diff options
36 files changed, 351 insertions, 161 deletions
@@ -299,6 +299,8 @@ Martin Kepplinger <martink@posteo.de> <martin.kepplinger@puri.sm> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com> Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com> <martyna.szapar-mudlaw@intel.com> Mathieu Othacehe <m.othacehe@gmail.com> +Mat Martineau <martineau@kernel.org> <mathew.j.martineau@linux.intel.com> +Mat Martineau <martineau@kernel.org> <mathewm@codeaurora.org> Matthew Wilcox <willy@infradead.org> <matthew.r.wilcox@intel.com> Matthew Wilcox <willy@infradead.org> <matthew@wil.cx> Matthew Wilcox <willy@infradead.org> <mawilcox@linuxonhyperv.com> diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst index 10f282c2117c..2f60e34ab926 100644 --- a/Documentation/networking/devlink/ice.rst +++ b/Documentation/networking/devlink/ice.rst @@ -7,6 +7,21 @@ ice devlink support This document describes the devlink features implemented by the ``ice`` device driver. +Parameters +========== + +.. list-table:: Generic parameters implemented + + * - Name + - Mode + - Notes + * - ``enable_roce`` + - runtime + - mutually exclusive with ``enable_iwarp`` + * - ``enable_iwarp`` + - runtime + - mutually exclusive with ``enable_roce`` + Info versions ============= diff --git a/MAINTAINERS b/MAINTAINERS index 0e64787aace8..c6545eb54104 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14594,6 +14594,7 @@ F: net/netlabel/ NETWORKING [MPTCP] M: Matthieu Baerts <matthieu.baerts@tessares.net> +M: Mat Martineau <martineau@kernel.org> L: netdev@vger.kernel.org L: mptcp@lists.linux.dev S: Maintained diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index d0846ba818ee..6b1876e4ad3f 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -539,7 +539,7 @@ static void bpf_jit_plt(void *plt, void *ret, void *target) { memcpy(plt, bpf_plt, BPF_PLT_SIZE); *(void **)((char *)plt + (bpf_plt_ret - bpf_plt)) = ret; - *(void **)((char *)plt + (bpf_plt_target - bpf_plt)) = target; + *(void **)((char *)plt + (bpf_plt_target - bpf_plt)) = target ?: ret; } /* @@ -2010,7 +2010,9 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, } __packed insn; char expected_plt[BPF_PLT_SIZE]; char current_plt[BPF_PLT_SIZE]; + char new_plt[BPF_PLT_SIZE]; char *plt; + char *ret; int err; /* Verify the branch to be patched. */ @@ -2032,12 +2034,15 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, err = copy_from_kernel_nofault(current_plt, plt, BPF_PLT_SIZE); if (err < 0) return err; - bpf_jit_plt(expected_plt, (char *)ip + 6, old_addr); + ret = (char *)ip + 6; + bpf_jit_plt(expected_plt, ret, old_addr); if (memcmp(current_plt, expected_plt, BPF_PLT_SIZE)) return -EINVAL; /* Adjust the call address. */ + bpf_jit_plt(new_plt, ret, new_addr); s390_kernel_write(plt + (bpf_plt_target - bpf_plt), - &new_addr, sizeof(void *)); + new_plt + (bpf_plt_target - bpf_plt), + sizeof(void *)); } /* Adjust the mask of the branch. */ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 8cc9a74789b7..7a7d584f378a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1777,14 +1777,15 @@ void bond_lower_state_changed(struct slave *slave) /* The bonding driver uses ether_setup() to convert a master bond device * to ARPHRD_ETHER, that resets the target netdevice's flags so we always - * have to restore the IFF_MASTER flag, and only restore IFF_SLAVE if it was set + * have to restore the IFF_MASTER flag, and only restore IFF_SLAVE and IFF_UP + * if they were set */ static void bond_ether_setup(struct net_device *bond_dev) { - unsigned int slave_flag = bond_dev->flags & IFF_SLAVE; + unsigned int flags = bond_dev->flags & (IFF_SLAVE | IFF_UP); ether_setup(bond_dev); - bond_dev->flags |= IFF_MASTER | slave_flag; + bond_dev->flags |= IFF_MASTER | flags; bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING; } diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 3fffd5da8d3b..ffcad057d065 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -96,7 +96,7 @@ static int ksz8795_change_mtu(struct ksz_device *dev, int frame_size) if (frame_size > KSZ8_LEGAL_PACKET_SIZE) ctrl2 |= SW_LEGAL_PACKET_DISABLE; - else if (frame_size > KSZ8863_NORMAL_PACKET_SIZE) + if (frame_size > KSZ8863_NORMAL_PACKET_SIZE) ctrl1 |= SW_HUGE_PACKET; ret = ksz_rmw8(dev, REG_SW_CTRL_1, SW_HUGE_PACKET, ctrl1); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c23e3b397bcf..651b79ce5d80 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2388,7 +2388,7 @@ static int bnxt_async_event_process(struct bnxt *bp, case ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE: { switch (BNXT_EVENT_PHC_EVENT_TYPE(data1)) { case ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE: - if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) { + if (BNXT_PTP_USE_RTC(bp)) { struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; u64 ns; @@ -7627,7 +7627,7 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp) u8 flags; int rc; - if (bp->hwrm_spec_code < 0x10801) { + if (bp->hwrm_spec_code < 0x10801 || !BNXT_CHIP_P5_THOR(bp)) { rc = -ENODEV; goto no_ptp; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index e7b5e28ee29f..852eb449ccae 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -304,7 +304,7 @@ void bnxt_rdma_aux_device_uninit(struct bnxt *bp) struct auxiliary_device *adev; /* Skip if no auxiliary device init was done. */ - if (!(bp->flags & BNXT_FLAG_ROCE_CAP)) + if (!bp->aux_priv) return; aux_priv = bp->aux_priv; @@ -324,6 +324,7 @@ static void bnxt_aux_dev_release(struct device *dev) bp->edev = NULL; kfree(aux_priv->edev); kfree(aux_priv); + bp->aux_priv = NULL; } static void bnxt_set_edev_info(struct bnxt_en_dev *edev, struct bnxt *bp) @@ -359,19 +360,18 @@ void bnxt_rdma_aux_device_init(struct bnxt *bp) if (!(bp->flags & BNXT_FLAG_ROCE_CAP)) return; - bp->aux_priv = kzalloc(sizeof(*bp->aux_priv), GFP_KERNEL); - if (!bp->aux_priv) + aux_priv = kzalloc(sizeof(*bp->aux_priv), GFP_KERNEL); + if (!aux_priv) goto exit; - bp->aux_priv->id = ida_alloc(&bnxt_aux_dev_ids, GFP_KERNEL); - if (bp->aux_priv->id < 0) { + aux_priv->id = ida_alloc(&bnxt_aux_dev_ids, GFP_KERNEL); + if (aux_priv->id < 0) { netdev_warn(bp->dev, "ida alloc failed for ROCE auxiliary device\n"); - kfree(bp->aux_priv); + kfree(aux_priv); goto exit; } - aux_priv = bp->aux_priv; aux_dev = &aux_priv->aux_dev; aux_dev->id = aux_priv->id; aux_dev->name = "rdma"; @@ -380,10 +380,11 @@ void bnxt_rdma_aux_device_init(struct bnxt *bp) rc = auxiliary_device_init(aux_dev); if (rc) { - ida_free(&bnxt_aux_dev_ids, bp->aux_priv->id); - kfree(bp->aux_priv); + ida_free(&bnxt_aux_dev_ids, aux_priv->id); + kfree(aux_priv); goto exit; } + bp->aux_priv = aux_priv; /* From this point, all cleanup will happen via the .release callback & * any error unwinding will need to include a call to diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index dd9be229819a..d3541159487d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -1135,7 +1135,7 @@ void cxgb4_cleanup_tc_flower(struct adapter *adap) return; if (adap->flower_stats_timer.function) - del_timer_sync(&adap->flower_stats_timer); + timer_shutdown_sync(&adap->flower_stats_timer); cancel_work_sync(&adap->flower_stats_work); rhashtable_destroy(&adap->flower_tbl); adap->tc_flower_initialized = false; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index e1eb1de88bf9..e14d1e45318f 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5288,31 +5288,6 @@ static void e1000_watchdog_task(struct work_struct *work) ew32(TARC(0), tarc0); } - /* disable TSO for pcie and 10/100 speeds, to avoid - * some hardware issues - */ - if (!(adapter->flags & FLAG_TSO_FORCE)) { - switch (adapter->link_speed) { - case SPEED_10: - case SPEED_100: - e_info("10/100 speed: disabling TSO\n"); - netdev->features &= ~NETIF_F_TSO; - netdev->features &= ~NETIF_F_TSO6; - break; - case SPEED_1000: - netdev->features |= NETIF_F_TSO; - netdev->features |= NETIF_F_TSO6; - break; - default: - /* oops */ - break; - } - if (hw->mac.type == e1000_pch_spt) { - netdev->features &= ~NETIF_F_TSO; - netdev->features &= ~NETIF_F_TSO6; - } - } - /* enable transmits in the hardware, need to do this * after setting TARC(0) */ @@ -7526,6 +7501,32 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_RXCSUM | NETIF_F_HW_CSUM); + /* disable TSO for pcie and 10/100 speeds to avoid + * some hardware issues and for i219 to fix transfer + * speed being capped at 60% + */ + if (!(adapter->flags & FLAG_TSO_FORCE)) { + switch (adapter->link_speed) { + case SPEED_10: + case SPEED_100: + e_info("10/100 speed: disabling TSO\n"); + netdev->features &= ~NETIF_F_TSO; + netdev->features &= ~NETIF_F_TSO6; + break; + case SPEED_1000: + netdev->features |= NETIF_F_TSO; + netdev->features |= NETIF_F_TSO6; + break; + default: + /* oops */ + break; + } + if (hw->mac.type == e1000_pch_spt) { + netdev->features &= ~NETIF_F_TSO; + netdev->features &= ~NETIF_F_TSO6; + } + } + /* Set user-changeable features (subset of all device features) */ netdev->hw_features = netdev->features; netdev->hw_features |= NETIF_F_RXFCS; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 228cd502bb48..7c30abd0dfc2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -11059,8 +11059,11 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) pf->hw.aq.asq_last_status)); } /* reinit the misc interrupt */ - if (pf->flags & I40E_FLAG_MSIX_ENABLED) + if (pf->flags & I40E_FLAG_MSIX_ENABLED) { ret = i40e_setup_misc_vector(pf); + if (ret) + goto end_unlock; + } /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out @@ -14133,15 +14136,15 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) vsi->id = ctxt.vsi_number; } - vsi->active_filters = 0; - clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); spin_lock_bh(&vsi->mac_filter_hash_lock); + vsi->active_filters = 0; /* If macvlan filters already exist, force them to get loaded */ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { f->state = I40E_FILTER_NEW; f_count++; } spin_unlock_bh(&vsi->mac_filter_hash_lock); + clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); if (f_count) { vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 445fe30c3d0b..2e7806001fdc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -59,9 +59,6 @@ bool mlx5_eth_supported(struct mlx5_core_dev *dev) if (!IS_ENABLED(CONFIG_MLX5_CORE_EN)) return false; - if (mlx5_core_is_management_pf(dev)) - return false; - if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) return false; @@ -201,9 +198,6 @@ bool mlx5_rdma_supported(struct mlx5_core_dev *dev) if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) return false; - if (mlx5_core_is_management_pf(dev)) - return false; - if (dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index 7c9c4e40c019..d000236ddbac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -75,10 +75,6 @@ int mlx5_ec_init(struct mlx5_core_dev *dev) if (!mlx5_core_is_ecpf(dev)) return 0; - /* Management PF don't have a peer PF */ - if (mlx5_core_is_management_pf(dev)) - return 0; - return mlx5_host_pf_init(dev); } @@ -89,10 +85,6 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev) if (!mlx5_core_is_ecpf(dev)) return; - /* Management PF don't have a peer PF */ - if (mlx5_core_is_management_pf(dev)) - return; - mlx5_host_pf_cleanup(dev); err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 8bdf28762f41..19fed514fc17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1488,7 +1488,7 @@ int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 * void *hca_caps; int err; - if (!mlx5_core_is_ecpf(dev) || mlx5_core_is_management_pf(dev)) { + if (!mlx5_core_is_ecpf(dev)) { *max_sfs = 0; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c index 017d68f1e123..972c571b4158 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c @@ -31,6 +31,8 @@ mlxfw_mfa2_tlv_next(const struct mlxfw_mfa2_file *mfa2_file, if (tlv->type == MLXFW_MFA2_TLV_MULTI_PART) { multi = mlxfw_mfa2_tlv_multi_get(mfa2_file, tlv); + if (!multi) + return NULL; tlv_len = NLA_ALIGN(tlv_len + be16_to_cpu(multi->total_len)); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index 48dbfea0a2a1..7cdf0ce24f28 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -26,7 +26,7 @@ #define MLXSW_PCI_CIR_TIMEOUT_MSECS 1000 #define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 900000 -#define MLXSW_PCI_SW_RESET_WAIT_MSECS 200 +#define MLXSW_PCI_SW_RESET_WAIT_MSECS 400 #define MLXSW_PCI_FW_READY 0xA1844 #define MLXSW_PCI_FW_READY_MASK 0xFFFF #define MLXSW_PCI_FW_READY_MAGIC 0x5E diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 884d8d168862..1eceffa02b55 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -541,7 +541,6 @@ int efx_net_open(struct net_device *net_dev) else efx->state = STATE_NET_UP; - efx_selftest_async_start(efx); return 0; } diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c index cc30524c2fe4..361687de308d 100644 --- a/drivers/net/ethernet/sfc/efx_common.c +++ b/drivers/net/ethernet/sfc/efx_common.c @@ -544,6 +544,8 @@ void efx_start_all(struct efx_nic *efx) /* Start the hardware monitor if there is one */ efx_start_monitor(efx); + efx_selftest_async_start(efx); + /* Link state detection is normally event-driven; we have * to poll now because we could have missed a change */ diff --git a/drivers/net/hamradio/Kconfig b/drivers/net/hamradio/Kconfig index a9c44f08199d..a94c7bd5db2e 100644 --- a/drivers/net/hamradio/Kconfig +++ b/drivers/net/hamradio/Kconfig @@ -47,7 +47,7 @@ config BPQETHER config SCC tristate "Z8530 SCC driver" - depends on ISA && AX25 && ISA_DMA_API + depends on ISA && AX25 help These cards are used to connect your Linux box to an amateur radio in order to communicate with other computers. If you want to use diff --git a/drivers/net/veth.c b/drivers/net/veth.c index e1b38fbf1dd9..4b3c6647edc6 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1262,11 +1262,12 @@ static void veth_set_xdp_features(struct net_device *dev) peer = rtnl_dereference(priv->peer); if (peer && peer->real_num_tx_queues <= dev->real_num_rx_queues) { + struct veth_priv *priv_peer = netdev_priv(peer); xdp_features_t val = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_RX_SG; - if (priv->_xdp_prog || veth_gro_requested(dev)) + if (priv_peer->_xdp_prog || veth_gro_requested(peer)) val |= NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_NDO_XMIT_SG; xdp_set_features_flag(dev, val); @@ -1504,19 +1505,23 @@ static int veth_set_features(struct net_device *dev, { netdev_features_t changed = features ^ dev->features; struct veth_priv *priv = netdev_priv(dev); + struct net_device *peer; int err; if (!(changed & NETIF_F_GRO) || !(dev->flags & IFF_UP) || priv->_xdp_prog) return 0; + peer = rtnl_dereference(priv->peer); if (features & NETIF_F_GRO) { err = veth_napi_enable(dev); if (err) return err; - xdp_features_set_redirect_target(dev, true); + if (peer) + xdp_features_set_redirect_target(peer, true); } else { - xdp_features_clear_redirect_target(dev); + if (peer) + xdp_features_clear_redirect_target(peer); veth_napi_del(dev); } return 0; @@ -1598,13 +1603,13 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog, peer->max_mtu = max_mtu; } - xdp_features_set_redirect_target(dev, true); + xdp_features_set_redirect_target(peer, true); } if (old_prog) { if (!prog) { - if (!veth_gro_requested(dev)) - xdp_features_clear_redirect_target(dev); + if (peer && !veth_gro_requested(dev)) + xdp_features_clear_redirect_target(peer); if (dev->flags & IFF_UP) veth_disable_xdp(dev); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 2396c28c0122..ea1bd4bb326d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -814,8 +814,13 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, int page_off, unsigned int *len) { - struct page *page = alloc_page(GFP_ATOMIC); + int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + struct page *page; + + if (page_off + *len + tailroom > PAGE_SIZE) + return NULL; + page = alloc_page(GFP_ATOMIC); if (!page) return NULL; @@ -823,7 +828,6 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, page_off += *len; while (--*num_buf) { - int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); unsigned int buflen; void *buf; int off; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index da488cbb0542..f2b76ee866a4 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1504,7 +1504,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, goto rcd_done; } - if (rxDataRingUsed) { + if (rxDataRingUsed && adapter->rxdataring_enabled) { size_t sz; BUG_ON(rcd->len > rq->data_ring.desc_size); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f33389b42209..7e225e41d55b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1211,11 +1211,6 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_VF; } -static inline bool mlx5_core_is_management_pf(const struct mlx5_core_dev *dev) -{ - return MLX5_CAP_GEN(dev, num_ports) == 1 && !MLX5_CAP_GEN(dev, native_port_num); -} - static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ff7ad331fb82..dbcaac8b6966 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -294,6 +294,7 @@ struct nf_bridge_info { u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; + u8 sabotage_in_done:1; __u16 frag_max_size; struct net_device *physindev; @@ -4712,7 +4713,7 @@ static inline void nf_reset_ct(struct sk_buff *skb) static inline void nf_reset_trace(struct sk_buff *skb) { -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } @@ -4732,7 +4733,7 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 9430128aae99..1b8e305bb54a 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1085,6 +1085,10 @@ struct nft_chain { }; int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); +int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem); +int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d517d13878cf..767e8930b0bd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2967,6 +2967,21 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, } } else if (opcode == BPF_EXIT) { return -ENOTSUPP; + } else if (BPF_SRC(insn->code) == BPF_X) { + if (!(*reg_mask & (dreg | sreg))) + return 0; + /* dreg <cond> sreg + * Both dreg and sreg need precision before + * this insn. If only sreg was marked precise + * before it would be equally necessary to + * propagate it to dreg. + */ + *reg_mask |= (sreg | dreg); + /* else dreg <cond> K + * Only dreg still needs precision before + * this insn, so for the K-based conditional + * there is nothing new to be marked. + */ } } else if (class == BPF_LD) { if (!(*reg_mask & dreg)) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 638a4d5359db..4bc6761517bb 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -868,12 +868,17 @@ static unsigned int ip_sabotage_in(void *priv, { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); - if (nf_bridge && !nf_bridge->in_prerouting && - !netif_is_l3_master(skb->dev) && - !netif_is_l3_slave(skb->dev)) { - nf_bridge_info_free(skb); - state->okfn(state->net, state->sk, skb); - return NF_STOLEN; + if (nf_bridge) { + if (nf_bridge->sabotage_in_done) + return NF_ACCEPT; + + if (!nf_bridge->in_prerouting && + !netif_is_l3_master(skb->dev) && + !netif_is_l3_slave(skb->dev)) { + nf_bridge->sabotage_in_done = 1; + state->okfn(state->net, state->sk, skb); + return NF_STOLEN; + } } return NF_ACCEPT; diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index de18e9c1d7a7..ba95c4d74a60 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -148,6 +148,17 @@ br_switchdev_fdb_notify(struct net_bridge *br, if (test_bit(BR_FDB_LOCKED, &fdb->flags)) return; + /* Entries with these flags were created using ndm_state == NUD_REACHABLE, + * ndm_flags == NTF_MASTER( | NTF_STICKY), ext_flags == 0 by something + * equivalent to 'bridge fdb add ... master dynamic (sticky)'. + * Drivers don't know how to deal with these, so don't notify them to + * avoid confusing them. + */ + if (test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags) && + !test_bit(BR_FDB_STATIC, &fdb->flags) && + !test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) + return; + br_switchdev_fdb_populate(br, &item, fdb, NULL); switch (type) { diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c index 488aec9e1a74..d1876f192225 100644 --- a/net/ipv6/rpl.c +++ b/net/ipv6/rpl.c @@ -32,7 +32,8 @@ static void *ipv6_rpl_segdata_pos(const struct ipv6_rpl_sr_hdr *hdr, int i) size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, unsigned char cmpre) { - return (n * IPV6_PFXTAIL_LEN(cmpri)) + IPV6_PFXTAIL_LEN(cmpre); + return sizeof(struct ipv6_rpl_sr_hdr) + (n * IPV6_PFXTAIL_LEN(cmpri)) + + IPV6_PFXTAIL_LEN(cmpre); } void ipv6_rpl_srh_decompress(struct ipv6_rpl_sr_hdr *outhdr, diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 06c5872e3b00..b998e9df53ce 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2315,7 +2315,26 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, unsigned int flags) { struct mptcp_sock *msk = mptcp_sk(sk); - bool need_push, dispose_it; + bool dispose_it, need_push = false; + + /* If the first subflow moved to a close state before accept, e.g. due + * to an incoming reset, mptcp either: + * - if either the subflow or the msk are dead, destroy the context + * (the subflow socket is deleted by inet_child_forget) and the msk + * - otherwise do nothing at the moment and take action at accept and/or + * listener shutdown - user-space must be able to accept() the closed + * socket. + */ + if (msk->in_accept_queue && msk->first == ssk) { + if (!sock_flag(sk, SOCK_DEAD) && !sock_flag(ssk, SOCK_DEAD)) + return; + + /* ensure later check in mptcp_worker() will dispose the msk */ + sock_set_flag(sk, SOCK_DEAD); + lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); + mptcp_subflow_drop_ctx(ssk); + goto out_release; + } dispose_it = !msk->subflow || ssk != msk->subflow->sk; if (dispose_it) @@ -2351,28 +2370,22 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (!inet_csk(ssk)->icsk_ulp_ops) { WARN_ON_ONCE(!sock_flag(ssk, SOCK_DEAD)); kfree_rcu(subflow, rcu); - } else if (msk->in_accept_queue && msk->first == ssk) { - /* if the first subflow moved to a close state, e.g. due to - * incoming reset and we reach here before inet_child_forget() - * the TCP stack could later try to close it via - * inet_csk_listen_stop(), or deliver it to the user space via - * accept(). - * We can't delete the subflow - or risk a double free - nor let - * the msk survive - or will be leaked in the non accept scenario: - * fallback and let TCP cope with the subflow cleanup. - */ - WARN_ON_ONCE(sock_flag(ssk, SOCK_DEAD)); - mptcp_subflow_drop_ctx(ssk); } else { /* otherwise tcp will dispose of the ssk and subflow ctx */ - if (ssk->sk_state == TCP_LISTEN) + if (ssk->sk_state == TCP_LISTEN) { + tcp_set_state(ssk, TCP_CLOSE); + mptcp_subflow_queue_clean(sk, ssk); + inet_csk_listen_stop(ssk); mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); + } __tcp_close(ssk, 0); /* close acquired an extra ref */ __sock_put(ssk); } + +out_release: release_sock(ssk); sock_put(ssk); @@ -2427,21 +2440,14 @@ static void __mptcp_close_subflow(struct sock *sk) mptcp_close_ssk(sk, ssk, subflow); } - /* if the MPC subflow has been closed before the msk is accepted, - * msk will never be accept-ed, close it now - */ - if (!msk->first && msk->in_accept_queue) { - sock_set_flag(sk, SOCK_DEAD); - inet_sk_state_store(sk, TCP_CLOSE); - } } -static bool mptcp_check_close_timeout(const struct sock *sk) +static bool mptcp_should_close(const struct sock *sk) { s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp; struct mptcp_subflow_context *subflow; - if (delta >= TCP_TIMEWAIT_LEN) + if (delta >= TCP_TIMEWAIT_LEN || mptcp_sk(sk)->in_accept_queue) return true; /* if all subflows are in closed status don't bother with additional @@ -2649,7 +2655,7 @@ static void mptcp_worker(struct work_struct *work) * even if it is orphaned and in FIN_WAIT2 state */ if (sock_flag(sk, SOCK_DEAD)) { - if (mptcp_check_close_timeout(sk)) { + if (mptcp_should_close(sk)) { inet_sk_state_store(sk, TCP_CLOSE); mptcp_do_fastclose(sk); } @@ -2895,6 +2901,14 @@ static void __mptcp_destroy_sock(struct sock *sk) sock_put(sk); } +void __mptcp_unaccepted_force_close(struct sock *sk) +{ + sock_set_flag(sk, SOCK_DEAD); + inet_sk_state_store(sk, TCP_CLOSE); + mptcp_do_fastclose(sk); + __mptcp_destroy_sock(sk); +} + static __poll_t mptcp_check_readable(struct mptcp_sock *msk) { /* Concurrent splices from sk_receive_queue into receive_queue will @@ -3733,6 +3747,18 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (!ssk->sk_socket) mptcp_sock_graft(ssk, newsock); } + + /* Do late cleanup for the first subflow as necessary. Also + * deal with bad peers not doing a complete shutdown. + */ + if (msk->first && + unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) { + __mptcp_close_ssk(newsk, msk->first, + mptcp_subflow_ctx(msk->first), 0); + if (unlikely(list_empty(&msk->conn_list))) + inet_sk_state_store(newsk, TCP_CLOSE); + } + release_sock(newsk); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 339a6f072989..d6469b6ab38e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -629,10 +629,12 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow); void __mptcp_subflow_send_ack(struct sock *ssk); void mptcp_subflow_reset(struct sock *ssk); +void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk); void mptcp_sock_graft(struct sock *sk, struct socket *parent); struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); bool __mptcp_close(struct sock *sk, long timeout); void mptcp_cancel_work(struct sock *sk); +void __mptcp_unaccepted_force_close(struct sock *sk); void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk); bool mptcp_addresses_equal(const struct mptcp_addr_info *a, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index d34588850545..281c1cc8dc8d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -723,9 +723,12 @@ void mptcp_subflow_drop_ctx(struct sock *ssk) if (!ctx) return; - subflow_ulp_fallback(ssk, ctx); - if (ctx->conn) - sock_put(ctx->conn); + list_del(&mptcp_subflow_ctx(ssk)->node); + if (inet_csk(ssk)->icsk_ulp_ops) { + subflow_ulp_fallback(ssk, ctx); + if (ctx->conn) + sock_put(ctx->conn); + } kfree_rcu(ctx, rcu); } @@ -1819,6 +1822,77 @@ static void subflow_state_change(struct sock *sk) } } +void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) +{ + struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; + struct mptcp_sock *msk, *next, *head = NULL; + struct request_sock *req; + struct sock *sk; + + /* build a list of all unaccepted mptcp sockets */ + spin_lock_bh(&queue->rskq_lock); + for (req = queue->rskq_accept_head; req; req = req->dl_next) { + struct mptcp_subflow_context *subflow; + struct sock *ssk = req->sk; + + if (!sk_is_mptcp(ssk)) + continue; + + subflow = mptcp_subflow_ctx(ssk); + if (!subflow || !subflow->conn) + continue; + + /* skip if already in list */ + sk = subflow->conn; + msk = mptcp_sk(sk); + if (msk->dl_next || msk == head) + continue; + + sock_hold(sk); + msk->dl_next = head; + head = msk; + } + spin_unlock_bh(&queue->rskq_lock); + if (!head) + return; + + /* can't acquire the msk socket lock under the subflow one, + * or will cause ABBA deadlock + */ + release_sock(listener_ssk); + + for (msk = head; msk; msk = next) { + sk = (struct sock *)msk; + + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); + next = msk->dl_next; + msk->dl_next = NULL; + + __mptcp_unaccepted_force_close(sk); + release_sock(sk); + + /* lockdep will report a false positive ABBA deadlock + * between cancel_work_sync and the listener socket. + * The involved locks belong to different sockets WRT + * the existing AB chain. + * Using a per socket key is problematic as key + * deregistration requires process context and must be + * performed at socket disposal time, in atomic + * context. + * Just tell lockdep to consider the listener socket + * released here. + */ + mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_); + mptcp_cancel_work(sk); + mutex_acquire(&listener_sk->sk_lock.dep_map, 0, 0, _RET_IP_); + + sock_put(sk); + } + + /* we are still under the listener msk socket lock */ + lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); +} + static int subflow_ulp_init(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 6004d4b24451..e48ab8dfb541 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3447,6 +3447,64 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) return 0; } +int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; + const struct nft_data *data; + int err; + + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && + *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) + return 0; + + data = nft_set_ext_data(ext); + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + pctx->level++; + err = nft_chain_validate(ctx, data->verdict.chain); + if (err < 0) + return err; + pctx->level--; + break; + default: + break; + } + + return 0; +} + +struct nft_set_elem_catchall { + struct list_head list; + struct rcu_head rcu; + void *elem; +}; + +int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) +{ + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_elem_catchall *catchall; + struct nft_set_elem elem; + struct nft_set_ext *ext; + int ret = 0; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask)) + continue; + + elem.priv = catchall->elem; + ret = nft_setelem_validate(ctx, set, NULL, &elem); + if (ret < 0) + return ret; + } + + return ret; +} + static struct nft_rule *nft_rule_lookup_byid(const struct net *net, const struct nft_chain *chain, const struct nlattr *nla); @@ -4759,12 +4817,6 @@ err_set_name: return err; } -struct nft_set_elem_catchall { - struct list_head list; - struct rcu_head rcu; - void *elem; -}; - static void nft_set_catchall_destroy(const struct nft_ctx *ctx, struct nft_set *set) { @@ -6056,7 +6108,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) + if (((flags & NFT_SET_ELEM_CATCHALL) && nla[NFTA_SET_ELEM_KEY]) || + (!(flags & NFT_SET_ELEM_CATCHALL) && !nla[NFTA_SET_ELEM_KEY])) return -EINVAL; if (flags != 0) { @@ -7052,7 +7105,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, } if (nla[NFTA_OBJ_USERDATA]) { - obj->udata = nla_memdup(nla[NFTA_OBJ_USERDATA], GFP_KERNEL); + obj->udata = nla_memdup(nla[NFTA_OBJ_USERDATA], GFP_KERNEL_ACCOUNT); if (obj->udata == NULL) goto err_userdata; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index cae5a6724163..cecf8ab90e58 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -199,37 +199,6 @@ nla_put_failure: return -1; } -static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, - struct nft_set *set, - const struct nft_set_iter *iter, - struct nft_set_elem *elem) -{ - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); - struct nft_ctx *pctx = (struct nft_ctx *)ctx; - const struct nft_data *data; - int err; - - if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && - *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) - return 0; - - data = nft_set_ext_data(ext); - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - pctx->level++; - err = nft_chain_validate(ctx, data->verdict.chain); - if (err < 0) - return err; - pctx->level--; - break; - default: - break; - } - - return 0; -} - static int nft_lookup_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **d) @@ -245,9 +214,12 @@ static int nft_lookup_validate(const struct nft_ctx *ctx, iter.skip = 0; iter.count = 0; iter.err = 0; - iter.fn = nft_lookup_validate_setelem; + iter.fn = nft_setelem_validate; priv->set->ops->walk(ctx, priv->set, &iter); + if (!iter.err) + iter.err = nft_set_catchall_validate(ctx, priv->set); + if (iter.err < 0) return iter.err; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2a6b6be0811b..35785a36c802 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3235,6 +3235,9 @@ int tcf_exts_init_ex(struct tcf_exts *exts, struct net *net, int action, err_miss_alloc: tcf_exts_destroy(exts); +#ifdef CONFIG_NET_CLS_ACT + exts->actions = NULL; +#endif return err; } EXPORT_SYMBOL(tcf_exts_init_ex); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index cf5ebe43b3b4..02098a02943e 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -421,15 +421,16 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } else weight = 1; - if (tb[TCA_QFQ_LMAX]) { + if (tb[TCA_QFQ_LMAX]) lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { - pr_notice("qfq: invalid max length %u\n", lmax); - return -EINVAL; - } - } else + else lmax = psched_mtu(qdisc_dev(sch)); + if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { + pr_notice("qfq: invalid max length %u\n", lmax); + return -EINVAL; + } + inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; |