame_control)) goto err; @@ -3027,7 +3208,7 @@ static int ath10k_htt_rx_in_ord_ind(struct ath10k *ar, struct sk_buff *skb) ath10k_htt_rx_h_ppdu(ar, &amsdu, status, vdev_id); ath10k_htt_rx_h_filter(ar, &amsdu, status, NULL); ath10k_htt_rx_h_mpdu(ar, &amsdu, status, false, NULL, - NULL); + NULL, peer_id, frag); ath10k_htt_rx_h_enqueue(ar, &amsdu, status); break; case -EAGAIN: diff --git a/drivers/net/wireless/ath/ath10k/rx_desc.h b/drivers/net/wireless/ath/ath10k/rx_desc.h index f2b6bf8f0d60..705b6295e466 100644 --- a/drivers/net/wireless/ath/ath10k/rx_desc.h +++ b/drivers/net/wireless/ath/ath10k/rx_desc.h @@ -1282,7 +1282,19 @@ struct fw_rx_desc_base { #define FW_RX_DESC_UDP (1 << 6) struct fw_rx_desc_hl { - u8 info0; + union { + struct { + u8 discard:1, + forward:1, + any_err:1, + dup_err:1, + reserved:1, + inspect:1, + extension:2; + } bits; + u8 info0; + } u; + u8 version; u8 len; u8 flags; diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index 1d9aa1bb6b6e..603d2f93ac18 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -260,6 +260,16 @@ static void ath11k_dp_rxdesc_set_msdu_len(struct ath11k_base *ab, ab->hw_params.hw_ops->rx_desc_set_msdu_len(desc, len); } +static bool ath11k_dp_rx_h_attn_is_mcbc(struct ath11k_base *ab, + struct hal_rx_desc *desc) +{ + struct rx_attention *attn = ath11k_dp_rx_get_attention(ab, desc); + + return ath11k_dp_rx_h_msdu_end_first_msdu(ab, desc) && + (!!FIELD_GET(RX_ATTENTION_INFO1_MCAST_BCAST, + __le32_to_cpu(attn->info1))); +} + static void ath11k_dp_service_mon_ring(struct timer_list *t) { struct ath11k_base *ab = from_timer(ab, t, mon_reap_timer); @@ -852,6 +862,24 @@ static void ath11k_dp_rx_frags_cleanup(struct dp_rx_tid *rx_tid, bool rel_link_d __skb_queue_purge(&rx_tid->rx_frags); } +void ath11k_peer_frags_flush(struct ath11k *ar, struct ath11k_peer *peer) +{ + struct dp_rx_tid *rx_tid; + int i; + + lockdep_assert_held(&ar->ab->base_lock); + + for (i = 0; i <= IEEE80211_NUM_TIDS; i++) { + rx_tid = &peer->rx_tid[i]; + + spin_unlock_bh(&ar->ab->base_lock); + del_timer_sync(&rx_tid->frag_timer); + spin_lock_bh(&ar->ab->base_lock); + + ath11k_dp_rx_frags_cleanup(rx_tid, true); + } +} + void ath11k_peer_rx_tid_cleanup(struct ath11k *ar, struct ath11k_peer *peer) { struct dp_rx_tid *rx_tid; @@ -3450,6 +3478,7 @@ static int ath11k_dp_rx_frag_h_mpdu(struct ath11k *ar, u8 tid; int ret = 0; bool more_frags; + bool is_mcbc; rx_desc = (struct hal_rx_desc *)msdu->data; peer_id = ath11k_dp_rx_h_mpdu_start_peer_id(ar->ab, rx_desc); @@ -3457,6 +3486,11 @@ static int ath11k_dp_rx_frag_h_mpdu(struct ath11k *ar, seqno = ath11k_dp_rx_h_mpdu_start_seq_no(ar->ab, rx_desc); frag_no = ath11k_dp_rx_h_mpdu_start_frag_no(ar->ab, msdu); more_frags = ath11k_dp_rx_h_mpdu_start_more_frags(ar->ab, msdu); + is_mcbc = ath11k_dp_rx_h_attn_is_mcbc(ar->ab, rx_desc); + + /* Multicast/Broadcast fragments are not expected */ + if (is_mcbc) + return -EINVAL; if (!ath11k_dp_rx_h_mpdu_start_seq_ctrl_valid(ar->ab, rx_desc) || !ath11k_dp_rx_h_mpdu_start_fc_valid(ar->ab, rx_desc) || diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.h b/drivers/net/wireless/ath/ath11k/dp_rx.h index bf399312b5ff..623da3bf9dc8 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.h +++ b/drivers/net/wireless/ath/ath11k/dp_rx.h @@ -49,6 +49,7 @@ int ath11k_dp_peer_rx_pn_replay_config(struct ath11k_vif *arvif, const u8 *peer_addr, enum set_key_cmd key_cmd, struct ieee80211_key_conf *key); +void ath11k_peer_frags_flush(struct ath11k *ar, struct ath11k_peer *peer); void ath11k_peer_rx_tid_cleanup(struct ath11k *ar, struct ath11k_peer *peer); void ath11k_peer_rx_tid_delete(struct ath11k *ar, struct ath11k_peer *peer, u8 tid); diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 4df425dd31a2..9d0ff150ec30 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -2779,6 +2779,12 @@ static int ath11k_mac_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, */ spin_lock_bh(&ab->base_lock); peer = ath11k_peer_find(ab, arvif->vdev_id, peer_addr); + + /* flush the fragments cache during key (re)install to + * ensure all frags in the new frag list belong to the same key. + */ + if (peer && cmd == SET_KEY) + ath11k_peer_frags_flush(ar, peer); spin_unlock_bh(&ab->base_lock); if (!peer) { diff --git a/drivers/nfc/nfcmrvl/fw_dnld.h b/drivers/nfc/nfcmrvl/fw_dnld.h index ee4a339c05fd..058ce77b3cbc 100644 --- a/drivers/nfc/nfcmrvl/fw_dnld.h +++ b/drivers/nfc/nfcmrvl/fw_dnld.h @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC driver: Firmware downloader * * Copyright (C) 2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index 18cd96284b77..c5420616b7bc 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC-over-I2C driver: I2C interface related functions * * Copyright (C) 2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/nfcmrvl.h b/drivers/nfc/nfcmrvl/nfcmrvl.h index de68ff45e49a..e84ee18c73ae 100644 --- a/drivers/nfc/nfcmrvl/nfcmrvl.h +++ b/drivers/nfc/nfcmrvl/nfcmrvl.h @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC driver * * Copyright (C) 2014-2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/spi.c b/drivers/nfc/nfcmrvl/spi.c index 8e0ddb434770..dec0d3eb3648 100644 --- a/drivers/nfc/nfcmrvl/spi.c +++ b/drivers/nfc/nfcmrvl/spi.c @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC-over-SPI driver: SPI interface related functions * * Copyright (C) 2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c index e5a622ce4b95..7194dd7ef0f1 100644 --- a/drivers/nfc/nfcmrvl/uart.c +++ b/drivers/nfc/nfcmrvl/uart.c @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC-over-UART driver * * Copyright (C) 2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/usb.c b/drivers/nfc/nfcmrvl/usb.c index 888e298f610b..bcd563cb556c 100644 --- a/drivers/nfc/nfcmrvl/usb.c +++ b/drivers/nfc/nfcmrvl/usb.c @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC-over-USB driver: USB interface related functions * * Copyright (C) 2014, Marvell International Ltd. diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 530e5f90095e..0d1034e3ed0f 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -324,7 +324,7 @@ ptp_ocp_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (!bp->base) { dev_err(&pdev->dev, "io_remap bar0\n"); err = -ENOMEM; - goto out; + goto out_release_regions; } bp->reg = bp->base + OCP_REGISTER_OFFSET; bp->tod = bp->base + TOD_REGISTER_OFFSET; @@ -347,6 +347,8 @@ ptp_ocp_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; out: + pci_iounmap(pdev, bp->base); +out_release_regions: pci_release_regions(pdev); out_disable: pci_disable_device(pdev); diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 189e4385df40..dda5dc6f7737 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -15,6 +15,7 @@ #include <linux/mlx5/vport.h> #include <linux/mlx5/fs.h> #include <linux/mlx5/mlx5_ifc_vdpa.h> +#include <linux/mlx5/mpfs.h> #include "mlx5_vdpa.h" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); @@ -1859,11 +1860,16 @@ static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb static void mlx5_vdpa_free(struct vdpa_device *vdev) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_core_dev *pfmdev; struct mlx5_vdpa_net *ndev; ndev = to_mlx5_vdpa_ndev(mvdev); free_resources(ndev); + if (!is_zero_ether_addr(ndev->config.mac)) { + pfmdev = pci_get_drvdata(pci_physfn(mvdev->mdev->pdev)); + mlx5_mpfs_del_mac(pfmdev, ndev->config.mac); + } mlx5_vdpa_free_resources(&ndev->mvdev); mutex_destroy(&ndev->reslock); } @@ -1990,6 +1996,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name) { struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev); struct virtio_net_config *config; + struct mlx5_core_dev *pfmdev; struct mlx5_vdpa_dev *mvdev; struct mlx5_vdpa_net *ndev; struct mlx5_core_dev *mdev; @@ -2023,10 +2030,17 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name) if (err) goto err_mtu; + if (!is_zero_ether_addr(config->mac)) { + pfmdev = pci_get_drvdata(pci_physfn(mdev->pdev)); + err = mlx5_mpfs_add_mac(pfmdev, config->mac); + if (err) + goto err_mtu; + } + mvdev->vdev.dma_dev = mdev->device; err = mlx5_vdpa_alloc_resources(&ndev->mvdev); if (err) - goto err_mtu; + goto err_mpfs; err = alloc_resources(ndev); if (err) @@ -2044,6 +2058,9 @@ err_reg: free_resources(ndev); err_res: mlx5_vdpa_free_resources(&ndev->mvdev); +err_mpfs: + if (!is_zero_ether_addr(config->mac)) + mlx5_mpfs_del_mac(pfmdev, config->mac); err_mtu: mutex_destroy(&ndev->reslock); put_device(&mvdev->vdev.dev); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f8e8d7e90616..020a8f7fdbdd 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -703,6 +703,27 @@ struct mlx5_hv_vhca; #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity)) #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)) +enum { + MLX5_PROF_MASK_QP_SIZE = (u64)1 << 0, + MLX5_PROF_MASK_MR_CACHE = (u64)1 << 1, +}; + +enum { + MR_CACHE_LAST_STD_ENTRY = 20, + MLX5_IMR_MTT_CACHE_ENTRY, + MLX5_IMR_KSM_CACHE_ENTRY, + MAX_MR_CACHE_ENTRIES +}; + +struct mlx5_profile { + u64 mask; + u8 log_max_qp; + struct { + int size; + int limit; + } mr_cache[MAX_MR_CACHE_ENTRIES]; +}; + struct mlx5_core_dev { struct device *device; enum mlx5_coredev_type coredev_type; @@ -731,7 +752,7 @@ struct mlx5_core_dev { struct mutex intf_state_mutex; unsigned long intf_state; struct mlx5_priv priv; - struct mlx5_profile *profile; + struct mlx5_profile profile; u32 issi; struct mlx5e_resources mlx5e_res; struct mlx5_dm *dm; @@ -1083,18 +1104,6 @@ static inline u8 mlx5_mkey_variant(u32 mkey) return mkey & 0xff; } -enum { - MLX5_PROF_MASK_QP_SIZE = (u64)1 << 0, - MLX5_PROF_MASK_MR_CACHE = (u64)1 << 1, -}; - -enum { - MR_CACHE_LAST_STD_ENTRY = 20, - MLX5_IMR_MTT_CACHE_ENTRY, - MLX5_IMR_KSM_CACHE_ENTRY, - MAX_MR_CACHE_ENTRIES -}; - /* Async-atomic event notifier used by mlx5 core to forward FW * evetns recived from event queue to mlx5 consumers. * Optimise event queue dipatching. @@ -1148,15 +1157,6 @@ int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev, struct ib_device *device, struct rdma_netdev_alloc_params *params); -struct mlx5_profile { - u64 mask; - u8 log_max_qp; - struct { - int size; - int limit; - } mr_cache[MAX_MR_CACHE_ENTRIES]; -}; - enum { MLX5_PCI_DEV_IS_VF = 1 << 0, }; diff --git a/include/linux/mlx5/mpfs.h b/include/linux/mlx5/mpfs.h new file mode 100644 index 000000000000..bf700c8d5516 --- /dev/null +++ b/include/linux/mlx5/mpfs.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB + * Copyright (c) 2021 Mellanox Technologies Ltd. + */ + +#ifndef _MLX5_MPFS_ +#define _MLX5_MPFS_ + +struct mlx5_core_dev; + +#ifdef CONFIG_MLX5_MPFS +int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac); +int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac); +#else /* #ifndef CONFIG_MLX5_MPFS */ +static inline int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } +static inline int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } +#endif + +#endif diff --git a/include/linux/phy.h b/include/linux/phy.h index 60d2b26026a2..852743f07e3e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -496,6 +496,11 @@ struct macsec_ops; * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. + * Bits [15:0] are free to use by the PHY driver to communicate + * driver specific behavior. + * Bits [23:16] are currently reserved for future use. + * Bits [31:24] are reserved for defining generic + * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) * @phy_timer: The timer for handling the state machine * @phylink: Pointer to phylink instance for this PHY diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5224f885a99a..58c2cd417e89 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5760,7 +5760,7 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr); */ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, const u8 *addr, enum nl80211_iftype iftype, - u8 data_offset); + u8 data_offset, bool is_amsdu); /** * ieee80211_data_to_8023 - convert an 802.11 data frame to 802.3 @@ -5772,7 +5772,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, enum nl80211_iftype iftype) { - return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype, 0); + return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype, 0, false); } /** diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 51d8eb99764d..48ef7460ff30 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -157,7 +157,6 @@ enum nf_flow_flags { NF_FLOW_HW, NF_FLOW_HW_DYING, NF_FLOW_HW_DEAD, - NF_FLOW_HW_REFRESH, NF_FLOW_HW_PENDING, }; diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index bd76e8e082c0..1df0f8074c9d 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -298,6 +298,7 @@ int nci_nfcc_loopback(struct nci_dev *ndev, void *data, size_t data_len, struct sk_buff **resp); struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev); +void nci_hci_deallocate(struct nci_dev *ndev); int nci_hci_send_event(struct nci_dev *ndev, u8 gate, u8 event, const u8 *param, size_t param_len); int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate, diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 255e4f4b521f..ec7823921bd2 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -709,6 +709,17 @@ tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common, cls_common->extack = extack; } +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) +static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb) +{ + struct tc_skb_ext *tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); + + if (tc_skb_ext) + memset(tc_skb_ext, 0, sizeof(*tc_skb_ext)); + return tc_skb_ext; +} +#endif + enum tc_matchall_command { TC_CLSMATCHALL_REPLACE, TC_CLSMATCHALL_DESTROY, diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index f5c1bee0cd6a..6d7b12cba015 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -128,12 +128,7 @@ void __qdisc_run(struct Qdisc *q); static inline void qdisc_run(struct Qdisc *q) { if (qdisc_run_begin(q)) { - /* NOLOCK qdisc must check 'state' under the qdisc seqlock - * to avoid racing with dev_qdisc_reset() - */ - if (!(q->flags & TCQ_F_NOLOCK) || - likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) - __qdisc_run(q); + __qdisc_run(q); qdisc_run_end(q); } } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index f7a6e14491fb..1e625519ae96 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -36,6 +36,7 @@ struct qdisc_rate_table { enum qdisc_state_t { __QDISC_STATE_SCHED, __QDISC_STATE_DEACTIVATED, + __QDISC_STATE_MISSED, }; struct qdisc_size_table { @@ -159,8 +160,33 @@ static inline bool qdisc_is_empty(const struct Qdisc *qdisc) static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { + if (spin_trylock(&qdisc->seqlock)) + goto nolock_empty; + + /* If the MISSED flag is set, it means other thread has + * set the MISSED flag before second spin_trylock(), so + * we can return false here to avoid multi cpus doing + * the set_bit() and second spin_trylock() concurrently. + */ + if (test_bit(__QDISC_STATE_MISSED, &qdisc->state)) + return false; + + /* Set the MISSED flag before the second spin_trylock(), + * if the second spin_trylock() return false, it means + * other cpu holding the lock will do dequeuing for us + * or it will see the MISSED flag set after releasing + * lock and reschedule the net_tx_action() to do the + * dequeuing. + */ + set_bit(__QDISC_STATE_MISSED, &qdisc->state); + + /* Retry again in case other CPU may not see the new flag + * after it releases the lock at the end of qdisc_run_end(). + */ if (!spin_trylock(&qdisc->seqlock)) return false; + +nolock_empty: WRITE_ONCE(qdisc->empty, false); } else if (qdisc_is_running(qdisc)) { return false; @@ -176,8 +202,15 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) static inline void qdisc_run_end(struct Qdisc *qdisc) { write_seqcount_end(&qdisc->running); - if (qdisc->flags & TCQ_F_NOLOCK) + if (qdisc->flags & TCQ_F_NOLOCK) { spin_unlock(&qdisc->seqlock); + + if (unlikely(test_bit(__QDISC_STATE_MISSED, + &qdisc->state))) { + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + __netif_schedule(qdisc); + } + } } static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) diff --git a/include/net/sock.h b/include/net/sock.h index 42bc5e1a627f..0e962d8bc73b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2231,13 +2231,15 @@ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) sk_mem_charge(sk, skb->truesize); } -static inline void skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk) +static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk) { if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) { skb_orphan(skb); skb->destructor = sock_efree; skb->sk = sk; + return true; } + return false; } void sk_reset_timer(struct sock *sk, struct timer_list *timer, diff --git a/init/Kconfig b/init/Kconfig index 1ea12c64e4c9..a61c92066c2e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -442,6 +442,7 @@ config AUDITSYSCALL source "kernel/irq/Kconfig" source "kernel/time/Kconfig" +source "kernel/bpf/Kconfig" source "kernel/Kconfig.preempt" menu "CPU/Task time and stats accounting" @@ -1713,46 +1714,6 @@ config KALLSYMS_BASE_RELATIVE # syscall, maps, verifier -config BPF_LSM - bool "LSM Instrumentation with BPF" - depends on BPF_EVENTS - depends on BPF_SYSCALL - depends on SECURITY - depends on BPF_JIT - help - Enables instrumentation of the security hooks with eBPF programs for - implementing dynamic MAC and Audit Policies. - - If you are unsure how to answer this question, answer N. - -config BPF_SYSCALL - bool "Enable bpf() system call" - select BPF - select IRQ_WORK - select TASKS_TRACE_RCU - select BINARY_PRINTF - select NET_SOCK_MSG if INET - default n - help - Enable the bpf() system call that allows to manipulate eBPF - programs and maps via file descriptors. - -config ARCH_WANT_DEFAULT_BPF_JIT - bool - -config BPF_JIT_ALWAYS_ON - bool "Permanently enable BPF JIT and remove BPF interpreter" - depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT - help - Enables BPF JIT and removes BPF interpreter to avoid - speculative execution of BPF instructions by the interpreter - -config BPF_JIT_DEFAULT_ON - def_bool ARCH_WANT_DEFAULT_BPF_JIT || BPF_JIT_ALWAYS_ON - depends on HAVE_EBPF_JIT && BPF_JIT - -source "kernel/bpf/preload/Kconfig" - config USERFAULTFD bool "Enable userfaultfd() system call" depends on MMU diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig new file mode 100644 index 000000000000..bd04f4a44c01 --- /dev/null +++ b/kernel/bpf/Kconfig @@ -0,0 +1,89 @@ +# SPDX-License-Identifier: GPL-2.0-only + +# BPF interpreter that, for example, classic socket filters depend on. +config BPF + bool + +# Used by archs to tell that they support BPF JIT compiler plus which +# flavour. Only one of the two can be selected for a specific arch since +# eBPF JIT supersedes the cBPF JIT. + +# Classic BPF JIT (cBPF) +config HAVE_CBPF_JIT + bool + +# Extended BPF JIT (eBPF) +config HAVE_EBPF_JIT + bool + +# Used by archs to tell that they want the BPF JIT compiler enabled by +# default for kernels that were compiled with BPF JIT support. +config ARCH_WANT_DEFAULT_BPF_JIT + bool + +menu "BPF subsystem" + +config BPF_SYSCALL + bool "Enable bpf() system call" + select BPF + select IRQ_WORK + select TASKS_TRACE_RCU + select BINARY_PRINTF + select NET_SOCK_MSG if INET + default n + help + Enable the bpf() system call that allows to manipulate BPF programs + and maps via file descriptors. + +config BPF_JIT + bool "Enable BPF Just In Time compiler" + depends on BPF + depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT + depends on MODULES + help + BPF programs are normally handled by a BPF interpreter. This option + allows the kernel to generate native code when a program is loaded + into the kernel. This will significantly speed-up processing of BPF + programs. + + Note, an admin should enable this feature changing: + /proc/sys/net/core/bpf_jit_enable + /proc/sys/net/core/bpf_jit_harden (optional) + /proc/sys/net/core/bpf_jit_kallsyms (optional) + +config BPF_JIT_ALWAYS_ON + bool "Permanently enable BPF JIT and remove BPF interpreter" + depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT + help + Enables BPF JIT and removes BPF interpreter to avoid speculative + execution of BPF instructions by the interpreter. + +config BPF_JIT_DEFAULT_ON + def_bool ARCH_WANT_DEFAULT_BPF_JIT || BPF_JIT_ALWAYS_ON + depends on HAVE_EBPF_JIT && BPF_JIT + +config BPF_UNPRIV_DEFAULT_OFF + bool "Disable unprivileged BPF by default" + depends on BPF_SYSCALL + help + Disables unprivileged BPF by default by setting the corresponding + /proc/sys/kernel/unprivileged_bpf_disabled knob to 2. An admin can + still reenable it by setting it to 0 later on, or permanently + disable it by setting it to 1 (from which no other transition to + 0 is possible anymore). + +source "kernel/bpf/preload/Kconfig" + +config BPF_LSM + bool "Enable BPF LSM Instrumentation" + depends on BPF_EVENTS + depends on BPF_SYSCALL + depends on SECURITY + depends on BPF_JIT + help + Enables instrumentation of the security hooks with BPF programs for + implementing dynamic MAC and Audit Policies. + + If you are unsure how to answer this question, answer N. + +endmenu # "BPF subsystem" diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 5efb2b24012c..da471bf01b97 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -107,10 +107,12 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_inode_storage_get_proto; case BPF_FUNC_inode_storage_delete: return &bpf_inode_storage_delete_proto; +#ifdef CONFIG_NET case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; +#endif /* CONFIG_NET */ case BPF_FUNC_spin_lock: return &bpf_spin_lock_proto; case BPF_FUNC_spin_unlock: diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 0600ed325fa0..f982a9f0dbc4 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5206,6 +5206,12 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, m->ret_size = ret; for (i = 0; i < nargs; i++) { + if (i == nargs - 1 && args[i].type == 0) { + bpf_log(log, + "The function %s with variable args is unsupported.\n", + tname); + return -EINVAL; + } ret = __get_type_size(btf, args[i].type, &t); if (ret < 0) { bpf_log(log, @@ -5213,6 +5219,12 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, tname, i, btf_kind_str[BTF_INFO_KIND(t->info)]); return -EINVAL; } + if (ret == 0) { + bpf_log(log, + "The function %s has malformed void argument.\n", + tname); + return -EINVAL; + } m->arg_size[i] = ret; } m->nr_args = nargs; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 544773970dbc..73443498d88f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -692,38 +692,41 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype, return -EINVAL; } -/* Per-cpu temp buffers which can be used by printf-like helpers for %s or %p +/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary + * arguments representation. */ -#define MAX_PRINTF_BUF_LEN 512 +#define MAX_BPRINTF_BUF_LEN 512 -struct bpf_printf_buf { - char tmp_buf[MAX_PRINTF_BUF_LEN]; +/* Support executing three nested bprintf helper calls on a given CPU */ +#define MAX_BPRINTF_NEST_LEVEL 3 +struct bpf_bprintf_buffers { + char tmp_bufs[MAX_BPRINTF_NEST_LEVEL][MAX_BPRINTF_BUF_LEN]; }; -static DEFINE_PER_CPU(struct bpf_printf_buf, bpf_printf_buf); -static DEFINE_PER_CPU(int, bpf_printf_buf_used); +static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs); +static DEFINE_PER_CPU(int, bpf_bprintf_nest_level); static int try_get_fmt_tmp_buf(char **tmp_buf) { - struct bpf_printf_buf *bufs; - int used; + struct bpf_bprintf_buffers *bufs; + int nest_level; preempt_disable(); - used = this_cpu_inc_return(bpf_printf_buf_used); - if (WARN_ON_ONCE(used > 1)) { - this_cpu_dec(bpf_printf_buf_used); + nest_level = this_cpu_inc_return(bpf_bprintf_nest_level); + if (WARN_ON_ONCE(nest_level > MAX_BPRINTF_NEST_LEVEL)) { + this_cpu_dec(bpf_bprintf_nest_level); preempt_enable(); return -EBUSY; } - bufs = this_cpu_ptr(&bpf_printf_buf); - *tmp_buf = bufs->tmp_buf; + bufs = this_cpu_ptr(&bpf_bprintf_bufs); + *tmp_buf = bufs->tmp_bufs[nest_level - 1]; return 0; } void bpf_bprintf_cleanup(void) { - if (this_cpu_read(bpf_printf_buf_used)) { - this_cpu_dec(bpf_printf_buf_used); + if (this_cpu_read(bpf_bprintf_nest_level)) { + this_cpu_dec(bpf_bprintf_nest_level); preempt_enable(); } } @@ -760,7 +763,7 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, if (num_args && try_get_fmt_tmp_buf(&tmp_buf)) return -EBUSY; - tmp_buf_end = tmp_buf + MAX_PRINTF_BUF_LEN; + tmp_buf_end = tmp_buf + MAX_BPRINTF_BUF_LEN; *bin_args = (u32 *)tmp_buf; } diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index f25b719ac786..84b3b35fc0d0 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -221,25 +221,20 @@ static int ringbuf_map_get_next_key(struct bpf_map *map, void *key, return -ENOTSUPP; } -static size_t bpf_ringbuf_mmap_page_cnt(const struct bpf_ringbuf *rb) -{ - size_t data_pages = (rb->mask + 1) >> PAGE_SHIFT; - - /* consumer page + producer page + 2 x data pages */ - return RINGBUF_POS_PAGES + 2 * data_pages; -} - static int ringbuf_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) { struct bpf_ringbuf_map *rb_map; - size_t mmap_sz; rb_map = container_of(map, struct bpf_ringbuf_map, map); - mmap_sz = bpf_ringbuf_mmap_page_cnt(rb_map->rb) << PAGE_SHIFT; - - if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) > mmap_sz) - return -EINVAL; + if (vma->vm_flags & VM_WRITE) { + /* allow writable mapping for the consumer_pos only */ + if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) + return -EPERM; + } else { + vma->vm_flags &= ~VM_MAYWRITE; + } + /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); } @@ -315,6 +310,9 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) return NULL; len = round_up(size + BPF_RINGBUF_HDR_SZ, 8); + if (len > rb->mask + 1) + return NULL; + cons_pos = smp_load_acquire(&rb->consumer_pos); if (in_nmi()) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 941ca06d9dfa..ea04b0deb5ce 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -50,7 +50,8 @@ static DEFINE_SPINLOCK(map_idr_lock); static DEFINE_IDR(link_idr); static DEFINE_SPINLOCK(link_idr_lock); -int sysctl_unprivileged_bpf_disabled __read_mostly; +int sysctl_unprivileged_bpf_disabled __read_mostly = + IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 757476c91c98..94ba5163d4c5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6409,18 +6409,10 @@ enum { }; static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, - const struct bpf_reg_state *off_reg, - u32 *alu_limit, u8 opcode) + u32 *alu_limit, bool mask_to_left) { - bool off_is_neg = off_reg->smin_value < 0; - bool mask_to_left = (opcode == BPF_ADD && off_is_neg) || - (opcode == BPF_SUB && !off_is_neg); u32 max = 0, ptr_limit = 0; - if (!tnum_is_const(off_reg->var_off) && - (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) - return REASON_BOUNDS; - switch (ptr_reg->type) { case PTR_TO_STACK: /* Offset 0 is out-of-bounds, but acceptable start for the @@ -6486,15 +6478,20 @@ static bool sanitize_needed(u8 opcode) return opcode == BPF_ADD || opcode == BPF_SUB; } +struct bpf_sanitize_info { + struct bpf_insn_aux_data aux; + bool mask_to_left; +}; + static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg, struct bpf_reg_state *dst_reg, - struct bpf_insn_aux_data *tmp_aux, + struct bpf_sanitize_info *info, const bool commit_window) { - struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : tmp_aux; + struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : &info->aux; struct bpf_verifier_state *vstate = env->cur_state; bool off_is_imm = tnum_is_const(off_reg->var_off); bool off_is_neg = off_reg->smin_value < 0; @@ -6515,7 +6512,16 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, if (vstate->speculative) goto do_sim; - err = retrieve_ptr_limit(ptr_reg, off_reg, &alu_limit, opcode); + if (!commit_window) { + if (!tnum_is_const(off_reg->var_off) && + (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) + return REASON_BOUNDS; + + info->mask_to_left = (opcode == BPF_ADD && off_is_neg) || + (opcode == BPF_SUB && !off_is_neg); + } + + err = retrieve_ptr_limit(ptr_reg, &alu_limit, info->mask_to_left); if (err < 0) return err; @@ -6523,8 +6529,8 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, /* In commit phase we narrow the masking window based on * the observed pointer move after the simulated operation. */ - alu_state = tmp_aux->alu_state; - alu_limit = abs(tmp_aux->alu_limit - alu_limit); + alu_state = info->aux.alu_state; + alu_limit = abs(info->aux.alu_limit - alu_limit); } else { alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0; @@ -6539,8 +6545,12 @@ do_sim: /* If we're in commit phase, we're done here given we already * pushed the truncated dst_reg into the speculative verification * stack. + * + * Also, when register is a known constant, we rewrite register-based + * operation to immediate-based, and thus do not need masking (and as + * a consequence, do not need to simulate the zero-truncation either). */ - if (commit_window) + if (commit_window || off_is_imm) return 0; /* Simulate and find potential out-of-bounds access under @@ -6685,7 +6695,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value, umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value; - struct bpf_insn_aux_data tmp_aux = {}; + struct bpf_sanitize_info info = {}; u8 opcode = BPF_OP(insn->code); u32 dst = insn->dst_reg; int ret; @@ -6754,7 +6764,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg, - &tmp_aux, false); + &info, false); if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } @@ -6895,7 +6905,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg, - &tmp_aux, true); + &info, true); if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } @@ -7084,11 +7094,10 @@ static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, s32 smin_val = src_reg->s32_min_value; u32 umax_val = src_reg->u32_max_value; - /* Assuming scalar64_min_max_and will be called so its safe - * to skip updating register for known 32-bit case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get our minimum from the var_off, since that's inherently * bitwise. Our maximum is the minimum of the operands' maxima. @@ -7108,7 +7117,6 @@ static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } - } static void scalar_min_max_and(struct bpf_reg_state *dst_reg, @@ -7155,11 +7163,10 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, s32 smin_val = src_reg->s32_min_value; u32 umin_val = src_reg->u32_min_value; - /* Assuming scalar64_min_max_or will be called so it is safe - * to skip updating register for known case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get our maximum from the var_off, and our minimum is the * maximum of the operands' minima @@ -7224,11 +7231,10 @@ static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg, struct tnum var32_off = tnum_subreg(dst_reg->var_off); s32 smin_val = src_reg->s32_min_value; - /* Assuming scalar64_min_max_xor will be called so it is safe - * to skip updating register for known case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get both minimum and maximum from the var32_off. */ dst_reg->u32_min_value = var32_off.value; @@ -13200,6 +13206,17 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, return 0; } +BTF_SET_START(btf_id_deny) +BTF_ID_UNUSED +#ifdef CONFIG_SMP +BTF_ID(func, migrate_disable) +BTF_ID(func, migrate_enable) +#endif +#if !defined CONFIG_PREEMPT_RCU && !defined CONFIG_TINY_RCU +BTF_ID(func, rcu_read_unlock_strict) +#endif +BTF_SET_END(btf_id_deny) + static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; @@ -13259,6 +13276,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) ret = bpf_lsm_verify_prog(&env->log, prog); if (ret < 0) return ret; + } else if (prog->type == BPF_PROG_TYPE_TRACING && + btf_id_set_contains(&btf_id_deny, btf_id)) { + return -EINVAL; } key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id); @@ -13358,12 +13378,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; - if (bpf_prog_is_dev_bound(env->prog->aux)) { - ret = bpf_prog_offload_verifier_prep(env->prog); - if (ret) - goto skip_full_check; - } - env->explored_states = kvcalloc(state_htab_size(env), sizeof(struct bpf_verifier_state_list *), GFP_USER); @@ -13391,6 +13405,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, if (ret < 0) goto skip_full_check; + if (bpf_prog_is_dev_bound(env->prog->aux)) { + ret = bpf_prog_offload_verifier_prep(env->prog); + if (ret) + goto skip_full_check; + } + ret = check_cfg(env); if (ret < 0) goto skip_full_check; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 14edf84cc571..d4a78e08f6d8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -225,7 +225,27 @@ static int bpf_stats_handler(struct ctl_table *table, int write, mutex_unlock(&bpf_stats_enabled_mutex); return ret; } -#endif + +static int bpf_unpriv_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret, unpriv_enable = *(int *)table->data; + bool locked_state = unpriv_enable == 1; + struct ctl_table tmp = *table; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + tmp.data = &unpriv_enable; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret) { + if (locked_state && unpriv_enable != 1) + return -EPERM; + *(int *)table->data = unpriv_enable; + } + return ret; +} +#endif /* CONFIG_BPF_SYSCALL && CONFIG_SYSCTL */ /* * /proc/sys support @@ -2600,10 +2620,9 @@ static struct ctl_table kern_table[] = { .data = &sysctl_unprivileged_bpf_disabled, .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), .mode = 0644, - /* only handle a transition from default "0" to "1" */ - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ONE, - .extra2 = SYSCTL_ONE, + .proc_handler = bpf_unpriv_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = &two, }, { .procname = "bpf_stats_enabled", diff --git a/net/Kconfig b/net/Kconfig index f5ee7c65e6b4..c7392c449b25 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -302,21 +302,6 @@ config BQL select DQL default y -config BPF_JIT - bool "enable BPF Just In Time compiler" - depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT - depends on MODULES - help - Berkeley Packet Filter filtering capabilities are normally handled - by an interpreter. This option allows kernel to generate a native - code when filter is loaded in memory. This should speedup - packet sniffing (libpcap/tcpdump). - - Note, admin should enable this feature changing: - /proc/sys/net/core/bpf_jit_enable - /proc/sys/net/core/bpf_jit_harden (optional) - /proc/sys/net/core/bpf_jit_kallsyms (optional) - config BPF_STREAM_PARSER bool "enable BPF STREAM_PARSER" depends on INET @@ -470,15 +455,3 @@ config ETHTOOL_NETLINK e.g. notification messages. endif # if NET - -# Used by archs to tell that they support BPF JIT compiler plus which flavour. -# Only one of the two can be selected for a specific arch since eBPF JIT supersedes -# the cBPF JIT. - -# Classic BPF JIT (cBPF) -config HAVE_CBPF_JIT - bool - -# Extended BPF JIT (eBPF) -config HAVE_EBPF_JIT - bool diff --git a/net/can/isotp.c b/net/can/isotp.c index 9f94ad3caee9..253b24417c8e 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1062,27 +1062,31 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (len < ISOTP_MIN_NAMELEN) return -EINVAL; + if (addr->can_addr.tp.tx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) + return -EADDRNOTAVAIL; + + if (!addr->can_ifindex) + return -ENODEV; + + lock_sock(sk); + /* do not register frame reception for functional addressing */ if (so->opt.flags & CAN_ISOTP_SF_BROADCAST) do_rx_reg = 0; /* do not validate rx address for functional addressing */ if (do_rx_reg) { - if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id) - return -EADDRNOTAVAIL; + if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id) { + err = -EADDRNOTAVAIL; + goto out; + } - if (addr->can_addr.tp.rx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) - return -EADDRNOTAVAIL; + if (addr->can_addr.tp.rx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) { + err = -EADDRNOTAVAIL; + goto out; + } } - if (addr->can_addr.tp.tx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) - return -EADDRNOTAVAIL; - - if (!addr->can_ifindex) - return -ENODEV; - - lock_sock(sk); - if (so->bound && addr->can_ifindex == so->ifindex && addr->can_addr.tp.rx_id == so->rxid && addr->can_addr.tp.tx_id == so->txid) @@ -1164,16 +1168,13 @@ static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer) return ISOTP_MIN_NAMELEN; } -static int isotp_setsockopt(struct socket *sock, int level, int optname, +static int isotp_setsockopt_locked(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); int ret = 0; - if (level != SOL_CAN_ISOTP) - return -EINVAL; - if (so->bound) return -EISCONN; @@ -1248,6 +1249,22 @@ static int isotp_setsockopt(struct socket *sock, int level, int optname, return ret; } +static int isotp_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) + +{ + struct sock *sk = sock->sk; + int ret; + + if (level != SOL_CAN_ISOTP) + return -EINVAL; + + lock_sock(sk); + ret = isotp_setsockopt_locked(sock, level, optname, optval, optlen); + release_sock(sk); + return ret; +} + static int isotp_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { diff --git a/net/core/dev.c b/net/core/dev.c index 222b1d322c96..ef8cf7619baf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3853,7 +3853,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, if (q->flags & TCQ_F_NOLOCK) { rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - qdisc_run(q); + if (likely(!netif_xmit_frozen_or_stopped(txq))) + qdisc_run(q); if (unlikely(to_free)) kfree_skb_list(to_free); @@ -5025,25 +5026,43 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) sd->output_queue_tailp = &sd->output_queue; local_irq_enable(); + rcu_read_lock(); + while (head) { struct Qdisc *q = head; spinlock_t *root_lock = NULL; head = head->next_sched; - if (!(q->flags & TCQ_F_NOLOCK)) { - root_lock = qdisc_lock(q); - spin_lock(root_lock); - } /* We need to make sure head->next_sched is read * before clearing __QDISC_STATE_SCHED */ smp_mb__before_atomic(); + + if (!(q->flags & TCQ_F_NOLOCK)) { + root_lock = qdisc_lock(q); + spin_lock(root_lock); + } else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, + &q->state))) { + /* There is a synchronize_net() between + * STATE_DEACTIVATED flag being set and + * qdisc_reset()/some_qdisc_is_busy() in + * dev_deactivate(), so we can safely bail out + * early here to avoid data race between + * qdisc_deactivate() and some_qdisc_is_busy() + * for lockless qdisc. + */ + clear_bit(__QDISC_STATE_SCHED, &q->state); + continue; + } + clear_bit(__QDISC_STATE_SCHED, &q->state); qdisc_run(q); if (root_lock) spin_unlock(root_lock); } + + rcu_read_unlock(); } xfrm_dev_backlog(sd); diff --git a/net/core/filter.c b/net/core/filter.c index cae56d08a670..65ab4e21c087 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3784,6 +3784,7 @@ static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, __skb_push(skb, head_room); memset(skb->data, 0, head_room); skb_reset_mac_header(skb); + skb_reset_mac_len(skb); } return ret; diff --git a/net/core/sock.c b/net/core/sock.c index c761c4a0b66b..958614ea16ed 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2132,10 +2132,10 @@ void skb_orphan_partial(struct sk_buff *skb) if (skb_is_tcp_pure_ack(skb)) return; - if (can_skb_orphan_partial(skb)) - skb_set_owner_sk_safe(skb, skb->sk); - else - skb_orphan(skb); + if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk)) + return; + + skb_orphan(skb); } EXPORT_SYMBOL(skb_orphan_partial); diff --git a/net/dsa/master.c b/net/dsa/master.c index 052a977914a6..63adbc21a735 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -147,8 +147,7 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, struct dsa_switch *ds = cpu_dp->ds; int port = cpu_dp->index; int len = ETH_GSTRING_LEN; - int mcount = 0, count; - unsigned int i; + int mcount = 0, count, i; uint8_t pfx[4]; uint8_t *ndata; @@ -178,6 +177,8 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, */ ds->ops->get_strings(ds, port, stringset, ndata); count = ds->ops->get_sset_count(ds, port, stringset); + if (count < 0) + return; for (i = 0; i < count; i++) { memmove(ndata + (i * len + sizeof(pfx)), ndata + i * len, len - sizeof(pfx)); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 8c0f3c6ab365..d4756b920108 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -776,13 +776,15 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { - int count; + int count = 0; - count = 4; - if (ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds, dp->index, sset); + if (ds->ops->get_sset_count) { + count = ds->ops->get_sset_count(ds, dp->index, sset); + if (count < 0) + return count; + } - return count; + return count + 4; } else if (sset == ETH_SS_TEST) { return net_selftest_get_count(); } diff --git a/net/ethtool/stats.c b/net/ethtool/stats.c index b7642dc96d50..ec07f5765e03 100644 --- a/net/ethtool/stats.c +++ b/net/ethtool/stats.c @@ -119,7 +119,7 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base, */ memset(&data->phy_stats, 0xff, sizeof(data->phy_stats)); memset(&data->mac_stats, 0xff, sizeof(data->mac_stats)); - memset(&data->ctrl_stats, 0xff, sizeof(data->mac_stats)); + memset(&data->ctrl_stats, 0xff, sizeof(data->ctrl_stats)); memset(&data->rmon_stats, 0xff, sizeof(data->rmon_stats)); if (test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask) && diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index bfcdc75fc01e..26c32407f029 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -218,6 +218,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) if (master) { skb->dev = master->dev; skb_reset_mac_header(skb); + skb_reset_mac_len(skb); hsr_forward_skb(skb, master); } else { atomic_long_inc(&dev->tx_dropped); @@ -259,6 +260,7 @@ static struct sk_buff *hsr_init_skb(struct hsr_port *master) goto out; skb_reset_mac_header(skb); + skb_reset_mac_len(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 6852e9bccf5b..ceb8afb2a62f 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -474,8 +474,8 @@ static void handle_std_frame(struct sk_buff *skb, } } -void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame) +int hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame) { struct hsr_port *port = frame->port_rcv; struct hsr_priv *hsr = port->hsr; @@ -483,20 +483,26 @@ void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, /* HSRv0 supervisory frames double as a tag so treat them as tagged. */ if ((!hsr->prot_version && proto == htons(ETH_P_PRP)) || proto == htons(ETH_P_HSR)) { + /* Check if skb contains hsr_ethhdr */ + if (skb->mac_len < sizeof(struct hsr_ethhdr)) + return -EINVAL; + /* HSR tagged frame :- Data or Supervision */ frame->skb_std = NULL; frame->skb_prp = NULL; frame->skb_hsr = skb; frame->sequence_nr = hsr_get_skb_sequence_nr(skb); - return; + return 0; } /* Standard frame or PRP from master port */ handle_std_frame(skb, frame); + + return 0; } -void prp_fill_frame_info(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame) +int prp_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame) { /* Supervision frame */ struct prp_rct *rct = skb_get_PRP_rct(skb); @@ -507,9 +513,11 @@ void prp_fill_frame_info(__be16 proto, struct sk_buff *skb, frame->skb_std = NULL; frame->skb_prp = skb; frame->sequence_nr = prp_get_skb_sequence_nr(rct); - return; + return 0; } handle_std_frame(skb, frame); + + return 0; } static int fill_frame_info(struct hsr_frame_info *frame, @@ -519,9 +527,10 @@ static int fill_frame_info(struct hsr_frame_info *frame, struct hsr_vlan_ethhdr *vlan_hdr; struct ethhdr *ethhdr; __be16 proto; + int ret; - /* Check if skb contains hsr_ethhdr */ - if (skb->mac_len < sizeof(struct hsr_ethhdr)) + /* Check if skb contains ethhdr */ + if (skb->mac_len < sizeof(struct ethhdr)) return -EINVAL; memset(frame, 0, sizeof(*frame)); @@ -548,7 +557,10 @@ static int fill_frame_info(struct hsr_frame_info *frame, frame->is_from_san = false; frame->port_rcv = port; - hsr->proto_ops->fill_frame_info(proto, skb, frame); + ret = hsr->proto_ops->fill_frame_info(proto, skb, frame); + if (ret) + return ret; + check_local_dest(port->hsr, skb, frame); return 0; diff --git a/net/hsr/hsr_forward.h b/net/hsr/hsr_forward.h index b6acaafa83fc..206636750b30 100644 --- a/net/hsr/hsr_forward.h +++ b/net/hsr/hsr_forward.h @@ -24,8 +24,8 @@ struct sk_buff *prp_get_untagged_frame(struct hsr_frame_info *frame, struct hsr_port *port); bool prp_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port); bool hsr_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port); -void prp_fill_frame_info(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame); -void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame); +int prp_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame); +int hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame); #endif /* __HSR_FORWARD_H */ diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 8f264672b70b..53d1f7a82463 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -186,8 +186,8 @@ struct hsr_proto_ops { struct hsr_port *port); struct sk_buff * (*create_tagged_frame)(struct hsr_frame_info *frame, struct hsr_port *port); - void (*fill_frame_info)(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame); + int (*fill_frame_info)(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame); bool (*invalid_dan_ingress_frame)(__be16 protocol); void (*update_san_info)(struct hsr_node *node, bool is_sup); }; diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index c5227d42faf5..b70e6bbf6021 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -60,12 +60,11 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) goto finish_pass; skb_push(skb, ETH_HLEN); - - if (skb_mac_header(skb) != skb->data) { - WARN_ONCE(1, "%s:%d: Malformed frame at source port %s)\n", - __func__, __LINE__, port->dev->name); - goto finish_consume; - } + skb_reset_mac_header(skb); + if ((!hsr->prot_version && protocol == htons(ETH_P_PRP)) || + protocol == htons(ETH_P_HSR)) + skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); + skb_reset_mac_len(skb); hsr_forward_skb(skb, port); diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index dff4f0eb96b0..9e41eff4a685 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -185,6 +185,7 @@ BTF_ID(func, tcp_reno_cong_avoid) BTF_ID(func, tcp_reno_undo_cwnd) BTF_ID(func, tcp_slow_start) BTF_ID(func, tcp_cong_avoid_ai) +#ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE #if IS_BUILTIN(CONFIG_TCP_CONG_CUBIC) BTF_ID(func, cubictcp_init) @@ -213,6 +214,7 @@ BTF_ID(func, bbr_min_tso_segs) BTF_ID(func, bbr_set_state) #endif #endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_X86 */ BTF_SET_END(bpf_tcp_ca_kfunc_ids) static bool bpf_tcp_ca_check_kfunc_call(u32 kfunc_btf_id) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 0d59efb6b49e..d36ef9d25e73 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1745,10 +1745,7 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) IPV6_TLV_PADN, 0 }; /* we assume size > sizeof(ra) here */ - /* limit our allocations to order-0 page */ - size = min_t(int, size, SKB_MAX_ORDER(0, 0)); skb = sock_alloc_send_skb(sk, size, 1, &err); - if (!skb) return NULL; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 47a0dc46cbdb..28e44782c94d 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -343,7 +343,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); - if (!(fhdr->frag_off & htons(0xFFF9))) { + if (!(fhdr->frag_off & htons(IP6_OFFSET | IP6_MF))) { /* It is not a fragmented frame */ skb->transport_header += sizeof(struct frag_hdr); __IP6_INC_STATS(net, @@ -351,6 +351,8 @@ static int ipv6_frag_rcv(struct sk_buff *skb) IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb); IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; + IP6CB(skb)->frag_max_size = ntohs(hdr->payload_len) + + sizeof(struct ipv6hdr); return 1; } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 8fcbaa1eedf3..214404a558fb 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -50,12 +50,6 @@ struct ieee80211_local; #define IEEE80211_ENCRYPT_HEADROOM 8 #define IEEE80211_ENCRYPT_TAILROOM 18 -/* IEEE 802.11 (Ch. 9.5 Defragmentation) requires support for concurrent - * reception of at least three fragmented frames. This limit can be increased - * by changing this define, at the cost of slower frame reassembly and - * increased memory use (about 2 kB of RAM per entry). */ -#define IEEE80211_FRAGMENT_MAX 4 - /* power level hasn't been configured (or set to automatic) */ #define IEEE80211_UNSET_POWER_LEVEL INT_MIN @@ -88,18 +82,6 @@ extern const u8 ieee80211_ac_to_qos_mask[IEEE80211_NUM_ACS]; #define IEEE80211_MAX_NAN_INSTANCE_ID 255 -struct ieee80211_fragment_entry { - struct sk_buff_head skb_list; - unsigned long first_frag_time; - u16 seq; - u16 extra_len; - u16 last_frag; - u8 rx_queue; - bool check_sequential_pn; /* needed for CCMP/GCMP */ - u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ -}; - - struct ieee80211_bss { u32 device_ts_beacon, device_ts_presp; @@ -241,8 +223,15 @@ struct ieee80211_rx_data { */ int security_idx; - u32 tkip_iv32; - u16 tkip_iv16; + union { + struct { + u32 iv32; + u16 iv16; + } tkip; + struct { + u8 pn[IEEE80211_CCMP_PN_LEN]; + } ccm_gcm; + }; }; struct ieee80211_csa_settings { @@ -902,9 +891,7 @@ struct ieee80211_sub_if_data { char name[IFNAMSIZ]; - /* Fragment table for host-based reassembly */ - struct ieee80211_fragment_entry fragments[IEEE80211_FRAGMENT_MAX]; - unsigned int fragment_next; + struct ieee80211_fragment_cache frags; /* TID bitmap for NoAck policy */ u16 noack_map; @@ -2320,4 +2307,7 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, #define debug_noinline #endif +void ieee80211_init_frag_cache(struct ieee80211_fragment_cache *cache); +void ieee80211_destroy_frag_cache(struct ieee80211_fragment_cache *cache); + #endif /* IEEE80211_I_H */ diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 7032a2b59249..2e2f73a4aa73 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -8,7 +8,7 @@ * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (c) 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/slab.h> #include <linux/kernel.h> @@ -677,16 +677,12 @@ static void ieee80211_set_multicast_list(struct net_device *dev) */ static void ieee80211_teardown_sdata(struct ieee80211_sub_if_data *sdata) { - int i; - /* free extra data */ ieee80211_free_keys(sdata, false); ieee80211_debugfs_remove_netdev(sdata); - for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) - __skb_queue_purge(&sdata->fragments[i].skb_list); - sdata->fragment_next = 0; + ieee80211_destroy_frag_cache(&sdata->frags); if (ieee80211_vif_is_mesh(&sdata->vif)) ieee80211_mesh_teardown_sdata(sdata); @@ -1930,8 +1926,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sdata->wdev.wiphy = local->hw.wiphy; sdata->local = local; - for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) - skb_queue_head_init(&sdata->fragments[i].skb_list); + ieee80211_init_frag_cache(&sdata->frags); INIT_LIST_HEAD(&sdata->key_list); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 56c068cb49c4..f695fc80088b 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -799,6 +799,7 @@ int ieee80211_key_link(struct ieee80211_key *key, struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { + static atomic_t key_color = ATOMIC_INIT(0); struct ieee80211_key *old_key; int idx = key->conf.keyidx; bool pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE; @@ -850,6 +851,12 @@ int ieee80211_key_link(struct ieee80211_key *key, key->sdata = sdata; key->sta = sta; + /* + * Assign a unique ID to every key so we can easily prevent mixed + * key and fragment cache attacks. + */ + key->color = atomic_inc_return(&key_color); + increment_tailroom_need_count(sdata); ret = ieee80211_key_replace(sdata, sta, pairwise, old_key, key); diff --git a/net/mac80211/key.h b/net/mac80211/key.h index 7ad72e9b4991..1e326c89d721 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -128,6 +128,8 @@ struct ieee80211_key { } debugfs; #endif + unsigned int color; + /* * key config, must be last because it contains key * material as variable length member diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 62047e93e217..1bb43edd47b6 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -6,7 +6,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/jiffies.h> @@ -2123,19 +2123,34 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) return result; } +void ieee80211_init_frag_cache(struct ieee80211_fragment_cache *cache) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cache->entries); i++) + skb_queue_head_init(&cache->entries[i].skb_list); +} + +void ieee80211_destroy_frag_cache(struct ieee80211_fragment_cache *cache) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cache->entries); i++) + __skb_queue_purge(&cache->entries[i].skb_list); +} + static inline struct ieee80211_fragment_entry * -ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, +ieee80211_reassemble_add(struct ieee80211_fragment_cache *cache, unsigned int frag, unsigned int seq, int rx_queue, struct sk_buff **skb) { struct ieee80211_fragment_entry *entry; - entry = &sdata->fragments[sdata->fragment_next++]; - if (sdata->fragment_next >= IEEE80211_FRAGMENT_MAX) - sdata->fragment_next = 0; + entry = &cache->entries[cache->next++]; + if (cache->next >= IEEE80211_FRAGMENT_MAX) + cache->next = 0; - if (!skb_queue_empty(&entry->skb_list)) - __skb_queue_purge(&entry->skb_list); + __skb_queue_purge(&entry->skb_list); __skb_queue_tail(&entry->skb_list, *skb); /* no need for locking */ *skb = NULL; @@ -2150,14 +2165,14 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, } static inline struct ieee80211_fragment_entry * -ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, +ieee80211_reassemble_find(struct ieee80211_fragment_cache *cache, unsigned int frag, unsigned int seq, int rx_queue, struct ieee80211_hdr *hdr) { struct ieee80211_fragment_entry *entry; int i, idx; - idx = sdata->fragment_next; + idx = cache->next; for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) { struct ieee80211_hdr *f_hdr; struct sk_buff *f_skb; @@ -2166,7 +2181,7 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, if (idx < 0) idx = IEEE80211_FRAGMENT_MAX - 1; - entry = &sdata->fragments[idx]; + entry = &cache->entries[idx]; if (skb_queue_empty(&entry->skb_list) || entry->seq != seq || entry->rx_queue != rx_queue || entry->last_frag + 1 != frag) @@ -2194,15 +2209,27 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, return NULL; } +static bool requires_sequential_pn(struct ieee80211_rx_data *rx, __le16 fc) +{ + return rx->key && + (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && + ieee80211_has_protected(fc); +} + static ieee80211_rx_result debug_noinline ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) { + struct ieee80211_fragment_cache *cache = &rx->sdata->frags; struct ieee80211_hdr *hdr; u16 sc; __le16 fc; unsigned int frag, seq; struct ieee80211_fragment_entry *entry; struct sk_buff *skb; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); hdr = (struct ieee80211_hdr *)rx->skb->data; fc = hdr->frame_control; @@ -2218,6 +2245,9 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) goto out_no_led; } + if (rx->sta) + cache = &rx->sta->frags; + if (likely(!ieee80211_has_morefrags(fc) && frag == 0)) goto out; @@ -2236,20 +2266,17 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) if (frag == 0) { /* This is the first fragment of a new frame. */ - entry = ieee80211_reassemble_add(rx->sdata, frag, seq, + entry = ieee80211_reassemble_add(cache, frag, seq, rx->seqno_idx, &(rx->skb)); - if (rx->key && - (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && - ieee80211_has_protected(fc)) { + if (requires_sequential_pn(rx, fc)) { int queue = rx->security_idx; /* Store CCMP/GCMP PN so that we can verify that the * next fragment has a sequential PN value. */ entry->check_sequential_pn = true; + entry->is_protected = true; + entry->key_color = rx->key->color; memcpy(entry->last_pn, rx->key->u.ccmp.rx_pn[queue], IEEE80211_CCMP_PN_LEN); @@ -2261,6 +2288,11 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sizeof(rx->key->u.gcmp.rx_pn[queue])); BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN != IEEE80211_GCMP_PN_LEN); + } else if (rx->key && + (ieee80211_has_protected(fc) || + (status->flag & RX_FLAG_DECRYPTED))) { + entry->is_protected = true; + entry->key_color = rx->key->color; } return RX_QUEUED; } @@ -2268,7 +2300,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) /* This is a fragment for a frame that should already be pending in * fragment cache. Add this fragment to the end of the pending entry. */ - entry = ieee80211_reassemble_find(rx->sdata, frag, seq, + entry = ieee80211_reassemble_find(cache, frag, seq, rx->seqno_idx, hdr); if (!entry) { I802_DEBUG_INC(rx->local->rx_handlers_drop_defrag); @@ -2283,25 +2315,39 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) if (entry->check_sequential_pn) { int i; u8 pn[IEEE80211_CCMP_PN_LEN], *rpn; - int queue; - if (!rx->key || - (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256 && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP_256)) + if (!requires_sequential_pn(rx, fc)) + return RX_DROP_UNUSABLE; + + /* Prevent mixed key and fragment cache attacks */ + if (entry->key_color != rx->key->color) return RX_DROP_UNUSABLE; + memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN); for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) { pn[i]++; if (pn[i]) break; } - queue = rx->security_idx; - rpn = rx->key->u.ccmp.rx_pn[queue]; + + rpn = rx->ccm_gcm.pn; if (memcmp(pn, rpn, IEEE80211_CCMP_PN_LEN)) return RX_DROP_UNUSABLE; memcpy(entry->last_pn, pn, IEEE80211_CCMP_PN_LEN); + } else if (entry->is_protected && + (!rx->key || + (!ieee80211_has_protected(fc) && + !(status->flag & RX_FLAG_DECRYPTED)) || + rx->key->color != entry->key_color)) { + /* Drop this as a mixed key or fragment cache attack, even + * if for TKIP Michael MIC should protect us, and WEP is a + * lost cause anyway. + */ + return RX_DROP_UNUSABLE; + } else if (entry->is_protected && rx->key && + entry->key_color != rx->key->color && + (status->flag & RX_FLAG_DECRYPTED)) { + return RX_DROP_UNUSABLE; } skb_pull(rx->skb, ieee80211_hdrlen(fc)); @@ -2494,13 +2540,13 @@ static bool ieee80211_frame_allowed(struct ieee80211_rx_data *rx, __le16 fc) struct ethhdr *ehdr = (struct ethhdr *) rx->skb->data; /* - * Allow EAPOL frames to us/the PAE group address regardless - * of whether the frame was encrypted or not. + * Allow EAPOL frames to us/the PAE group address regardless of + * whether the frame was encrypted or not, and always disallow + * all other destination addresses for them. */ - if (ehdr->h_proto == rx->sdata->control_port_protocol && - (ether_addr_equal(ehdr->h_dest, rx->sdata->vif.addr) || - ether_addr_equal(ehdr->h_dest, pae_group_addr))) - return true; + if (unlikely(ehdr->h_proto == rx->sdata->control_port_protocol)) + return ether_addr_equal(ehdr->h_dest, rx->sdata->vif.addr) || + ether_addr_equal(ehdr->h_dest, pae_group_addr); if (ieee80211_802_1x_port_control(rx) || ieee80211_drop_unencrypted(rx, fc)) @@ -2525,8 +2571,28 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb, cfg80211_rx_control_port(dev, skb, noencrypt); dev_kfree_skb(skb); } else { + struct ethhdr *ehdr = (void *)skb_mac_header(skb); + memset(skb->cb, 0, sizeof(skb->cb)); + /* + * 802.1X over 802.11 requires that the authenticator address + * be used for EAPOL frames. However, 802.1X allows the use of + * the PAE group address instead. If the interface is part of + * a bridge and we pass the frame with the PAE group address, + * then the bridge will forward it to the network (even if the + * client was not associated yet), which isn't supposed to + * happen. + * To avoid that, rewrite the destination address to our own + * address, so that the authenticator (e.g. hostapd) will see + * the frame, but bridge won't forward it anywhere else. Note + * that due to earlier filtering, the only other address can + * be the PAE group address. + */ + if (unlikely(skb->protocol == sdata->control_port_protocol && + !ether_addr_equal(ehdr->h_dest, sdata->vif.addr))) + ether_addr_copy(ehdr->h_dest, sdata->vif.addr); + /* deliver to local stack */ if (rx->list) list_add_tail(&skb->list, rx->list); @@ -2566,6 +2632,7 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) if ((sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_AP_VLAN) && !(sdata->flags & IEEE80211_SDATA_DONT_BRIDGE_PACKETS) && + ehdr->h_proto != rx->sdata->control_port_protocol && (sdata->vif.type != NL80211_IFTYPE_AP_VLAN || !sdata->u.vlan.sta)) { if (is_multicast_ether_addr(ehdr->h_dest) && ieee80211_vif_get_num_mcast_if(sdata) != 0) { @@ -2675,7 +2742,7 @@ __ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset) if (ieee80211_data_to_8023_exthdr(skb, ðhdr, rx->sdata->vif.addr, rx->sdata->vif.type, - data_offset)) + data_offset, true)) return RX_DROP_UNUSABLE; ieee80211_amsdu_to_8023s(skb, &frame_list, dev->dev_addr, @@ -2732,6 +2799,23 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) if (is_multicast_ether_addr(hdr->addr1)) return RX_DROP_UNUSABLE; + if (rx->key) { + /* + * We should not receive A-MSDUs on pre-HT connections, + * and HT connections cannot use old ciphers. Thus drop + * them, as in those cases we couldn't even have SPP + * A-MSDUs or such. + */ + switch (rx->key->conf.cipher) { + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + case WLAN_CIPHER_SUITE_TKIP: + return RX_DROP_UNUSABLE; + default: + break; + } + } + return __ieee80211_rx_h_amsdu(rx, 0); } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index ec6973ee88ef..f2fb69da9b6e 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -4,7 +4,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/module.h> @@ -392,6 +392,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, u64_stats_init(&sta->rx_stats.syncp); + ieee80211_init_frag_cache(&sta->frags); + sta->sta_state = IEEE80211_STA_NONE; /* Mark TID as unreserved */ @@ -1102,6 +1104,8 @@ static void __sta_info_destroy_part2(struct sta_info *sta) ieee80211_sta_debugfs_remove(sta); + ieee80211_destroy_frag_cache(&sta->frags); + cleanup_single_sta(sta); } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 78b9d0c7cc58..0333072ebd98 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -3,7 +3,7 @@ * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright(c) 2020 Intel Corporation + * Copyright(c) 2020-2021 Intel Corporation */ #ifndef STA_INFO_H @@ -439,6 +439,34 @@ struct ieee80211_sta_rx_stats { }; /* + * IEEE 802.11-2016 (10.6 "Defragmentation") recommends support for "concurrent + * reception of at least one MSDU per access category per associated STA" + * on APs, or "at least one MSDU per access category" on other interface types. + * + * This limit can be increased by changing this define, at the cost of slower + * frame reassembly and increased memory use while fragments are pending. + */ +#define IEEE80211_FRAGMENT_MAX 4 + +struct ieee80211_fragment_entry { + struct sk_buff_head skb_list; + unsigned long first_frag_time; + u16 seq; + u16 extra_len; + u16 last_frag; + u8 rx_queue; + u8 check_sequential_pn:1, /* needed for CCMP/GCMP */ + is_protected:1; + u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ + unsigned int key_color; +}; + +struct ieee80211_fragment_cache { + struct ieee80211_fragment_entry entries[IEEE80211_FRAGMENT_MAX]; + unsigned int next; +}; + +/* * The bandwidth threshold below which the per-station CoDel parameters will be * scaled to be more lenient (to prevent starvation of slow stations). This * value will be scaled by the number of active stations when it is being @@ -531,6 +559,7 @@ struct ieee80211_sta_rx_stats { * @status_stats.last_ack_signal: last ACK signal * @status_stats.ack_signal_filled: last ACK signal validity * @status_stats.avg_ack_signal: average ACK signal + * @frags: fragment cache */ struct sta_info { /* General information, mostly static */ @@ -639,6 +668,8 @@ struct sta_info { struct cfg80211_chan_def tdls_chandef; + struct ieee80211_fragment_cache frags; + /* keep last! */ struct ieee80211_sta sta; }; diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 91bf32af55e9..bca47fad5a16 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -3,6 +3,7 @@ * Copyright 2002-2004, Instant802 Networks, Inc. * Copyright 2008, Jouni Malinen <j@w1.fi> * Copyright (C) 2016-2017 Intel Deutschland GmbH + * Copyright (C) 2020-2021 Intel Corporation */ #include <linux/netdevice.h> @@ -167,8 +168,8 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) update_iv: /* update IV in key information to be able to detect replays */ - rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip_iv32; - rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip_iv16; + rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip.iv32; + rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip.iv16; return RX_CONTINUE; @@ -294,8 +295,8 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) key, skb->data + hdrlen, skb->len - hdrlen, rx->sta->sta.addr, hdr->addr1, hwaccel, rx->security_idx, - &rx->tkip_iv32, - &rx->tkip_iv16); + &rx->tkip.iv32, + &rx->tkip.iv16); if (res != TKIP_DECRYPT_OK) return RX_DROP_UNUSABLE; @@ -553,6 +554,8 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, } memcpy(key->u.ccmp.rx_pn[queue], pn, IEEE80211_CCMP_PN_LEN); + if (unlikely(ieee80211_is_frag(hdr))) + memcpy(rx->ccm_gcm.pn, pn, IEEE80211_CCMP_PN_LEN); } /* Remove CCMP header and MIC */ @@ -781,6 +784,8 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) } memcpy(key->u.gcmp.rx_pn[queue], pn, IEEE80211_GCMP_PN_LEN); + if (unlikely(ieee80211_is_frag(hdr))) + memcpy(rx->ccm_gcm.pn, pn, IEEE80211_CCMP_PN_LEN); } /* Remove GCMP header and MIC */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 99fc21406168..6b825fb3fa83 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -130,7 +130,6 @@ static void mptcp_parse_option(const struct sk_buff *skb, memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN); pr_debug("MP_JOIN hmac"); } else { - pr_warn("MP_JOIN bad option size"); mp_opt->mp_join = 0; } break; @@ -1024,7 +1023,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR); } else { mptcp_pm_add_addr_echoed(msk, &mp_opt.addr); - mptcp_pm_del_add_timer(msk, &mp_opt.addr); + mptcp_pm_del_add_timer(msk, &mp_opt.addr, true); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD); } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 6ba040897738..2469e06a3a9d 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -346,18 +346,18 @@ out: struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, - struct mptcp_addr_info *addr) + struct mptcp_addr_info *addr, bool check_id) { struct mptcp_pm_add_entry *entry; struct sock *sk = (struct sock *)msk; spin_lock_bh(&msk->pm.lock); entry = mptcp_lookup_anno_list_by_saddr(msk, addr); - if (entry) + if (entry && (!check_id || entry->addr.id == addr->id)) entry->retrans_times = ADD_ADDR_RETRANS_MAX; spin_unlock_bh(&msk->pm.lock); - if (entry) + if (entry && (!check_id || entry->addr.id == addr->id)) sk_stop_timer_sync(sk, &entry->add_timer); return entry; @@ -1064,7 +1064,7 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, { struct mptcp_pm_add_entry *entry; - entry = mptcp_pm_del_add_timer(msk, addr); + entry = mptcp_pm_del_add_timer(msk, addr, false); if (entry) { list_del(&entry->list); kfree(entry); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 29a2d690d8d5..2bc199549a88 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -879,12 +879,18 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq, !mpext->frozen; } +/* we can append data to the given data frag if: + * - there is space available in the backing page_frag + * - the data frag tail matches the current page_frag free offset + * - the data frag end sequence number matches the current write seq + */ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk, const struct page_frag *pfrag, const struct mptcp_data_frag *df) { return df && pfrag->page == df->page && pfrag->size - pfrag->offset > 0 && + pfrag->offset == (df->offset + df->data_len) && df->data_seq + df->data_len == msk->write_seq; } @@ -2418,13 +2424,12 @@ static int __mptcp_init_sock(struct sock *sk) timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0); timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0); - tcp_assign_congestion_control(sk); - return 0; } static int mptcp_init_sock(struct sock *sk) { + struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); int ret; @@ -2442,6 +2447,16 @@ static int mptcp_init_sock(struct sock *sk) if (ret) return ret; + /* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will + * propagate the correct value + */ + tcp_assign_congestion_control(sk); + strcpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name); + + /* no need to keep a reference to the ops, the name will suffice */ + tcp_cleanup_congestion_control(sk); + icsk->icsk_ca_ops = NULL; + sk_sockets_allocated_inc(sk); sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1]; @@ -2616,7 +2631,6 @@ static void __mptcp_destroy_sock(struct sock *sk) sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); - tcp_cleanup_congestion_control(sk); sk_refcnt_debug_release(sk); mptcp_dispose_initial_subflow(msk); sock_put(sk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index edc0128730df..0c6f99c67345 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -258,6 +258,7 @@ struct mptcp_sock { } rcvq_space; u32 setsockopt_seq; + char ca_name[TCP_CA_NAME_MAX]; }; #define mptcp_lock_sock(___sk, cb) do { \ @@ -671,7 +672,7 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk); bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, - struct mptcp_addr_info *addr); + struct mptcp_addr_info *addr, bool check_id); struct mptcp_pm_add_entry * mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk, struct mptcp_addr_info *addr); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 00d941b66c1e..a79798189599 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -547,7 +547,7 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t } if (ret == 0) - tcp_set_congestion_control(sk, name, false, cap_net_admin); + strcpy(msk->ca_name, name); release_sock(sk); return ret; @@ -705,7 +705,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) sock_valbool_flag(ssk, SOCK_DBG, sock_flag(sk, SOCK_DBG)); if (inet_csk(sk)->icsk_ca_ops != inet_csk(ssk)->icsk_ca_ops) - tcp_set_congestion_control(ssk, inet_csk(sk)->icsk_ca_ops->name, false, true); + tcp_set_congestion_control(ssk, msk->ca_name, false, true); } static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index a5ede357cfbc..bde6be77ea73 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -867,7 +867,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk, data_len = mpext->data_len; if (data_len == 0) { - pr_err("Infinite mapping not handled"); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX); return MAPPING_INVALID; } diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 39c02d1aeedf..1d02650dd715 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -306,8 +306,7 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, { flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; - if (likely(!nf_flowtable_hw_offload(flow_table) || - !test_and_clear_bit(NF_FLOW_HW_REFRESH, &flow->flags))) + if (likely(!nf_flowtable_hw_offload(flow_table))) return; nf_flow_offload_add(flow_table, flow); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 2af7bdb38407..528b2f172684 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -902,10 +902,11 @@ static void flow_offload_work_add(struct flow_offload_work *offload) err = flow_offload_rule_add(offload, flow_rule); if (err < 0) - set_bit(NF_FLOW_HW_REFRESH, &offload->flow->flags); - else - set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); + goto out; + + set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); +out: nf_flow_offload_destroy(flow_rule); } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 528a2d7ca991..dce866d93fee 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -408,8 +408,8 @@ int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, * * Return: true on match, false otherwise. */ -static bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); unsigned long *res_map, *fill_map; diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index 25a75591583e..d84afb8fa79a 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -178,6 +178,8 @@ struct nft_pipapo_elem { int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, union nft_pipapo_map_bucket *mt, bool match_only); +bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); /** * pipapo_and_field_buckets_4bit() - Intersect 4-bit buckets diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index d65ae0e23028..eabdb8d552ee 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1131,6 +1131,9 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, bool map_index; int i, ret = 0; + if (unlikely(!irq_fpu_usable())) + return nft_pipapo_lookup(net, set, key, ext); + m = rcu_dereference(priv->match); /* This also protects access to all data related to scratch maps */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 3a62f97acf39..6133e412b948 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -461,11 +461,13 @@ void netlink_table_ungrab(void) static inline void netlink_lock_table(void) { + unsigned long flags; + /* read_lock() synchronizes us to netlink_table_grab */ - read_lock(&nl_table_lock); + read_lock_irqsave(&nl_table_lock, flags); atomic_inc(&nl_table_users); - read_unlock(&nl_table_lock); + read_unlock_irqrestore(&nl_table_lock, flags); } static inline void diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 9a585332ea84..da7fe9db1b00 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1191,6 +1191,7 @@ EXPORT_SYMBOL(nci_allocate_device); void nci_free_device(struct nci_dev *ndev) { nfc_free_device(ndev->nfc_dev); + nci_hci_deallocate(ndev); kfree(ndev); } EXPORT_SYMBOL(nci_free_device); diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index 6b275a387a92..96865142104f 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -792,3 +792,8 @@ struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev) return hdev; } + +void nci_hci_deallocate(struct nci_dev *ndev) +{ + kfree(ndev->hci_dev); +} diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 9c7eb8455ba8..5f1d438a0a23 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -329,7 +329,7 @@ static int rawsock_create(struct net *net, struct socket *sock, return -ESOCKTNOSUPPORT; if (sock->type == SOCK_RAW) { - if (!capable(CAP_NET_RAW)) + if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; sock->ops = &rawsock_raw_ops; } else { diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 96b524ceabca..896b8f5bc885 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -611,6 +611,14 @@ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb, spin_lock(&meter->lock); long_delta_ms = (now_ms - meter->used); /* ms */ + if (long_delta_ms < 0) { + /* This condition means that we have several threads fighting + * for a meter lock, and the one who received the packets a + * bit later wins. Assuming that all racing threads received + * packets at the same time to avoid overflow. + */ + long_delta_ms = 0; + } /* Make sure delta_ms will not be too large, so that bucket will not * wrap around below. diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ba96db1880ea..ae906eb4b269 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -422,7 +422,8 @@ static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts, ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts)) return TP_STATUS_TS_RAW_HARDWARE; - if (ktime_to_timespec64_cond(skb->tstamp, ts)) + if ((flags & SOF_TIMESTAMPING_SOFTWARE) && + ktime_to_timespec64_cond(skb->tstamp, ts)) return TP_STATUS_TS_SOFTWARE; return 0; @@ -2340,7 +2341,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, skb_copy_bits(skb, 0, h.raw + macoff, snaplen); - if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp))) + /* Always timestamp; prefer an existing software timestamp taken + * closer to the time of capture. + */ + ts_status = tpacket_get_timestamp(skb, &ts, + po->tp_tstamp | SOF_TIMESTAMPING_SOFTWARE); + if (!ts_status) ktime_get_real_ts64(&ts); status |= ts_status; diff --git a/net/rds/connection.c b/net/rds/connection.c index f2fcab182095..a3bc4b54d491 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -240,12 +240,23 @@ static struct rds_connection *__rds_conn_create(struct net *net, if (loop_trans) { rds_trans_put(loop_trans); conn->c_loopback = 1; - if (is_outgoing && trans->t_prefer_loopback) { - /* "outgoing" connection - and the transport - * says it wants the connection handled by the - * loopback transport. This is what TCP does. - */ - trans = &rds_loop_transport; + if (trans->t_prefer_loopback) { + if (likely(is_outgoing)) { + /* "outgoing" connection to local address. + * Protocol says it wants the connection + * handled by the loopback transport. + * This is what TCP does. + */ + trans = &rds_loop_transport; + } else { + /* No transport currently in use + * should end up here, but if it + * does, reset/destroy the connection. + */ + kmem_cache_free(rds_conn_slab, conn); + conn = ERR_PTR(-EOPNOTSUPP); + goto out; + } } } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 43db0eca911f..abf19c0e3ba0 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -313,8 +313,8 @@ out: } #endif -static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, - __u32 scope_id) +int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, + __u32 scope_id) { struct net_device *dev = NULL; #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/rds/tcp.h b/net/rds/tcp.h index bad9cf49d565..dc8d745d6857 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -59,7 +59,8 @@ u32 rds_tcp_snd_una(struct rds_tcp_connection *tc); u64 rds_tcp_map_seq(struct rds_tcp_connection *tc, u32 seq); extern struct rds_transport rds_tcp_transport; void rds_tcp_accept_work(struct sock *sk); - +int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, + __u32 scope_id); /* tcp_connect.c */ int rds_tcp_conn_path_connect(struct rds_conn_path *cp); void rds_tcp_conn_path_shutdown(struct rds_conn_path *conn); diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 101cf14215a0..09cadd556d1e 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -167,6 +167,12 @@ int rds_tcp_accept_one(struct socket *sock) } #endif + if (!rds_tcp_laddr_check(sock_net(sock->sk), peer_addr, dev_if)) { + /* local address connection is only allowed via loopback */ + ret = -EOPNOTSUPP; + goto out; + } + conn = rds_conn_create(sock_net(sock->sk), my_addr, peer_addr, &rds_tcp_transport, 0, GFP_KERNEL, dev_if); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 40fbea626dfd..279f9e2a2319 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1624,7 +1624,7 @@ int tcf_classify_ingress(struct sk_buff *skb, /* If we missed on some chain */ if (ret == TC_ACT_UNSPEC && last_executed_chain) { - ext = skb_ext_add(skb, TC_SKB_EXT); + ext = tc_skb_ext_alloc(skb); if (WARN_ON_ONCE(!ext)) return TC_ACT_SHOT; ext->chain = last_executed_chain; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index cd2748e2d4a2..d320bcfb2da2 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -407,7 +407,8 @@ static void dsmark_reset(struct Qdisc *sch) struct dsmark_qdisc_data *p = qdisc_priv(sch); pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - qdisc_reset(p->q); + if (p->q) + qdisc_reset(p->q); sch->qstats.backlog = 0; sch->q.qlen = 0; } diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 949163fe68af..cac684952edc 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -138,8 +138,15 @@ static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Classifies packet into corresponding flow */ idx = fq_pie_classify(skb, sch, &ret); - sel_flow = &q->flows[idx]; + if (idx == 0) { + if (ret & __NET_XMIT_BYPASS) + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + return ret; + } + idx--; + sel_flow = &q->flows[idx]; /* Checks whether adding a new packet would exceed memory limit */ get_pie_cb(skb)->mem_usage = skb->truesize; memory_limited = q->memory_usage > q->memory_limit + skb->truesize; @@ -297,9 +304,9 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, goto flow_error; } q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]); - if (!q->flows_cnt || q->flows_cnt >= 65536) { + if (!q->flows_cnt || q->flows_cnt > 65536) { NL_SET_ERR_MSG_MOD(extack, - "Number of flows must range in [1..65535]"); + "Number of flows must range in [1..65536]"); goto flow_error; } } @@ -367,7 +374,7 @@ static void fq_pie_timer(struct timer_list *t) struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer); struct Qdisc *sch = q->sch; spinlock_t *root_lock; /* to lock qdisc for probability calculations */ - u16 idx; + u32 idx; root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -388,7 +395,7 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, { struct fq_pie_sched_data *q = qdisc_priv(sch); int err; - u16 idx; + u32 idx; pie_params_init(&q->p_params); sch->limit = 10 * 1024; @@ -500,7 +507,7 @@ static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) static void fq_pie_reset(struct Qdisc *sch) { struct fq_pie_sched_data *q = qdisc_priv(sch); - u16 idx; + u32 idx; INIT_LIST_HEAD(&q->new_flows); INIT_LIST_HEAD(&q->old_flows); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 44991ea726fc..fc8b56bcabf3 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -35,6 +35,25 @@ const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops; EXPORT_SYMBOL(default_qdisc_ops); +static void qdisc_maybe_clear_missed(struct Qdisc *q, + const struct netdev_queue *txq) +{ + clear_bit(__QDISC_STATE_MISSED, &q->state); + + /* Make sure the below netif_xmit_frozen_or_stopped() + * checking happens after clearing STATE_MISSED. + */ + smp_mb__after_atomic(); + + /* Checking netif_xmit_frozen_or_stopped() again to + * make sure STATE_MISSED is set if the STATE_MISSED + * set by netif_tx_wake_queue()'s rescheduling of + * net_tx_action() is cleared by the above clear_bit(). + */ + if (!netif_xmit_frozen_or_stopped(txq)) + set_bit(__QDISC_STATE_MISSED, &q->state); +} + /* Main transmission queue. */ /* Modifications to data participating in scheduling must be protected with @@ -74,6 +93,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q) } } else { skb = SKB_XOFF_MAGIC; + qdisc_maybe_clear_missed(q, txq); } } @@ -242,6 +262,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, } } else { skb = NULL; + qdisc_maybe_clear_missed(q, txq); } if (lock) spin_unlock(lock); @@ -251,8 +272,10 @@ validate: *validate = true; if ((q->flags & TCQ_F_ONETXQUEUE) && - netif_xmit_frozen_or_stopped(txq)) + netif_xmit_frozen_or_stopped(txq)) { + qdisc_maybe_clear_missed(q, txq); return skb; + } skb = qdisc_dequeue_skb_bad_txq(q); if (unlikely(skb)) { @@ -311,6 +334,8 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); + else + qdisc_maybe_clear_missed(q, txq); HARD_TX_UNLOCK(dev, txq); } else { @@ -640,8 +665,10 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct sk_buff *skb = NULL; + bool need_retry = true; int band; +retry: for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) { struct skb_array *q = band2list(priv, band); @@ -652,6 +679,23 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) } if (likely(skb)) { qdisc_update_stats_at_dequeue(qdisc, skb); + } else if (need_retry && + test_bit(__QDISC_STATE_MISSED, &qdisc->state)) { + /* Delay clearing the STATE_MISSED here to reduce + * the overhead of the second spin_trylock() in + * qdisc_run_begin() and __netif_schedule() calling + * in qdisc_run_end(). + */ + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + + /* Make sure dequeuing happens after clearing + * STATE_MISSED. + */ + smp_mb__after_atomic(); + + need_retry = false; + + goto retry; } else { WRITE_ONCE(qdisc->empty, true); } @@ -1158,8 +1202,10 @@ static void dev_reset_queue(struct net_device *dev, qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); - if (nolock) + if (nolock) { + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); spin_unlock_bh(&qdisc->seqlock); + } } static bool some_qdisc_is_busy(struct net_device *dev) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 40f9f6c4a0a1..a79d193ff872 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4473,6 +4473,7 @@ static int sctp_setsockopt_encap_port(struct sock *sk, transports) t->encap_port = encap_port; + asoc->encap_port = encap_port; return 0; } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index e92df779af73..55871b277f47 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -307,7 +307,7 @@ static struct ctl_table sctp_net_table[] = { .data = &init_net.sctp.encap_port, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &udp_port_max, }, diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 94b31f2551bc..967712ba52a0 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -429,6 +429,8 @@ EXPORT_SYMBOL_GPL(smcd_alloc_dev); int smcd_register_dev(struct smcd_dev *smcd) { + int rc; + mutex_lock(&smcd_dev_list.mutex); if (list_empty(&smcd_dev_list.list)) { u8 *system_eid = NULL; @@ -448,7 +450,14 @@ int smcd_register_dev(struct smcd_dev *smcd) dev_name(&smcd->dev), smcd->pnetid, smcd->pnetid_by_user ? " (user defined)" : ""); - return device_add(&smcd->dev); + rc = device_add(&smcd->dev); + if (rc) { + mutex_lock(&smcd_dev_list.mutex); + list_del(&smcd->list); + mutex_unlock(&smcd_dev_list.mutex); + } + + return rc; } EXPORT_SYMBOL_GPL(smcd_register_dev); diff --git a/net/tipc/core.c b/net/tipc/core.c index 5cc1f0307215..3f4542e0f065 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -60,7 +60,7 @@ static int __net_init tipc_init_net(struct net *net) tn->trial_addr = 0; tn->addr_trial_end = 0; tn->capabilities = TIPC_NODE_CAPABILITIES; - INIT_WORK(&tn->final_work.work, tipc_net_finalize_work); + INIT_WORK(&tn->work, tipc_net_finalize_work); memset(tn->node_id, 0, sizeof(tn->node_id)); memset(tn->node_id_string, 0, sizeof(tn->node_id_string)); tn->mon_threshold = TIPC_DEF_MON_THRESHOLD; @@ -110,7 +110,7 @@ static void __net_exit tipc_exit_net(struct net *net) tipc_detach_loopback(net); /* Make sure the tipc_net_finalize_work() finished */ - cancel_work_sync(&tn->final_work.work); + cancel_work_sync(&tn->work); tipc_net_stop(net); tipc_bcast_stop(net); @@ -119,6 +119,8 @@ static void __net_exit tipc_exit_net(struct net *net) #ifdef CONFIG_TIPC_CRYPTO tipc_crypto_stop(&tipc_net(net)->crypto_tx); #endif + while (atomic_read(&tn->wq_count)) + cond_resched(); } static void __net_exit tipc_pernet_pre_exit(struct net *net) diff --git a/net/tipc/core.h b/net/tipc/core.h index 03de7b213f55..0a3f7a70a50a 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -91,12 +91,6 @@ extern unsigned int tipc_net_id __read_mostly; extern int sysctl_tipc_rmem[3] __read_mostly; extern int sysctl_tipc_named_timeout __read_mostly; -struct tipc_net_work { - struct work_struct work; - struct net *net; - u32 addr; -}; - struct tipc_net { u8 node_id[NODE_ID_LEN]; u32 node_addr; @@ -148,7 +142,9 @@ struct tipc_net { struct tipc_crypto *crypto_tx; #endif /* Work item for net finalize */ - struct tipc_net_work final_work; + struct work_struct work; + /* The numbers of work queues in schedule */ + atomic_t wq_count; }; static inline struct tipc_net *tipc_net(struct net *net) diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 5380f605b851..da69e1abf68f 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -168,7 +168,7 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, /* Apply trial address if we just left trial period */ if (!trial && !self) { - tipc_sched_net_finalize(net, tn->trial_addr); + schedule_work(&tn->work); msg_set_prevnode(buf_msg(d->skb), tn->trial_addr); msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); } @@ -308,7 +308,7 @@ static void tipc_disc_timeout(struct timer_list *t) if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) { mod_timer(&d->timer, jiffies + TIPC_DISC_INIT); spin_unlock_bh(&d->lock); - tipc_sched_net_finalize(net, tn->trial_addr); + schedule_work(&tn->work); return; } diff --git a/net/tipc/link.c b/net/tipc/link.c index 115109259430..c44b4bfaaee6 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -372,6 +372,11 @@ char tipc_link_plane(struct tipc_link *l) return l->net_plane; } +struct net *tipc_link_net(struct tipc_link *l) +{ + return l->net; +} + void tipc_link_update_caps(struct tipc_link *l, u16 capabilities) { l->peer_caps = capabilities; diff --git a/net/tipc/link.h b/net/tipc/link.h index fc07232c9a12..a16f401fdabd 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -156,4 +156,5 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq); bool tipc_link_too_silent(struct tipc_link *l); +struct net *tipc_link_net(struct tipc_link *l); #endif diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 3f0a25345a7c..ce6ab54822d8 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -149,18 +149,13 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (unlikely(head)) goto err; *buf = NULL; + if (skb_has_frag_list(frag) && __skb_linearize(frag)) + goto err; frag = skb_unshare(frag, GFP_ATOMIC); if (unlikely(!frag)) goto err; head = *headbuf = frag; TIPC_SKB_CB(head)->tail = NULL; - if (skb_is_nonlinear(head)) { - skb_walk_frags(head, tail) { - TIPC_SKB_CB(head)->tail = tail; - } - } else { - skb_frag_list_init(head); - } return 0; } diff --git a/net/tipc/net.c b/net/tipc/net.c index a130195af188..0e95572e56b4 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -41,6 +41,7 @@ #include "socket.h" #include "node.h" #include "bcast.h" +#include "link.h" #include "netlink.h" #include "monitor.h" @@ -142,19 +143,9 @@ static void tipc_net_finalize(struct net *net, u32 addr) void tipc_net_finalize_work(struct work_struct *work) { - struct tipc_net_work *fwork; + struct tipc_net *tn = container_of(work, struct tipc_net, work); - fwork = container_of(work, struct tipc_net_work, work); - tipc_net_finalize(fwork->net, fwork->addr); -} - -void tipc_sched_net_finalize(struct net *net, u32 addr) -{ - struct tipc_net *tn = tipc_net(net); - - tn->final_work.net = net; - tn->final_work.addr = addr; - schedule_work(&tn->final_work.work); + tipc_net_finalize(tipc_link_net(tn->bcl), tn->trial_addr); } void tipc_net_stop(struct net *net) diff --git a/net/tipc/node.c b/net/tipc/node.c index 8217905348f4..81af92954c6c 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -423,18 +423,18 @@ static void tipc_node_write_unlock(struct tipc_node *n) write_unlock_bh(&n->lock); if (flags & TIPC_NOTIFY_NODE_DOWN) - tipc_publ_notify(net, publ_list, n->addr, n->capabilities); + tipc_publ_notify(net, publ_list, sk.node, n->capabilities); if (flags & TIPC_NOTIFY_NODE_UP) - tipc_named_node_up(net, n->addr, n->capabilities); + tipc_named_node_up(net, sk.node, n->capabilities); if (flags & TIPC_NOTIFY_LINK_UP) { - tipc_mon_peer_up(net, n->addr, bearer_id); - tipc_nametbl_publish(net, &ua, &sk, n->link_id); + tipc_mon_peer_up(net, sk.node, bearer_id); + tipc_nametbl_publish(net, &ua, &sk, sk.ref); } if (flags & TIPC_NOTIFY_LINK_DOWN) { - tipc_mon_peer_down(net, n->addr, bearer_id); - tipc_nametbl_withdraw(net, &ua, &sk, n->link_id); + tipc_mon_peer_down(net, sk.node, bearer_id); + tipc_nametbl_withdraw(net, &ua, &sk, sk.ref); } } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 58935cd0d068..53af72824c9c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1262,7 +1262,10 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, spin_lock_bh(&inputq->lock); if (skb_peek(arrvq) == skb) { skb_queue_splice_tail_init(&tmpq, inputq); - __skb_dequeue(arrvq); + /* Decrease the skb's refcnt as increasing in the + * function tipc_skb_peek + */ + kfree_skb(__skb_dequeue(arrvq)); } spin_unlock_bh(&inputq->lock); __skb_queue_purge(&tmpq); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index e556d2cdc064..c2bb818704c8 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -814,6 +814,7 @@ static void cleanup_bearer(struct work_struct *work) kfree_rcu(rcast, rcu); } + atomic_dec(&tipc_net(sock_net(ub->ubsock->sk))->wq_count); dst_cache_destroy(&ub->rcast.dst_cache); udp_tunnel_sock_release(ub->ubsock); synchronize_net(); @@ -834,6 +835,7 @@ static void tipc_udp_disable(struct tipc_bearer *b) RCU_INIT_POINTER(ub->bearer, NULL); /* sock_release need to be done outside of rtnl lock */ + atomic_inc(&tipc_net(sock_net(ub->ubsock->sk))->wq_count); INIT_WORK(&ub->work, cleanup_bearer); schedule_work(&ub->work); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 1dcb34dfd56b..694de024d0ee 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -37,6 +37,7 @@ #include <linux/sched/signal.h> #include <linux/module.h> +#include <linux/splice.h> #include <crypto/aead.h> #include <net/strparser.h> @@ -1281,7 +1282,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, } static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock, - int flags, long timeo, int *err) + bool nonblock, long timeo, int *err) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); @@ -1306,7 +1307,7 @@ static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock, if (sock_flag(sk, SOCK_DONE)) return NULL; - if ((flags & MSG_DONTWAIT) || !timeo) { + if (nonblock || !timeo) { *err = -EAGAIN; return NULL; } @@ -1786,7 +1787,7 @@ int tls_sw_recvmsg(struct sock *sk, bool async_capable; bool async = false; - skb = tls_wait_data(sk, psock, flags, timeo, &err); + skb = tls_wait_data(sk, psock, flags & MSG_DONTWAIT, timeo, &err); if (!skb) { if (psock) { int ret = sk_msg_recvmsg(sk, psock, msg, len, @@ -1990,9 +1991,9 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, lock_sock(sk); - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK); - skb = tls_wait_data(sk, NULL, flags, timeo, &err); + skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, &err); if (!skb) goto splice_read_end; diff --git a/net/wireless/util.c b/net/wireless/util.c index 382c5262d997..7ec021a610ae 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -542,7 +542,7 @@ EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen); int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, const u8 *addr, enum nl80211_iftype iftype, - u8 data_offset) + u8 data_offset, bool is_amsdu) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct { @@ -629,7 +629,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, skb_copy_bits(skb, hdrlen, &payload, sizeof(payload)); tmp.h_proto = payload.proto; - if (likely((ether_addr_equal(payload.hdr, rfc1042_header) && + if (likely((!is_amsdu && ether_addr_equal(payload.hdr, rfc1042_header) && tmp.h_proto != htons(ETH_P_AARP) && tmp.h_proto != htons(ETH_P_IPX)) || ether_addr_equal(payload.hdr, bridge_tunnel_header))) @@ -771,6 +771,9 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, remaining = skb->len - offset; if (subframe_len > remaining) goto purge; + /* mitigate A-MSDU aggregation injection attacks */ + if (ether_addr_equal(eth.h_dest, rfc1042_header)) + goto purge; offset += sizeof(struct ethhdr); last = remaining <= subframe_len + padding; diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index aa696854be78..53e300f860bb 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -1255,7 +1255,7 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size) for (i = 0; i < batch_size; i++) { struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); - tx_desc->addr = (*frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT; + tx_desc->addr = (*frame_nb + i) * opt_xsk_frame_size; tx_desc->len = PKT_SIZE; } diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 790944c35602..baee8591ac76 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -30,7 +30,8 @@ CGROUP COMMANDS | *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | | **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | | **getpeername4** | **getpeername6** | **getsockname4** | **getsockname6** | **sendmsg4** | -| **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** } +| **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** | +| **sock_release** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION @@ -106,6 +107,7 @@ DESCRIPTION **getpeername6** call to getpeername(2) for an inet6 socket (since 5.8); **getsockname4** call to getsockname(2) for an inet4 socket (since 5.8); **getsockname6** call to getsockname(2) for an inet6 socket (since 5.8). + **sock_release** closing an userspace inet socket (since 5.9). **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* Detach *PROG* from the cgroup *CGROUP* and attach type diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 358c7309d419..fe1b38e7e887 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -44,7 +44,7 @@ PROG COMMANDS | **cgroup/connect4** | **cgroup/connect6** | **cgroup/getpeername4** | **cgroup/getpeername6** | | **cgroup/getsockname4** | **cgroup/getsockname6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** | | **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** | -| **cgroup/getsockopt** | **cgroup/setsockopt** | +| **cgroup/getsockopt** | **cgroup/setsockopt** | **cgroup/sock_release** | | **struct_ops** | **fentry** | **fexit** | **freplace** | **sk_lookup** | } | *ATTACH_TYPE* := { diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index d67518bcbd44..cc33c5824a2f 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -478,7 +478,7 @@ _bpftool() cgroup/recvmsg4 cgroup/recvmsg6 \ cgroup/post_bind4 cgroup/post_bind6 \ cgroup/sysctl cgroup/getsockopt \ - cgroup/setsockopt struct_ops \ + cgroup/setsockopt cgroup/sock_release struct_ops \ fentry fexit freplace sk_lookup" -- \ "$cur" ) ) return 0 @@ -1021,7 +1021,7 @@ _bpftool() device bind4 bind6 post_bind4 post_bind6 connect4 connect6 \ getpeername4 getpeername6 getsockname4 getsockname6 \ sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl getsockopt \ - setsockopt' + setsockopt sock_release' local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag name' case $prev in @@ -1032,7 +1032,7 @@ _bpftool() ingress|egress|sock_create|sock_ops|device|bind4|bind6|\ post_bind4|post_bind6|connect4|connect6|getpeername4|\ getpeername6|getsockname4|getsockname6|sendmsg4|sendmsg6|\ - recvmsg4|recvmsg6|sysctl|getsockopt|setsockopt) + recvmsg4|recvmsg6|sysctl|getsockopt|setsockopt|sock_release) COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ "$cur" ) ) return 0 diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index d901cc1b904a..6e53b1d393f4 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -28,7 +28,8 @@ " connect6 | getpeername4 | getpeername6 |\n" \ " getsockname4 | getsockname6 | sendmsg4 |\n" \ " sendmsg6 | recvmsg4 | recvmsg6 |\n" \ - " sysctl | getsockopt | setsockopt }" + " sysctl | getsockopt | setsockopt |\n" \ + " sock_release }" static unsigned int query_flags; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 3f067d2d7584..da4846c9856a 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -2138,7 +2138,7 @@ static int do_help(int argc, char **argv) " cgroup/getpeername4 | cgroup/getpeername6 |\n" " cgroup/getsockname4 | cgroup/getsockname6 | cgroup/sendmsg4 |\n" " cgroup/sendmsg6 | cgroup/recvmsg4 | cgroup/recvmsg6 |\n" - " cgroup/getsockopt | cgroup/setsockopt |\n" + " cgroup/getsockopt | cgroup/setsockopt | cgroup/sock_release |\n" " struct_ops | fentry | fexit | freplace | sk_lookup }\n" " ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n" " flow_dissector }\n" diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e2a3cf437814..c41d9b2b59ac 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -3216,6 +3216,9 @@ static int add_dummy_ksym_var(struct btf *btf) const struct btf_var_secinfo *vs; const struct btf_type *sec; + if (!btf) + return 0; + sec_btf_id = btf__find_by_name_kind(btf, KSYMS_SEC, BTF_KIND_DATASEC); if (sec_btf_id < 0) diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index ee426226928f..acbcf6c7bdf8 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -41,6 +41,11 @@ #define ELF_C_READ_MMAP ELF_C_READ #endif +/* Older libelf all end up in this expression, for both 32 and 64 bit */ +#ifndef GELF_ST_VISIBILITY +#define GELF_ST_VISIBILITY(o) ((o) & 0x03) +#endif + #define BTF_INFO_ENC(kind, kind_flag, vlen) \ ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) #define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type) diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 12ee40284da0..2060bc122c53 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -40,7 +40,7 @@ struct ipv6_packet pkt_v6 = { .tcp.doff = 5, }; -static int settimeo(int fd, int timeout_ms) +int settimeo(int fd, int timeout_ms) { struct timeval timeout = { .tv_sec = 3 }; diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 7205f8afdba1..5e0d51c07b63 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -33,6 +33,7 @@ struct ipv6_packet { } __packed; extern struct ipv6_packet pkt_v6; +int settimeo(int fd, int timeout_ms); int start_server(int family, int type, const char *addr, __u16 port, int timeout_ms); int connect_to_fd(int server_fd, int timeout_ms); diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index de78617f6550..f9a8ae331963 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -86,8 +86,9 @@ void test_ringbuf(void) const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample); pthread_t thread; long bg_ret = -1; - int err, cnt; + int err, cnt, rb_fd; int page_size = getpagesize(); + void *mmap_ptr, *tmp_ptr; skel = test_ringbuf__open(); if (CHECK(!skel, "skel_open", "skeleton open failed\n")) @@ -101,6 +102,52 @@ void test_ringbuf(void) if (CHECK(err != 0, "skel_load", "skeleton load failed\n")) goto cleanup; + rb_fd = bpf_map__fd(skel->maps.ringbuf); + /* good read/write cons_pos */ + mmap_ptr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rb_fd, 0); + ASSERT_OK_PTR(mmap_ptr, "rw_cons_pos"); + tmp_ptr = mremap(mmap_ptr, page_size, 2 * page_size, MREMAP_MAYMOVE); + if (!ASSERT_ERR_PTR(tmp_ptr, "rw_extend")) + goto cleanup; + ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_EXEC), "exec_cons_pos_protect"); + ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_rw"); + + /* bad writeable prod_pos */ + mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, page_size); + err = -errno; + ASSERT_ERR_PTR(mmap_ptr, "wr_prod_pos"); + ASSERT_EQ(err, -EPERM, "wr_prod_pos_err"); + + /* bad writeable data pages */ + mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, 2 * page_size); + err = -errno; + ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_one"); + ASSERT_EQ(err, -EPERM, "wr_data_page_one_err"); + mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, 3 * page_size); + ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_two"); + mmap_ptr = mmap(NULL, 2 * page_size, PROT_WRITE, MAP_SHARED, rb_fd, 2 * page_size); + ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_all"); + + /* good read-only pages */ + mmap_ptr = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED, rb_fd, 0); + if (!ASSERT_OK_PTR(mmap_ptr, "ro_prod_pos")) + goto cleanup; + + ASSERT_ERR(mprotect(mmap_ptr, 4 * page_size, PROT_WRITE), "write_protect"); + ASSERT_ERR(mprotect(mmap_ptr, 4 * page_size, PROT_EXEC), "exec_protect"); + ASSERT_ERR_PTR(mremap(mmap_ptr, 0, 4 * page_size, MREMAP_MAYMOVE), "ro_remap"); + ASSERT_OK(munmap(mmap_ptr, 4 * page_size), "unmap_ro"); + + /* good read-only pages with initial offset */ + mmap_ptr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, rb_fd, page_size); + if (!ASSERT_OK_PTR(mmap_ptr, "ro_prod_pos")) + goto cleanup; + + ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_WRITE), "write_protect"); + ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_EXEC), "exec_protect"); + ASSERT_ERR_PTR(mremap(mmap_ptr, 0, 3 * page_size, MREMAP_MAYMOVE), "ro_remap"); + ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_ro"); + /* only trigger BPF program for current process */ skel->bss->pid = getpid(); diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c new file mode 100644 index 000000000000..5703c918812b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -0,0 +1,785 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* + * This test sets up 3 netns (src <-> fwd <-> dst). There is no direct veth link + * between src and dst. The netns fwd has veth links to each src and dst. The + * client is in src and server in dst. The test installs a TC BPF program to each + * host facing veth in fwd which calls into i) bpf_redirect_neigh() to perform the + * neigh addr population and redirect or ii) bpf_redirect_peer() for namespace + * switch from ingress side; it also installs a checker prog on the egress side + * to drop unexpected traffic. + */ + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <linux/limits.h> +#include <linux/sysctl.h> +#include <linux/if_tun.h> +#include <linux/if.h> +#include <sched.h> +#include <stdbool.h> +#include <stdio.h> +#include <sys/stat.h> +#include <sys/mount.h> + +#include "test_progs.h" +#include "network_helpers.h" +#include "test_tc_neigh_fib.skel.h" +#include "test_tc_neigh.skel.h" +#include "test_tc_peer.skel.h" + +#define NS_SRC "ns_src" +#define NS_FWD "ns_fwd" +#define NS_DST "ns_dst" + +#define IP4_SRC "172.16.1.100" +#define IP4_DST "172.16.2.100" +#define IP4_TUN_SRC "172.17.1.100" +#define IP4_TUN_FWD "172.17.1.200" +#define IP4_PORT 9004 + +#define IP6_SRC "0::1:dead:beef:cafe" +#define IP6_DST "0::2:dead:beef:cafe" +#define IP6_TUN_SRC "1::1:dead:beef:cafe" +#define IP6_TUN_FWD "1::2:dead:beef:cafe" +#define IP6_PORT 9006 + +#define IP4_SLL "169.254.0.1" +#define IP4_DLL "169.254.0.2" +#define IP4_NET "169.254.0.0" + +#define MAC_DST_FWD "00:11:22:33:44:55" +#define MAC_DST "00:22:33:44:55:66" + +#define IFADDR_STR_LEN 18 +#define PING_ARGS "-i 0.2 -c 3 -w 10 -q" + +#define SRC_PROG_PIN_FILE "/sys/fs/bpf/test_tc_src" +#define DST_PROG_PIN_FILE "/sys/fs/bpf/test_tc_dst" +#define CHK_PROG_PIN_FILE "/sys/fs/bpf/test_tc_chk" + +#define TIMEOUT_MILLIS 10000 + +#define log_err(MSG, ...) \ + fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ + __FILE__, __LINE__, strerror(errno), ##__VA_ARGS__) + +static const char * const namespaces[] = {NS_SRC, NS_FWD, NS_DST, NULL}; + +static int write_file(const char *path, const char *newval) +{ + FILE *f; + + f = fopen(path, "r+"); + if (!f) + return -1; + if (fwrite(newval, strlen(newval), 1, f) != 1) { + log_err("writing to %s failed", path); + fclose(f); + return -1; + } + fclose(f); + return 0; +} + +struct nstoken { + int orig_netns_fd; +}; + +static int setns_by_fd(int nsfd) +{ + int err; + + err = setns(nsfd, CLONE_NEWNET); + close(nsfd); + + if (!ASSERT_OK(err, "setns")) + return err; + + /* Switch /sys to the new namespace so that e.g. /sys/class/net + * reflects the devices in the new namespace. + */ + err = unshare(CLONE_NEWNS); + if (!ASSERT_OK(err, "unshare")) + return err; + + err = umount2("/sys", MNT_DETACH); + if (!ASSERT_OK(err, "umount2 /sys")) + return err; + + err = mount("sysfs", "/sys", "sysfs", 0, NULL); + if (!ASSERT_OK(err, "mount /sys")) + return err; + + err = mount("bpffs", "/sys/fs/bpf", "bpf", 0, NULL); + if (!ASSERT_OK(err, "mount /sys/fs/bpf")) + return err; + + return 0; +} + +/** + * open_netns() - Switch to specified network namespace by name. + * + * Returns token with which to restore the original namespace + * using close_netns(). + */ +static struct nstoken *open_netns(const char *name) +{ + int nsfd; + char nspath[PATH_MAX]; + int err; + struct nstoken *token; + + token = malloc(sizeof(struct nstoken)); + if (!ASSERT_OK_PTR(token, "malloc token")) + return NULL; + + token->orig_netns_fd = open("/proc/self/ns/net", O_RDONLY); + if (!ASSERT_GE(token->orig_netns_fd, 0, "open /proc/self/ns/net")) + goto fail; + + snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name); + nsfd = open(nspath, O_RDONLY | O_CLOEXEC); + if (!ASSERT_GE(nsfd, 0, "open netns fd")) + goto fail; + + err = setns_by_fd(nsfd); + if (!ASSERT_OK(err, "setns_by_fd")) + goto fail; + + return token; +fail: + free(token); + return NULL; +} + +static void close_netns(struct nstoken *token) +{ + ASSERT_OK(setns_by_fd(token->orig_netns_fd), "setns_by_fd"); + free(token); +} + +static int netns_setup_namespaces(const char *verb) +{ + const char * const *ns = namespaces; + char cmd[128]; + + while (*ns) { + snprintf(cmd, sizeof(cmd), "ip netns %s %s", verb, *ns); + if (!ASSERT_OK(system(cmd), cmd)) + return -1; + ns++; + } + return 0; +} + +struct netns_setup_result { + int ifindex_veth_src_fwd; + int ifindex_veth_dst_fwd; +}; + +static int get_ifaddr(const char *name, char *ifaddr) +{ + char path[PATH_MAX]; + FILE *f; + int ret; + + snprintf(path, PATH_MAX, "/sys/class/net/%s/address", name); + f = fopen(path, "r"); + if (!ASSERT_OK_PTR(f, path)) + return -1; + + ret = fread(ifaddr, 1, IFADDR_STR_LEN, f); + if (!ASSERT_EQ(ret, IFADDR_STR_LEN, "fread ifaddr")) { + fclose(f); + return -1; + } + fclose(f); + return 0; +} + +static int get_ifindex(const char *name) +{ + char path[PATH_MAX]; + char buf[32]; + FILE *f; + int ret; + + snprintf(path, PATH_MAX, "/sys/class/net/%s/ifindex", name); + f = fopen(path, "r"); + if (!ASSERT_OK_PTR(f, path)) + return -1; + + ret = fread(buf, 1, sizeof(buf), f); + if (!ASSERT_GT(ret, 0, "fread ifindex")) { + fclose(f); + return -1; + } + fclose(f); + return atoi(buf); +} + +#define SYS(fmt, ...) \ + ({ \ + char cmd[1024]; \ + snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \ + if (!ASSERT_OK(system(cmd), cmd)) \ + goto fail; \ + }) + +static int netns_setup_links_and_routes(struct netns_setup_result *result) +{ + struct nstoken *nstoken = NULL; + char veth_src_fwd_addr[IFADDR_STR_LEN+1] = {}; + + SYS("ip link add veth_src type veth peer name veth_src_fwd"); + SYS("ip link add veth_dst type veth peer name veth_dst_fwd"); + + SYS("ip link set veth_dst_fwd address " MAC_DST_FWD); + SYS("ip link set veth_dst address " MAC_DST); + + if (get_ifaddr("veth_src_fwd", veth_src_fwd_addr)) + goto fail; + + result->ifindex_veth_src_fwd = get_ifindex("veth_src_fwd"); + if (result->ifindex_veth_src_fwd < 0) + goto fail; + result->ifindex_veth_dst_fwd = get_ifindex("veth_dst_fwd"); + if (result->ifindex_veth_dst_fwd < 0) + goto fail; + + SYS("ip link set veth_src netns " NS_SRC); + SYS("ip link set veth_src_fwd netns " NS_FWD); + SYS("ip link set veth_dst_fwd netns " NS_FWD); + SYS("ip link set veth_dst netns " NS_DST); + + /** setup in 'src' namespace */ + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns src")) + goto fail; + + SYS("ip addr add " IP4_SRC "/32 dev veth_src"); + SYS("ip addr add " IP6_SRC "/128 dev veth_src nodad"); + SYS("ip link set dev veth_src up"); + + SYS("ip route add " IP4_DST "/32 dev veth_src scope global"); + SYS("ip route add " IP4_NET "/16 dev veth_src scope global"); + SYS("ip route add " IP6_DST "/128 dev veth_src scope global"); + + SYS("ip neigh add " IP4_DST " dev veth_src lladdr %s", + veth_src_fwd_addr); + SYS("ip neigh add " IP6_DST " dev veth_src lladdr %s", + veth_src_fwd_addr); + + close_netns(nstoken); + + /** setup in 'fwd' namespace */ + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + goto fail; + + /* The fwd netns automatically gets a v6 LL address / routes, but also + * needs v4 one in order to start ARP probing. IP4_NET route is added + * to the endpoints so that the ARP processing will reply. + */ + SYS("ip addr add " IP4_SLL "/32 dev veth_src_fwd"); + SYS("ip addr add " IP4_DLL "/32 dev veth_dst_fwd"); + SYS("ip link set dev veth_src_fwd up"); + SYS("ip link set dev veth_dst_fwd up"); + + SYS("ip route add " IP4_SRC "/32 dev veth_src_fwd scope global"); + SYS("ip route add " IP6_SRC "/128 dev veth_src_fwd scope global"); + SYS("ip route add " IP4_DST "/32 dev veth_dst_fwd scope global"); + SYS("ip route add " IP6_DST "/128 dev veth_dst_fwd scope global"); + + close_netns(nstoken); + + /** setup in 'dst' namespace */ + nstoken = open_netns(NS_DST); + if (!ASSERT_OK_PTR(nstoken, "setns dst")) + goto fail; + + SYS("ip addr add " IP4_DST "/32 dev veth_dst"); + SYS("ip addr add " IP6_DST "/128 dev veth_dst nodad"); + SYS("ip link set dev veth_dst up"); + + SYS("ip route add " IP4_SRC "/32 dev veth_dst scope global"); + SYS("ip route add " IP4_NET "/16 dev veth_dst scope global"); + SYS("ip route add " IP6_SRC "/128 dev veth_dst scope global"); + + SYS("ip neigh add " IP4_SRC " dev veth_dst lladdr " MAC_DST_FWD); + SYS("ip neigh add " IP6_SRC " dev veth_dst lladdr " MAC_DST_FWD); + + close_netns(nstoken); + + return 0; +fail: + if (nstoken) + close_netns(nstoken); + return -1; +} + +static int netns_load_bpf(void) +{ + SYS("tc qdisc add dev veth_src_fwd clsact"); + SYS("tc filter add dev veth_src_fwd ingress bpf da object-pinned " + SRC_PROG_PIN_FILE); + SYS("tc filter add dev veth_src_fwd egress bpf da object-pinned " + CHK_PROG_PIN_FILE); + + SYS("tc qdisc add dev veth_dst_fwd clsact"); + SYS("tc filter add dev veth_dst_fwd ingress bpf da object-pinned " + DST_PROG_PIN_FILE); + SYS("tc filter add dev veth_dst_fwd egress bpf da object-pinned " + CHK_PROG_PIN_FILE); + + return 0; +fail: + return -1; +} + +static void test_tcp(int family, const char *addr, __u16 port) +{ + int listen_fd = -1, accept_fd = -1, client_fd = -1; + char buf[] = "testing testing"; + int n; + struct nstoken *nstoken; + + nstoken = open_netns(NS_DST); + if (!ASSERT_OK_PTR(nstoken, "setns dst")) + return; + + listen_fd = start_server(family, SOCK_STREAM, addr, port, 0); + if (!ASSERT_GE(listen_fd, 0, "listen")) + goto done; + + close_netns(nstoken); + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns src")) + goto done; + + client_fd = connect_to_fd(listen_fd, TIMEOUT_MILLIS); + if (!ASSERT_GE(client_fd, 0, "connect_to_fd")) + goto done; + + accept_fd = accept(listen_fd, NULL, NULL); + if (!ASSERT_GE(accept_fd, 0, "accept")) + goto done; + + if (!ASSERT_OK(settimeo(accept_fd, TIMEOUT_MILLIS), "settimeo")) + goto done; + + n = write(client_fd, buf, sizeof(buf)); + if (!ASSERT_EQ(n, sizeof(buf), "send to server")) + goto done; + + n = read(accept_fd, buf, sizeof(buf)); + ASSERT_EQ(n, sizeof(buf), "recv from server"); + +done: + if (nstoken) + close_netns(nstoken); + if (listen_fd >= 0) + close(listen_fd); + if (accept_fd >= 0) + close(accept_fd); + if (client_fd >= 0) + close(client_fd); +} + +static int test_ping(int family, const char *addr) +{ + const char *ping = family == AF_INET6 ? "ping6" : "ping"; + + SYS("ip netns exec " NS_SRC " %s " PING_ARGS " %s > /dev/null", ping, addr); + return 0; +fail: + return -1; +} + +static void test_connectivity(void) +{ + test_tcp(AF_INET, IP4_DST, IP4_PORT); + test_ping(AF_INET, IP4_DST); + test_tcp(AF_INET6, IP6_DST, IP6_PORT); + test_ping(AF_INET6, IP6_DST); +} + +static int set_forwarding(bool enable) +{ + int err; + + err = write_file("/proc/sys/net/ipv4/ip_forward", enable ? "1" : "0"); + if (!ASSERT_OK(err, "set ipv4.ip_forward=0")) + return err; + + err = write_file("/proc/sys/net/ipv6/conf/all/forwarding", enable ? "1" : "0"); + if (!ASSERT_OK(err, "set ipv6.forwarding=0")) + return err; + + return 0; +} + +static void test_tc_redirect_neigh_fib(struct netns_setup_result *setup_result) +{ + struct nstoken *nstoken = NULL; + struct test_tc_neigh_fib *skel = NULL; + int err; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + return; + + skel = test_tc_neigh_fib__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_neigh_fib__open")) + goto done; + + if (!ASSERT_OK(test_tc_neigh_fib__load(skel), "test_tc_neigh_fib__load")) + goto done; + + err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto done; + + if (netns_load_bpf()) + goto done; + + /* bpf_fib_lookup() checks if forwarding is enabled */ + if (!ASSERT_OK(set_forwarding(true), "enable forwarding")) + goto done; + + test_connectivity(); + +done: + if (skel) + test_tc_neigh_fib__destroy(skel); + close_netns(nstoken); +} + +static void test_tc_redirect_neigh(struct netns_setup_result *setup_result) +{ + struct nstoken *nstoken = NULL; + struct test_tc_neigh *skel = NULL; + int err; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + return; + + skel = test_tc_neigh__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_neigh__open")) + goto done; + + skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_neigh__load(skel); + if (!ASSERT_OK(err, "test_tc_neigh__load")) + goto done; + + err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto done; + + if (netns_load_bpf()) + goto done; + + if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) + goto done; + + test_connectivity(); + +done: + if (skel) + test_tc_neigh__destroy(skel); + close_netns(nstoken); +} + +static void test_tc_redirect_peer(struct netns_setup_result *setup_result) +{ + struct nstoken *nstoken; + struct test_tc_peer *skel; + int err; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + return; + + skel = test_tc_peer__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_peer__open")) + goto done; + + skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_peer__load(skel); + if (!ASSERT_OK(err, "test_tc_peer__load")) + goto done; + + err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto done; + + if (netns_load_bpf()) + goto done; + + if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) + goto done; + + test_connectivity(); + +done: + if (skel) + test_tc_peer__destroy(skel); + close_netns(nstoken); +} + +static int tun_open(char *name) +{ + struct ifreq ifr; + int fd, err; + + fd = open("/dev/net/tun", O_RDWR); + if (!ASSERT_GE(fd, 0, "open /dev/net/tun")) + return -1; + + memset(&ifr, 0, sizeof(ifr)); + + ifr.ifr_flags = IFF_TUN | IFF_NO_PI; + if (*name) + strncpy(ifr.ifr_name, name, IFNAMSIZ); + + err = ioctl(fd, TUNSETIFF, &ifr); + if (!ASSERT_OK(err, "ioctl TUNSETIFF")) + goto fail; + + SYS("ip link set dev %s up", name); + + return fd; +fail: + close(fd); + return -1; +} + +#define MAX(a, b) ((a) > (b) ? (a) : (b)) +enum { + SRC_TO_TARGET = 0, + TARGET_TO_SRC = 1, +}; + +static int tun_relay_loop(int src_fd, int target_fd) +{ + fd_set rfds, wfds; + + FD_ZERO(&rfds); + FD_ZERO(&wfds); + + for (;;) { + char buf[1500]; + int direction, nread, nwrite; + + FD_SET(src_fd, &rfds); + FD_SET(target_fd, &rfds); + + if (select(1 + MAX(src_fd, target_fd), &rfds, NULL, NULL, NULL) < 0) { + log_err("select failed"); + return 1; + } + + direction = FD_ISSET(src_fd, &rfds) ? SRC_TO_TARGET : TARGET_TO_SRC; + + nread = read(direction == SRC_TO_TARGET ? src_fd : target_fd, buf, sizeof(buf)); + if (nread < 0) { + log_err("read failed"); + return 1; + } + + nwrite = write(direction == SRC_TO_TARGET ? target_fd : src_fd, buf, nread); + if (nwrite != nread) { + log_err("write failed"); + return 1; + } + } +} + +static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) +{ + struct test_tc_peer *skel = NULL; + struct nstoken *nstoken = NULL; + int err; + int tunnel_pid = -1; + int src_fd, target_fd; + int ifindex; + + /* Start a L3 TUN/TAP tunnel between the src and dst namespaces. + * This test is using TUN/TAP instead of e.g. IPIP or GRE tunnel as those + * expose the L2 headers encapsulating the IP packet to BPF and hence + * don't have skb in suitable state for this test. Alternative to TUN/TAP + * would be e.g. Wireguard which would appear as a pure L3 device to BPF, + * but that requires much more complicated setup. + */ + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_SRC)) + return; + + src_fd = tun_open("tun_src"); + if (!ASSERT_GE(src_fd, 0, "tun_open tun_src")) + goto fail; + + close_netns(nstoken); + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_FWD)) + goto fail; + + target_fd = tun_open("tun_fwd"); + if (!ASSERT_GE(target_fd, 0, "tun_open tun_fwd")) + goto fail; + + tunnel_pid = fork(); + if (!ASSERT_GE(tunnel_pid, 0, "fork tun_relay_loop")) + goto fail; + + if (tunnel_pid == 0) + exit(tun_relay_loop(src_fd, target_fd)); + + skel = test_tc_peer__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_peer__open")) + goto fail; + + ifindex = get_ifindex("tun_fwd"); + if (!ASSERT_GE(ifindex, 0, "get_ifindex tun_fwd")) + goto fail; + + skel->rodata->IFINDEX_SRC = ifindex; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_peer__load(skel); + if (!ASSERT_OK(err, "test_tc_peer__load")) + goto fail; + + err = bpf_program__pin(skel->progs.tc_src_l3, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto fail; + + err = bpf_program__pin(skel->progs.tc_dst_l3, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto fail; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto fail; + + /* Load "tc_src_l3" to the tun_fwd interface to redirect packets + * towards dst, and "tc_dst" to redirect packets + * and "tc_chk" on veth_dst_fwd to drop non-redirected packets. + */ + SYS("tc qdisc add dev tun_fwd clsact"); + SYS("tc filter add dev tun_fwd ingress bpf da object-pinned " + SRC_PROG_PIN_FILE); + + SYS("tc qdisc add dev veth_dst_fwd clsact"); + SYS("tc filter add dev veth_dst_fwd ingress bpf da object-pinned " + DST_PROG_PIN_FILE); + SYS("tc filter add dev veth_dst_fwd egress bpf da object-pinned " + CHK_PROG_PIN_FILE); + + /* Setup route and neigh tables */ + SYS("ip -netns " NS_SRC " addr add dev tun_src " IP4_TUN_SRC "/24"); + SYS("ip -netns " NS_FWD " addr add dev tun_fwd " IP4_TUN_FWD "/24"); + + SYS("ip -netns " NS_SRC " addr add dev tun_src " IP6_TUN_SRC "/64 nodad"); + SYS("ip -netns " NS_FWD " addr add dev tun_fwd " IP6_TUN_FWD "/64 nodad"); + + SYS("ip -netns " NS_SRC " route del " IP4_DST "/32 dev veth_src scope global"); + SYS("ip -netns " NS_SRC " route add " IP4_DST "/32 via " IP4_TUN_FWD + " dev tun_src scope global"); + SYS("ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev veth_dst scope global"); + SYS("ip -netns " NS_SRC " route del " IP6_DST "/128 dev veth_src scope global"); + SYS("ip -netns " NS_SRC " route add " IP6_DST "/128 via " IP6_TUN_FWD + " dev tun_src scope global"); + SYS("ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev veth_dst scope global"); + + SYS("ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD); + SYS("ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD); + + if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) + goto fail; + + test_connectivity(); + +fail: + if (tunnel_pid > 0) { + kill(tunnel_pid, SIGTERM); + waitpid(tunnel_pid, NULL, 0); + } + if (src_fd >= 0) + close(src_fd); + if (target_fd >= 0) + close(target_fd); + if (skel) + test_tc_peer__destroy(skel); + if (nstoken) + close_netns(nstoken); +} + +#define RUN_TEST(name) \ + ({ \ + struct netns_setup_result setup_result; \ + if (test__start_subtest(#name)) \ + if (ASSERT_OK(netns_setup_namespaces("add"), "setup namespaces")) { \ + if (ASSERT_OK(netns_setup_links_and_routes(&setup_result), \ + "setup links and routes")) \ + test_ ## name(&setup_result); \ + netns_setup_namespaces("delete"); \ + } \ + }) + +static void *test_tc_redirect_run_tests(void *arg) +{ + RUN_TEST(tc_redirect_peer); + RUN_TEST(tc_redirect_peer_l3); + RUN_TEST(tc_redirect_neigh); + RUN_TEST(tc_redirect_neigh_fib); + return NULL; +} + +void test_tc_redirect(void) +{ + pthread_t test_thread; + int err; + + /* Run the tests in their own thread to isolate the namespace changes + * so they do not affect the environment of other tests. + * (specifically needed because of unshare(CLONE_NEWNS) in open_netns()) + */ + err = pthread_create(&test_thread, NULL, &test_tc_redirect_run_tests, NULL); + if (ASSERT_OK(err, "pthread_create")) + ASSERT_OK(pthread_join(test_thread, NULL), "pthread_join"); +} diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c index b985ac4e7a81..0c93d326a663 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c @@ -33,17 +33,8 @@ a.s6_addr32[3] == b.s6_addr32[3]) #endif -enum { - dev_src, - dev_dst, -}; - -struct bpf_map_def SEC("maps") ifindex_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 2, -}; +volatile const __u32 IFINDEX_SRC; +volatile const __u32 IFINDEX_DST; static __always_inline bool is_remote_ep_v4(struct __sk_buff *skb, __be32 addr) @@ -79,14 +70,8 @@ static __always_inline bool is_remote_ep_v6(struct __sk_buff *skb, return v6_equal(ip6h->daddr, addr); } -static __always_inline int get_dev_ifindex(int which) -{ - int *ifindex = bpf_map_lookup_elem(&ifindex_map, &which); - - return ifindex ? *ifindex : 0; -} - -SEC("chk_egress") int tc_chk(struct __sk_buff *skb) +SEC("classifier/chk_egress") +int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); void *data = ctx_ptr(skb->data); @@ -98,7 +83,8 @@ SEC("chk_egress") int tc_chk(struct __sk_buff *skb) return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK; } -SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) +SEC("classifier/dst_ingress") +int tc_dst(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; bool redirect = false; @@ -119,10 +105,11 @@ SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0) return TC_ACT_SHOT; - return bpf_redirect_neigh(get_dev_ifindex(dev_src), NULL, 0, 0); + return bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0); } -SEC("src_ingress") int tc_src(struct __sk_buff *skb) +SEC("classifier/src_ingress") +int tc_src(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; bool redirect = false; @@ -143,7 +130,7 @@ SEC("src_ingress") int tc_src(struct __sk_buff *skb) if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0) return TC_ACT_SHOT; - return bpf_redirect_neigh(get_dev_ifindex(dev_dst), NULL, 0, 0); + return bpf_redirect_neigh(IFINDEX_DST, NULL, 0, 0); } char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c index d82ed3457030..f7ab69cf018e 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c @@ -75,7 +75,8 @@ static __always_inline int fill_fib_params_v6(struct __sk_buff *skb, return 0; } -SEC("chk_egress") int tc_chk(struct __sk_buff *skb) +SEC("classifier/chk_egress") +int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); void *data = ctx_ptr(skb->data); @@ -142,12 +143,14 @@ static __always_inline int tc_redir(struct __sk_buff *skb) /* these are identical, but keep them separate for compatibility with the * section names expected by test_tc_redirect.sh */ -SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) +SEC("classifier/dst_ingress") +int tc_dst(struct __sk_buff *skb) { return tc_redir(skb); } -SEC("src_ingress") int tc_src(struct __sk_buff *skb) +SEC("classifier/src_ingress") +int tc_src(struct __sk_buff *skb) { return tc_redir(skb); } diff --git a/tools/testing/selftests/bpf/progs/test_tc_peer.c b/tools/testing/selftests/bpf/progs/test_tc_peer.c index fc84a7685aa2..fe818cd5f010 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_peer.c +++ b/tools/testing/selftests/bpf/progs/test_tc_peer.c @@ -5,41 +5,59 @@ #include <linux/bpf.h> #include <linux/stddef.h> #include <linux/pkt_cls.h> +#include <linux/if_ether.h> +#include <linux/ip.h> #include <bpf/bpf_helpers.h> -enum { - dev_src, - dev_dst, -}; +volatile const __u32 IFINDEX_SRC; +volatile const __u32 IFINDEX_DST; -struct bpf_map_def SEC("maps") ifindex_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 2, -}; +static const __u8 src_mac[] = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55}; +static const __u8 dst_mac[] = {0x00, 0x22, 0x33, 0x44, 0x55, 0x66}; -static __always_inline int get_dev_ifindex(int which) +SEC("classifier/chk_egress") +int tc_chk(struct __sk_buff *skb) { - int *ifindex = bpf_map_lookup_elem(&ifindex_map, &which); + return TC_ACT_SHOT; +} - return ifindex ? *ifindex : 0; +SEC("classifier/dst_ingress") +int tc_dst(struct __sk_buff *skb) +{ + return bpf_redirect_peer(IFINDEX_SRC, 0); } -SEC("chk_egress") int tc_chk(struct __sk_buff *skb) +SEC("classifier/src_ingress") +int tc_src(struct __sk_buff *skb) { - return TC_ACT_SHOT; + return bpf_redirect_peer(IFINDEX_DST, 0); } -SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) +SEC("classifier/dst_ingress_l3") +int tc_dst_l3(struct __sk_buff *skb) { - return bpf_redirect_peer(get_dev_ifindex(dev_src), 0); + return bpf_redirect(IFINDEX_SRC, 0); } -SEC("src_ingress") int tc_src(struct __sk_buff *skb) +SEC("classifier/src_ingress_l3") +int tc_src_l3(struct __sk_buff *skb) { - return bpf_redirect_peer(get_dev_ifindex(dev_dst), 0); + __u16 proto = skb->protocol; + + if (bpf_skb_change_head(skb, ETH_HLEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, 0, &src_mac, ETH_ALEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, ETH_ALEN, &dst_mac, ETH_ALEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, ETH_ALEN + ETH_ALEN, &proto, sizeof(__u16), 0) != 0) + return TC_ACT_SHOT; + + return bpf_redirect_peer(IFINDEX_DST, 0); } char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_tc_redirect.sh b/tools/testing/selftests/bpf/test_tc_redirect.sh deleted file mode 100755 index 8868aa1ca902..000000000000 --- a/tools/testing/selftests/bpf/test_tc_redirect.sh +++ /dev/null @@ -1,216 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# This test sets up 3 netns (src <-> fwd <-> dst). There is no direct veth link -# between src and dst. The netns fwd has veth links to each src and dst. The -# client is in src and server in dst. The test installs a TC BPF program to each -# host facing veth in fwd which calls into i) bpf_redirect_neigh() to perform the -# neigh addr population and redirect or ii) bpf_redirect_peer() for namespace -# switch from ingress side; it also installs a checker prog on the egress side -# to drop unexpected traffic. - -if [[ $EUID -ne 0 ]]; then - echo "This script must be run as root" - echo "FAIL" - exit 1 -fi - -# check that needed tools are present -command -v nc >/dev/null 2>&1 || \ - { echo >&2 "nc is not available"; exit 1; } -command -v dd >/dev/null 2>&1 || \ - { echo >&2 "dd is not available"; exit 1; } -command -v timeout >/dev/null 2>&1 || \ - { echo >&2 "timeout is not available"; exit 1; } -command -v ping >/dev/null 2>&1 || \ - { echo >&2 "ping is not available"; exit 1; } -if command -v ping6 >/dev/null 2>&1; then PING6=ping6; else PING6=ping; fi -command -v perl >/dev/null 2>&1 || \ - { echo >&2 "perl is not available"; exit 1; } -command -v jq >/dev/null 2>&1 || \ - { echo >&2 "jq is not available"; exit 1; } -command -v bpftool >/dev/null 2>&1 || \ - { echo >&2 "bpftool is not available"; exit 1; } - -readonly GREEN='\033[0;92m' -readonly RED='\033[0;31m' -readonly NC='\033[0m' # No Color - -readonly PING_ARG="-c 3 -w 10 -q" - -readonly TIMEOUT=10 - -readonly NS_SRC="ns-src-$(mktemp -u XXXXXX)" -readonly NS_FWD="ns-fwd-$(mktemp -u XXXXXX)" -readonly NS_DST="ns-dst-$(mktemp -u XXXXXX)" - -readonly IP4_SRC="172.16.1.100" -readonly IP4_DST="172.16.2.100" - -readonly IP6_SRC="::1:dead:beef:cafe" -readonly IP6_DST="::2:dead:beef:cafe" - -readonly IP4_SLL="169.254.0.1" -readonly IP4_DLL="169.254.0.2" -readonly IP4_NET="169.254.0.0" - -netns_cleanup() -{ - ip netns del ${NS_SRC} - ip netns del ${NS_FWD} - ip netns del ${NS_DST} -} - -netns_setup() -{ - ip netns add "${NS_SRC}" - ip netns add "${NS_FWD}" - ip netns add "${NS_DST}" - - ip link add veth_src type veth peer name veth_src_fwd - ip link add veth_dst type veth peer name veth_dst_fwd - - ip link set veth_src netns ${NS_SRC} - ip link set veth_src_fwd netns ${NS_FWD} - - ip link set veth_dst netns ${NS_DST} - ip link set veth_dst_fwd netns ${NS_FWD} - - ip -netns ${NS_SRC} addr add ${IP4_SRC}/32 dev veth_src - ip -netns ${NS_DST} addr add ${IP4_DST}/32 dev veth_dst - - # The fwd netns automatically get a v6 LL address / routes, but also - # needs v4 one in order to start ARP probing. IP4_NET route is added - # to the endpoints so that the ARP processing will reply. - - ip -netns ${NS_FWD} addr add ${IP4_SLL}/32 dev veth_src_fwd - ip -netns ${NS_FWD} addr add ${IP4_DLL}/32 dev veth_dst_fwd - - ip -netns ${NS_SRC} addr add ${IP6_SRC}/128 dev veth_src nodad - ip -netns ${NS_DST} addr add ${IP6_DST}/128 dev veth_dst nodad - - ip -netns ${NS_SRC} link set dev veth_src up - ip -netns ${NS_FWD} link set dev veth_src_fwd up - - ip -netns ${NS_DST} link set dev veth_dst up - ip -netns ${NS_FWD} link set dev veth_dst_fwd up - - ip -netns ${NS_SRC} route add ${IP4_DST}/32 dev veth_src scope global - ip -netns ${NS_SRC} route add ${IP4_NET}/16 dev veth_src scope global - ip -netns ${NS_FWD} route add ${IP4_SRC}/32 dev veth_src_fwd scope global - - ip -netns ${NS_SRC} route add ${IP6_DST}/128 dev veth_src scope global - ip -netns ${NS_FWD} route add ${IP6_SRC}/128 dev veth_src_fwd scope global - - ip -netns ${NS_DST} route add ${IP4_SRC}/32 dev veth_dst scope global - ip -netns ${NS_DST} route add ${IP4_NET}/16 dev veth_dst scope global - ip -netns ${NS_FWD} route add ${IP4_DST}/32 dev veth_dst_fwd scope global - - ip -netns ${NS_DST} route add ${IP6_SRC}/128 dev veth_dst scope global - ip -netns ${NS_FWD} route add ${IP6_DST}/128 dev veth_dst_fwd scope global - - fmac_src=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_src_fwd/address) - fmac_dst=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_dst_fwd/address) - - ip -netns ${NS_SRC} neigh add ${IP4_DST} dev veth_src lladdr $fmac_src - ip -netns ${NS_DST} neigh add ${IP4_SRC} dev veth_dst lladdr $fmac_dst - - ip -netns ${NS_SRC} neigh add ${IP6_DST} dev veth_src lladdr $fmac_src - ip -netns ${NS_DST} neigh add ${IP6_SRC} dev veth_dst lladdr $fmac_dst -} - -netns_test_connectivity() -{ - set +e - - ip netns exec ${NS_DST} bash -c "nc -4 -l -p 9004 &" - ip netns exec ${NS_DST} bash -c "nc -6 -l -p 9006 &" - - TEST="TCPv4 connectivity test" - ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero bs=1000 count=100 > /dev/tcp/${IP4_DST}/9004" - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - TEST="TCPv6 connectivity test" - ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero bs=1000 count=100 > /dev/tcp/${IP6_DST}/9006" - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - TEST="ICMPv4 connectivity test" - ip netns exec ${NS_SRC} ping $PING_ARG ${IP4_DST} - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - TEST="ICMPv6 connectivity test" - ip netns exec ${NS_SRC} $PING6 $PING_ARG ${IP6_DST} - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - set -e -} - -hex_mem_str() -{ - perl -e 'print join(" ", unpack("(H2)8", pack("L", @ARGV)))' $1 -} - -netns_setup_bpf() -{ - local obj=$1 - local use_forwarding=${2:-0} - - ip netns exec ${NS_FWD} tc qdisc add dev veth_src_fwd clsact - ip netns exec ${NS_FWD} tc filter add dev veth_src_fwd ingress bpf da obj $obj sec src_ingress - ip netns exec ${NS_FWD} tc filter add dev veth_src_fwd egress bpf da obj $obj sec chk_egress - - ip netns exec ${NS_FWD} tc qdisc add dev veth_dst_fwd clsact - ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd ingress bpf da obj $obj sec dst_ingress - ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd egress bpf da obj $obj sec chk_egress - - if [ "$use_forwarding" -eq "1" ]; then - # bpf_fib_lookup() checks if forwarding is enabled - ip netns exec ${NS_FWD} sysctl -w net.ipv4.ip_forward=1 - ip netns exec ${NS_FWD} sysctl -w net.ipv6.conf.veth_dst_fwd.forwarding=1 - ip netns exec ${NS_FWD} sysctl -w net.ipv6.conf.veth_src_fwd.forwarding=1 - return 0 - fi - - veth_src=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_src_fwd/ifindex) - veth_dst=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_dst_fwd/ifindex) - - progs=$(ip netns exec ${NS_FWD} bpftool net --json | jq -r '.[] | .tc | map(.id) | .[]') - for prog in $progs; do - map=$(bpftool prog show id $prog --json | jq -r '.map_ids | .? | .[]') - if [ ! -z "$map" ]; then - bpftool map update id $map key hex $(hex_mem_str 0) value hex $(hex_mem_str $veth_src) - bpftool map update id $map key hex $(hex_mem_str 1) value hex $(hex_mem_str $veth_dst) - fi - done -} - -trap netns_cleanup EXIT -set -e - -netns_setup -netns_setup_bpf test_tc_neigh.o -netns_test_connectivity -netns_cleanup -netns_setup -netns_setup_bpf test_tc_neigh_fib.o 1 -netns_test_connectivity -netns_cleanup -netns_setup -netns_setup_bpf test_tc_peer.o -netns_test_connectivity diff --git a/tools/testing/selftests/bpf/verifier/stack_ptr.c b/tools/testing/selftests/bpf/verifier/stack_ptr.c index 07eaa04412ae..8ab94d65f3d5 100644 --- a/tools/testing/selftests/bpf/verifier/stack_ptr.c +++ b/tools/testing/selftests/bpf/verifier/stack_ptr.c @@ -295,8 +295,6 @@ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), BPF_EXIT_INSN(), }, - .result_unpriv = REJECT, - .errstr_unpriv = "invalid write to stack R1 off=0 size=1", .result = ACCEPT, .retval = 42, }, diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index e5913fd3b903..7ae2859d495c 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -300,8 +300,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -371,8 +369,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -472,8 +468,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -766,8 +760,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { diff --git a/tools/testing/selftests/nci/.gitignore b/tools/testing/selftests/nci/.gitignore new file mode 100644 index 000000000000..448eeb4590fc --- /dev/null +++ b/tools/testing/selftests/nci/.gitignore @@ -0,0 +1 @@ +/nci_dev diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json index 1cda2e11b3ad..773c5027553d 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json @@ -9,11 +9,11 @@ "setup": [ "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY root fq_pie flows 65536", - "expExitCode": "2", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_pie flows 65536", + "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc", - "matchCount": "0", + "matchPattern": "qdisc fq_pie 1: root refcnt 2 limit 10240p flows 65536", + "matchCount": "1", "teardown": [ "$IP link del dev $DUMMY" ] |