diff options
76 files changed, 768 insertions, 349 deletions
diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst index d46429be334e..7df2465fd108 100644 --- a/Documentation/bpf/index.rst +++ b/Documentation/bpf/index.rst @@ -36,6 +36,12 @@ Two sets of Questions and Answers (Q&A) are maintained. bpf_devel_QA +Helper functions +================ + +* `bpf-helpers(7)`_ maintains a list of helpers available to eBPF programs. + + Program types ============= @@ -79,4 +85,5 @@ Other .. _networking-filter: ../networking/filter.rst .. _man-pages: https://www.kernel.org/doc/man-pages/ .. _bpf(2): https://man7.org/linux/man-pages/man2/bpf.2.html +.. _bpf-helpers(7): https://man7.org/linux/man-pages/man7/bpf-helpers.7.html .. _BPF and XDP Reference Guide: https://docs.cilium.io/en/latest/bpf/ diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index 24168b0d16bd..adc314639085 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -2860,17 +2860,6 @@ version of the linux kernel, found on http://kernel.org The latest version of this document can be found in the latest kernel source (named Documentation/networking/bonding.rst). -Discussions regarding the usage of the bonding driver take place on the -bonding-devel mailing list, hosted at sourceforge.net. If you have questions or -problems, post them to the list. The list address is: - -bonding-devel@lists.sourceforge.net - -The administrative interface (to subscribe or unsubscribe) can -be found at: - -https://lists.sourceforge.net/lists/listinfo/bonding-devel - Discussions regarding the development of the bonding driver take place on the main Linux network mailing list, hosted at vger.kernel.org. The list address is: @@ -2881,10 +2870,3 @@ The administrative interface (to subscribe or unsubscribe) can be found at: http://vger.kernel.org/vger-lists.html#netdev - -Donald Becker's Ethernet Drivers and diag programs may be found at : - - - http://web.archive.org/web/%2E/http://www.scyld.com/network/ - -You will also find a lot of information regarding Ethernet, NWay, MII, -etc. at www.scyld.com. diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 31e43a2197a3..cddaa43a9d52 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -130,7 +130,7 @@ static inline struct bonding *__get_bond_by_port(struct port *port) /** * __get_first_agg - get the first aggregator in the bond - * @bond: the bond we're looking at + * @port: the port we're looking at * * Return the aggregator of the first slave in @bond, or %NULL if it can't be * found. @@ -1626,7 +1626,7 @@ static int agg_device_up(const struct aggregator *agg) /** * ad_agg_selection_logic - select an aggregation group for a team - * @aggregator: the aggregator we're looking at + * @agg: the aggregator we're looking at * @update_slave_arr: Does slave array need update? * * It is assumed that only one aggregator may be selected for a team. @@ -1810,7 +1810,7 @@ static void ad_initialize_agg(struct aggregator *aggregator) /** * ad_initialize_port - initialize a given port's parameters - * @aggregator: the aggregator we're looking at + * @port: the port we're looking at * @lacp_fast: boolean. whether fast periodic should be used */ static void ad_initialize_port(struct port *port, int lacp_fast) @@ -1967,6 +1967,7 @@ static void ad_marker_response_received(struct bond_marker *marker, /** * bond_3ad_initiate_agg_selection - initate aggregator selection * @bond: bonding struct + * @timeout: timeout value to set * * Set the aggregation selection timer, to initiate an agg selection in * the very near future. Called during first initialization, and during @@ -2259,7 +2260,7 @@ void bond_3ad_update_ad_actor_settings(struct bonding *bond) /** * bond_3ad_state_machine_handler - handle state machines timeout - * @bond: bonding struct to work on + * @work: work context to fetch bonding struct to work on from * * The state machine handling concept in this module is to check every tick * which state machine should operate any function. The execution order is @@ -2500,7 +2501,7 @@ void bond_3ad_adapter_speed_duplex_changed(struct slave *slave) /** * bond_3ad_handle_link_change - handle a slave's link status change indication * @slave: slave struct to work on - * @status: whether the link is now up or down + * @link: whether the link is now up or down * * Handle reselection of aggregator (if needed) for this port. */ @@ -2551,7 +2552,7 @@ void bond_3ad_handle_link_change(struct slave *slave, char link) /** * bond_3ad_set_carrier - set link state for bonding master - * @bond - bonding structure + * @bond: bonding structure * * if we have an active aggregator, we're up, if not, we're down. * Presumes that we cannot have an active aggregator if there are @@ -2664,7 +2665,7 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, /** * bond_3ad_update_lacp_rate - change the lacp rate - * @bond - bonding struct + * @bond: bonding struct * * When modify lacp_rate parameter via sysfs, * update actor_oper_port_state of each port. diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 095ea51d1853..4e1b7deb724b 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1206,8 +1206,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav /** * alb_set_mac_address - * @bond: - * @addr: + * @bond: bonding we're working on + * @addr: MAC address to set * * In TLB mode all slaves are configured to the bond's hw address, but set * their dev_addr field to different addresses (based on their permanent hw diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 5ad43aaf76e5..415a37e44cae 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -322,6 +322,7 @@ netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, /** * bond_vlan_rx_add_vid - Propagates adding an id to slaves * @bond_dev: bonding net device that got called + * @proto: network protocol ID * @vid: vlan id being added */ static int bond_vlan_rx_add_vid(struct net_device *bond_dev, @@ -355,6 +356,7 @@ unwind: /** * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves * @bond_dev: bonding net device that got called + * @proto: network protocol ID * @vid: vlan id being removed */ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, @@ -948,7 +950,7 @@ static bool bond_should_notify_peers(struct bonding *bond) /** * change_active_interface - change the active slave into the specified one * @bond: our bonding struct - * @new: the new slave to make the active one + * @new_active: the new slave to make the active one * * Set the new slave to the bond's settings and unset them on the old * curr_active_slave. @@ -2205,7 +2207,8 @@ static int bond_release_and_destroy(struct net_device *bond_dev, int ret; ret = __bond_release_one(bond_dev, slave_dev, false, true); - if (ret == 0 && !bond_has_slaves(bond)) { + if (ret == 0 && !bond_has_slaves(bond) && + bond_dev->reg_state != NETREG_UNREGISTERING) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; netdev_info(bond_dev, "Destroying bond\n"); bond_remove_proc_entry(bond); @@ -4552,13 +4555,23 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) return ret; } +static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed) +{ + if (speed == 0 || speed == SPEED_UNKNOWN) + speed = slave->speed; + else + speed = min(speed, slave->speed); + + return speed; +} + static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev, struct ethtool_link_ksettings *cmd) { struct bonding *bond = netdev_priv(bond_dev); - unsigned long speed = 0; struct list_head *iter; struct slave *slave; + u32 speed = 0; cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; @@ -4570,8 +4583,13 @@ static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev, */ bond_for_each_slave(bond, slave, iter) { if (bond_slave_can_tx(slave)) { - if (slave->speed != SPEED_UNKNOWN) - speed += slave->speed; + if (slave->speed != SPEED_UNKNOWN) { + if (BOND_MODE(bond) == BOND_MODE_BROADCAST) + speed = bond_mode_bcast_speed(slave, + speed); + else + speed += slave->speed; + } if (cmd->base.duplex == DUPLEX_UNKNOWN && slave->duplex != DUPLEX_UNKNOWN) cmd->base.duplex = slave->duplex; diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c index ef1c3151fbb2..bd0ada4e81b0 100644 --- a/drivers/net/ethernet/3com/3c574_cs.c +++ b/drivers/net/ethernet/3com/3c574_cs.c @@ -951,7 +951,7 @@ static struct net_device_stats *el3_get_stats(struct net_device *dev) static void update_stats(struct net_device *dev) { unsigned int ioaddr = dev->base_addr; - u8 rx, tx, up; + u8 up; pr_debug("%s: updating the statistics.\n", dev->name); @@ -972,8 +972,8 @@ static void update_stats(struct net_device *dev) dev->stats.tx_packets += (up&0x30) << 4; /* Rx packets */ inb(ioaddr + 7); /* Tx deferrals */ inb(ioaddr + 8); - rx = inw(ioaddr + 10); - tx = inw(ioaddr + 12); + /* rx */ inw(ioaddr + 10); + /* tx */ inw(ioaddr + 12); EL3WINDOW(4); /* BadSSD */ inb(ioaddr + 12); diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c index aeae7966a082..08db4c9da2fa 100644 --- a/drivers/net/ethernet/8390/axnet_cs.c +++ b/drivers/net/ethernet/8390/axnet_cs.c @@ -898,6 +898,7 @@ static int ax_close(struct net_device *dev) /** * axnet_tx_timeout - handle transmit time out condition * @dev: network device which has apparently fallen asleep + * @txqueue: unused * * Called by kernel when device never acknowledges a transmit has * completed (or failed) - i.e. never posted a Tx related interrupt. diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 9934421814b4..fb37816a74db 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3715,11 +3715,11 @@ failed_mii_init: failed_irq: failed_init: fec_ptp_stop(pdev); - if (fep->reg_phy) - regulator_disable(fep->reg_phy); failed_reset: pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); + if (fep->reg_phy) + regulator_disable(fep->reg_phy); failed_regulator: clk_disable_unprepare(fep->clk_ahb); failed_clk_ahb: diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index a62ddd626929..c0c8efe42fce 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -981,7 +981,7 @@ struct i40e_aqc_set_vsi_promiscuous_modes { #define I40E_AQC_SET_VSI_PROMISC_BROADCAST 0x04 #define I40E_AQC_SET_VSI_DEFAULT 0x08 #define I40E_AQC_SET_VSI_PROMISC_VLAN 0x10 -#define I40E_AQC_SET_VSI_PROMISC_TX 0x8000 +#define I40E_AQC_SET_VSI_PROMISC_RX_ONLY 0x8000 __le16 seid; __le16 vlan_tag; #define I40E_AQC_SET_VSI_VLAN_VALID 0x8000 diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index afad5e9f80e0..6ab52cbd697a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1967,6 +1967,21 @@ i40e_status i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags, } /** + * i40e_is_aq_api_ver_ge + * @aq: pointer to AdminQ info containing HW API version to compare + * @maj: API major value + * @min: API minor value + * + * Assert whether current HW API version is greater/equal than provided. + **/ +static bool i40e_is_aq_api_ver_ge(struct i40e_adminq_info *aq, u16 maj, + u16 min) +{ + return (aq->api_maj_ver > maj || + (aq->api_maj_ver == maj && aq->api_min_ver >= min)); +} + +/** * i40e_aq_add_vsi * @hw: pointer to the hw struct * @vsi_ctx: pointer to a vsi context struct @@ -2091,18 +2106,16 @@ i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw, if (set) { flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST; - if (rx_only_promisc && - (((hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver >= 5)) || - (hw->aq.api_maj_ver > 1))) - flags |= I40E_AQC_SET_VSI_PROMISC_TX; + if (rx_only_promisc && i40e_is_aq_api_ver_ge(&hw->aq, 1, 5)) + flags |= I40E_AQC_SET_VSI_PROMISC_RX_ONLY; } cmd->promiscuous_flags = cpu_to_le16(flags); cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST); - if (((hw->aq.api_maj_ver >= 1) && (hw->aq.api_min_ver >= 5)) || - (hw->aq.api_maj_ver > 1)) - cmd->valid_flags |= cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_TX); + if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5)) + cmd->valid_flags |= + cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_RX_ONLY); cmd->seid = cpu_to_le16(seid); status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); @@ -2199,11 +2212,17 @@ enum i40e_status_code i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw, i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_vsi_promiscuous_modes); - if (enable) + if (enable) { flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST; + if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5)) + flags |= I40E_AQC_SET_VSI_PROMISC_RX_ONLY; + } cmd->promiscuous_flags = cpu_to_le16(flags); cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST); + if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5)) + cmd->valid_flags |= + cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_RX_ONLY); cmd->seid = cpu_to_le16(seid); cmd->vlan_tag = cpu_to_le16(vid | I40E_AQC_SET_VSI_VLAN_VALID); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b5399357a667..2e433fdbf2c3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -15463,6 +15463,9 @@ static void i40e_remove(struct pci_dev *pdev) i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0); i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0); + while (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) + usleep_range(1000, 2000); + /* no more scheduling of any task */ set_bit(__I40E_SUSPENDED, pf->state); set_bit(__I40E_DOWN, pf->state); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 7a6f2a0d413f..9593aa4eea36 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -5142,6 +5142,8 @@ static int igc_probe(struct pci_dev *pdev, device_set_wakeup_enable(&adapter->pdev->dev, adapter->flags & IGC_FLAG_WOL_SUPPORTED); + igc_ptp_init(adapter); + /* reset the hardware with the new settings */ igc_reset(adapter); @@ -5158,9 +5160,6 @@ static int igc_probe(struct pci_dev *pdev, /* carrier off reporting is important to ethtool even BEFORE open */ netif_carrier_off(netdev); - /* do hw tstamp init after resetting */ - igc_ptp_init(adapter); - /* Check if Media Autosense is enabled */ adapter->ei = *ei; diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index e67d4655b47e..36c999250fcc 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -496,8 +496,6 @@ void igc_ptp_init(struct igc_adapter *adapter) adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; - igc_ptp_reset(adapter); - adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps, &adapter->pdev->dev); if (IS_ERR(adapter->ptp_clock)) { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 5975521a4c86..93c4cf7fedbf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1226,8 +1226,8 @@ int otx2_config_npa(struct otx2_nic *pfvf) if (!hw->pool_cnt) return -EINVAL; - qset->pool = devm_kzalloc(pfvf->dev, sizeof(struct otx2_pool) * - hw->pool_cnt, GFP_KERNEL); + qset->pool = devm_kcalloc(pfvf->dev, hw->pool_cnt, + sizeof(struct otx2_pool), GFP_KERNEL); if (!qset->pool) return -ENOMEM; diff --git a/drivers/net/ethernet/sfc/ef100_rx.c b/drivers/net/ethernet/sfc/ef100_rx.c index 13ba1a4f66fc..012925e878f4 100644 --- a/drivers/net/ethernet/sfc/ef100_rx.c +++ b/drivers/net/ethernet/sfc/ef100_rx.c @@ -31,6 +31,11 @@ #define ESF_GZ_RX_PREFIX_NT_OR_INNER_L3_CLASS_WIDTH \ ESF_GZ_RX_PREFIX_HCLASS_NT_OR_INNER_L3_CLASS_WIDTH +bool ef100_rx_buf_hash_valid(const u8 *prefix) +{ + return PREFIX_FIELD(prefix, RSS_HASH_VALID); +} + static bool check_fcs(struct efx_channel *channel, u32 *prefix) { u16 rxclass; diff --git a/drivers/net/ethernet/sfc/ef100_rx.h b/drivers/net/ethernet/sfc/ef100_rx.h index f2f266863966..fe45b36458d1 100644 --- a/drivers/net/ethernet/sfc/ef100_rx.h +++ b/drivers/net/ethernet/sfc/ef100_rx.h @@ -14,6 +14,7 @@ #include "net_driver.h" +bool ef100_rx_buf_hash_valid(const u8 *prefix); void efx_ef100_ev_rx(struct efx_channel *channel, const efx_qword_t *p_event); void ef100_rx_write(struct efx_rx_queue *rx_queue); void __ef100_rx_packet(struct efx_channel *channel); diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index a9808e86068d..daf0c00c1242 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -45,6 +45,14 @@ static inline void efx_rx_flush_packet(struct efx_channel *channel) __ef100_rx_packet, __efx_rx_packet, channel); } +static inline bool efx_rx_buf_hash_valid(struct efx_nic *efx, const u8 *prefix) +{ + if (efx->type->rx_buf_hash_valid) + return INDIRECT_CALL_1(efx->type->rx_buf_hash_valid, + ef100_rx_buf_hash_valid, + prefix); + return true; +} /* Maximum number of TCP segments we support for soft-TSO */ #define EFX_TSO_MAX_SEGS 100 diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 7bb7ecb480ae..dcb741d8bd11 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -1265,6 +1265,7 @@ struct efx_udp_tunnel { * @rx_write: Write RX descriptors and doorbell * @rx_defer_refill: Generate a refill reminder event * @rx_packet: Receive the queued RX buffer on a channel + * @rx_buf_hash_valid: Determine whether the RX prefix contains a valid hash * @ev_probe: Allocate resources for event queue * @ev_init: Initialise event queue on the NIC * @ev_fini: Deinitialise event queue on the NIC @@ -1409,6 +1410,7 @@ struct efx_nic_type { void (*rx_write)(struct efx_rx_queue *rx_queue); void (*rx_defer_refill)(struct efx_rx_queue *rx_queue); void (*rx_packet)(struct efx_channel *channel); + bool (*rx_buf_hash_valid)(const u8 *prefix); int (*ev_probe)(struct efx_channel *channel); int (*ev_init)(struct efx_channel *channel); void (*ev_fini)(struct efx_channel *channel); diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index fb77c7bbe4af..ef9bca92b0b7 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -525,7 +525,8 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf, return; } - if (efx->net_dev->features & NETIF_F_RXHASH) + if (efx->net_dev->features & NETIF_F_RXHASH && + efx_rx_buf_hash_valid(efx, eh)) skb_set_hash(skb, efx_rx_buf_hash(efx, eh), PKT_HASH_TYPE_L3); if (csum) { diff --git a/drivers/net/fddi/skfp/cfm.c b/drivers/net/fddi/skfp/cfm.c index e9bf42996de8..4eea3408034b 100644 --- a/drivers/net/fddi/skfp/cfm.c +++ b/drivers/net/fddi/skfp/cfm.c @@ -36,10 +36,6 @@ #define KERNEL #include "h/smtstate.h" -#ifndef lint -static const char ID_sccs[] = "@(#)cfm.c 2.18 98/10/06 (C) SK " ; -#endif - /* * FSM Macros */ @@ -208,7 +204,6 @@ void cfm(struct s_smc *smc, int event) { int state ; /* remember last state */ int cond ; - int oldstate ; /* We will do the following: */ /* - compute the variable WC_Flag for every port (This is where */ @@ -222,7 +217,6 @@ void cfm(struct s_smc *smc, int event) /* - change the portstates */ cem_priv_state (smc, event); - oldstate = smc->mib.fddiSMTCF_State ; do { DB_CFM("CFM : state %s%s event %s", smc->mib.fddiSMTCF_State & AFLAG ? "ACTIONS " : "", @@ -250,18 +244,11 @@ void cfm(struct s_smc *smc, int event) if (cond != smc->mib.fddiSMTPeerWrapFlag) smt_srf_event(smc,SMT_COND_SMT_PEER_WRAP,0,cond) ; -#if 0 /* - * Don't send ever MAC_PATH_CHANGE events. Our MAC is hard-wired + * Don't ever send MAC_PATH_CHANGE events. Our MAC is hard-wired * to the primary path. */ - /* - * path change - */ - if (smc->mib.fddiSMTCF_State != oldstate) { - smt_srf_event(smc,SMT_EVENT_MAC_PATH_CHANGE,INDEX_MAC,0) ; - } -#endif + #endif /* no SLIM_SMT */ /* diff --git a/drivers/net/fddi/skfp/fplustm.c b/drivers/net/fddi/skfp/fplustm.c index 02966d141948..4cbb145c74ab 100644 --- a/drivers/net/fddi/skfp/fplustm.c +++ b/drivers/net/fddi/skfp/fplustm.c @@ -21,10 +21,6 @@ #include <linux/bitrev.h> #include <linux/etherdevice.h> -#ifndef lint -static const char ID_sccs[] = "@(#)fplustm.c 1.32 99/02/23 (C) SK " ; -#endif - #ifndef UNUSED #ifdef lint #define UNUSED(x) (x) = (x) diff --git a/drivers/net/fddi/skfp/hwmtm.c b/drivers/net/fddi/skfp/hwmtm.c index 3412e0fb0ac4..107039056511 100644 --- a/drivers/net/fddi/skfp/hwmtm.c +++ b/drivers/net/fddi/skfp/hwmtm.c @@ -10,10 +10,6 @@ * ******************************************************************************/ -#ifndef lint -static char const ID_sccs[] = "@(#)hwmtm.c 1.40 99/05/31 (C) SK" ; -#endif - #define HWMTM #ifndef FDDI diff --git a/drivers/net/fddi/skfp/smt.c b/drivers/net/fddi/skfp/smt.c index b8c59d803ce6..774a6e3b0a67 100644 --- a/drivers/net/fddi/skfp/smt.c +++ b/drivers/net/fddi/skfp/smt.c @@ -20,10 +20,6 @@ #define KERNEL #include "h/smtstate.h" -#ifndef lint -static const char ID_sccs[] = "@(#)smt.c 2.43 98/11/23 (C) SK " ; -#endif - /* * FC in SMbuf */ @@ -1561,7 +1557,7 @@ u_long smt_get_tid(struct s_smc *smc) return tid & 0x3fffffffL; } - +#ifdef LITTLE_ENDIAN /* * table of parameter lengths */ @@ -1641,6 +1637,7 @@ static const struct smt_pdef { } ; #define N_SMT_PLEN ARRAY_SIZE(smt_pdef) +#endif int smt_check_para(struct s_smc *smc, struct smt_header *sm, const u_short list[]) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 15e87c097b0b..5bca94c99006 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -106,12 +106,21 @@ static void ipvlan_port_destroy(struct net_device *dev) kfree(port); } +#define IPVLAN_ALWAYS_ON_OFLOADS \ + (NETIF_F_SG | NETIF_F_HW_CSUM | \ + NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL) + +#define IPVLAN_ALWAYS_ON \ + (IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED) + #define IPVLAN_FEATURES \ - (NETIF_F_SG | NETIF_F_CSUM_MASK | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ + (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_ALL_TSO | NETIF_F_GSO_ROBUST | \ NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) + /* NETIF_F_GSO_ENCAP_ALL NETIF_F_GSO_SOFTWARE Newly added */ + #define IPVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) @@ -125,7 +134,9 @@ static int ipvlan_init(struct net_device *dev) dev->state = (dev->state & ~IPVLAN_STATE_MASK) | (phy_dev->state & IPVLAN_STATE_MASK); dev->features = phy_dev->features & IPVLAN_FEATURES; - dev->features |= NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED; + dev->features |= IPVLAN_ALWAYS_ON; + dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES; + dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS; dev->hw_enc_features |= dev->features; dev->gso_max_size = phy_dev->gso_max_size; dev->gso_max_segs = phy_dev->gso_max_segs; @@ -227,7 +238,14 @@ static netdev_features_t ipvlan_fix_features(struct net_device *dev, { struct ipvl_dev *ipvlan = netdev_priv(dev); - return features & (ipvlan->sfeatures | ~IPVLAN_FEATURES); + features |= NETIF_F_ALL_FOR_ALL; + features &= (ipvlan->sfeatures | ~IPVLAN_FEATURES); + features = netdev_increment_features(ipvlan->phy_dev->features, + features, features); + features |= IPVLAN_ALWAYS_ON; + features &= (IPVLAN_FEATURES | IPVLAN_ALWAYS_ON); + + return features; } static void ipvlan_change_rx_flags(struct net_device *dev, int change) @@ -734,10 +752,9 @@ static int ipvlan_device_event(struct notifier_block *unused, case NETDEV_FEAT_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { - ipvlan->dev->features = dev->features & IPVLAN_FEATURES; ipvlan->dev->gso_max_size = dev->gso_max_size; ipvlan->dev->gso_max_segs = dev->gso_max_segs; - netdev_features_change(ipvlan->dev); + netdev_update_features(ipvlan->dev); } break; diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c index 7bcee41905cf..3ca4daf63389 100644 --- a/drivers/net/wan/dlci.c +++ b/drivers/net/wan/dlci.c @@ -295,14 +295,13 @@ static int dlci_close(struct net_device *dev) { struct dlci_local *dlp; struct frad_local *flp; - int err; netif_stop_queue(dev); dlp = netdev_priv(dev); flp = netdev_priv(dlp->slave); - err = (*flp->deactivate)(dlp->slave, dev); + (*flp->deactivate)(dlp->slave, dev); return 0; } diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c index dfc16770458d..386ed2aa31fd 100644 --- a/drivers/net/wan/hdlc.c +++ b/drivers/net/wan/hdlc.c @@ -230,6 +230,7 @@ static void hdlc_setup_dev(struct net_device *dev) dev->max_mtu = HDLC_MAX_MTU; dev->type = ARPHRD_RAWHDLC; dev->hard_header_len = 16; + dev->needed_headroom = 0; dev->addr_len = 0; dev->header_ops = &hdlc_null_ops; } diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c index f70336bb6f52..f52b9fed0593 100644 --- a/drivers/net/wan/hdlc_x25.c +++ b/drivers/net/wan/hdlc_x25.c @@ -107,8 +107,14 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) { int result; + /* There should be a pseudo header of 1 byte added by upper layers. + * Check to make sure it is there before reading it. + */ + if (skb->len < 1) { + kfree_skb(skb); + return NETDEV_TX_OK; + } - /* X.25 to LAPB */ switch (skb->data[0]) { case X25_IFACE_DATA: /* Data to be transmitted */ skb_pull(skb, 1); @@ -294,6 +300,15 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr) return result; memcpy(&state(hdlc)->settings, &new_settings, size); + + /* There's no header_ops so hard_header_len should be 0. */ + dev->hard_header_len = 0; + /* When transmitting data: + * first we'll remove a pseudo header of 1 byte, + * then we'll prepend an LAPB header of at most 3 bytes. + */ + dev->needed_headroom = 3 - 1; + dev->type = ARPHRD_X25; call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, dev); netif_dormant_off(dev); diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index aac42c28fe62..9b67394471e1 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -58,7 +58,6 @@ struct nf_ipv6_ops { int (*output)(struct net *, struct sock *, struct sk_buff *)); int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); #if IS_MODULE(CONFIG_IPV6) - int (*br_defrag)(struct net *net, struct sk_buff *skb, u32 user); int (*br_fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, @@ -117,23 +116,6 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, #include <net/netfilter/ipv6/nf_defrag_ipv6.h> -static inline int nf_ipv6_br_defrag(struct net *net, struct sk_buff *skb, - u32 user) -{ -#if IS_MODULE(CONFIG_IPV6) - const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); - - if (!v6_ops) - return 1; - - return v6_ops->br_defrag(net, skb, user); -#elif IS_BUILTIN(CONFIG_IPV6) - return nf_ct_frag6_gather(net, skb, user); -#else - return 1; -#endif -} - int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, diff --git a/include/linux/phylink.h b/include/linux/phylink.h index a8e876317e25..c36fb41a7d90 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -402,7 +402,8 @@ void pcs_get_state(struct phylink_pcs *pcs, * For most 10GBASE-R, there is no advertisement. */ int pcs_config(struct phylink_pcs *pcs, unsigned int mode, - phy_interface_t interface, const unsigned long *advertising); + phy_interface_t interface, const unsigned long *advertising, + bool permit_pause_to_mac); /** * pcs_an_restart() - restart 802.3z BaseX autonegotiation diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 4fd830a62be2..cfed0ac44d38 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -213,11 +213,13 @@ static int stack_map_get_build_id_32(void *page_addr, phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr)); - for (i = 0; i < ehdr->e_phnum; ++i) - if (phdr[i].p_type == PT_NOTE) - return stack_map_parse_build_id(page_addr, build_id, - page_addr + phdr[i].p_offset, - phdr[i].p_filesz); + for (i = 0; i < ehdr->e_phnum; ++i) { + if (phdr[i].p_type == PT_NOTE && + !stack_map_parse_build_id(page_addr, build_id, + page_addr + phdr[i].p_offset, + phdr[i].p_filesz)) + return 0; + } return -EINVAL; } @@ -236,11 +238,13 @@ static int stack_map_get_build_id_64(void *page_addr, phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr)); - for (i = 0; i < ehdr->e_phnum; ++i) - if (phdr[i].p_type == PT_NOTE) - return stack_map_parse_build_id(page_addr, build_id, - page_addr + phdr[i].p_offset, - phdr[i].p_filesz); + for (i = 0; i < ehdr->e_phnum; ++i) { + if (phdr[i].p_type == PT_NOTE && + !stack_map_parse_build_id(page_addr, build_id, + page_addr + phdr[i].p_offset, + phdr[i].p_filesz)) + return 0; + } return -EINVAL; } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 1641f414d1ba..ebe33b60efd6 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2238,6 +2238,10 @@ static int compat_do_ebt_get_ctl(struct sock *sk, int cmd, struct ebt_table *t; struct net *net = sock_net(sk); + if ((cmd == EBT_SO_GET_INFO || cmd == EBT_SO_GET_INIT_INFO) && + *len != sizeof(struct compat_ebt_replace)) + return -EINVAL; + if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 809673222382..8d033a75a766 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -168,6 +168,7 @@ static unsigned int nf_ct_br_defrag4(struct sk_buff *skb, static unsigned int nf_ct_br_defrag6(struct sk_buff *skb, const struct nf_hook_state *state) { +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) u16 zone_id = NF_CT_DEFAULT_ZONE_ID; enum ip_conntrack_info ctinfo; struct br_input_skb_cb cb; @@ -180,14 +181,17 @@ static unsigned int nf_ct_br_defrag6(struct sk_buff *skb, br_skb_cb_save(skb, &cb, sizeof(struct inet6_skb_parm)); - err = nf_ipv6_br_defrag(state->net, skb, - IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id); + err = nf_ct_frag6_gather(state->net, skb, + IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id); /* queued */ if (err == -EINPROGRESS) return NF_STOLEN; br_skb_cb_restore(skb, &cb, IP6CB(skb)->frag_max_size); return err == 0 ? NF_ACCEPT : NF_DROP; +#else + return NF_ACCEPT; +#endif } static int nf_ct_br_ip_check(const struct sk_buff *skb) diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 78ff9b3f1d40..b93876c57fc4 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -398,6 +398,7 @@ static int j1939_sk_init(struct sock *sk) spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); sk->sk_destruct = j1939_sk_sock_destruct; + sk->sk_protocol = CAN_J1939; return 0; } @@ -466,6 +467,14 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out_release_sock; } + if (!ndev->ml_priv) { + netdev_warn_once(ndev, + "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n"); + dev_put(ndev); + ret = -ENODEV; + goto out_release_sock; + } + priv = j1939_netdev_start(ndev); dev_put(ndev); if (IS_ERR(priv)) { @@ -553,6 +562,11 @@ static int j1939_sk_connect(struct socket *sock, struct sockaddr *uaddr, static void j1939_sk_sock2sockaddr_can(struct sockaddr_can *addr, const struct j1939_sock *jsk, int peer) { + /* There are two holes (2 bytes and 3 bytes) to clear to avoid + * leaking kernel information to user space. + */ + memset(addr, 0, J1939_MIN_NAMELEN); + addr->can_family = AF_CAN; addr->can_ifindex = jsk->ifindex; addr->can_addr.j1939.pgn = jsk->addr.pgn; diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 9f99af5b0b11..a8dd956b5e8e 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -352,17 +352,16 @@ void j1939_session_skb_queue(struct j1939_session *session, skb_queue_tail(&session->skb_queue, skb); } -static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) +static struct +sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, + unsigned int offset_start) { struct j1939_priv *priv = session->priv; + struct j1939_sk_buff_cb *do_skcb; struct sk_buff *skb = NULL; struct sk_buff *do_skb; - struct j1939_sk_buff_cb *do_skcb; - unsigned int offset_start; unsigned long flags; - offset_start = session->pkt.dpo * 7; - spin_lock_irqsave(&session->skb_queue.lock, flags); skb_queue_walk(&session->skb_queue, do_skb) { do_skcb = j1939_skb_to_cb(do_skb); @@ -382,6 +381,14 @@ static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) return skb; } +static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) +{ + unsigned int offset_start; + + offset_start = session->pkt.dpo * 7; + return j1939_session_skb_find_by_offset(session, offset_start); +} + /* see if we are receiver * returns 0 for broadcasts, although we will receive them */ @@ -716,10 +723,12 @@ static int j1939_session_tx_rts(struct j1939_session *session) return ret; session->last_txcmd = dat[0]; - if (dat[0] == J1939_TP_CMD_BAM) + if (dat[0] == J1939_TP_CMD_BAM) { j1939_tp_schedule_txtimer(session, 50); - - j1939_tp_set_rxtimeout(session, 1250); + j1939_tp_set_rxtimeout(session, 250); + } else { + j1939_tp_set_rxtimeout(session, 1250); + } netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); @@ -766,7 +775,7 @@ static int j1939_session_tx_dat(struct j1939_session *session) int ret = 0; u8 dat[8]; - se_skb = j1939_session_skb_find(session); + se_skb = j1939_session_skb_find_by_offset(session, session->pkt.tx * 7); if (!se_skb) return -ENOBUFS; @@ -787,6 +796,18 @@ static int j1939_session_tx_dat(struct j1939_session *session) if (len > 7) len = 7; + if (offset + len > se_skb->len) { + netdev_err_once(priv->ndev, + "%s: 0x%p: requested data outside of queued buffer: offset %i, len %i, pkt.tx: %i\n", + __func__, session, skcb->offset, se_skb->len , session->pkt.tx); + return -EOVERFLOW; + } + + if (!len) { + ret = -ENOBUFS; + break; + } + memcpy(&dat[1], &tpdat[offset], len); ret = j1939_tp_tx_dat(session, dat, len + 1); if (ret < 0) { @@ -1055,9 +1076,9 @@ static void __j1939_session_cancel(struct j1939_session *session, lockdep_assert_held(&session->priv->active_session_list_lock); session->err = j1939_xtp_abort_to_errno(priv, err); + session->state = J1939_SESSION_WAITING_ABORT; /* do not send aborts on incoming broadcasts */ if (!j1939_cb_is_broadcast(&session->skcb)) { - session->state = J1939_SESSION_WAITING_ABORT; j1939_xtp_tx_abort(priv, &session->skcb, !session->transmission, err, session->skcb.addr.pgn); @@ -1120,6 +1141,9 @@ static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) * cleanup including propagation of the error to user space. */ break; + case -EOVERFLOW: + j1939_session_cancel(session, J1939_XTP_ABORT_ECTS_TOO_BIG); + break; case 0: session->tx_retry = 0; break; @@ -1651,8 +1675,12 @@ static void j1939_xtp_rx_rts(struct j1939_priv *priv, struct sk_buff *skb, return; } session = j1939_xtp_rx_rts_session_new(priv, skb); - if (!session) + if (!session) { + if (cmd == J1939_TP_CMD_BAM && j1939_sk_recv_match(priv, skcb)) + netdev_info(priv->ndev, "%s: failed to create TP BAM session\n", + __func__); return; + } } else { if (j1939_xtp_rx_rts_session_active(session, skb)) { j1939_session_put(session); @@ -1661,11 +1689,15 @@ static void j1939_xtp_rx_rts(struct j1939_priv *priv, struct sk_buff *skb, } session->last_cmd = cmd; - j1939_tp_set_rxtimeout(session, 1250); - - if (cmd != J1939_TP_CMD_BAM && !session->transmission) { - j1939_session_txtimer_cancel(session); - j1939_tp_schedule_txtimer(session, 0); + if (cmd == J1939_TP_CMD_BAM) { + if (!session->transmission) + j1939_tp_set_rxtimeout(session, 750); + } else { + if (!session->transmission) { + j1939_session_txtimer_cancel(session); + j1939_tp_schedule_txtimer(session, 0); + } + j1939_tp_set_rxtimeout(session, 1250); } j1939_session_put(session); @@ -1716,6 +1748,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, int offset; int nbytes; bool final = false; + bool remain = false; bool do_cts_eoma = false; int packet; @@ -1750,7 +1783,8 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, __func__, session); goto out_session_cancel; } - se_skb = j1939_session_skb_find(session); + + se_skb = j1939_session_skb_find_by_offset(session, packet * 7); if (!se_skb) { netdev_warn(priv->ndev, "%s: 0x%p: no skb found\n", __func__, session); @@ -1769,7 +1803,20 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, } tpdat = se_skb->data; - memcpy(&tpdat[offset], &dat[1], nbytes); + if (!session->transmission) { + memcpy(&tpdat[offset], &dat[1], nbytes); + } else { + int err; + + err = memcmp(&tpdat[offset], &dat[1], nbytes); + if (err) + netdev_err_once(priv->ndev, + "%s: 0x%p: Data of RX-looped back packet (%*ph) doesn't match TX data (%*ph)!\n", + __func__, session, + nbytes, &dat[1], + nbytes, &tpdat[offset]); + } + if (packet == session->pkt.rx) session->pkt.rx++; @@ -1777,6 +1824,8 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, j1939_cb_is_broadcast(&session->skcb)) { if (session->pkt.rx >= session->pkt.total) final = true; + else + remain = true; } else { /* never final, an EOMA must follow */ if (session->pkt.rx >= session->pkt.last) @@ -1784,7 +1833,11 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, } if (final) { + j1939_session_timers_cancel(session); j1939_session_completed(session); + } else if (remain) { + if (!session->transmission) + j1939_tp_set_rxtimeout(session, 750); } else if (do_cts_eoma) { j1939_tp_set_rxtimeout(session, 1250); if (!session->transmission) @@ -1829,6 +1882,13 @@ static void j1939_xtp_rx_dat(struct j1939_priv *priv, struct sk_buff *skb) else j1939_xtp_rx_dat_one(session, skb); } + + if (j1939_cb_is_broadcast(skcb)) { + session = j1939_session_get_by_addr(priv, &skcb->addr, false, + false); + if (session) + j1939_xtp_rx_dat_one(session, skb); + } } /* j1939 main intf */ @@ -1920,7 +1980,7 @@ static void j1939_tp_cmd_recv(struct j1939_priv *priv, struct sk_buff *skb) if (j1939_tp_im_transmitter(skcb)) j1939_xtp_rx_rts(priv, skb, true); - if (j1939_tp_im_receiver(skcb)) + if (j1939_tp_im_receiver(skcb) || j1939_cb_is_broadcast(skcb)) j1939_xtp_rx_rts(priv, skb, false); break; @@ -1984,7 +2044,7 @@ int j1939_tp_recv(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); - if (!j1939_tp_im_involved_anydir(skcb)) + if (!j1939_tp_im_involved_anydir(skcb) && !j1939_cb_is_broadcast(skcb)) return 0; switch (skcb->addr.pgn) { @@ -2017,6 +2077,10 @@ void j1939_simple_recv(struct j1939_priv *priv, struct sk_buff *skb) if (!skb->sk) return; + if (skb->sk->sk_family != AF_CAN || + skb->sk->sk_protocol != CAN_J1939) + return; + j1939_session_list_lock(priv); session = j1939_session_get_simple(priv, skb); j1939_session_list_unlock(priv); diff --git a/net/core/dev.c b/net/core/dev.c index 7df6c9617321..b5d1129d8310 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8913,10 +8913,6 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack NL_SET_ERR_MSG(extack, "Active program does not match expected"); return -EEXIST; } - if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) { - NL_SET_ERR_MSG(extack, "XDP program already attached"); - return -EBUSY; - } /* put effective new program into new_prog */ if (link) @@ -8927,6 +8923,10 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB ? XDP_MODE_DRV : XDP_MODE_SKB; + if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) { + NL_SET_ERR_MSG(extack, "XDP program already attached"); + return -EBUSY; + } if (!offload && dev_xdp_prog(dev, other_mode)) { NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time"); return -EEXIST; diff --git a/net/core/devlink.c b/net/core/devlink.c index e674f0f46dc2..e5feb87beca7 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4063,7 +4063,7 @@ static int __devlink_snapshot_id_insert(struct devlink *devlink, u32 id) { lockdep_assert_held(&devlink->lock); - if (WARN_ON(xa_load(&devlink->snapshot_ids, id))) + if (xa_load(&devlink->snapshot_ids, id)) return -EEXIST; return xa_err(xa_store(&devlink->snapshot_ids, id, xa_mk_value(0), diff --git a/net/core/filter.c b/net/core/filter.c index 7124f0fe6974..b2df52086445 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8317,15 +8317,31 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ + int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 2; \ BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + fullsock_reg = reg; \ + jmp += 2; \ + } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ - si->dst_reg, si->src_reg, \ + fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_fullsock)); \ - *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 2); \ + *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ + if (si->dst_reg == si->src_reg) \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ si->dst_reg, si->src_reg, \ @@ -8334,6 +8350,49 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, OBJ_FIELD), \ si->dst_reg, si->dst_reg, \ offsetof(OBJ, OBJ_FIELD)); \ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_JMP_A(1); \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + } \ + } while (0) + +#define SOCK_OPS_GET_SK() \ + do { \ + int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 1; \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + fullsock_reg = reg; \ + jmp += 2; \ + } \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, \ + is_fullsock), \ + fullsock_reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + is_fullsock)); \ + *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ + if (si->dst_reg == si->src_reg) \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, sk),\ + si->dst_reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, sk));\ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_JMP_A(1); \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + } \ } while (0) #define SOCK_OPS_GET_TCP_SOCK_FIELD(FIELD) \ @@ -8620,17 +8679,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked); break; case offsetof(struct bpf_sock_ops, sk): - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct bpf_sock_ops_kern, - is_fullsock), - si->dst_reg, si->src_reg, - offsetof(struct bpf_sock_ops_kern, - is_fullsock)); - *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct bpf_sock_ops_kern, sk), - si->dst_reg, si->src_reg, - offsetof(struct bpf_sock_ops_kern, sk)); + SOCK_OPS_GET_SK(); break; } return insn - insn_buf; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 7e2e502ef519..5c3b906aeef3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5418,8 +5418,8 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb) skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) goto err_free; - - if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) + /* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */ + if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short)))) goto err_free; vhdr = (struct vlan_hdr *)skb->data; diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 409e79b84a83..6d0e942d082d 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -245,9 +245,6 @@ static const struct nf_ipv6_ops ipv6ops = { .route_input = ip6_route_input, .fragment = ip6_fragment, .reroute = nf_ip6_reroute, -#if IS_MODULE(CONFIG_IPV6) && IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) - .br_defrag = nf_ct_frag6_gather, -#endif #if IS_MODULE(CONFIG_IPV6) .br_fragment = br_ip6_fragment, #endif diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 8c1d1a595701..1aad411a0e46 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -725,8 +725,10 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, if (!psize) return -EINVAL; - if (!sk_wmem_schedule(sk, psize + dfrag->overhead)) + if (!sk_wmem_schedule(sk, psize + dfrag->overhead)) { + iov_iter_revert(&msg->msg_iter, psize); return -ENOMEM; + } } else { offset = dfrag->offset; psize = min_t(size_t, dfrag->data_len, avail_size); @@ -737,8 +739,11 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, */ ret = do_tcp_sendpages(ssk, page, offset, psize, msg->msg_flags | MSG_SENDPAGE_NOTLAST | MSG_DONTWAIT); - if (ret <= 0) + if (ret <= 0) { + if (!retransmission) + iov_iter_revert(&msg->msg_iter, psize); return ret; + } frag_truesize += ret; if (!retransmission) { @@ -1388,7 +1393,9 @@ static void mptcp_worker(struct work_struct *work) struct mptcp_data_frag *dfrag; u64 orig_write_seq; size_t copied = 0; - struct msghdr msg; + struct msghdr msg = { + .msg_flags = MSG_DONTWAIT, + }; long timeo = 0; lock_sock(sk); @@ -1421,7 +1428,6 @@ static void mptcp_worker(struct work_struct *work) lock_sock(ssk); - msg.msg_flags = MSG_DONTWAIT; orig_len = dfrag->data_len; orig_offset = dfrag->offset; orig_write_seq = dfrag->data_seq; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d878e34e3354..fd814e514f94 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2018,8 +2018,10 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (nla[NFTA_CHAIN_NAME]) { chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); } else { - if (!(flags & NFT_CHAIN_BINDING)) - return -EINVAL; + if (!(flags & NFT_CHAIN_BINDING)) { + err = -EINVAL; + goto err1; + } snprintf(name, sizeof(name), "__chain%llu", ++chain_id); chain->name = kstrdup(name, GFP_KERNEL); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 6428856ccbec..8e56f353ff35 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -27,8 +27,6 @@ struct nft_xt_match_priv { void *info; }; -static refcount_t nft_compat_pending_destroy = REFCOUNT_INIT(1); - static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx, const char *tablename) { @@ -215,6 +213,17 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) return 0; } +static void nft_compat_wait_for_destructors(void) +{ + /* xtables matches or targets can have side effects, e.g. + * creation/destruction of /proc files. + * The xt ->destroy functions are run asynchronously from + * work queue. If we have pending invocations we thus + * need to wait for those to finish. + */ + nf_tables_trans_destroy_flush_work(); +} + static int nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -238,14 +247,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv); - /* xtables matches or targets can have side effects, e.g. - * creation/destruction of /proc files. - * The xt ->destroy functions are run asynchronously from - * work queue. If we have pending invocations we thus - * need to wait for those to finish. - */ - if (refcount_read(&nft_compat_pending_destroy) > 1) - nf_tables_trans_destroy_flush_work(); + nft_compat_wait_for_destructors(); ret = xt_check_target(&par, size, proto, inv); if (ret < 0) @@ -260,7 +262,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, static void __nft_mt_tg_destroy(struct module *me, const struct nft_expr *expr) { - refcount_dec(&nft_compat_pending_destroy); module_put(me); kfree(expr->ops); } @@ -468,6 +469,8 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv); + nft_compat_wait_for_destructors(); + return xt_check_match(&par, size, proto, inv); } @@ -716,14 +719,6 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = { static struct nft_expr_type nft_match_type; -static void nft_mt_tg_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - enum nft_trans_phase phase) -{ - if (phase == NFT_TRANS_COMMIT) - refcount_inc(&nft_compat_pending_destroy); -} - static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -762,7 +757,6 @@ nft_match_select_ops(const struct nft_ctx *ctx, ops->type = &nft_match_type; ops->eval = nft_match_eval; ops->init = nft_match_init; - ops->deactivate = nft_mt_tg_deactivate, ops->destroy = nft_match_destroy; ops->dump = nft_match_dump; ops->validate = nft_match_validate; @@ -853,7 +847,6 @@ nft_target_select_ops(const struct nft_ctx *ctx, ops->size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); ops->init = nft_target_init; ops->destroy = nft_target_destroy; - ops->deactivate = nft_mt_tg_deactivate, ops->dump = nft_target_dump; ops->validate = nft_target_validate; ops->data = target; @@ -917,8 +910,6 @@ static void __exit nft_compat_module_exit(void) nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); - - WARN_ON_ONCE(refcount_read(&nft_compat_pending_destroy) != 1); } MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT); diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 07782836fad6..3c48cdc8935d 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -44,7 +44,7 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL); if (priv->flags & NFT_EXTHDR_F_PRESENT) { - *dest = (err >= 0); + nft_reg_store8(dest, err >= 0); return; } else if (err < 0) { goto err; @@ -141,7 +141,7 @@ static void nft_exthdr_ipv4_eval(const struct nft_expr *expr, err = ipv4_find_option(nft_net(pkt), skb, &offset, priv->type); if (priv->flags & NFT_EXTHDR_F_PRESENT) { - *dest = (err >= 0); + nft_reg_store8(dest, err >= 0); return; } else if (err < 0) { goto err; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index b4c0db0b7d31..90c558f89d46 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -692,23 +692,25 @@ static void qrtr_port_remove(struct qrtr_sock *ipc) */ static int qrtr_port_assign(struct qrtr_sock *ipc, int *port) { + u32 min_port; int rc; mutex_lock(&qrtr_port_lock); if (!*port) { - rc = idr_alloc(&qrtr_ports, ipc, - QRTR_MIN_EPH_SOCKET, QRTR_MAX_EPH_SOCKET + 1, - GFP_ATOMIC); - if (rc >= 0) - *port = rc; + min_port = QRTR_MIN_EPH_SOCKET; + rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, QRTR_MAX_EPH_SOCKET, GFP_ATOMIC); + if (!rc) + *port = min_port; } else if (*port < QRTR_MIN_EPH_SOCKET && !capable(CAP_NET_ADMIN)) { rc = -EACCES; } else if (*port == QRTR_PORT_CTRL) { - rc = idr_alloc(&qrtr_ports, ipc, 0, 1, GFP_ATOMIC); + min_port = 0; + rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, 0, GFP_ATOMIC); } else { - rc = idr_alloc(&qrtr_ports, ipc, *port, *port + 1, GFP_ATOMIC); - if (rc >= 0) - *port = rc; + min_port = *port; + rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, *port, GFP_ATOMIC); + if (!rc) + *port = min_port; } mutex_unlock(&qrtr_port_lock); diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index 9dd780215eef..be1c4003d67d 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -6,6 +6,7 @@ menuconfig TIPC tristate "The TIPC Protocol" depends on INET + depends on IPV6 || IPV6=n help The Transparent Inter Process Communication (TIPC) protocol is specially designed for intra cluster communication. This protocol diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 217516357ef2..90e3c70a91ad 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -275,8 +275,9 @@ err_out: static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, struct tipc_nl_compat_msg *msg) { - int err; + struct nlmsghdr *nlh; struct sk_buff *arg; + int err; if (msg->req_type && (!msg->req_size || !TLV_CHECK_TYPE(msg->req, msg->req_type))) @@ -305,6 +306,15 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, return -ENOMEM; } + nlh = nlmsg_put(arg, 0, 0, tipc_genl_family.id, 0, NLM_F_MULTI); + if (!nlh) { + kfree_skb(arg); + kfree_skb(msg->rep); + msg->rep = NULL; + return -EMSGSIZE; + } + nlmsg_end(arg, nlh); + err = __tipc_nl_compat_dumpit(cmd, msg, arg); if (err) { kfree_skb(msg->rep); diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index ede162f83eea..0e9310727281 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -67,7 +67,7 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, if (!info->btf_id || !info->nr_func_info || btf__get_from_id(info->btf_id, &prog_btf)) goto print; - finfo = (struct bpf_func_info *)info->func_info; + finfo = u64_to_ptr(info->func_info); func_type = btf__type_by_id(prog_btf, finfo->type_id); if (!func_type || !btf_is_func(func_type)) goto print; diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 8a4c2b3b0cd6..f61184653633 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -143,6 +143,20 @@ static int codegen_datasec_def(struct bpf_object *obj, var_name, align); return -EINVAL; } + /* Assume 32-bit architectures when generating data section + * struct memory layout. Given bpftool can't know which target + * host architecture it's emitting skeleton for, we need to be + * conservative and assume 32-bit one to ensure enough padding + * bytes are generated for pointer and long types. This will + * still work correctly for 64-bit architectures, because in + * the worst case we'll generate unnecessary padding field, + * which on 64-bit architectures is not strictly necessary and + * would be handled by natural 8-byte alignment. But it still + * will be a correct memory layout, based on recorded offsets + * in BTF. + */ + if (align > 4) + align = 4; align_off = (off + align - 1) / align * align; if (align_off != need_off) { @@ -397,7 +411,7 @@ static int do_skeleton(int argc, char **argv) { \n\ struct %1$s *obj; \n\ \n\ - obj = (typeof(obj))calloc(1, sizeof(*obj)); \n\ + obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ if (!obj) \n\ return NULL; \n\ if (%1$s__create_skeleton(obj)) \n\ @@ -461,7 +475,7 @@ static int do_skeleton(int argc, char **argv) { \n\ struct bpf_object_skeleton *s; \n\ \n\ - s = (typeof(s))calloc(1, sizeof(*s)); \n\ + s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ if (!s) \n\ return -1; \n\ obj->skeleton = s; \n\ @@ -479,7 +493,7 @@ static int do_skeleton(int argc, char **argv) /* maps */ \n\ s->map_cnt = %zu; \n\ s->map_skel_sz = sizeof(*s->maps); \n\ - s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz);\n\ + s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ if (!s->maps) \n\ goto err; \n\ ", @@ -515,7 +529,7 @@ static int do_skeleton(int argc, char **argv) /* programs */ \n\ s->prog_cnt = %zu; \n\ s->prog_skel_sz = sizeof(*s->progs); \n\ - s->progs = (typeof(s->progs))calloc(s->prog_cnt, s->prog_skel_sz);\n\ + s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ if (!s->progs) \n\ goto err; \n\ ", diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index 1b793759170e..a89f09e3c848 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -106,7 +106,7 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) switch (info->type) { case BPF_LINK_TYPE_RAW_TRACEPOINT: jsonw_string_field(json_wtr, "tp_name", - (const char *)info->raw_tracepoint.tp_name); + u64_to_ptr(info->raw_tracepoint.tp_name)); break; case BPF_LINK_TYPE_TRACING: err = get_prog_info(info->prog_id, &prog_info); @@ -185,7 +185,7 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) switch (info->type) { case BPF_LINK_TYPE_RAW_TRACEPOINT: printf("\n\ttp '%s' ", - (const char *)info->raw_tracepoint.tp_name); + (const char *)u64_to_ptr(info->raw_tracepoint.tp_name)); break; case BPF_LINK_TYPE_TRACING: err = get_prog_info(info->prog_id, &prog_info); diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index e3a79b5a9960..c46e52137b87 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -21,7 +21,15 @@ /* Make sure we do not use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 -#define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64)(unsigned long)ptr; +} + +static inline void *u64_to_ptr(__u64 ptr) +{ + return (void *)(unsigned long)ptr; +} #define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) #define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 158995d853b0..d393eb8263a6 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -428,14 +428,14 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, p_info("no instructions returned"); return -1; } - buf = (unsigned char *)(info->jited_prog_insns); + buf = u64_to_ptr(info->jited_prog_insns); member_len = info->jited_prog_len; } else { /* DUMP_XLATED */ if (info->xlated_prog_len == 0 || !info->xlated_prog_insns) { p_err("error retrieving insn dump: kernel.kptr_restrict set?"); return -1; } - buf = (unsigned char *)info->xlated_prog_insns; + buf = u64_to_ptr(info->xlated_prog_insns); member_len = info->xlated_prog_len; } @@ -444,7 +444,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, return -1; } - func_info = (void *)info->func_info; + func_info = u64_to_ptr(info->func_info); if (info->nr_line_info) { prog_linfo = bpf_prog_linfo__new(info); @@ -462,7 +462,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, n = write(fd, buf, member_len); close(fd); - if (n != member_len) { + if (n != (ssize_t)member_len) { p_err("error writing output file: %s", n < 0 ? strerror(errno) : "short write"); return -1; @@ -492,13 +492,13 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, __u32 i; if (info->nr_jited_ksyms) { kernel_syms_load(&dd); - ksyms = (__u64 *) info->jited_ksyms; + ksyms = u64_to_ptr(info->jited_ksyms); } if (json_output) jsonw_start_array(json_wtr); - lens = (__u32 *) info->jited_func_lens; + lens = u64_to_ptr(info->jited_func_lens); for (i = 0; i < info->nr_jited_func_lens; i++) { if (ksyms) { sym = kernel_syms_search(&dd, ksyms[i]); @@ -559,7 +559,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, } else { kernel_syms_load(&dd); dd.nr_jited_ksyms = info->nr_jited_ksyms; - dd.jited_ksyms = (__u64 *) info->jited_ksyms; + dd.jited_ksyms = u64_to_ptr(info->jited_ksyms); dd.btf = btf; dd.func_info = func_info; dd.finfo_rec_size = info->func_info_rec_size; @@ -1681,7 +1681,7 @@ static char *profile_target_name(int tgt_fd) goto out; } - func_info = (struct bpf_func_info *)(info_linear->info.func_info); + func_info = u64_to_ptr(info_linear->info.func_info); t = btf__type_by_id(btf, func_info[0].type_id); if (!t) { p_err("btf %d doesn't have type %d", diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index bc14db706b88..e9a4ecddb7a5 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -40,7 +40,7 @@ * Helper macro to manipulate data structures */ #ifndef offsetof -#define offsetof(TYPE, MEMBER) __builtin_offsetof(TYPE, MEMBER) +#define offsetof(TYPE, MEMBER) ((unsigned long)&((TYPE *)0)->MEMBER) #endif #ifndef container_of #define container_of(ptr, type, member) \ diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 4843e44916f7..7dfca7016aaa 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -41,6 +41,7 @@ struct btf { __u32 types_size; __u32 data_size; int fd; + int ptr_sz; }; static inline __u64 ptr_to_u64(const void *ptr) @@ -221,6 +222,70 @@ const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) return btf->types[type_id]; } +static int determine_ptr_size(const struct btf *btf) +{ + const struct btf_type *t; + const char *name; + int i; + + for (i = 1; i <= btf->nr_types; i++) { + t = btf__type_by_id(btf, i); + if (!btf_is_int(t)) + continue; + + name = btf__name_by_offset(btf, t->name_off); + if (!name) + continue; + + if (strcmp(name, "long int") == 0 || + strcmp(name, "long unsigned int") == 0) { + if (t->size != 4 && t->size != 8) + continue; + return t->size; + } + } + + return -1; +} + +static size_t btf_ptr_sz(const struct btf *btf) +{ + if (!btf->ptr_sz) + ((struct btf *)btf)->ptr_sz = determine_ptr_size(btf); + return btf->ptr_sz < 0 ? sizeof(void *) : btf->ptr_sz; +} + +/* Return pointer size this BTF instance assumes. The size is heuristically + * determined by looking for 'long' or 'unsigned long' integer type and + * recording its size in bytes. If BTF type information doesn't have any such + * type, this function returns 0. In the latter case, native architecture's + * pointer size is assumed, so will be either 4 or 8, depending on + * architecture that libbpf was compiled for. It's possible to override + * guessed value by using btf__set_pointer_size() API. + */ +size_t btf__pointer_size(const struct btf *btf) +{ + if (!btf->ptr_sz) + ((struct btf *)btf)->ptr_sz = determine_ptr_size(btf); + + if (btf->ptr_sz < 0) + /* not enough BTF type info to guess */ + return 0; + + return btf->ptr_sz; +} + +/* Override or set pointer size in bytes. Only values of 4 and 8 are + * supported. + */ +int btf__set_pointer_size(struct btf *btf, size_t ptr_sz) +{ + if (ptr_sz != 4 && ptr_sz != 8) + return -EINVAL; + btf->ptr_sz = ptr_sz; + return 0; +} + static bool btf_type_is_void(const struct btf_type *t) { return t == &btf_void || btf_is_fwd(t); @@ -253,7 +318,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) size = t->size; goto done; case BTF_KIND_PTR: - size = sizeof(void *); + size = btf_ptr_sz(btf); goto done; case BTF_KIND_TYPEDEF: case BTF_KIND_VOLATILE: @@ -293,9 +358,9 @@ int btf__align_of(const struct btf *btf, __u32 id) switch (kind) { case BTF_KIND_INT: case BTF_KIND_ENUM: - return min(sizeof(void *), (size_t)t->size); + return min(btf_ptr_sz(btf), (size_t)t->size); case BTF_KIND_PTR: - return sizeof(void *); + return btf_ptr_sz(btf); case BTF_KIND_TYPEDEF: case BTF_KIND_VOLATILE: case BTF_KIND_CONST: @@ -533,6 +598,18 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) if (IS_ERR(btf)) goto done; + switch (gelf_getclass(elf)) { + case ELFCLASS32: + btf__set_pointer_size(btf, 4); + break; + case ELFCLASS64: + btf__set_pointer_size(btf, 8); + break; + default: + pr_warn("failed to get ELF class (bitness) for %s\n", path); + break; + } + if (btf_ext && btf_ext_data) { *btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size); diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index f4a1a1d2b9a3..1ca14448df4c 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -76,6 +76,8 @@ LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf, LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf); LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); +LIBBPF_API size_t btf__pointer_size(const struct btf *btf); +LIBBPF_API int btf__set_pointer_size(struct btf *btf, size_t ptr_sz); LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id); diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index cf711168d34a..fe39bd774697 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -13,6 +13,7 @@ #include <errno.h> #include <linux/err.h> #include <linux/btf.h> +#include <linux/kernel.h> #include "btf.h" #include "hashmap.h" #include "libbpf.h" @@ -60,6 +61,7 @@ struct btf_dump { const struct btf_ext *btf_ext; btf_dump_printf_fn_t printf_fn; struct btf_dump_opts opts; + int ptr_sz; bool strip_mods; /* per-type auxiliary state */ @@ -138,6 +140,7 @@ struct btf_dump *btf_dump__new(const struct btf *btf, d->btf_ext = btf_ext; d->printf_fn = printf_fn; d->opts.ctx = opts ? opts->ctx : NULL; + d->ptr_sz = btf__pointer_size(btf) ? : sizeof(void *); d->type_names = hashmap__new(str_hash_fn, str_equal_fn, NULL); if (IS_ERR(d->type_names)) { @@ -549,6 +552,9 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) } } +static void btf_dump_emit_missing_aliases(struct btf_dump *d, __u32 id, + const struct btf_type *t); + static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id, const struct btf_type *t); static void btf_dump_emit_struct_def(struct btf_dump *d, __u32 id, @@ -671,6 +677,9 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) switch (kind) { case BTF_KIND_INT: + /* Emit type alias definitions if necessary */ + btf_dump_emit_missing_aliases(d, id, t); + tstate->emit_state = EMITTED; break; case BTF_KIND_ENUM: @@ -797,7 +806,7 @@ static void btf_dump_emit_bit_padding(const struct btf_dump *d, int align, int lvl) { int off_diff = m_off - cur_off; - int ptr_bits = sizeof(void *) * 8; + int ptr_bits = d->ptr_sz * 8; if (off_diff <= 0) /* no gap */ @@ -870,7 +879,7 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, btf_dump_printf(d, ": %d", m_sz); off = m_off + m_sz; } else { - m_sz = max(0, btf__resolve_size(d->btf, m->type)); + m_sz = max(0LL, btf__resolve_size(d->btf, m->type)); off = m_off + m_sz * 8; } btf_dump_printf(d, ";"); @@ -890,6 +899,32 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, btf_dump_printf(d, " __attribute__((packed))"); } +static const char *missing_base_types[][2] = { + /* + * GCC emits typedefs to its internal __PolyX_t types when compiling Arm + * SIMD intrinsics. Alias them to standard base types. + */ + { "__Poly8_t", "unsigned char" }, + { "__Poly16_t", "unsigned short" }, + { "__Poly64_t", "unsigned long long" }, + { "__Poly128_t", "unsigned __int128" }, +}; + +static void btf_dump_emit_missing_aliases(struct btf_dump *d, __u32 id, + const struct btf_type *t) +{ + const char *name = btf_dump_type_name(d, id); + int i; + + for (i = 0; i < ARRAY_SIZE(missing_base_types); i++) { + if (strcmp(name, missing_base_types[i][0]) == 0) { + btf_dump_printf(d, "typedef %s %s;\n\n", + missing_base_types[i][1], name); + break; + } + } +} + static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id, const struct btf_type *t) { diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 0a06124f7999..5d20b2da4427 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -2434,6 +2434,8 @@ static int bpf_object__init_btf(struct bpf_object *obj, BTF_ELF_SEC, err); goto out; } + /* enforce 8-byte pointers for BPF-targeted BTFs */ + btf__set_pointer_size(obj->btf, 8); err = 0; } if (btf_ext_data) { @@ -2542,6 +2544,8 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) if (IS_ERR(kern_btf)) return PTR_ERR(kern_btf); + /* enforce 8-byte pointers for BPF-targeted BTFs */ + btf__set_pointer_size(obj->btf, 8); bpf_object__sanitize_btf(obj, kern_btf); } @@ -3478,10 +3482,11 @@ bpf_object__probe_global_data(struct bpf_object *obj) map = bpf_create_map_xattr(&map_attr); if (map < 0) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + ret = -errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, errno); - return -errno; + __func__, cp, -ret); + return ret; } insns[0].imm = map; @@ -5194,7 +5199,8 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, static int bpf_object__collect_map_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data *data) { - int i, j, nrels, new_sz, ptr_sz = sizeof(void *); + const int bpf_ptr_sz = 8, host_ptr_sz = sizeof(void *); + int i, j, nrels, new_sz; const struct btf_var_secinfo *vi = NULL; const struct btf_type *sec, *var, *def; const struct btf_member *member; @@ -5243,7 +5249,7 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, vi = btf_var_secinfos(sec) + map->btf_var_idx; if (vi->offset <= rel.r_offset && - rel.r_offset + sizeof(void *) <= vi->offset + vi->size) + rel.r_offset + bpf_ptr_sz <= vi->offset + vi->size) break; } if (j == obj->nr_maps) { @@ -5279,17 +5285,20 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, return -EINVAL; moff = rel.r_offset - vi->offset - moff; - if (moff % ptr_sz) + /* here we use BPF pointer size, which is always 64 bit, as we + * are parsing ELF that was built for BPF target + */ + if (moff % bpf_ptr_sz) return -EINVAL; - moff /= ptr_sz; + moff /= bpf_ptr_sz; if (moff >= map->init_slots_sz) { new_sz = moff + 1; - tmp = realloc(map->init_slots, new_sz * ptr_sz); + tmp = realloc(map->init_slots, new_sz * host_ptr_sz); if (!tmp) return -ENOMEM; map->init_slots = tmp; memset(map->init_slots + map->init_slots_sz, 0, - (new_sz - map->init_slots_sz) * ptr_sz); + (new_sz - map->init_slots_sz) * host_ptr_sz); map->init_slots_sz = new_sz; } map->init_slots[moff] = targ_map; @@ -6012,9 +6021,10 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path, } if (bpf_obj_pin(prog->instances.fds[instance], path)) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warn("failed to pin program: %s\n", cp); - return -errno; + return err; } pr_debug("pinned program '%s'\n", path); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 0c4722bfdd0a..e35bd6cdbdbf 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -295,5 +295,7 @@ LIBBPF_0.1.0 { bpf_program__set_sk_lookup; btf__parse; btf__parse_raw; + btf__pointer_size; btf__set_fd; + btf__set_pointer_size; } LIBBPF_0.0.9; diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c index 7afa4160416f..284d5921c345 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c @@ -159,15 +159,15 @@ void test_bpf_obj_id(void) /* Check getting link info */ info_len = sizeof(struct bpf_link_info) * 2; bzero(&link_infos[i], info_len); - link_infos[i].raw_tracepoint.tp_name = (__u64)&tp_name; + link_infos[i].raw_tracepoint.tp_name = ptr_to_u64(&tp_name); link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name); err = bpf_obj_get_info_by_fd(bpf_link__fd(links[i]), &link_infos[i], &info_len); if (CHECK(err || link_infos[i].type != BPF_LINK_TYPE_RAW_TRACEPOINT || link_infos[i].prog_id != prog_infos[i].id || - link_infos[i].raw_tracepoint.tp_name != (__u64)&tp_name || - strcmp((char *)link_infos[i].raw_tracepoint.tp_name, + link_infos[i].raw_tracepoint.tp_name != ptr_to_u64(&tp_name) || + strcmp(u64_to_ptr(link_infos[i].raw_tracepoint.tp_name), "sys_enter") || info_len != sizeof(struct bpf_link_info), "get-link-info(fd)", @@ -178,7 +178,7 @@ void test_bpf_obj_id(void) link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT, link_infos[i].id, link_infos[i].prog_id, prog_infos[i].id, - (char *)link_infos[i].raw_tracepoint.tp_name, + (const char *)u64_to_ptr(link_infos[i].raw_tracepoint.tp_name), "sys_enter")) goto done; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index cb33a7ee4e04..39fb81d9daeb 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -12,15 +12,16 @@ void btf_dump_printf(void *ctx, const char *fmt, va_list args) static struct btf_dump_test_case { const char *name; const char *file; + bool known_ptr_sz; struct btf_dump_opts opts; } btf_dump_test_cases[] = { - {"btf_dump: syntax", "btf_dump_test_case_syntax", {}}, - {"btf_dump: ordering", "btf_dump_test_case_ordering", {}}, - {"btf_dump: padding", "btf_dump_test_case_padding", {}}, - {"btf_dump: packing", "btf_dump_test_case_packing", {}}, - {"btf_dump: bitfields", "btf_dump_test_case_bitfields", {}}, - {"btf_dump: multidim", "btf_dump_test_case_multidim", {}}, - {"btf_dump: namespacing", "btf_dump_test_case_namespacing", {}}, + {"btf_dump: syntax", "btf_dump_test_case_syntax", true, {}}, + {"btf_dump: ordering", "btf_dump_test_case_ordering", false, {}}, + {"btf_dump: padding", "btf_dump_test_case_padding", true, {}}, + {"btf_dump: packing", "btf_dump_test_case_packing", true, {}}, + {"btf_dump: bitfields", "btf_dump_test_case_bitfields", true, {}}, + {"btf_dump: multidim", "btf_dump_test_case_multidim", false, {}}, + {"btf_dump: namespacing", "btf_dump_test_case_namespacing", false, {}}, }; static int btf_dump_all_types(const struct btf *btf, @@ -62,6 +63,18 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t) goto done; } + /* tests with t->known_ptr_sz have no "long" or "unsigned long" type, + * so it's impossible to determine correct pointer size; but if they + * do, it should be 8 regardless of host architecture, becaues BPF + * target is always 64-bit + */ + if (!t->known_ptr_sz) { + btf__set_pointer_size(btf, 8); + } else { + CHECK(btf__pointer_size(btf) != 8, "ptr_sz", "exp %d, got %zu\n", + 8, btf__pointer_size(btf)); + } + snprintf(out_file, sizeof(out_file), "/tmp/%s.output.XXXXXX", t->file); fd = mkstemp(out_file); if (CHECK(fd < 0, "create_tmp", "failed to create file: %d\n", fd)) { diff --git a/tools/testing/selftests/bpf/prog_tests/core_extern.c b/tools/testing/selftests/bpf/prog_tests/core_extern.c index b093787e9448..1931a158510e 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_extern.c +++ b/tools/testing/selftests/bpf/prog_tests/core_extern.c @@ -159,8 +159,8 @@ void test_core_extern(void) exp = (uint64_t *)&t->data; for (j = 0; j < n; j++) { CHECK(got[j] != exp[j], "check_res", - "result #%d: expected %lx, but got %lx\n", - j, exp[j], got[j]); + "result #%d: expected %llx, but got %llx\n", + j, (__u64)exp[j], (__u64)got[j]); } cleanup: test_core_extern__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 084ed26a7d78..a54eafc5e4b3 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -237,8 +237,8 @@ .union_sz = sizeof(((type *)0)->union_field), \ .arr_sz = sizeof(((type *)0)->arr_field), \ .arr_elem_sz = sizeof(((type *)0)->arr_field[0]), \ - .ptr_sz = sizeof(((type *)0)->ptr_field), \ - .enum_sz = sizeof(((type *)0)->enum_field), \ + .ptr_sz = 8, /* always 8-byte pointer for BPF */ \ + .enum_sz = sizeof(((type *)0)->enum_field), \ } #define SIZE_CASE(name) { \ @@ -432,20 +432,20 @@ static struct core_reloc_test_case test_cases[] = { .sb4 = -1, .sb20 = -0x17654321, .u32 = 0xBEEF, - .s32 = -0x3FEDCBA987654321, + .s32 = -0x3FEDCBA987654321LL, }), BITFIELDS_CASE(bitfields___bitfield_vs_int, { - .ub1 = 0xFEDCBA9876543210, + .ub1 = 0xFEDCBA9876543210LL, .ub2 = 0xA6, - .ub7 = -0x7EDCBA987654321, - .sb4 = -0x6123456789ABCDE, - .sb20 = 0xD00D, + .ub7 = -0x7EDCBA987654321LL, + .sb4 = -0x6123456789ABCDELL, + .sb20 = 0xD00DLL, .u32 = -0x76543, - .s32 = 0x0ADEADBEEFBADB0B, + .s32 = 0x0ADEADBEEFBADB0BLL, }), BITFIELDS_CASE(bitfields___just_big_enough, { - .ub1 = 0xF, - .ub2 = 0x0812345678FEDCBA, + .ub1 = 0xFLL, + .ub2 = 0x0812345678FEDCBALL, }), BITFIELDS_ERR_CASE(bitfields___err_too_big_bitfield), diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index a895bfed55db..197d0d217b56 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -16,7 +16,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, __u32 duration = 0, retval; struct bpf_map *data_map; const int zero = 0; - u64 *result = NULL; + __u64 *result = NULL; err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC, &pkt_obj, &pkt_fd); @@ -29,7 +29,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, link = calloc(sizeof(struct bpf_link *), prog_cnt); prog = calloc(sizeof(struct bpf_program *), prog_cnt); - result = malloc((prog_cnt + 32 /* spare */) * sizeof(u64)); + result = malloc((prog_cnt + 32 /* spare */) * sizeof(__u64)); if (CHECK(!link || !prog || !result, "alloc_memory", "failed to alloc memory")) goto close_prog; @@ -72,7 +72,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, goto close_prog; for (i = 0; i < prog_cnt; i++) - if (CHECK(result[i] != 1, "result", "fexit_bpf2bpf failed err %ld\n", + if (CHECK(result[i] != 1, "result", "fexit_bpf2bpf failed err %llu\n", result[i])) goto close_prog; diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index f11f187990e9..cd6dc80edf18 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -591,7 +591,7 @@ void test_flow_dissector(void) CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) || err || tattr.retval != 1, tests[i].name, - "err %d errno %d retval %d duration %d size %u/%lu\n", + "err %d errno %d retval %d duration %d size %u/%zu\n", err, errno, tattr.retval, tattr.duration, tattr.data_size_out, sizeof(flow_keys)); CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c index e3cb62b0a110..9efa7e50eab2 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data.c @@ -5,7 +5,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration) { int i, err, map_fd; - uint64_t num; + __u64 num; map_fd = bpf_find_map(__func__, obj, "result_number"); if (CHECK_FAIL(map_fd < 0)) @@ -14,7 +14,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration) struct { char *name; uint32_t key; - uint64_t num; + __u64 num; } tests[] = { { "relocate .bss reference", 0, 0 }, { "relocate .data reference", 1, 42 }, @@ -32,7 +32,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration) for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { err = bpf_map_lookup_elem(map_fd, &tests[i].key, &num); CHECK(err || num != tests[i].num, tests[i].name, - "err %d result %lx expected %lx\n", + "err %d result %llx expected %llx\n", err, num, tests[i].num); } } diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c index 43d0b5578f46..9c3c5c0f068f 100644 --- a/tools/testing/selftests/bpf/prog_tests/mmap.c +++ b/tools/testing/selftests/bpf/prog_tests/mmap.c @@ -21,7 +21,7 @@ void test_mmap(void) const long page_size = sysconf(_SC_PAGE_SIZE); int err, duration = 0, i, data_map_fd, data_map_id, tmp_fd, rdmap_fd; struct bpf_map *data_map, *bss_map; - void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2; + void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp0, *tmp1, *tmp2; struct test_mmap__bss *bss_data; struct bpf_map_info map_info; __u32 map_info_sz = sizeof(map_info); @@ -183,16 +183,23 @@ void test_mmap(void) /* check some more advanced mmap() manipulations */ + tmp0 = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED | MAP_ANONYMOUS, + -1, 0); + if (CHECK(tmp0 == MAP_FAILED, "adv_mmap0", "errno %d\n", errno)) + goto cleanup; + /* map all but last page: pages 1-3 mapped */ - tmp1 = mmap(NULL, 3 * page_size, PROT_READ, MAP_SHARED, + tmp1 = mmap(tmp0, 3 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED, data_map_fd, 0); - if (CHECK(tmp1 == MAP_FAILED, "adv_mmap1", "errno %d\n", errno)) + if (CHECK(tmp0 != tmp1, "adv_mmap1", "tmp0: %p, tmp1: %p\n", tmp0, tmp1)) { + munmap(tmp0, 4 * page_size); goto cleanup; + } /* unmap second page: pages 1, 3 mapped */ err = munmap(tmp1 + page_size, page_size); if (CHECK(err, "adv_mmap2", "errno %d\n", errno)) { - munmap(tmp1, map_sz); + munmap(tmp1, 4 * page_size); goto cleanup; } @@ -201,7 +208,7 @@ void test_mmap(void) MAP_SHARED | MAP_FIXED, data_map_fd, 0); if (CHECK(tmp2 == MAP_FAILED, "adv_mmap3", "errno %d\n", errno)) { munmap(tmp1, page_size); - munmap(tmp1 + 2*page_size, page_size); + munmap(tmp1 + 2*page_size, 2 * page_size); goto cleanup; } CHECK(tmp1 + page_size != tmp2, "adv_mmap4", @@ -211,7 +218,7 @@ void test_mmap(void) tmp2 = mmap(tmp1, 4 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED, data_map_fd, 0); if (CHECK(tmp2 == MAP_FAILED, "adv_mmap5", "errno %d\n", errno)) { - munmap(tmp1, 3 * page_size); /* unmap page 1 */ + munmap(tmp1, 4 * page_size); /* unmap page 1 */ goto cleanup; } CHECK(tmp1 != tmp2, "adv_mmap6", "tmp1: %p, tmp2: %p\n", tmp1, tmp2); diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c index dde2b7ae7bc9..935a294f049a 100644 --- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c +++ b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c @@ -28,7 +28,7 @@ void test_prog_run_xattr(void) "err %d errno %d retval %d\n", err, errno, tattr.retval); CHECK_ATTR(tattr.data_size_out != sizeof(pkt_v4), "data_size_out", - "incorrect output size, want %lu have %u\n", + "incorrect output size, want %zu have %u\n", sizeof(pkt_v4), tattr.data_size_out); CHECK_ATTR(buf[5] != 0, "overflow", diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c index c571584c00f5..9ff0412e1fd3 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c @@ -309,6 +309,7 @@ static void v4_to_v6(struct sockaddr_storage *ss) v6->sin6_addr.s6_addr[10] = 0xff; v6->sin6_addr.s6_addr[11] = 0xff; memcpy(&v6->sin6_addr.s6_addr[12], &v4.sin_addr.s_addr, 4); + memset(&v6->sin6_addr.s6_addr[0], 0, 10); } static int udp_recv_send(int server_fd) diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index 25de86af2d03..fafeddaad6a9 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -81,7 +81,7 @@ void test_skb_ctx(void) CHECK_ATTR(tattr.ctx_size_out != sizeof(skb), "ctx_size_out", - "incorrect output size, want %lu have %u\n", + "incorrect output size, want %zu have %u\n", sizeof(skb), tattr.ctx_size_out); for (i = 0; i < 5; i++) diff --git a/tools/testing/selftests/bpf/prog_tests/varlen.c b/tools/testing/selftests/bpf/prog_tests/varlen.c index c75525eab02c..dd324b4933db 100644 --- a/tools/testing/selftests/bpf/prog_tests/varlen.c +++ b/tools/testing/selftests/bpf/prog_tests/varlen.c @@ -44,25 +44,25 @@ void test_varlen(void) CHECK_VAL(bss->payload1_len2, size2); CHECK_VAL(bss->total1, size1 + size2); CHECK(memcmp(bss->payload1, exp_str, size1 + size2), "content_check", - "doesn't match!"); + "doesn't match!\n"); CHECK_VAL(data->payload2_len1, size1); CHECK_VAL(data->payload2_len2, size2); CHECK_VAL(data->total2, size1 + size2); CHECK(memcmp(data->payload2, exp_str, size1 + size2), "content_check", - "doesn't match!"); + "doesn't match!\n"); CHECK_VAL(data->payload3_len1, size1); CHECK_VAL(data->payload3_len2, size2); CHECK_VAL(data->total3, size1 + size2); CHECK(memcmp(data->payload3, exp_str, size1 + size2), "content_check", - "doesn't match!"); + "doesn't match!\n"); CHECK_VAL(data->payload4_len1, size1); CHECK_VAL(data->payload4_len2, size2); CHECK_VAL(data->total4, size1 + size2); CHECK(memcmp(data->payload4, exp_str, size1 + size2), "content_check", - "doesn't match!"); + "doesn't match!\n"); cleanup: test_varlen__destroy(skel); } diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h index 34d84717c946..69139ed66216 100644 --- a/tools/testing/selftests/bpf/progs/core_reloc_types.h +++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h @@ -1,5 +1,10 @@ #include <stdint.h> #include <stdbool.h> + +void preserce_ptr_sz_fn(long x) {} + +#define __bpf_aligned __attribute__((aligned(8))) + /* * KERNEL */ @@ -444,51 +449,51 @@ struct core_reloc_primitives { char a; int b; enum core_reloc_primitives_enum c; - void *d; - int (*f)(const char *); + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; }; struct core_reloc_primitives___diff_enum_def { char a; int b; - void *d; - int (*f)(const char *); + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; enum { X = 100, Y = 200, - } c; /* inline enum def with differing set of values */ + } c __bpf_aligned; /* inline enum def with differing set of values */ }; struct core_reloc_primitives___diff_func_proto { - void (*f)(int); /* incompatible function prototype */ - void *d; - enum core_reloc_primitives_enum c; + void (*f)(int) __bpf_aligned; /* incompatible function prototype */ + void *d __bpf_aligned; + enum core_reloc_primitives_enum c __bpf_aligned; int b; char a; }; struct core_reloc_primitives___diff_ptr_type { - const char * const d; /* different pointee type + modifiers */ - char a; + const char * const d __bpf_aligned; /* different pointee type + modifiers */ + char a __bpf_aligned; int b; enum core_reloc_primitives_enum c; - int (*f)(const char *); + int (*f)(const char *) __bpf_aligned; }; struct core_reloc_primitives___err_non_enum { char a[1]; int b; int c; /* int instead of enum */ - void *d; - int (*f)(const char *); + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; }; struct core_reloc_primitives___err_non_int { char a[1]; - int *b; /* ptr instead of int */ - enum core_reloc_primitives_enum c; - void *d; - int (*f)(const char *); + int *b __bpf_aligned; /* ptr instead of int */ + enum core_reloc_primitives_enum c __bpf_aligned; + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; }; struct core_reloc_primitives___err_non_ptr { @@ -496,7 +501,7 @@ struct core_reloc_primitives___err_non_ptr { int b; enum core_reloc_primitives_enum c; int d; /* int instead of ptr */ - int (*f)(const char *); + int (*f)(const char *) __bpf_aligned; }; /* @@ -507,7 +512,7 @@ struct core_reloc_mods_output { }; typedef const int int_t; -typedef const char *char_ptr_t; +typedef const char *char_ptr_t __bpf_aligned; typedef const int arr_t[7]; struct core_reloc_mods_substruct { @@ -523,9 +528,9 @@ typedef struct { struct core_reloc_mods { int a; int_t b; - char *c; + char *c __bpf_aligned; char_ptr_t d; - int e[3]; + int e[3] __bpf_aligned; arr_t f; struct core_reloc_mods_substruct g; core_reloc_mods_substruct_t h; @@ -535,9 +540,9 @@ struct core_reloc_mods { struct core_reloc_mods___mod_swap { int b; int_t a; - char *d; + char *d __bpf_aligned; char_ptr_t c; - int f[3]; + int f[3] __bpf_aligned; arr_t e; struct { int y; @@ -555,7 +560,7 @@ typedef arr1_t arr2_t; typedef arr2_t arr3_t; typedef arr3_t arr4_t; -typedef const char * const volatile fancy_char_ptr_t; +typedef const char * const volatile fancy_char_ptr_t __bpf_aligned; typedef core_reloc_mods_substruct_t core_reloc_mods_substruct_tt; @@ -567,7 +572,7 @@ struct core_reloc_mods___typedefs { arr4_t e; fancy_char_ptr_t d; fancy_char_ptr_t c; - int3_t b; + int3_t b __bpf_aligned; int3_t a; }; @@ -739,19 +744,19 @@ struct core_reloc_bitfields___bit_sz_change { int8_t sb4: 1; /* 4 -> 1 */ int32_t sb20: 30; /* 20 -> 30 */ /* non-bitfields */ - uint16_t u32; /* 32 -> 16 */ - int64_t s32; /* 32 -> 64 */ + uint16_t u32; /* 32 -> 16 */ + int64_t s32 __bpf_aligned; /* 32 -> 64 */ }; /* turn bitfield into non-bitfield and vice versa */ struct core_reloc_bitfields___bitfield_vs_int { uint64_t ub1; /* 3 -> 64 non-bitfield */ uint8_t ub2; /* 20 -> 8 non-bitfield */ - int64_t ub7; /* 7 -> 64 non-bitfield signed */ - int64_t sb4; /* 4 -> 64 non-bitfield signed */ - uint64_t sb20; /* 20 -> 16 non-bitfield unsigned */ - int32_t u32: 20; /* 32 non-bitfield -> 20 bitfield */ - uint64_t s32: 60; /* 32 non-bitfield -> 60 bitfield */ + int64_t ub7 __bpf_aligned; /* 7 -> 64 non-bitfield signed */ + int64_t sb4 __bpf_aligned; /* 4 -> 64 non-bitfield signed */ + uint64_t sb20 __bpf_aligned; /* 20 -> 16 non-bitfield unsigned */ + int32_t u32: 20; /* 32 non-bitfield -> 20 bitfield */ + uint64_t s32: 60 __bpf_aligned; /* 32 non-bitfield -> 60 bitfield */ }; struct core_reloc_bitfields___just_big_enough { diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index 1f1966e86e9f..3e6912e4df3d 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -54,6 +54,7 @@ SEC("sockops") int bpf_testcb(struct bpf_sock_ops *skops) { char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)]; + struct bpf_sock_ops *reuse = skops; struct tcphdr *thdr; int good_call_rv = 0; int bad_call_rv = 0; @@ -62,6 +63,46 @@ int bpf_testcb(struct bpf_sock_ops *skops) int v = 0; int op; + /* Test reading fields in bpf_sock_ops using single register */ + asm volatile ( + "%[reuse] = *(u32 *)(%[reuse] +96)" + : [reuse] "+r"(reuse) + :); + + asm volatile ( + "%[op] = *(u32 *)(%[skops] +96)" + : [op] "+r"(op) + : [skops] "r"(skops) + :); + + asm volatile ( + "r9 = %[skops];\n" + "r8 = *(u32 *)(r9 +164);\n" + "*(u32 *)(r9 +164) = r8;\n" + :: [skops] "r"(skops) + : "r9", "r8"); + + asm volatile ( + "r1 = %[skops];\n" + "r1 = *(u64 *)(r1 +184);\n" + "if r1 == 0 goto +1;\n" + "r1 = *(u32 *)(r1 +4);\n" + :: [skops] "r"(skops):"r1"); + + asm volatile ( + "r9 = %[skops];\n" + "r9 = *(u64 *)(r9 +184);\n" + "if r9 == 0 goto +1;\n" + "r9 = *(u32 *)(r9 +4);\n" + :: [skops] "r"(skops):"r9"); + + asm volatile ( + "r1 = %[skops];\n" + "r2 = *(u64 *)(r1 +184);\n" + "if r2 == 0 goto +1;\n" + "r2 = *(u32 *)(r2 +4);\n" + :: [skops] "r"(skops):"r1", "r2"); + op = (int) skops->op; update_event_map(op); diff --git a/tools/testing/selftests/bpf/progs/test_varlen.c b/tools/testing/selftests/bpf/progs/test_varlen.c index cd4b72c55dfe..913acdffd90f 100644 --- a/tools/testing/selftests/bpf/progs/test_varlen.c +++ b/tools/testing/selftests/bpf/progs/test_varlen.c @@ -15,9 +15,9 @@ int test_pid = 0; bool capture = false; /* .bss */ -long payload1_len1 = 0; -long payload1_len2 = 0; -long total1 = 0; +__u64 payload1_len1 = 0; +__u64 payload1_len2 = 0; +__u64 total1 = 0; char payload1[MAX_LEN + MAX_LEN] = {}; /* .data */ diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 305fae8f80a9..c75fc6447186 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -3883,7 +3883,7 @@ static int test_big_btf_info(unsigned int test_num) info_garbage.garbage = 0; err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len); if (CHECK(err || info_len != sizeof(*info), - "err:%d errno:%d info_len:%u sizeof(*info):%lu", + "err:%d errno:%d info_len:%u sizeof(*info):%zu", err, errno, info_len, sizeof(*info))) { err = -1; goto done; @@ -4094,7 +4094,7 @@ static int do_test_get_info(unsigned int test_num) if (CHECK(err || !info.id || info_len != sizeof(info) || info.btf_size != raw_btf_size || (ret = memcmp(raw_btf, user_btf, expected_nbytes)), - "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%lu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d", + "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%zu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d", err, errno, info.id, info_len, sizeof(info), raw_btf_size, info.btf_size, expected_nbytes, ret)) { err = -1; @@ -4730,7 +4730,7 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind, nexpected_line = snprintf(expected_line, line_size, "%s%u: {%u,0,%d,0x%x,0x%x,0x%x," - "{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s," + "{%llu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s," "%u,0x%x,[[%d,%d],[%d,%d]]}\n", percpu_map ? "\tcpu" : "", percpu_map ? cpu : next_key, @@ -4738,7 +4738,7 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind, v->unused_bits2a, v->bits28, v->unused_bits2b, - v->ui64, + (__u64)v->ui64, v->ui8a[0], v->ui8a[1], v->ui8a[2], v->ui8a[3], v->ui8a[4], v->ui8a[5], diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 6e09bf738473..dbb820dde138 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -135,6 +135,11 @@ static inline __u64 ptr_to_u64(const void *ptr) return (__u64) (unsigned long) ptr; } +static inline void *u64_to_ptr(__u64 ptr) +{ + return (void *) (unsigned long) ptr; +} + int bpf_find_map(const char *test, struct bpf_object *obj, const char *name); int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh index 18c5de53558a..bf361f30d6ef 100755 --- a/tools/testing/selftests/net/icmp_redirect.sh +++ b/tools/testing/selftests/net/icmp_redirect.sh @@ -180,6 +180,8 @@ setup() ;; r[12]) ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1 ip netns exec $ns sysctl -q -w net.ipv4.conf.all.send_redirects=1 + ip netns exec $ns sysctl -q -w net.ipv4.conf.default.rp_filter=0 + ip netns exec $ns sysctl -q -w net.ipv4.conf.all.rp_filter=0 ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1 ip netns exec $ns sysctl -q -w net.ipv6.route.mtu_expires=10 diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index d3e0809ab368..a47d1d832210 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -2,13 +2,18 @@ # SPDX-License-Identifier: GPL-2.0 # # This tests basic flowtable functionality. -# Creates following topology: +# Creates following default topology: # # Originator (MTU 9000) <-Router1-> MTU 1500 <-Router2-> Responder (MTU 2000) # Router1 is the one doing flow offloading, Router2 has no special # purpose other than having a link that is smaller than either Originator # and responder, i.e. TCPMSS announced values are too large and will still # result in fragmentation and/or PMTU discovery. +# +# You can check with different Orgininator/Link/Responder MTU eg: +# sh nft_flowtable.sh -o1000 -l500 -r100 +# + # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 @@ -21,29 +26,18 @@ ns2out="" log_netns=$(sysctl -n net.netfilter.nf_log_all_netns) -nft --version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without nft tool" - exit $ksft_skip -fi - -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi - -which nc > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without nc (netcat)" - exit $ksft_skip -fi +checktool (){ + $1 > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not $2" + exit $ksft_skip + fi +} -ip netns add nsr1 -if [ $? -ne 0 ];then - echo "SKIP: Could not create net namespace" - exit $ksft_skip -fi +checktool "nft --version" "run test without nft tool" +checktool "ip -Version" "run test without ip tool" +checktool "which nc" "run test without nc (netcat)" +checktool "ip netns add nsr1" "create net namespace" ip netns add ns1 ip netns add ns2 @@ -89,11 +83,24 @@ ip -net nsr2 addr add dead:2::1/64 dev veth1 # ns2 is going via nsr2 with a smaller mtu, so that TCPMSS announced by both peers # is NOT the lowest link mtu. -ip -net nsr1 link set veth0 mtu 9000 -ip -net ns1 link set eth0 mtu 9000 +omtu=9000 +lmtu=1500 +rmtu=2000 + +while getopts "o:l:r:" o +do + case $o in + o) omtu=$OPTARG;; + l) lmtu=$OPTARG;; + r) rmtu=$OPTARG;; + esac +done + +ip -net nsr1 link set veth0 mtu $omtu +ip -net ns1 link set eth0 mtu $omtu -ip -net nsr2 link set veth1 mtu 2000 -ip -net ns2 link set eth0 mtu 2000 +ip -net nsr2 link set veth1 mtu $rmtu +ip -net ns2 link set eth0 mtu $rmtu # transfer-net between nsr1 and nsr2. # these addresses are not used for connections. @@ -147,7 +154,7 @@ table inet filter { # as PMTUd is off. # This rule is deleted for the last test, when we expect PMTUd # to kick in and ensure all packets meet mtu requirements. - meta length gt 1500 accept comment something-to-grep-for + meta length gt $lmtu accept comment something-to-grep-for # next line blocks connection w.o. working offload. # we only do this for reverse dir, because we expect packets to @@ -243,8 +250,14 @@ test_tcp_forwarding_ip() sleep 3 - kill $lpid - kill $cpid + if ps -p $lpid > /dev/null;then + kill $lpid + fi + + if ps -p $cpid > /dev/null;then + kill $cpid + fi + wait check_transfer "$ns1in" "$ns2out" "ns1 -> ns2" |