diff options
90 files changed, 1366 insertions, 235 deletions
@@ -179,6 +179,7 @@ E: ralf@gnu.org P: 1024/AF7B30C1 CF 97 C2 CC 6D AE A7 FE C8 BA 9C FC 88 DE 32 C3 D: Linux/MIPS port D: Linux/68k hacker +D: AX25 maintainer S: Hauptstrasse 19 S: 79837 St. Blasien S: Germany @@ -677,6 +678,10 @@ D: Media subsystem (V4L/DVB) drivers and core D: EDAC drivers and EDAC 3.0 core rework S: Brazil +N: Landen Chao +E: Landen.Chao@mediatek.com +D: MT7531 Ethernet switch support + N: Raymond Chen E: raymondc@microsoft.com D: Author of Configure script @@ -814,6 +819,10 @@ D: Support for Xircom PGSDB9 (firmware and host driver) S: Bucharest S: Romania +N: John Crispin +E: john@phrozen.org +D: MediaTek MT7623 Gigabit ethernet support + N: Laurence Culhane E: loz@holmes.demon.co.uk D: Wrote the initial alpha SLIP code @@ -1538,6 +1547,10 @@ N: Andrew Haylett E: ajh@primag.co.uk D: Selection mechanism +N: Johan Hedberg +E: johan.hedberg@gmail.com +D: Bluetooth subsystem maintainer + N: Andre Hedrick E: andre@linux-ide.org E: andre@linuxdiskcert.org @@ -3052,6 +3065,10 @@ S: Demonstratsii 8-382 S: Tula 300000 S: Russia +N: Thomas Petazzoni +E: thomas.petazzoni@bootlin.com +D: Driver for the Marvell Armada 370/XP network unit. + N: Gordon Peters E: GordPeters@smarttech.com D: Isochronous receive for IEEE 1394 driver (OHCI module). diff --git a/MAINTAINERS b/MAINTAINERS index 85f9d818c257..8709c7cd3656 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3390,9 +3390,8 @@ F: Documentation/devicetree/bindings/iio/adc/avia-hx711.yaml F: drivers/iio/adc/hx711.c AX.25 NETWORK LAYER -M: Ralf Baechle <ralf@linux-mips.org> L: linux-hams@vger.kernel.org -S: Maintained +S: Orphan W: https://linux-ax25.in-berlin.de F: include/net/ax25.h F: include/uapi/linux/ax25.h @@ -3631,7 +3630,6 @@ F: drivers/mtd/devices/block2mtd.c BLUETOOTH DRIVERS M: Marcel Holtmann <marcel@holtmann.org> -M: Johan Hedberg <johan.hedberg@gmail.com> M: Luiz Augusto von Dentz <luiz.dentz@gmail.com> L: linux-bluetooth@vger.kernel.org S: Supported @@ -4726,11 +4724,8 @@ F: drivers/i2c/busses/i2c-octeon* F: drivers/i2c/busses/i2c-thunderx* CAVIUM LIQUIDIO NETWORK DRIVER -M: Derek Chickles <dchickles@marvell.com> -M: Satanand Burla <sburla@marvell.com> -M: Felix Manlunas <fmanlunas@marvell.com> L: netdev@vger.kernel.org -S: Supported +S: Orphan W: http://www.marvell.com F: drivers/net/ethernet/cavium/liquidio/ @@ -10239,7 +10234,6 @@ IBM Power SRIOV Virtual NIC Device Driver M: Haren Myneni <haren@linux.ibm.com> M: Rick Lindsley <ricklind@linux.ibm.com> R: Nick Child <nnac123@linux.ibm.com> -R: Dany Madden <danymadden@us.ibm.com> R: Thomas Falcon <tlfalcon@linux.ibm.com> L: netdev@vger.kernel.org S: Supported @@ -13003,10 +12997,10 @@ S: Maintained F: drivers/thermal/armada_thermal.c MARVELL MVNETA ETHERNET DRIVER -M: Thomas Petazzoni <thomas.petazzoni@bootlin.com> +M: Marcin Wojtas <marcin.s.wojtas@gmail.com> L: netdev@vger.kernel.org S: Maintained -F: drivers/net/ethernet/marvell/mvneta.* +F: drivers/net/ethernet/marvell/mvneta* MARVELL MVPP2 ETHERNET DRIVER M: Marcin Wojtas <marcin.s.wojtas@gmail.com> @@ -13656,7 +13650,6 @@ F: drivers/dma/mediatek/ MEDIATEK ETHERNET DRIVER M: Felix Fietkau <nbd@nbd.name> -M: John Crispin <john@phrozen.org> M: Sean Wang <sean.wang@mediatek.com> M: Mark Lee <Mark-MC.Lee@mediatek.com> M: Lorenzo Bianconi <lorenzo@kernel.org> @@ -13812,7 +13805,6 @@ F: include/soc/mediatek/smi.h MEDIATEK SWITCH DRIVER M: Arınç ÜNAL <arinc.unal@arinc9.com> M: Daniel Golle <daniel@makrotopia.org> -M: Landen Chao <Landen.Chao@mediatek.com> M: DENG Qingfang <dqfext@gmail.com> M: Sean Wang <sean.wang@mediatek.com> L: netdev@vger.kernel.org diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 53415e83821c..68e79b1272f6 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -11,7 +11,7 @@ #include <linux/net.h> #include <linux/igmp.h> #include <linux/workqueue.h> -#include <net/sch_generic.h> +#include <net/pkt_sched.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/udp.h> @@ -80,11 +80,11 @@ static struct mld2_grec mldv2_zero_grec; static struct amt_skb_cb *amt_skb_cb(struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(struct amt_skb_cb) + sizeof(struct qdisc_skb_cb) > + BUILD_BUG_ON(sizeof(struct amt_skb_cb) + sizeof(struct tc_skb_cb) > sizeof_field(struct sk_buff, cb)); return (struct amt_skb_cb *)((void *)skb->cb + - sizeof(struct qdisc_skb_cb)); + sizeof(struct tc_skb_cb)); } static void __amt_source_gc_work(void) diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index dd50502e2122..ae70eac3be28 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -1135,6 +1135,8 @@ static int vsc73xx_gpio_probe(struct vsc73xx *vsc) vsc->gc.label = devm_kasprintf(vsc->dev, GFP_KERNEL, "VSC%04x", vsc->chipid); + if (!vsc->gc.label) + return -ENOMEM; vsc->gc.ngpio = 4; vsc->gc.owner = THIS_MODULE; vsc->gc.parent = vsc->dev; diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c index 068ed52b66c9..b3c81a2e9d46 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c @@ -1490,7 +1490,7 @@ int cn23xx_get_vf_stats(struct octeon_device *oct, int vfidx, mbox_cmd.q_no = vfidx * oct->sriov_info.rings_per_vf; mbox_cmd.recv_len = 0; mbox_cmd.recv_status = 0; - mbox_cmd.fn = (octeon_mbox_callback_t)cn23xx_get_vf_stats_callback; + mbox_cmd.fn = cn23xx_get_vf_stats_callback; ctx.stats = stats; atomic_set(&ctx.status, 0); mbox_cmd.fn_arg = (void *)&ctx; diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c index dd5d80fee24f..d2fcb3da484e 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c @@ -429,7 +429,7 @@ int cn23xx_octeon_pfvf_handshake(struct octeon_device *oct) mbox_cmd.q_no = 0; mbox_cmd.recv_len = 0; mbox_cmd.recv_status = 0; - mbox_cmd.fn = (octeon_mbox_callback_t)octeon_pfvf_hs_callback; + mbox_cmd.fn = octeon_pfvf_hs_callback; mbox_cmd.fn_arg = &status; octeon_mbox_write(oct, &mbox_cmd); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h index d92bd7e16477..9ac85d22c615 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h @@ -57,7 +57,10 @@ union octeon_mbox_message { } s; }; -typedef void (*octeon_mbox_callback_t)(void *, void *, void *); +struct octeon_mbox_cmd; + +typedef void (*octeon_mbox_callback_t)(struct octeon_device *, + struct octeon_mbox_cmd *, void *); struct octeon_mbox_cmd { union octeon_mbox_message msg; diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 18a1c3b6d72c..c8f35d4de271 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -5,6 +5,7 @@ #define _I40E_ADMINQ_CMD_H_ #include <linux/bits.h> +#include <linux/types.h> /* This header file defines the i40e Admin Queue commands and is shared between * i40e Firmware and Software. diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.h b/drivers/net/ethernet/intel/i40e/i40e_diag.h index ece3a6b9a5c6..ab20202a3da3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.h +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.h @@ -4,6 +4,7 @@ #ifndef _I40E_DIAG_H_ #define _I40E_DIAG_H_ +#include <linux/types.h> #include "i40e_adminq_cmd.h" /* forward-declare the HW struct for the compiler */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c index 4728ba34b0e3..76218f1cb459 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c @@ -506,6 +506,7 @@ u32 rpm2_get_lmac_fifo_len(void *rpmd, int lmac_id) rpm_t *rpm = rpmd; u8 num_lmacs; u32 fifo_len; + u16 max_lmac; lmac_info = rpm_read(rpm, 0, RPM2_CMRX_RX_LMACS); /* LMACs are divided into two groups and each group @@ -513,7 +514,11 @@ u32 rpm2_get_lmac_fifo_len(void *rpmd, int lmac_id) * Group0 lmac_id range {0..3} * Group1 lmac_id range {4..7} */ - fifo_len = rpm->mac_ops->fifo_len / 2; + max_lmac = (rpm_read(rpm, 0, CGX_CONST) >> 24) & 0xFF; + if (max_lmac > 4) + fifo_len = rpm->mac_ops->fifo_len / 2; + else + fifo_len = rpm->mac_ops->fifo_len; if (lmac_id < 4) { num_lmacs = hweight8(lmac_info & 0xF); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c index 4c98950380d5..d231f4d2888b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c @@ -301,6 +301,7 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core, unsigned long *p_index) { unsigned int num_rows, entry_size; + unsigned long index; /* We only allow allocations of entire rows */ if (num_erps % erp_core->num_erp_banks != 0) @@ -309,10 +310,11 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core, entry_size = erp_core->erpt_entries_size[region_type]; num_rows = num_erps / erp_core->num_erp_banks; - *p_index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size); - if (*p_index == 0) + index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size); + if (!index) return -ENOBUFS; - *p_index -= MLXSW_SP_ACL_ERP_GENALLOC_OFFSET; + + *p_index = index - MLXSW_SP_ACL_ERP_GENALLOC_OFFSET; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index d50786b0a6ce..50ea1eff02b2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -681,13 +681,13 @@ static void mlxsw_sp_acl_tcam_region_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_region *region) { + struct mlxsw_sp_acl_tcam *tcam = mlxsw_sp_acl_to_tcam(mlxsw_sp->acl); const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; ops->region_fini(mlxsw_sp, region->priv); mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region); mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region); - mlxsw_sp_acl_tcam_region_id_put(region->group->tcam, - region->id); + mlxsw_sp_acl_tcam_region_id_put(tcam, region->id); kfree(region); } @@ -1564,6 +1564,8 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, tcam->max_groups = max_groups; tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUP_SIZE); + tcam->max_group_size = min_t(unsigned int, tcam->max_group_size, + MLXSW_REG_PAGT_ACL_MAX_NUM); err = ops->init(mlxsw_sp, tcam->priv, tcam); if (err) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 2c255ed9b8a9..7164f9e6370f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -11472,6 +11472,13 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_register_netevent_notifier; + mlxsw_sp->router->netdevice_nb.notifier_call = + mlxsw_sp_router_netdevice_event; + err = register_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), + &mlxsw_sp->router->netdevice_nb); + if (err) + goto err_register_netdev_notifier; + mlxsw_sp->router->nexthop_nb.notifier_call = mlxsw_sp_nexthop_obj_event; err = register_nexthop_notifier(mlxsw_sp_net(mlxsw_sp), @@ -11487,22 +11494,15 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_register_fib_notifier; - mlxsw_sp->router->netdevice_nb.notifier_call = - mlxsw_sp_router_netdevice_event; - err = register_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), - &mlxsw_sp->router->netdevice_nb); - if (err) - goto err_register_netdev_notifier; - return 0; -err_register_netdev_notifier: - unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), - &mlxsw_sp->router->fib_nb); err_register_fib_notifier: unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->router->nexthop_nb); err_register_nexthop_notifier: + unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), + &router->netdevice_nb); +err_register_netdev_notifier: unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); err_register_netevent_notifier: unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb); @@ -11550,11 +11550,11 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_router *router = mlxsw_sp->router; - unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), - &router->netdevice_nb); unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), &router->fib_nb); unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp), &router->nexthop_nb); + unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), + &router->netdevice_nb); unregister_netevent_notifier(&router->netevent_nb); unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb); unregister_inetaddr_validator_notifier(&router->inetaddr_valid_nb); diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 61d8bfd12d5f..55408f16fbbc 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -414,6 +414,7 @@ static const u64 fix_mac[] = { END_SIGN }; +MODULE_DESCRIPTION("Neterion 10GbE driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 39d24e07f306..5b69b9268c75 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -396,7 +396,7 @@ nla_put_failure: struct rtnl_link_ops rmnet_link_ops __read_mostly = { .kind = "rmnet", - .maxtype = __IFLA_RMNET_MAX, + .maxtype = IFLA_RMNET_MAX, .priv_size = sizeof(struct rmnet_priv), .setup = rmnet_vnd_setup, .validate = rmnet_rtnl_validate, diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 8649b3e90edb..0e3731f50fc2 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1949,7 +1949,7 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) struct ravb_tstamp_skb *ts_skb; struct ravb_tx_desc *desc; unsigned long flags; - u32 dma_addr; + dma_addr_t dma_addr; void *buffer; u32 entry; u32 len; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 9f89acf31050..f155e4841c62 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -267,6 +267,7 @@ struct stmmac_priv { u32 msg_enable; int wolopts; int wol_irq; + bool wol_irq_disabled; int clk_csr; struct timer_list eee_ctrl_timer; int lpi_irq; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index dd05437b51f9..42d27b97dd1d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -321,8 +321,9 @@ static int stmmac_ethtool_get_link_ksettings(struct net_device *dev, { struct stmmac_priv *priv = netdev_priv(dev); - if (priv->hw->pcs & STMMAC_PCS_RGMII || - priv->hw->pcs & STMMAC_PCS_SGMII) { + if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) && + (priv->hw->pcs & STMMAC_PCS_RGMII || + priv->hw->pcs & STMMAC_PCS_SGMII)) { struct rgmii_adv adv; u32 supported, advertising, lp_advertising; @@ -407,8 +408,9 @@ stmmac_ethtool_set_link_ksettings(struct net_device *dev, { struct stmmac_priv *priv = netdev_priv(dev); - if (priv->hw->pcs & STMMAC_PCS_RGMII || - priv->hw->pcs & STMMAC_PCS_SGMII) { + if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) && + (priv->hw->pcs & STMMAC_PCS_RGMII || + priv->hw->pcs & STMMAC_PCS_SGMII)) { /* Only support ANE */ if (cmd->base.autoneg != AUTONEG_ENABLE) return -EINVAL; @@ -830,10 +832,16 @@ static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) if (wol->wolopts) { pr_info("stmmac: wakeup enable\n"); device_set_wakeup_enable(priv->device, 1); - enable_irq_wake(priv->wol_irq); + /* Avoid unbalanced enable_irq_wake calls */ + if (priv->wol_irq_disabled) + enable_irq_wake(priv->wol_irq); + priv->wol_irq_disabled = false; } else { device_set_wakeup_enable(priv->device, 0); - disable_irq_wake(priv->wol_irq); + /* Avoid unbalanced disable_irq_wake calls */ + if (!priv->wol_irq_disabled) + disable_irq_wake(priv->wol_irq); + priv->wol_irq_disabled = true; } mutex_lock(&priv->lock); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 47de466e432c..a0e46369ae15 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3628,6 +3628,7 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev) /* Request the Wake IRQ in case of another line * is used for WoL */ + priv->wol_irq_disabled = true; if (priv->wol_irq > 0 && priv->wol_irq != dev->irq) { int_name = priv->int_name_wol; sprintf(int_name, "%s:%s", dev->name, "wol"); @@ -4435,6 +4436,28 @@ dma_map_err: } /** + * stmmac_has_ip_ethertype() - Check if packet has IP ethertype + * @skb: socket buffer to check + * + * Check if a packet has an ethertype that will trigger the IP header checks + * and IP/TCP checksum engine of the stmmac core. + * + * Return: true if the ethertype can trigger the checksum engine, false + * otherwise + */ +static bool stmmac_has_ip_ethertype(struct sk_buff *skb) +{ + int depth = 0; + __be16 proto; + + proto = __vlan_get_protocol(skb, eth_header_parse_protocol(skb), + &depth); + + return (depth <= ETH_HLEN) && + (proto == htons(ETH_P_IP) || proto == htons(ETH_P_IPV6)); +} + +/** * stmmac_xmit - Tx entry point of the driver * @skb : the socket buffer * @dev : device pointer @@ -4498,9 +4521,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* DWMAC IPs can be synthesized to support tx coe only for a few tx * queues. In that case, checksum offloading for those queues that don't * support tx coe needs to fallback to software checksum calculation. + * + * Packets that won't trigger the COE e.g. most DSA-tagged packets will + * also have to be checksummed in software. */ if (csum_insertion && - priv->plat->tx_queues_cfg[queue].coe_unsupported) { + (priv->plat->tx_queues_cfg[queue].coe_unsupported || + !stmmac_has_ip_ethertype(skb))) { if (unlikely(skb_checksum_help(skb))) goto dma_map_err; csum_insertion = !csum_insertion; @@ -5065,7 +5092,7 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue, stmmac_rx_vlan(priv->dev, skb); skb->protocol = eth_type_trans(skb, priv->dev); - if (unlikely(!coe)) + if (unlikely(!coe) || !stmmac_has_ip_ethertype(skb)) skb_checksum_none_assert(skb); else skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -5588,7 +5615,7 @@ drain_data: skb->protocol = eth_type_trans(skb, priv->dev); - if (unlikely(!coe)) + if (unlikely(!coe) || !stmmac_has_ip_ethertype(skb)) skb_checksum_none_assert(skb); else skb->ip_summed = CHECKSUM_UNNECESSARY; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index faa0561e988e..9d2f4ac783e4 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -56,7 +56,7 @@ #define AM65_CPSW_MAX_PORTS 8 #define AM65_CPSW_MIN_PACKET_SIZE VLAN_ETH_ZLEN -#define AM65_CPSW_MAX_PACKET_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) +#define AM65_CPSW_MAX_PACKET_SIZE 2024 #define AM65_CPSW_REG_CTL 0x004 #define AM65_CPSW_REG_STAT_PORT_EN 0x014 @@ -2244,7 +2244,8 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx) eth_hw_addr_set(port->ndev, port->slave.mac_addr); port->ndev->min_mtu = AM65_CPSW_MIN_PACKET_SIZE; - port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE; + port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE - + (VLAN_ETH_HLEN + ETH_FCS_LEN); port->ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_CSUM | diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig index 23cd610bd376..85cdbdd44fec 100644 --- a/drivers/net/ethernet/wangxun/Kconfig +++ b/drivers/net/ethernet/wangxun/Kconfig @@ -26,7 +26,7 @@ config NGBE tristate "Wangxun(R) GbE PCI Express adapters support" depends on PCI select LIBWX - select PHYLIB + select PHYLINK help This driver supports Wangxun(R) GbE PCI Express family of adapters. diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 23355cc408fd..8706223a6e5a 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -2769,4 +2769,5 @@ void wx_set_ring(struct wx *wx, u32 new_tx_count, } EXPORT_SYMBOL(wx_set_ring); +MODULE_DESCRIPTION("Common library for Wangxun(R) Ethernet drivers."); MODULE_LICENSE("GPL"); diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index aecaf5f44374..77e8250282a5 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -369,6 +369,12 @@ static int nsim_init_netdevsim_vf(struct netdevsim *ns) return err; } +static void nsim_exit_netdevsim(struct netdevsim *ns) +{ + nsim_udp_tunnels_info_destroy(ns->netdev); + mock_phc_destroy(ns->phc); +} + struct netdevsim * nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) { @@ -417,8 +423,7 @@ void nsim_destroy(struct netdevsim *ns) } rtnl_unlock(); if (nsim_dev_port_is_pf(ns->nsim_dev_port)) - nsim_udp_tunnels_info_destroy(dev); - mock_phc_destroy(ns->phc); + nsim_exit_netdevsim(ns); free_netdev(dev); } diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index d2aa3d0695e3..81c20eb4b54b 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -3338,8 +3338,10 @@ static int lan8814_probe(struct phy_device *phydev) #define LAN8841_ADC_CHANNEL_MASK 198 #define LAN8841_PTP_RX_PARSE_L2_ADDR_EN 370 #define LAN8841_PTP_RX_PARSE_IP_ADDR_EN 371 +#define LAN8841_PTP_RX_VERSION 374 #define LAN8841_PTP_TX_PARSE_L2_ADDR_EN 434 #define LAN8841_PTP_TX_PARSE_IP_ADDR_EN 435 +#define LAN8841_PTP_TX_VERSION 438 #define LAN8841_PTP_CMD_CTL 256 #define LAN8841_PTP_CMD_CTL_PTP_ENABLE BIT(2) #define LAN8841_PTP_CMD_CTL_PTP_DISABLE BIT(1) @@ -3383,6 +3385,12 @@ static int lan8841_config_init(struct phy_device *phydev) phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, LAN8841_PTP_RX_PARSE_IP_ADDR_EN, 0); + /* Disable checking for minorVersionPTP field */ + phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, + LAN8841_PTP_RX_VERSION, 0xff00); + phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, + LAN8841_PTP_TX_VERSION, 0xff00); + /* 100BT Clause 40 improvenent errata */ phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG, LAN8841_ANALOG_CONTROL_1, @@ -4839,6 +4847,7 @@ static struct phy_driver ksphy_driver[] = { .flags = PHY_POLL_CABLE_TEST, .driver_data = &ksz9131_type, .probe = kszphy_probe, + .soft_reset = genphy_soft_reset, .config_init = ksz9131_config_init, .config_intr = kszphy_config_intr, .config_aneg = ksz9131_config_aneg, diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 6fa679b36290..db39dec7f247 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -151,10 +151,6 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned int br_min, br_nom, br_max; __ETHTOOL_DECLARE_LINK_MODE_MASK(modes) = { 0, }; - phylink_set(modes, Autoneg); - phylink_set(modes, Pause); - phylink_set(modes, Asym_Pause); - /* Decode the bitrate information to MBd */ br_min = br_nom = br_max = 0; if (id->base.br_nominal) { @@ -339,6 +335,10 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, } } + phylink_set(modes, Autoneg); + phylink_set(modes, Pause); + phylink_set(modes, Asym_Pause); + if (bus->sfp_quirk && bus->sfp_quirk->modes) bus->sfp_quirk->modes(id, modes, interfaces); diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c index ba93bab948e0..18df7ca66198 100644 --- a/drivers/net/slip/slhc.c +++ b/drivers/net/slip/slhc.c @@ -752,4 +752,5 @@ EXPORT_SYMBOL(slhc_compress); EXPORT_SYMBOL(slhc_uncompress); EXPORT_SYMBOL(slhc_toss); +MODULE_DESCRIPTION("Compression helpers for SLIP (serial line)"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index e4280e37fec9..0aba3569ccc0 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -1437,5 +1437,6 @@ out: } #endif +MODULE_DESCRIPTION("SLIP (serial line) protocol module"); MODULE_LICENSE("GPL"); MODULE_ALIAS_LDISC(N_SLIP); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 3cb8aa193884..d7ce4a1011ea 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -4295,10 +4295,11 @@ static int virtnet_find_vqs(struct virtnet_info *vi) { vq_callback_t **callbacks; struct virtqueue **vqs; - int ret = -ENOMEM; - int i, total_vqs; const char **names; + int ret = -ENOMEM; + int total_vqs; bool *ctx; + u16 i; /* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by @@ -4335,8 +4336,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi) for (i = 0; i < vi->max_queue_pairs; i++) { callbacks[rxq2vq(i)] = skb_recv_done; callbacks[txq2vq(i)] = skb_xmit_done; - sprintf(vi->rq[i].name, "input.%d", i); - sprintf(vi->sq[i].name, "output.%d", i); + sprintf(vi->rq[i].name, "input.%u", i); + sprintf(vi->sq[i].name, "output.%u", i); names[rxq2vq(i)] = vi->rq[i].name; names[txq2vq(i)] = vi->sq[i].name; if (ctx) diff --git a/drivers/net/wan/slic_ds26522.c b/drivers/net/wan/slic_ds26522.c index 8a51cfcff99e..cbb99fc5ea9f 100644 --- a/drivers/net/wan/slic_ds26522.c +++ b/drivers/net/wan/slic_ds26522.c @@ -28,6 +28,7 @@ static struct spi_device *g_spi; +MODULE_DESCRIPTION("Slic Maxim DS26522 driver"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Zhao Qiang<B45475@freescale.com>"); diff --git a/include/linux/btf.h b/include/linux/btf.h index 59d404e22814..cf5c6ff48981 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -512,7 +512,7 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner); struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id); -const struct btf_member * +const struct btf_type * btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg); diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index f980edfdd278..743475ca7e9d 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -42,7 +42,7 @@ static inline int nf_bridge_get_physinif(const struct sk_buff *skb) if (!nf_bridge) return 0; - return nf_bridge->physindev ? nf_bridge->physindev->ifindex : 0; + return nf_bridge->physinif; } static inline int nf_bridge_get_physoutif(const struct sk_buff *skb) @@ -56,11 +56,11 @@ static inline int nf_bridge_get_physoutif(const struct sk_buff *skb) } static inline struct net_device * -nf_bridge_get_physindev(const struct sk_buff *skb) +nf_bridge_get_physindev(const struct sk_buff *skb, struct net *net) { const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); - return nf_bridge ? nf_bridge->physindev : NULL; + return nf_bridge ? dev_get_by_index_rcu(net, nf_bridge->physinif) : NULL; } static inline struct net_device * diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a5ae952454c8..2dde34c29203 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -295,7 +295,7 @@ struct nf_bridge_info { u8 bridged_dnat:1; u8 sabotage_in_done:1; __u16 frag_max_size; - struct net_device *physindev; + int physinif; /* always valid & non-NULL from FORWARD on, for physdev match */ struct net_device *physoutdev; diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 27cc1d464321..4dfa9b69ca8d 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -3,6 +3,8 @@ #define _LINUX_VIRTIO_NET_H #include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/ipv6.h> #include <linux/udp.h> #include <uapi/linux/tcp.h> #include <uapi/linux/virtio_net.h> @@ -49,6 +51,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, const struct virtio_net_hdr *hdr, bool little_endian) { + unsigned int nh_min_len = sizeof(struct iphdr); unsigned int gso_type = 0; unsigned int thlen = 0; unsigned int p_off = 0; @@ -65,6 +68,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, gso_type = SKB_GSO_TCPV6; ip_proto = IPPROTO_TCP; thlen = sizeof(struct tcphdr); + nh_min_len = sizeof(struct ipv6hdr); break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; @@ -100,7 +104,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; - p_off = skb_transport_offset(skb) + thlen; + nh_min_len = max_t(u32, nh_min_len, skb_transport_offset(skb)); + p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } else { @@ -140,7 +145,7 @@ retry: skb_set_transport_header(skb, keys.control.thoff); } else if (gso_type) { - p_off = thlen; + p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index d68b0a483431..8b8ed4e13d74 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -128,7 +128,7 @@ netdev_txq_completed_mb(struct netdev_queue *dev_queue, netdev_txq_completed_mb(txq, pkts, bytes); \ \ _res = -1; \ - if (pkts && likely(get_desc > start_thrs)) { \ + if (pkts && likely(get_desc >= start_thrs)) { \ _res = 1; \ if (unlikely(netif_tx_queue_stopped(txq)) && \ !(down_cond)) { \ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 51e8b4bee0c8..596471189176 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5615,21 +5615,46 @@ static u8 bpf_ctx_convert_map[] = { #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE -const struct btf_member * -btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, enum bpf_prog_type prog_type, - int arg) +static const struct btf_type *find_canonical_prog_ctx_type(enum bpf_prog_type prog_type) { const struct btf_type *conv_struct; - const struct btf_type *ctx_struct; const struct btf_member *ctx_type; - const char *tname, *ctx_tname; conv_struct = bpf_ctx_convert.t; - if (!conv_struct) { - bpf_log(log, "btf_vmlinux is malformed\n"); + if (!conv_struct) return NULL; - } + /* prog_type is valid bpf program type. No need for bounds check. */ + ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; + /* ctx_type is a pointer to prog_ctx_type in vmlinux. + * Like 'struct __sk_buff' + */ + return btf_type_by_id(btf_vmlinux, ctx_type->type); +} + +static int find_kern_ctx_type_id(enum bpf_prog_type prog_type) +{ + const struct btf_type *conv_struct; + const struct btf_member *ctx_type; + + conv_struct = bpf_ctx_convert.t; + if (!conv_struct) + return -EFAULT; + /* prog_type is valid bpf program type. No need for bounds check. */ + ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1; + /* ctx_type is a pointer to prog_ctx_type in vmlinux. + * Like 'struct sk_buff' + */ + return ctx_type->type; +} + +const struct btf_type * +btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg) +{ + const struct btf_type *ctx_type; + const char *tname, *ctx_tname; + t = btf_type_by_id(btf, t->type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); @@ -5646,17 +5671,15 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, bpf_log(log, "arg#%d struct doesn't have a name\n", arg); return NULL; } - /* prog_type is valid bpf program type. No need for bounds check. */ - ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; - /* ctx_struct is a pointer to prog_ctx_type in vmlinux. - * Like 'struct __sk_buff' - */ - ctx_struct = btf_type_by_id(btf_vmlinux, ctx_type->type); - if (!ctx_struct) + + ctx_type = find_canonical_prog_ctx_type(prog_type); + if (!ctx_type) { + bpf_log(log, "btf_vmlinux is malformed\n"); /* should not happen */ return NULL; + } again: - ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off); + ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off); if (!ctx_tname) { /* should not happen */ bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n"); @@ -5677,28 +5700,167 @@ again: /* bpf_user_pt_regs_t is a typedef, so resolve it to * underlying struct and check name again */ - if (!btf_type_is_modifier(ctx_struct)) + if (!btf_type_is_modifier(ctx_type)) return NULL; - while (btf_type_is_modifier(ctx_struct)) - ctx_struct = btf_type_by_id(btf_vmlinux, ctx_struct->type); + while (btf_type_is_modifier(ctx_type)) + ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type); goto again; } return ctx_type; } +/* forward declarations for arch-specific underlying types of + * bpf_user_pt_regs_t; this avoids the need for arch-specific #ifdef + * compilation guards below for BPF_PROG_TYPE_PERF_EVENT checks, but still + * works correctly with __builtin_types_compatible_p() on respective + * architectures + */ +struct user_regs_struct; +struct user_pt_regs; + +static int btf_validate_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, int arg, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type) +{ + const struct btf_type *ctx_type; + const char *tname, *ctx_tname; + + if (!btf_is_ptr(t)) { + bpf_log(log, "arg#%d type isn't a pointer\n", arg); + return -EINVAL; + } + t = btf_type_by_id(btf, t->type); + + /* KPROBE and PERF_EVENT programs allow bpf_user_pt_regs_t typedef */ + if (prog_type == BPF_PROG_TYPE_KPROBE || prog_type == BPF_PROG_TYPE_PERF_EVENT) { + while (btf_type_is_modifier(t) && !btf_type_is_typedef(t)) + t = btf_type_by_id(btf, t->type); + + if (btf_type_is_typedef(t)) { + tname = btf_name_by_offset(btf, t->name_off); + if (tname && strcmp(tname, "bpf_user_pt_regs_t") == 0) + return 0; + } + } + + /* all other program types don't use typedefs for context type */ + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + + /* `void *ctx __arg_ctx` is always valid */ + if (btf_type_is_void(t)) + return 0; + + tname = btf_name_by_offset(btf, t->name_off); + if (str_is_empty(tname)) { + bpf_log(log, "arg#%d type doesn't have a name\n", arg); + return -EINVAL; + } + + /* special cases */ + switch (prog_type) { + case BPF_PROG_TYPE_KPROBE: + if (__btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return 0; + break; + case BPF_PROG_TYPE_PERF_EVENT: + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct pt_regs) && + __btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return 0; + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_pt_regs) && + __btf_type_is_struct(t) && strcmp(tname, "user_pt_regs") == 0) + return 0; + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_regs_struct) && + __btf_type_is_struct(t) && strcmp(tname, "user_regs_struct") == 0) + return 0; + break; + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + case BPF_PROG_TYPE_TRACING: + switch (attach_type) { + case BPF_TRACE_RAW_TP: + /* tp_btf program is TRACING, so need special case here */ + if (__btf_type_is_struct(t) && + strcmp(tname, "bpf_raw_tracepoint_args") == 0) + return 0; + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + case BPF_TRACE_ITER: + /* allow struct bpf_iter__xxx types only */ + if (__btf_type_is_struct(t) && + strncmp(tname, "bpf_iter__", sizeof("bpf_iter__") - 1) == 0) + return 0; + break; + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + case BPF_MODIFY_RETURN: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + default: + break; + } + break; + case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_STRUCT_OPS: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_SYSCALL: + case BPF_PROG_TYPE_EXT: + return 0; /* anything goes */ + default: + break; + } + + ctx_type = find_canonical_prog_ctx_type(prog_type); + if (!ctx_type) { + /* should not happen */ + bpf_log(log, "btf_vmlinux is malformed\n"); + return -EINVAL; + } + + /* resolve typedefs and check that underlying structs are matching as well */ + while (btf_type_is_modifier(ctx_type)) + ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type); + + /* if program type doesn't have distinctly named struct type for + * context, then __arg_ctx argument can only be `void *`, which we + * already checked above + */ + if (!__btf_type_is_struct(ctx_type)) { + bpf_log(log, "arg#%d should be void pointer\n", arg); + return -EINVAL; + } + + ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off); + if (!__btf_type_is_struct(t) || strcmp(ctx_tname, tname) != 0) { + bpf_log(log, "arg#%d should be `struct %s *`\n", arg, ctx_tname); + return -EINVAL; + } + + return 0; +} + static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg) { - const struct btf_member *prog_ctx_type, *kern_ctx_type; - - prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type, arg); - if (!prog_ctx_type) + if (!btf_get_prog_ctx_type(log, btf, t, prog_type, arg)) return -ENOENT; - kern_ctx_type = prog_ctx_type + 1; - return kern_ctx_type->type; + return find_kern_ctx_type_id(prog_type); } int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type) @@ -6934,6 +7096,23 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) return -EINVAL; } + for (i = 0; i < nargs; i++) { + const char *tag; + + if (sub->args[i].arg_type != ARG_PTR_TO_CTX) + continue; + + /* check if arg has "arg:ctx" tag */ + t = btf_type_by_id(btf, args[i].type); + tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:"); + if (IS_ERR_OR_NULL(tag) || strcmp(tag, "ctx") != 0) + continue; + + if (btf_validate_prog_ctx_type(log, btf, t, i, prog_type, + prog->expected_attach_type)) + return -EINVAL; + } + sub->arg_cnt = nargs; sub->args_cached = true; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index adbf330d364b..65f598694d55 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -12826,6 +12826,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } switch (base_type(ptr_reg->type)) { + case PTR_TO_FLOW_KEYS: + if (known) + break; + fallthrough; case CONST_PTR_TO_MAP: /* smin_val represents the known value */ if (known && smin_val == 0 && opcode == BPF_ADD) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 6adcb45bca75..ed1720890757 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -279,8 +279,17 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ if ((READ_ONCE(neigh->nud_state) & NUD_CONNECTED) && READ_ONCE(neigh->hh.hh_len)) { + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(skb, net); + if (!br_indev) { + neigh_release(neigh); + goto free_skb; + } + neigh_hh_bridge(&neigh->hh, skb); - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; + ret = br_handle_frame_finish(net, sk, skb); } else { /* the neighbour function below overwrites the complete @@ -352,12 +361,18 @@ br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb, */ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_device *dev = skb->dev; + struct net_device *dev = skb->dev, *br_indev; struct iphdr *iph = ip_hdr(skb); struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; int err; + br_indev = nf_bridge_get_physindev(skb, net); + if (!br_indev) { + kfree_skb(skb); + return 0; + } + nf_bridge->frag_max_size = IPCB(skb)->frag_max_size; if (nf_bridge->pkt_otherhost) { @@ -397,7 +412,7 @@ free_skb: } else { if (skb_dst(skb)->dev == dev) { bridged_dnat: - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, @@ -410,7 +425,7 @@ bridged_dnat: skb->pkt_type = PACKET_HOST; } } else { - rt = bridge_parent_rtable(nf_bridge->physindev); + rt = bridge_parent_rtable(br_indev); if (!rt) { kfree_skb(skb); return 0; @@ -419,7 +434,7 @@ bridged_dnat: skb_dst_set_noref(skb, &rt->dst); } - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL, @@ -456,7 +471,7 @@ struct net_device *setup_pre_routing(struct sk_buff *skb, const struct net *net) } nf_bridge->in_prerouting = 1; - nf_bridge->physindev = skb->dev; + nf_bridge->physinif = skb->dev->ifindex; skb->dev = brnf_get_logical_dev(skb, skb->dev, net); if (skb->protocol == htons(ETH_P_8021Q)) @@ -553,7 +568,11 @@ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff if (skb->protocol == htons(ETH_P_IPV6)) nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size; - in = nf_bridge->physindev; + in = nf_bridge_get_physindev(skb, net); + if (!in) { + kfree_skb(skb); + return 0; + } if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; @@ -899,6 +918,13 @@ static unsigned int ip_sabotage_in(void *priv, static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(skb, dev_net(skb->dev)); + if (!br_indev) { + kfree_skb(skb); + return; + } skb_pull(skb, ETH_HLEN); nf_bridge->bridged_dnat = 0; @@ -908,7 +934,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN), nf_bridge->neigh_header, ETH_HLEN - ETH_ALEN); - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge->physoutdev = NULL; br_handle_frame_finish(dev_net(skb->dev), NULL, skb); diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 2e24a743f917..e0421eaa3abc 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -102,9 +102,15 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; - struct net_device *dev = skb->dev; + struct net_device *dev = skb->dev, *br_indev; const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); + br_indev = nf_bridge_get_physindev(skb, net); + if (!br_indev) { + kfree_skb(skb); + return 0; + } + nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size; if (nf_bridge->pkt_otherhost) { @@ -122,7 +128,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc } if (skb_dst(skb)->dev == dev) { - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, @@ -133,7 +139,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); skb->pkt_type = PACKET_HOST; } else { - rt = bridge_parent_rtable(nf_bridge->physindev); + rt = bridge_parent_rtable(br_indev); if (!rt) { kfree_skb(skb); return 0; @@ -142,7 +148,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc skb_dst_set_noref(skb, &rt->dst); } - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5f6ed6da3cfc..f6f29eb03ec2 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2899,13 +2899,6 @@ static int do_setlink(const struct sk_buff *skb, call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); } - if (tb[IFLA_MASTER]) { - err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack); - if (err) - goto errout; - status |= DO_SETLINK_MODIFIED; - } - if (ifm->ifi_flags || ifm->ifi_change) { err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm), extack); @@ -2913,6 +2906,13 @@ static int do_setlink(const struct sk_buff *skb, goto errout; } + if (tb[IFLA_MASTER]) { + err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack); + if (err) + goto errout; + status |= DO_SETLINK_MODIFIED; + } + if (tb[IFLA_CARRIER]) { err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER])); if (err) diff --git a/net/dsa/user.c b/net/dsa/user.c index b738a466e2dc..b15e71cc342c 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -2806,13 +2806,14 @@ EXPORT_SYMBOL_GPL(dsa_user_dev_check); static int dsa_user_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { - struct dsa_port *dp = dsa_user_to_port(dev); struct netlink_ext_ack *extack; int err = NOTIFY_DONE; + struct dsa_port *dp; if (!dsa_user_dev_check(dev)) return err; + dp = dsa_user_to_port(dev); extack = netdev_notifier_info_to_extack(&info->info); if (netif_is_bridge_master(info->upper_dev)) { @@ -2865,11 +2866,13 @@ static int dsa_user_changeupper(struct net_device *dev, static int dsa_user_prechangeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { - struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_port *dp; if (!dsa_user_dev_check(dev)) return NOTIFY_DONE; + dp = dsa_user_to_port(dev); + if (netif_is_bridge_master(info->upper_dev) && !info->linking) dsa_port_pre_bridge_leave(dp, info->upper_dev); else if (netif_is_lag_master(info->upper_dev) && !info->linking) diff --git a/net/ethtool/features.c b/net/ethtool/features.c index a79af8c25a07..b6cb101d7f19 100644 --- a/net/ethtool/features.c +++ b/net/ethtool/features.c @@ -234,17 +234,20 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) dev = req_info.dev; rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; ethnl_features_to_bitmap(old_active, dev->features); ethnl_features_to_bitmap(old_wanted, dev->wanted_features); ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT, tb[ETHTOOL_A_FEATURES_WANTED], netdev_features_strings, info->extack); if (ret < 0) - goto out_rtnl; + goto out_ops; if (ethnl_bitmap_to_features(req_mask) & ~NETIF_F_ETHTOOL_BITS) { GENL_SET_ERR_MSG(info, "attempt to change non-ethtool features"); ret = -EINVAL; - goto out_rtnl; + goto out_ops; } /* set req_wanted bits not in req_mask from old_wanted */ @@ -281,6 +284,8 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) if (mod) netdev_features_change(dev); +out_ops: + ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); ethnl_parse_header_dev_put(&req_info); diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index b099c3150150..cb83c8feb746 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -167,4 +167,5 @@ static void __exit hsr_exit(void) module_init(hsr_init); module_exit(hsr_exit); +MODULE_DESCRIPTION("High-availability Seamless Redundancy (HSR) driver"); MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index f01b038fc1cd..04504b2b51df 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -239,7 +239,6 @@ static int nf_reject_fill_skb_dst(struct sk_buff *skb_in) void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { - struct net_device *br_indev __maybe_unused; struct sk_buff *nskb; struct iphdr *niph; const struct tcphdr *oth; @@ -289,9 +288,13 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, * build the eth header using the original destination's MAC as the * source, and send the RST packet directly. */ - br_indev = nf_bridge_get_physindev(oldskb); - if (br_indev) { + if (nf_bridge_info_exists(oldskb)) { struct ethhdr *oeth = eth_hdr(oldskb); + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(oldskb, net); + if (!br_indev) + goto free_nskb; nskb->dev = br_indev; niph->tot_len = htons(nskb->len); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 89e5a806b82e..148ffb007969 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -805,7 +805,7 @@ void udp_flush_pending_frames(struct sock *sk) if (up->pending) { up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); ip_flush_pending_frames(sk); } } @@ -993,7 +993,7 @@ int udp_push_pending_frames(struct sock *sk) out: up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); return err; } EXPORT_SYMBOL(udp_push_pending_frames); @@ -1070,7 +1070,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; fl4 = &inet->cork.fl.u.ip4; - if (up->pending) { + if (READ_ONCE(up->pending)) { /* * There are pending frames. * The socket lock must be held while it's corked. @@ -1269,7 +1269,7 @@ back_from_confirm: fl4->saddr = saddr; fl4->fl4_dport = dport; fl4->fl4_sport = inet->inet_sport; - up->pending = AF_INET; + WRITE_ONCE(up->pending, AF_INET); do_append_data: up->len += ulen; @@ -1281,7 +1281,7 @@ do_append_data: else if (!corkreq) err = udp_push_pending_frames(sk); else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) - up->pending = 0; + WRITE_ONCE(up->pending, 0); release_sock(sk); out: @@ -1319,7 +1319,7 @@ void udp_splice_eof(struct socket *sock) struct sock *sk = sock->sk; struct udp_sock *up = udp_sk(sk); - if (!up->pending || udp_test_bit(CORK, sk)) + if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk)) return; lock_sock(sk); @@ -3137,16 +3137,18 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq) struct bpf_udp_iter_state *iter = seq->private; struct udp_iter_state *state = &iter->state; struct net *net = seq_file_net(seq); + int resume_bucket, resume_offset; struct udp_table *udptable; unsigned int batch_sks = 0; bool resized = false; struct sock *sk; + resume_bucket = state->bucket; + resume_offset = iter->offset; + /* The current batch is done, so advance the bucket. */ - if (iter->st_bucket_done) { + if (iter->st_bucket_done) state->bucket++; - iter->offset = 0; - } udptable = udp_get_table_seq(seq, net); @@ -3166,19 +3168,19 @@ again: for (; state->bucket <= udptable->mask; state->bucket++) { struct udp_hslot *hslot2 = &udptable->hash2[state->bucket]; - if (hlist_empty(&hslot2->head)) { - iter->offset = 0; + if (hlist_empty(&hslot2->head)) continue; - } + iter->offset = 0; spin_lock_bh(&hslot2->lock); udp_portaddr_for_each_entry(sk, &hslot2->head) { if (seq_sk_match(seq, sk)) { /* Resume from the last iterated socket at the * offset in the bucket before iterator was stopped. */ - if (iter->offset) { - --iter->offset; + if (state->bucket == resume_bucket && + iter->offset < resume_offset) { + ++iter->offset; continue; } if (iter->end_sk < iter->max_sk) { @@ -3192,9 +3194,6 @@ again: if (iter->end_sk) break; - - /* Reset the current bucket's offset before moving to the next bucket. */ - iter->offset = 0; } /* All done: no batch made. */ @@ -3213,7 +3212,6 @@ again: /* After allocating a larger batch, retry one more time to grab * the whole bucket. */ - state->bucket--; goto again; } done: diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index b75d3c9d41bb..bc6e0a0bad3c 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2722,8 +2722,12 @@ void ipv6_mc_down(struct inet6_dev *idev) synchronize_net(); mld_query_stop_work(idev); mld_report_stop_work(idev); + + mutex_lock(&idev->mc_lock); mld_ifc_stop_work(idev); mld_gq_stop_work(idev); + mutex_unlock(&idev->mc_lock); + mld_dad_stop_work(idev); } diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index d45bc54b7ea5..196dd4ecb5e2 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -278,7 +278,6 @@ static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in) void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { - struct net_device *br_indev __maybe_unused; struct sk_buff *nskb; struct tcphdr _otcph; const struct tcphdr *otcph; @@ -354,9 +353,15 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, * build the eth header using the original destination's MAC as the * source, and send the RST packet directly. */ - br_indev = nf_bridge_get_physindev(oldskb); - if (br_indev) { + if (nf_bridge_info_exists(oldskb)) { struct ethhdr *oeth = eth_hdr(oldskb); + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(oldskb, net); + if (!br_indev) { + kfree_skb(nskb); + return; + } nskb->dev = br_indev; nskb->protocol = htons(ETH_P_IPV6); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 594e3f23c129..3f2249b4cd5f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1135,7 +1135,7 @@ static void udp_v6_flush_pending_frames(struct sock *sk) udp_flush_pending_frames(sk); else if (up->pending) { up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); ip6_flush_pending_frames(sk); } } @@ -1313,7 +1313,7 @@ static int udp_v6_push_pending_frames(struct sock *sk) &inet_sk(sk)->cork.base); out: up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); return err; } @@ -1370,7 +1370,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) default: return -EINVAL; } - } else if (!up->pending) { + } else if (!READ_ONCE(up->pending)) { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; @@ -1401,8 +1401,8 @@ do_udp_sendmsg: return -EMSGSIZE; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; - if (up->pending) { - if (up->pending == AF_INET) + if (READ_ONCE(up->pending)) { + if (READ_ONCE(up->pending) == AF_INET) return udp_sendmsg(sk, msg, len); /* * There are pending frames. @@ -1593,7 +1593,7 @@ back_from_confirm: goto out; } - up->pending = AF_INET6; + WRITE_ONCE(up->pending, AF_INET6); do_append_data: if (ipc6.dontfrag < 0) @@ -1607,7 +1607,7 @@ do_append_data: else if (!corkreq) err = udp_v6_push_pending_frames(sk); else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) - up->pending = 0; + WRITE_ONCE(up->pending, 0); if (err > 0) err = inet6_test_bit(RECVERR6, sk) ? net_xmit_errno(err) : 0; @@ -1648,7 +1648,7 @@ static void udpv6_splice_eof(struct socket *sock) struct sock *sk = sock->sk; struct udp_sock *up = udp_sk(sk); - if (!up->pending || udp_test_bit(CORK, sk)) + if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk)) return; lock_sock(sk); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index c53914012d01..d2527d189a79 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -123,8 +123,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_JOIN: - mp_opt->suboptions |= OPTIONS_MPTCP_MPJ; if (opsize == TCPOLEN_MPTCP_MPJ_SYN) { + mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYN; mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP; mp_opt->join_id = *ptr++; mp_opt->token = get_unaligned_be32(ptr); @@ -135,6 +135,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->backup, mp_opt->join_id, mp_opt->token, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) { + mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYNACK; mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP; mp_opt->join_id = *ptr++; mp_opt->thmac = get_unaligned_be64(ptr); @@ -145,11 +146,10 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->backup, mp_opt->join_id, mp_opt->thmac, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) { + mp_opt->suboptions |= OPTION_MPTCP_MPJ_ACK; ptr += 2; memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN); pr_debug("MP_JOIN hmac"); - } else { - mp_opt->suboptions &= ~OPTIONS_MPTCP_MPJ; } break; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 3eacd04e7099..0dcb721c89d1 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -157,8 +157,8 @@ static int subflow_check_req(struct request_sock *req, mptcp_get_options(skb, &mp_opt); - opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC); - opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ); + opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYN); + opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYN); if (opt_mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); @@ -254,8 +254,8 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, subflow_init_req(req, sk_listener); mptcp_get_options(skb, &mp_opt); - opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC); - opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ); + opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK); + opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK); if (opt_mp_capable && opt_mp_join) return -EINVAL; @@ -486,7 +486,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) mptcp_get_options(skb, &mp_opt); if (subflow->request_mptcp) { - if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) { + if (!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYNACK)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEFALLBACK); mptcp_do_fallback(sk); @@ -506,7 +506,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; - if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ)) { + if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYNACK)) { subflow->reset_reason = MPTCP_RST_EMPTCP; goto do_reset; } @@ -783,12 +783,13 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, * options. */ mptcp_get_options(skb, &mp_opt); - if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) + if (!(mp_opt.suboptions & + (OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_ACK))) fallback = true; } else if (subflow_req->mp_join) { mptcp_get_options(skb, &mp_opt); - if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ) || + if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK) || !subflow_hmac_valid(req, &mp_opt) || !mptcp_can_accept_new_subflow(subflow_req->msk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 95aeb31c60e0..30a655e5c4fd 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -138,9 +138,9 @@ hash_netiface4_data_next(struct hash_netiface4_elem *next, #include "ip_set_hash_gen.h" #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) -static const char *get_physindev_name(const struct sk_buff *skb) +static const char *get_physindev_name(const struct sk_buff *skb, struct net *net) { - struct net_device *dev = nf_bridge_get_physindev(skb); + struct net_device *dev = nf_bridge_get_physindev(skb, net); return dev ? dev->name : NULL; } @@ -177,7 +177,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - const char *eiface = SRCDIR ? get_physindev_name(skb) : + const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) : get_physoutdev_name(skb); if (!eiface) @@ -395,7 +395,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - const char *eiface = SRCDIR ? get_physindev_name(skb) : + const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) : get_physoutdev_name(skb); if (!eiface) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 9193e109e6b3..65e0259178da 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -271,7 +271,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); - __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); return false; } @@ -286,7 +286,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, { if (ip_hdr(skb)->ttl <= 1) { /* Tell the sender its packet died... */ - __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); + IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0); return false; } diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c index c66689ad2b49..58402226045e 100644 --- a/net/netfilter/nf_log_syslog.c +++ b/net/netfilter/nf_log_syslog.c @@ -111,7 +111,8 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, - const struct nf_loginfo *loginfo, const char *prefix) + const struct nf_loginfo *loginfo, const char *prefix, + struct net *net) { const struct net_device *physoutdev __maybe_unused; const struct net_device *physindev __maybe_unused; @@ -121,7 +122,7 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf, in ? in->name : "", out ? out->name : ""); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - physindev = nf_bridge_get_physindev(skb); + physindev = nf_bridge_get_physindev(skb, net); if (physindev && in != physindev) nf_log_buf_add(m, "PHYSIN=%s ", physindev->name); physoutdev = nf_bridge_get_physoutdev(skb); @@ -148,7 +149,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo, - prefix); + prefix, net); dump_arp_packet(m, loginfo, skb, skb_network_offset(skb)); nf_log_buf_close(m); @@ -845,7 +846,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, - out, loginfo, prefix); + out, loginfo, prefix, net); if (in) dump_mac_header(m, loginfo, skb); @@ -880,7 +881,7 @@ static void nf_log_ip6_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, - loginfo, prefix); + loginfo, prefix, net); if (in) dump_mac_header(m, loginfo, skb); @@ -916,7 +917,7 @@ static void nf_log_unknown_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo, - prefix); + prefix, net); dump_mac_header(m, loginfo, skb); diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 63d1516816b1..e2f334f70281 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -82,11 +82,9 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) const struct sk_buff *skb = entry->skb; - struct nf_bridge_info *nf_bridge; - nf_bridge = nf_bridge_info_get(skb); - if (nf_bridge) { - entry->physin = nf_bridge_get_physindev(skb); + if (nf_bridge_info_exists(skb)) { + entry->physin = nf_bridge_get_physindev(skb, entry->state.net); entry->physout = nf_bridge_get_physoutdev(skb); } else { entry->physin = NULL; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8438a8922e4a..4b55533ce5ca 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2977,6 +2977,9 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, */ int nft_register_expr(struct nft_expr_type *type) { + if (WARN_ON_ONCE(type->maxattr > NFT_EXPR_MAXATTR)) + return -ENOMEM; + nfnl_lock(NFNL_SUBSYS_NFTABLES); if (type->family == NFPROTO_UNSPEC) list_add_tail_rcu(&type->list, &nf_tables_expressions); @@ -3271,14 +3274,13 @@ int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) { int err; - if (src->ops->clone) { - dst->ops = src->ops; - err = src->ops->clone(dst, src); - if (err < 0) - return err; - } else { - memcpy(dst, src, src->ops->size); - } + if (WARN_ON_ONCE(!src->ops->clone)) + return -EINVAL; + + dst->ops = src->ops; + err = src->ops->clone(dst, src); + if (err < 0) + return err; __module_get(src->ops->type->owner); @@ -4811,8 +4813,8 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, static int nft_set_desc_concat(struct nft_set_desc *desc, const struct nlattr *nla) { + u32 num_regs = 0, key_num_regs = 0; struct nlattr *attr; - u32 num_regs = 0; int rem, err, i; nla_for_each_nested(attr, nla, rem) { @@ -4827,6 +4829,10 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, for (i = 0; i < desc->field_count; i++) num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32)); + key_num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32)); + if (key_num_regs != num_regs) + return -EINVAL; + if (num_regs > NFT_REG32_COUNT) return -E2BIG; @@ -5048,16 +5054,28 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, } desc.policy = NFT_SET_POL_PERFORMANCE; - if (nla[NFTA_SET_POLICY] != NULL) + if (nla[NFTA_SET_POLICY] != NULL) { desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY])); + switch (desc.policy) { + case NFT_SET_POL_PERFORMANCE: + case NFT_SET_POL_MEMORY: + break; + default: + return -EOPNOTSUPP; + } + } if (nla[NFTA_SET_DESC] != NULL) { err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]); if (err < 0) return err; - if (desc.field_count > 1 && !(flags & NFT_SET_CONCAT)) + if (desc.field_count > 1) { + if (!(flags & NFT_SET_CONCAT)) + return -EINVAL; + } else if (flags & NFT_SET_CONCAT) { return -EINVAL; + } } else if (flags & NFT_SET_CONCAT) { return -EINVAL; } @@ -5704,7 +5722,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_set_dump_args *args; - if (nft_set_elem_expired(ext)) + if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext)) return 0; args = container_of(iter, struct nft_set_dump_args, iter); @@ -6568,7 +6586,7 @@ static int nft_setelem_catchall_deactivate(const struct net *net, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_is_active(net, ext)) + if (!nft_is_active_next(net, ext)) continue; kfree(elem->priv); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index f03f4d4d7d88..134e05d31061 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -508,7 +508,7 @@ __build_packet_message(struct nfnl_log_net *log, htonl(br_port_get_rcu(indev)->br->dev->ifindex))) goto nla_put_failure; } else { - struct net_device *physindev; + int physinif; /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ @@ -516,10 +516,10 @@ __build_packet_message(struct nfnl_log_net *log, htonl(indev->ifindex))) goto nla_put_failure; - physindev = nf_bridge_get_physindev(skb); - if (physindev && + physinif = nf_bridge_get_physinif(skb); + if (physinif && nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, - htonl(physindev->ifindex))) + htonl(physinif))) goto nla_put_failure; } #endif diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 145dc62c6247..79039afde34e 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -58,6 +58,7 @@ static inline bool nft_limit_eval(struct nft_limit_priv *priv, u64 cost) static int nft_limit_init(struct nft_limit_priv *priv, const struct nlattr * const tb[], bool pkts) { + bool invert = false; u64 unit, tokens; if (tb[NFTA_LIMIT_RATE] == NULL || @@ -90,19 +91,23 @@ static int nft_limit_init(struct nft_limit_priv *priv, priv->rate); } + if (tb[NFTA_LIMIT_FLAGS]) { + u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS])); + + if (flags & ~NFT_LIMIT_F_INV) + return -EOPNOTSUPP; + + if (flags & NFT_LIMIT_F_INV) + invert = true; + } + priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL_ACCOUNT); if (!priv->limit) return -ENOMEM; priv->limit->tokens = tokens; priv->tokens_max = priv->limit->tokens; - - if (tb[NFTA_LIMIT_FLAGS]) { - u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS])); - - if (flags & NFT_LIMIT_F_INV) - priv->invert = true; - } + priv->invert = invert; priv->limit->last = ktime_get_ns(); spin_lock_init(&priv->limit->lock); diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index ec6ed6fda96c..343e65f377d4 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -59,7 +59,7 @@ physdev_mt(const struct sk_buff *skb, struct xt_action_param *par) (!!outdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED))) return false; - physdev = nf_bridge_get_physindev(skb); + physdev = nf_bridge_get_physindev(skb, xt_net(par)); indev = physdev ? physdev->name : NULL; if ((info->bitmask & XT_PHYSDEV_OP_ISIN && diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index d63d2e5dc60c..dae378f1d52b 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -858,4 +858,5 @@ void nfc_digital_unregister_device(struct nfc_digital_dev *ddev) } EXPORT_SYMBOL(nfc_digital_unregister_device); +MODULE_DESCRIPTION("NFC Digital protocol stack"); MODULE_LICENSE("GPL"); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 6c9592d05120..97348cedb16b 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1577,4 +1577,5 @@ static void nci_cmd_work(struct work_struct *work) } } +MODULE_DESCRIPTION("NFC Controller Interface"); MODULE_LICENSE("GPL"); diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c index b68150c971d0..6a93533c480e 100644 --- a/net/nfc/nci/spi.c +++ b/net/nfc/nci/spi.c @@ -319,4 +319,5 @@ done: } EXPORT_SYMBOL_GPL(nci_spi_read); +MODULE_DESCRIPTION("NFC Controller Interface (NCI) SPI link layer"); MODULE_LICENSE("GPL"); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 2f8b39a614c3..dbeb75c29857 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1079,6 +1079,7 @@ void rxrpc_send_version_request(struct rxrpc_local *local, /* * local_object.c */ +void rxrpc_local_dont_fragment(const struct rxrpc_local *local, bool set); struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc *); struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *, enum rxrpc_local_trace); struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *, enum rxrpc_local_trace); diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index c553a30e9c83..34d307368135 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -37,6 +37,17 @@ static void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, int err, } /* + * Set or clear the Don't Fragment flag on a socket. + */ +void rxrpc_local_dont_fragment(const struct rxrpc_local *local, bool set) +{ + if (set) + ip_sock_set_mtu_discover(local->socket->sk, IP_PMTUDISC_DO); + else + ip_sock_set_mtu_discover(local->socket->sk, IP_PMTUDISC_DONT); +} + +/* * Compare a local to an address. Return -ve, 0 or +ve to indicate less than, * same or greater than. * @@ -203,7 +214,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) ip_sock_set_recverr(usk); /* we want to set the don't fragment bit */ - ip_sock_set_mtu_discover(usk, IP_PMTUDISC_DO); + rxrpc_local_dont_fragment(local, true); /* We want receive timestamps. */ sock_enable_timestamps(usk); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 5e53429c6922..a0906145e829 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -494,14 +494,12 @@ send_fragmentable: switch (conn->local->srx.transport.family) { case AF_INET6: case AF_INET: - ip_sock_set_mtu_discover(conn->local->socket->sk, - IP_PMTUDISC_DONT); + rxrpc_local_dont_fragment(conn->local, false); rxrpc_inc_stat(call->rxnet, stat_tx_data_send_frag); ret = do_udp_sendmsg(conn->local->socket, &msg, len); conn->peer->last_tx_at = ktime_get_seconds(); - ip_sock_set_mtu_discover(conn->local->socket->sk, - IP_PMTUDISC_DO); + rxrpc_local_dont_fragment(conn->local, true); break; default: diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 1bf571a66e02..b52dedcebce0 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -724,7 +724,9 @@ static int rxkad_send_response(struct rxrpc_connection *conn, serial = atomic_inc_return(&conn->serial); whdr.serial = htonl(serial); + rxrpc_local_dont_fragment(conn->local, false); ret = kernel_sendmsg(conn->local->socket, &msg, iov, 3, len); + rxrpc_local_dont_fragment(conn->local, true); if (ret < 0) { trace_rxrpc_tx_fail(conn->debug_id, serial, ret, rxrpc_tx_point_rxkad_response); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e3236a3169c3..92a12e3d0fe6 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1424,6 +1424,14 @@ static void tcf_block_owner_del(struct tcf_block *block, WARN_ON(1); } +static bool tcf_block_tracks_dev(struct tcf_block *block, + struct tcf_block_ext_info *ei) +{ + return tcf_block_shared(block) && + (ei->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS || + ei->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS); +} + int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, struct tcf_block_ext_info *ei, struct netlink_ext_ack *extack) @@ -1462,7 +1470,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, if (err) goto err_block_offload_bind; - if (tcf_block_shared(block)) { + if (tcf_block_tracks_dev(block, ei)) { err = xa_insert(&block->ports, dev->ifindex, dev, GFP_KERNEL); if (err) { NL_SET_ERR_MSG(extack, "block dev insert failed"); @@ -1516,7 +1524,7 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, if (!block) return; - if (tcf_block_shared(block)) + if (tcf_block_tracks_dev(block, ei)) xa_erase(&block->ports, dev->ifindex); tcf_chain0_head_change_cb_del(block, ei); tcf_block_owner_del(block, q, ei->binder_type); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 1af71fbb0d80..c7af0220f82f 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -2280,6 +2280,7 @@ static void __exit exit_rpcsec_gss(void) } MODULE_ALIAS("rpc-auth-6"); +MODULE_DESCRIPTION("Sun RPC Kerberos RPCSEC_GSS client authentication"); MODULE_LICENSE("GPL"); module_param_named(expired_cred_retry_delay, gss_expired_cred_retry_delay, diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index e31cfdf7eadc..64cff717c3d9 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -650,6 +650,7 @@ static void __exit cleanup_kerberos_module(void) gss_mech_unregister(&gss_kerberos_mech); } +MODULE_DESCRIPTION("Sun RPC Kerberos 5 module"); MODULE_LICENSE("GPL"); module_init(init_kerberos_module); module_exit(cleanup_kerberos_module); diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index 691c0000e9ea..bab6cab29405 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -148,6 +148,7 @@ cleanup_sunrpc(void) #endif rcu_barrier(); /* Wait for completion of call_rcu()'s */ } +MODULE_DESCRIPTION("Sun RPC core"); MODULE_LICENSE("GPL"); fs_initcall(init_sunrpc); /* Ensure we're initialised before nfs */ module_exit(cleanup_sunrpc); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index e37b4d2e2acd..31e8a94dfc11 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1052,7 +1052,11 @@ alloc_encrypted: if (ret < 0) goto send_end; tls_ctx->pending_open_record_frags = true; - if (full_record || eor || sk_msg_full(msg_pl)) + + if (sk_msg_full(msg_pl)) + full_record = true; + + if (full_record || eor) goto copied; continue; } diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index c5a42ac309fd..afd09571c482 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -6695,6 +6695,67 @@ static struct { /* all other program types don't have "named" context structs */ }; +static bool need_func_arg_type_fixup(const struct btf *btf, const struct bpf_program *prog, + const char *subprog_name, int arg_idx, + int arg_type_id, const char *ctx_name) +{ + const struct btf_type *t; + const char *tname; + + /* check if existing parameter already matches verifier expectations */ + t = skip_mods_and_typedefs(btf, arg_type_id, NULL); + if (!btf_is_ptr(t)) + goto out_warn; + + /* typedef bpf_user_pt_regs_t is a special PITA case, valid for kprobe + * and perf_event programs, so check this case early on and forget + * about it for subsequent checks + */ + while (btf_is_mod(t)) + t = btf__type_by_id(btf, t->type); + if (btf_is_typedef(t) && + (prog->type == BPF_PROG_TYPE_KPROBE || prog->type == BPF_PROG_TYPE_PERF_EVENT)) { + tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>"; + if (strcmp(tname, "bpf_user_pt_regs_t") == 0) + return false; /* canonical type for kprobe/perf_event */ + } + + /* now we can ignore typedefs moving forward */ + t = skip_mods_and_typedefs(btf, t->type, NULL); + + /* if it's `void *`, definitely fix up BTF info */ + if (btf_is_void(t)) + return true; + + /* if it's already proper canonical type, no need to fix up */ + tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>"; + if (btf_is_struct(t) && strcmp(tname, ctx_name) == 0) + return false; + + /* special cases */ + switch (prog->type) { + case BPF_PROG_TYPE_KPROBE: + case BPF_PROG_TYPE_PERF_EVENT: + /* `struct pt_regs *` is expected, but we need to fix up */ + if (btf_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return true; + break; + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return true; + break; + default: + break; + } + +out_warn: + pr_warn("prog '%s': subprog '%s' arg#%d is expected to be of `struct %s *` type\n", + prog->name, subprog_name, arg_idx, ctx_name); + return false; +} + static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_program *prog) { int fn_id, fn_proto_id, ret_type_id, orig_proto_id; @@ -6757,6 +6818,69 @@ static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_progr return fn_id; } +static int probe_kern_arg_ctx_tag(void) +{ + /* To minimize merge conflicts with BPF token series that refactors + * feature detection code a lot, we don't integrate + * probe_kern_arg_ctx_tag() into kernel_supports() feature-detection + * framework yet, doing our own caching internally. + * This will be cleaned up a bit later when bpf/bpf-next trees settle. + */ + static int cached_result = -1; + static const char strs[] = "\0a\0b\0arg:ctx\0"; + const __u32 types[] = { + /* [1] INT */ + BTF_TYPE_INT_ENC(1 /* "a" */, BTF_INT_SIGNED, 0, 32, 4), + /* [2] PTR -> VOID */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0), + /* [3] FUNC_PROTO `int(void *a)` */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1), + BTF_PARAM_ENC(1 /* "a" */, 2), + /* [4] FUNC 'a' -> FUNC_PROTO (main prog) */ + BTF_TYPE_ENC(1 /* "a" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 3), + /* [5] FUNC_PROTO `int(void *b __arg_ctx)` */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1), + BTF_PARAM_ENC(3 /* "b" */, 2), + /* [6] FUNC 'b' -> FUNC_PROTO (subprog) */ + BTF_TYPE_ENC(3 /* "b" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 5), + /* [7] DECL_TAG 'arg:ctx' -> func 'b' arg 'b' */ + BTF_TYPE_DECL_TAG_ENC(5 /* "arg:ctx" */, 6, 0), + }; + const struct bpf_insn insns[] = { + /* main prog */ + BPF_CALL_REL(+1), + BPF_EXIT_INSN(), + /* global subprog */ + BPF_EMIT_CALL(BPF_FUNC_get_func_ip), /* needs PTR_TO_CTX */ + BPF_EXIT_INSN(), + }; + const struct bpf_func_info_min func_infos[] = { + { 0, 4 }, /* main prog -> FUNC 'a' */ + { 2, 6 }, /* subprog -> FUNC 'b' */ + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts); + int prog_fd, btf_fd, insn_cnt = ARRAY_SIZE(insns); + + if (cached_result >= 0) + return cached_result; + + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs)); + if (btf_fd < 0) + return 0; + + opts.prog_btf_fd = btf_fd; + opts.func_info = &func_infos; + opts.func_info_cnt = ARRAY_SIZE(func_infos); + opts.func_info_rec_size = sizeof(func_infos[0]); + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, "det_arg_ctx", + "GPL", insns, insn_cnt, &opts); + close(btf_fd); + + cached_result = probe_fd(prog_fd); + return cached_result; +} + /* Check if main program or global subprog's function prototype has `arg:ctx` * argument tags, and, if necessary, substitute correct type to match what BPF * verifier would expect, taking into account specific program type. This @@ -6766,7 +6890,7 @@ static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_progr */ static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_program *prog) { - const char *ctx_name = NULL, *ctx_tag = "arg:ctx"; + const char *ctx_name = NULL, *ctx_tag = "arg:ctx", *fn_name; struct bpf_func_info_min *func_rec; struct btf_type *fn_t, *fn_proto_t; struct btf *btf = obj->btf; @@ -6780,6 +6904,10 @@ static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_progra if (!obj->btf_ext || !prog->func_info) return 0; + /* don't do any fix ups if kernel natively supports __arg_ctx */ + if (probe_kern_arg_ctx_tag() > 0) + return 0; + /* some BPF program types just don't have named context structs, so * this fallback mechanism doesn't work for them */ @@ -6842,15 +6970,11 @@ static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_progra if (arg_idx < 0 || arg_idx >= arg_cnt) continue; - /* check if existing parameter already matches verifier expectations */ + /* check if we should fix up argument type */ p = &btf_params(fn_proto_t)[arg_idx]; - t = skip_mods_and_typedefs(btf, p->type, NULL); - if (btf_is_ptr(t) && - (t = skip_mods_and_typedefs(btf, t->type, NULL)) && - btf_is_struct(t) && - strcmp(btf__str_by_offset(btf, t->name_off), ctx_name) == 0) { - continue; /* no need for fix up */ - } + fn_name = btf__str_by_offset(btf, fn_t->name_off) ?: "<anon>"; + if (!need_func_arg_type_fixup(btf, prog, fn_name, arg_idx, p->type, ctx_name)) + continue; /* clone fn/fn_proto, unless we already did it for another arg */ if (func_rec->type_id == orig_fn_id) { diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c new file mode 100644 index 000000000000..0c365f36c73b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2024 Meta + +#include <test_progs.h> +#include "network_helpers.h" +#include "sock_iter_batch.skel.h" + +#define TEST_NS "sock_iter_batch_netns" + +static const int nr_soreuse = 4; + +static void do_test(int sock_type, bool onebyone) +{ + int err, i, nread, to_read, total_read, iter_fd = -1; + int first_idx, second_idx, indices[nr_soreuse]; + struct bpf_link *link = NULL; + struct sock_iter_batch *skel; + int *fds[2] = {}; + + skel = sock_iter_batch__open(); + if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open")) + return; + + /* Prepare 2 buckets of sockets in the kernel hashtable */ + for (i = 0; i < ARRAY_SIZE(fds); i++) { + int local_port; + + fds[i] = start_reuseport_server(AF_INET6, sock_type, "::1", 0, 0, + nr_soreuse); + if (!ASSERT_OK_PTR(fds[i], "start_reuseport_server")) + goto done; + local_port = get_socket_local_port(*fds[i]); + if (!ASSERT_GE(local_port, 0, "get_socket_local_port")) + goto done; + skel->rodata->ports[i] = ntohs(local_port); + } + + err = sock_iter_batch__load(skel); + if (!ASSERT_OK(err, "sock_iter_batch__load")) + goto done; + + link = bpf_program__attach_iter(sock_type == SOCK_STREAM ? + skel->progs.iter_tcp_soreuse : + skel->progs.iter_udp_soreuse, + NULL); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter")) + goto done; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_GE(iter_fd, 0, "bpf_iter_create")) + goto done; + + /* Test reading a bucket (either from fds[0] or fds[1]). + * Only read "nr_soreuse - 1" number of sockets + * from a bucket and leave one socket out from + * that bucket on purpose. + */ + to_read = (nr_soreuse - 1) * sizeof(*indices); + total_read = 0; + first_idx = -1; + do { + nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read); + if (nread <= 0 || nread % sizeof(*indices)) + break; + total_read += nread; + + if (first_idx == -1) + first_idx = indices[0]; + for (i = 0; i < nread / sizeof(*indices); i++) + ASSERT_EQ(indices[i], first_idx, "first_idx"); + } while (total_read < to_read); + ASSERT_EQ(nread, onebyone ? sizeof(*indices) : to_read, "nread"); + ASSERT_EQ(total_read, to_read, "total_read"); + + free_fds(fds[first_idx], nr_soreuse); + fds[first_idx] = NULL; + + /* Read the "whole" second bucket */ + to_read = nr_soreuse * sizeof(*indices); + total_read = 0; + second_idx = !first_idx; + do { + nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read); + if (nread <= 0 || nread % sizeof(*indices)) + break; + total_read += nread; + + for (i = 0; i < nread / sizeof(*indices); i++) + ASSERT_EQ(indices[i], second_idx, "second_idx"); + } while (total_read <= to_read); + ASSERT_EQ(nread, 0, "nread"); + /* Both so_reuseport ports should be in different buckets, so + * total_read must equal to the expected to_read. + * + * For a very unlikely case, both ports collide at the same bucket, + * the bucket offset (i.e. 3) will be skipped and it cannot + * expect the to_read number of bytes. + */ + if (skel->bss->bucket[0] != skel->bss->bucket[1]) + ASSERT_EQ(total_read, to_read, "total_read"); + +done: + for (i = 0; i < ARRAY_SIZE(fds); i++) + free_fds(fds[i], nr_soreuse); + if (iter_fd < 0) + close(iter_fd); + bpf_link__destroy(link); + sock_iter_batch__destroy(skel); +} + +void test_sock_iter_batch(void) +{ + struct nstoken *nstoken = NULL; + + SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null"); + SYS(done, "ip netns add %s", TEST_NS); + SYS(done, "ip -net %s link set dev lo up", TEST_NS); + + nstoken = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto done; + + if (test__start_subtest("tcp")) { + do_test(SOCK_STREAM, true); + do_test(SOCK_STREAM, false); + } + if (test__start_subtest("udp")) { + do_test(SOCK_DGRAM, true); + do_test(SOCK_DGRAM, false); + } + close_netns(nstoken); + +done: + SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null"); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c index 67d4ef9e62b3..e905cbaf6b3d 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -47,6 +47,19 @@ static void subtest_ctx_arg_rewrite(void) struct btf *btf = NULL; __u32 info_len = sizeof(info); int err, fd, i; + struct btf *kern_btf = NULL; + + kern_btf = btf__load_vmlinux_btf(); + if (!ASSERT_OK_PTR(kern_btf, "kern_btf_load")) + return; + + /* simple detection of kernel native arg:ctx tag support */ + if (btf__find_by_name_kind(kern_btf, "bpf_subprog_arg_info", BTF_KIND_STRUCT) > 0) { + test__skip(); + btf__free(kern_btf); + return; + } + btf__free(kern_btf); skel = test_global_func_ctx_args__open(); if (!ASSERT_OK_PTR(skel, "skel_open")) diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index 1bdc680b0e0e..e8bd4b7b5ef7 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -72,6 +72,8 @@ #define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr #define inet_dport sk.__sk_common.skc_dport +#define udp_portaddr_hash inet.sk.__sk_common.skc_u16hashes[1] + #define ir_loc_addr req.__req_common.skc_rcv_saddr #define ir_num req.__req_common.skc_num #define ir_rmt_addr req.__req_common.skc_daddr @@ -85,6 +87,7 @@ #define sk_rmem_alloc sk_backlog.rmem_alloc #define sk_refcnt __sk_common.skc_refcnt #define sk_state __sk_common.skc_state +#define sk_net __sk_common.skc_net #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_flags __sk_common.skc_flags diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c new file mode 100644 index 000000000000..ffbbfe1fa1c1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2024 Meta + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_endian.h> +#include "bpf_tracing_net.h" +#include "bpf_kfuncs.h" + +#define ATTR __always_inline +#include "test_jhash.h" + +static bool ipv6_addr_loopback(const struct in6_addr *a) +{ + return (a->s6_addr32[0] | a->s6_addr32[1] | + a->s6_addr32[2] | (a->s6_addr32[3] ^ bpf_htonl(1))) == 0; +} + +volatile const __u16 ports[2]; +unsigned int bucket[2]; + +SEC("iter/tcp") +int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) +{ + struct sock *sk = (struct sock *)ctx->sk_common; + struct inet_hashinfo *hinfo; + unsigned int hash; + struct net *net; + int idx; + + if (!sk) + return 0; + + sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock)); + if (sk->sk_family != AF_INET6 || + sk->sk_state != TCP_LISTEN || + !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr)) + return 0; + + if (sk->sk_num == ports[0]) + idx = 0; + else if (sk->sk_num == ports[1]) + idx = 1; + else + return 0; + + /* bucket selection as in inet_lhash2_bucket_sk() */ + net = sk->sk_net.net; + hash = jhash2(sk->sk_v6_rcv_saddr.s6_addr32, 4, net->hash_mix); + hash ^= sk->sk_num; + hinfo = net->ipv4.tcp_death_row.hashinfo; + bucket[idx] = hash & hinfo->lhash2_mask; + bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx)); + + return 0; +} + +#define udp_sk(ptr) container_of(ptr, struct udp_sock, inet.sk) + +SEC("iter/udp") +int iter_udp_soreuse(struct bpf_iter__udp *ctx) +{ + struct sock *sk = (struct sock *)ctx->udp_sk; + struct udp_table *udptable; + int idx; + + if (!sk) + return 0; + + sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock)); + if (sk->sk_family != AF_INET6 || + !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr)) + return 0; + + if (sk->sk_num == ports[0]) + idx = 0; + else if (sk->sk_num == ports[1]) + idx = 1; + else + return 0; + + /* bucket selection as in udp_hashslot2() */ + udptable = sk->sk_net.net->ipv4.udp_table; + bucket[idx] = udp_sk(sk)->udp_portaddr_hash & udptable->mask; + bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx)); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_jhash.h b/tools/testing/selftests/bpf/progs/test_jhash.h index c300734d26f6..ef53559bbbdf 100644 --- a/tools/testing/selftests/bpf/progs/test_jhash.h +++ b/tools/testing/selftests/bpf/progs/test_jhash.h @@ -69,3 +69,34 @@ u32 jhash(const void *key, u32 length, u32 initval) return c; } + +static __always_inline u32 jhash2(const u32 *k, u32 length, u32 initval) +{ + u32 a, b, c; + + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + (length<<2) + initval; + + /* Handle most of the key */ + while (length > 3) { + a += k[0]; + b += k[1]; + c += k[2]; + __jhash_mix(a, b, c); + length -= 3; + k += 3; + } + + /* Handle the last 3 u32's */ + switch (length) { + case 3: c += k[2]; + case 2: b += k[1]; + case 1: a += k[0]; + __jhash_final(a, b, c); + break; + case 0: /* Nothing left to add */ + break; + } + + return c; +} diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c index 9eeb2d89cda8..67dddd941891 100644 --- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c +++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c @@ -3,6 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> #include "bpf_misc.h" #include "xdp_metadata.h" #include "bpf_kfuncs.h" @@ -138,25 +139,182 @@ __weak int subprog_ctx_tag(void *ctx __arg_ctx) return bpf_get_stack(ctx, stack, sizeof(stack), 0); } +__weak int raw_tp_canonical(struct bpf_raw_tracepoint_args *ctx __arg_ctx) +{ + return 0; +} + +__weak int raw_tp_u64_array(u64 *ctx __arg_ctx) +{ + return 0; +} + SEC("?raw_tp") __success __log_level(2) int arg_tag_ctx_raw_tp(void *ctx) { - return subprog_ctx_tag(ctx); + return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx); +} + +SEC("?raw_tp.w") +__success __log_level(2) +int arg_tag_ctx_raw_tp_writable(void *ctx) +{ + return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx); +} + +SEC("?tp_btf/sys_enter") +__success __log_level(2) +int arg_tag_ctx_raw_tp_btf(void *ctx) +{ + return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx); +} + +struct whatever { }; + +__weak int tp_whatever(struct whatever *ctx __arg_ctx) +{ + return 0; } SEC("?tp") __success __log_level(2) int arg_tag_ctx_tp(void *ctx) { - return subprog_ctx_tag(ctx); + return subprog_ctx_tag(ctx) + tp_whatever(ctx); +} + +__weak int kprobe_subprog_pt_regs(struct pt_regs *ctx __arg_ctx) +{ + return 0; +} + +__weak int kprobe_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx) +{ + return 0; } SEC("?kprobe") __success __log_level(2) int arg_tag_ctx_kprobe(void *ctx) { - return subprog_ctx_tag(ctx); + return subprog_ctx_tag(ctx) + + kprobe_subprog_pt_regs(ctx) + + kprobe_subprog_typedef(ctx); +} + +__weak int perf_subprog_regs( +#if defined(bpf_target_riscv) + struct user_regs_struct *ctx __arg_ctx +#elif defined(bpf_target_s390) + /* user_pt_regs typedef is anonymous struct, so only `void *` works */ + void *ctx __arg_ctx +#elif defined(bpf_target_loongarch) || defined(bpf_target_arm64) || defined(bpf_target_powerpc) + struct user_pt_regs *ctx __arg_ctx +#else + struct pt_regs *ctx __arg_ctx +#endif +) +{ + return 0; +} + +__weak int perf_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx) +{ + return 0; +} + +__weak int perf_subprog_canonical(struct bpf_perf_event_data *ctx __arg_ctx) +{ + return 0; +} + +SEC("?perf_event") +__success __log_level(2) +int arg_tag_ctx_perf(void *ctx) +{ + return subprog_ctx_tag(ctx) + + perf_subprog_regs(ctx) + + perf_subprog_typedef(ctx) + + perf_subprog_canonical(ctx); +} + +__weak int iter_subprog_void(void *ctx __arg_ctx) +{ + return 0; +} + +__weak int iter_subprog_typed(struct bpf_iter__task *ctx __arg_ctx) +{ + return 0; +} + +SEC("?iter/task") +__success __log_level(2) +int arg_tag_ctx_iter_task(struct bpf_iter__task *ctx) +{ + return (iter_subprog_void(ctx) + iter_subprog_typed(ctx)) & 1; +} + +__weak int tracing_subprog_void(void *ctx __arg_ctx) +{ + return 0; +} + +__weak int tracing_subprog_u64(u64 *ctx __arg_ctx) +{ + return 0; +} + +int acc; + +SEC("?fentry/" SYS_PREFIX "sys_nanosleep") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_fentry) +{ + acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); + return 0; +} + +SEC("?fexit/" SYS_PREFIX "sys_nanosleep") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_fexit) +{ + acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); + return 0; +} + +SEC("?fmod_ret/" SYS_PREFIX "sys_nanosleep") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_fmod_ret) +{ + return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); +} + +SEC("?lsm/bpf") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_lsm) +{ + return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); +} + +SEC("?struct_ops/test_1") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_struct_ops) +{ + return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); +} + +SEC(".struct_ops") +struct bpf_dummy_ops dummy_1 = { + .test_1 = (void *)arg_tag_ctx_struct_ops, +}; + +SEC("?syscall") +__success __log_level(2) +int arg_tag_ctx_syscall(void *ctx) +{ + return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx) + tp_whatever(ctx); } __weak int subprog_dynptr(struct bpf_dynptr *dptr) diff --git a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c index 71814a753216..a9ab37d3b9e2 100644 --- a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c +++ b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c @@ -146,4 +146,23 @@ l0_%=: exit; \ : __clobber_all); } +SEC("flow_dissector") +__description("flow_keys illegal alu op with variable offset") +__failure __msg("R7 pointer arithmetic on flow_keys prohibited") +__naked void flow_keys_illegal_variable_offset_alu(void) +{ + asm volatile(" \ + r6 = r1; \ + r7 = *(u64*)(r6 + %[flow_keys_off]); \ + r8 = 8; \ + r8 /= 1; \ + r8 &= 8; \ + r7 += r8; \ + r0 = *(u64*)(r7 + 0); \ + exit; \ +" : + : __imm_const(flow_keys_off, offsetof(struct __sk_buff, flow_keys)) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index 70638fa50b2c..899d7fb6ea8e 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -1,2 +1,10 @@ CONFIG_BONDING=y +CONFIG_BRIDGE=y +CONFIG_DUMMY=y +CONFIG_IPV6=y CONFIG_MACVLAN=y +CONFIG_NET_ACT_GACT=y +CONFIG_NET_CLS_FLOWER=y +CONFIG_NET_SCH_INGRESS=y +CONFIG_NLMON=y +CONFIG_VETH=y diff --git a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh index ad4c845a4ac7..b76bf5030952 100755 --- a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh +++ b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Regression Test: diff --git a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh index 2330d37453f9..8c2619002147 100755 --- a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh +++ b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Regression Test: diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh index 42ce602d8d49..0f0f4f05807c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh @@ -40,7 +40,6 @@ # | + $swp1 $swp3 + + $swp4 | # | | iPOOL1 iPOOL0 | | iPOOL2 | # | | ePOOL4 ePOOL5 | | ePOOL4 | -# | | 1Gbps | | 1Gbps | # | | PFC:enabled=1 | | PFC:enabled=1 | # | +-|----------------------|-+ +-|------------------------+ | # | | + $swp1.111 $swp3.111 + | | + $swp4.111 | | @@ -120,6 +119,9 @@ h2_destroy() switch_create() { + local lanes_swp4 + local pg1_size + # pools # ----- @@ -229,7 +231,20 @@ switch_create() dcb pfc set dev $swp4 prio-pfc all:off 1:on # PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which # is (-2*MTU) about 80K of delay provision. - dcb buffer set dev $swp4 buffer-size all:0 1:$_100KB + pg1_size=$_100KB + + setup_wait_dev_with_timeout $swp4 + + lanes_swp4=$(ethtool $swp4 | grep 'Lanes:') + lanes_swp4=${lanes_swp4#*"Lanes: "} + + # 8-lane ports use two buffers among which the configured buffer + # is split, so double the size to get twice (20K + 80K). + if [[ $lanes_swp4 -eq 8 ]]; then + pg1_size=$((pg1_size * 2)) + fi + + dcb buffer set dev $swp4 buffer-size all:0 1:$pg1_size # bridges # ------- diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh index fb850e0ec837..616d3581419c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh @@ -10,7 +10,8 @@ lib_dir=$(dirname $0)/../../../../net/forwarding ALL_TESTS="single_mask_test identical_filters_test two_masks_test \ multiple_masks_test ctcam_edge_cases_test delta_simple_test \ delta_two_masks_one_key_test delta_simple_rehash_test \ - bloom_simple_test bloom_complex_test bloom_delta_test" + bloom_simple_test bloom_complex_test bloom_delta_test \ + max_erp_entries_test max_group_size_test" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/tc_common.sh @@ -983,6 +984,109 @@ bloom_delta_test() log_test "bloom delta test ($tcflags)" } +max_erp_entries_test() +{ + # The number of eRP entries is limited. Once the maximum number of eRPs + # has been reached, filters cannot be added. This test verifies that + # when this limit is reached, inserstion fails without crashing. + + RET=0 + + local num_masks=32 + local num_regions=15 + local chain_failed + local mask_failed + local ret + + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + + for ((i=1; i < $num_regions; i++)); do + for ((j=$num_masks; j >= 0; j--)); do + tc filter add dev $h2 ingress chain $i protocol ip \ + pref $i handle $j flower $tcflags \ + dst_ip 192.1.0.0/$j &> /dev/null + ret=$? + + if [ $ret -ne 0 ]; then + chain_failed=$i + mask_failed=$j + break 2 + fi + done + done + + # We expect to exceed the maximum number of eRP entries, so that + # insertion eventually fails. Otherwise, the test should be adjusted to + # add more filters. + check_fail $ret "expected to exceed number of eRP entries" + + for ((; i >= 1; i--)); do + for ((j=0; j <= $num_masks; j++)); do + tc filter del dev $h2 ingress chain $i protocol ip \ + pref $i handle $j flower &> /dev/null + done + done + + log_test "max eRP entries test ($tcflags). " \ + "max chain $chain_failed, mask $mask_failed" +} + +max_group_size_test() +{ + # The number of ACLs in an ACL group is limited. Once the maximum + # number of ACLs has been reached, filters cannot be added. This test + # verifies that when this limit is reached, insertion fails without + # crashing. + + RET=0 + + local num_acls=32 + local max_size + local ret + + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + + for ((i=1; i < $num_acls; i++)); do + if [[ $(( i % 2 )) == 1 ]]; then + tc filter add dev $h2 ingress pref $i proto ipv4 \ + flower $tcflags dst_ip 198.51.100.1/32 \ + ip_proto tcp tcp_flags 0x01/0x01 \ + action drop &> /dev/null + else + tc filter add dev $h2 ingress pref $i proto ipv6 \ + flower $tcflags dst_ip 2001:db8:1::1/128 \ + action drop &> /dev/null + fi + + ret=$? + [[ $ret -ne 0 ]] && max_size=$((i - 1)) && break + done + + # We expect to exceed the maximum number of ACLs in a group, so that + # insertion eventually fails. Otherwise, the test should be adjusted to + # add more filters. + check_fail $ret "expected to exceed number of ACLs in a group" + + for ((; i >= 1; i--)); do + if [[ $(( i % 2 )) == 1 ]]; then + tc filter del dev $h2 ingress pref $i proto ipv4 \ + flower $tcflags dst_ip 198.51.100.1/32 \ + ip_proto tcp tcp_flags 0x01/0x01 \ + action drop &> /dev/null + else + tc filter del dev $h2 ingress pref $i proto ipv6 \ + flower $tcflags dst_ip 2001:db8:1::1/128 \ + action drop &> /dev/null + fi + done + + log_test "max ACL group size test ($tcflags). max size $max_size" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/drivers/net/netdevsim/config b/tools/testing/selftests/drivers/net/netdevsim/config new file mode 100644 index 000000000000..adf45a3a78b4 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/config @@ -0,0 +1,10 @@ +CONFIG_DUMMY=y +CONFIG_GENEVE=m +CONFIG_IPV6=y +CONFIG_NETDEVSIM=m +CONFIG_NET_SCH_MQPRIO=y +CONFIG_NET_SCH_MULTIQ=y +CONFIG_NET_SCH_PRIO=y +CONFIG_PSAMPLE=y +CONFIG_PTP_1588_CLOCK_MOCK=y +CONFIG_VXLAN=m diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh index 922744059aaa..80160579e0cc 100644 --- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh @@ -51,6 +51,7 @@ function make_netdev { fi echo $NSIM_ID $@ > /sys/bus/netdevsim/new_device + udevadm settle # get new device name ls /sys/bus/netdevsim/devices/netdevsim${NSIM_ID}/net/ } diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh index 0c56746e9ce0..7d7829f57550 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh @@ -8,16 +8,20 @@ NSIM_NETDEV=$(make_netdev) set -o pipefail +# Since commit 2b3ddcb35357 ("ethtool: fec: Change the prompt ...") +# in ethtool CLI the Configured lines start with Supported/Configured. +configured=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2 | head -1 | cut -d' ' -f1) + # netdevsim starts out with None/None s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) -check $? "$s" "Configured FEC encodings: None +check $? "$s" "$configured FEC encodings: None Active FEC encoding: None" # Test Auto $ETHTOOL --set-fec $NSIM_NETDEV encoding auto check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) -check $? "$s" "Configured FEC encodings: Auto +check $? "$s" "$configured FEC encodings: Auto Active FEC encoding: Off" # Test case in-sensitivity @@ -25,7 +29,7 @@ for o in off Off OFF; do $ETHTOOL --set-fec $NSIM_NETDEV encoding $o check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) - check $? "$s" "Configured FEC encodings: Off + check $? "$s" "$configured FEC encodings: Off Active FEC encoding: Off" done @@ -33,7 +37,7 @@ for o in BaseR baser BAser; do $ETHTOOL --set-fec $NSIM_NETDEV encoding $o check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) - check $? "$s" "Configured FEC encodings: BaseR + check $? "$s" "$configured FEC encodings: BaseR Active FEC encoding: BaseR" done @@ -41,7 +45,7 @@ for o in llrs rs; do $ETHTOOL --set-fec $NSIM_NETDEV encoding $o check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) - check $? "$s" "Configured FEC encodings: ${o^^} + check $? "$s" "$configured FEC encodings: ${o^^} Active FEC encoding: ${o^^}" done @@ -49,13 +53,13 @@ done $ETHTOOL --set-fec $NSIM_NETDEV encoding rs llrs check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) -check $? "$s" "Configured FEC encodings: RS LLRS +check $? "$s" "$configured FEC encodings: RS LLRS Active FEC encoding: LLRS" $ETHTOOL --set-fec $NSIM_NETDEV encoding rs off auto check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) -check $? "$s" "Configured FEC encodings: Auto Off RS +check $? "$s" "$configured FEC encodings: Auto Off RS Active FEC encoding: RS" # Make sure other link modes are rejected diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh index 1b08e042cf94..4855ef597a15 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -233,6 +233,7 @@ function print_tables { function get_netdev_name { local -n old=$1 + udevadm settle new=$(ls /sys/class/net) for netdev in $new; do diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 8a61464ab6eb..8a61464ab6eb 100755..100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index a10a32952f21..4667d74579d1 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -28,6 +28,7 @@ ALL_TESTS=" kci_test_neigh_get kci_test_bridge_parent_id kci_test_address_proto + kci_test_enslave_bonding " devdummy="test-dummy0" @@ -1241,6 +1242,31 @@ kci_test_address_proto() return $ret } +kci_test_enslave_bonding() +{ + local bond="bond123" + local ret=0 + + setup_ns testns + if [ $? -ne 0 ]; then + end_test "SKIP bonding tests: cannot add net namespace $testns" + return $ksft_skip + fi + + run_cmd ip -netns $testns link add dev $bond type bond mode balance-rr + run_cmd ip -netns $testns link add dev $devdummy type dummy + run_cmd ip -netns $testns link set dev $devdummy up + run_cmd ip -netns $testns link set dev $devdummy master $bond down + if [ $ret -ne 0 ]; then + end_test "FAIL: initially up interface added to a bond and set down" + ip netns del "$testns" + return 1 + fi + + end_test "PASS: enslave interface in a bond" + ip netns del "$testns" +} + kci_test_rtnl() { local current_test diff --git a/tools/testing/selftests/net/tcp_ao/Makefile b/tools/testing/selftests/net/tcp_ao/Makefile index 8e60bae67aa9..522d991e310e 100644 --- a/tools/testing/selftests/net/tcp_ao/Makefile +++ b/tools/testing/selftests/net/tcp_ao/Makefile @@ -52,5 +52,5 @@ $(OUTPUT)/%_ipv6: %.c $(OUTPUT)/icmps-accept_ipv4: CFLAGS+= -DTEST_ICMPS_ACCEPT $(OUTPUT)/icmps-accept_ipv6: CFLAGS+= -DTEST_ICMPS_ACCEPT -$(OUTPUT)/bench-lookups_ipv4: LDFLAGS+= -lm -$(OUTPUT)/bench-lookups_ipv6: LDFLAGS+= -lm +$(OUTPUT)/bench-lookups_ipv4: LDLIBS+= -lm +$(OUTPUT)/bench-lookups_ipv6: LDLIBS+= -lm diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 464853a7f982..7799e042a971 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -707,6 +707,20 @@ TEST_F(tls, splice_from_pipe) EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } +TEST_F(tls, splice_more) +{ + unsigned int f = SPLICE_F_NONBLOCK | SPLICE_F_MORE | SPLICE_F_GIFT; + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + int i, send_pipe = 1; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_GE(write(p[1], mem_send, send_len), 0); + for (i = 0; i < 32; i++) + EXPECT_EQ(splice(p[0], NULL, self->fd, NULL, send_pipe, f), 1); +} + TEST_F(tls, splice_from_pipe2) { int send_len = 16000; |