diff options
78 files changed, 459 insertions, 204 deletions
diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst index 8ebe46b1af39..5dfcc4592b23 100644 --- a/Documentation/core-api/printk-formats.rst +++ b/Documentation/core-api/printk-formats.rst @@ -112,6 +112,20 @@ used when printing stack backtraces. The specifier takes into consideration the effect of compiler optimisations which may occur when tail-calls are used and marked with the noreturn GCC attribute. +Probed Pointers from BPF / tracing +---------------------------------- + +:: + + %pks kernel string + %pus user string + +The ``k`` and ``u`` specifiers are used for printing prior probed memory from +either kernel memory (k) or user memory (u). The subsequent ``s`` specifier +results in printing a string. For direct use in regular vsnprintf() the (k) +and (u) annotation is ignored, however, when used out of BPF's bpf_trace_printk(), +for example, it reads the memory it is pointing to without faulting. + Kernel Pointers --------------- diff --git a/MAINTAINERS b/MAINTAINERS index 091ec22c1a23..ecc0749810b0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11710,8 +11710,9 @@ F: net/core/drop_monitor.c NETWORKING DRIVERS M: "David S. Miller" <davem@davemloft.net> +M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org -S: Odd Fixes +S: Maintained W: http://www.linuxfoundation.org/en/Net Q: http://patchwork.ozlabs.org/project/netdev/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git @@ -14634,6 +14635,7 @@ F: drivers/iommu/s390-iommu.c S390 IUCV NETWORK LAYER M: Julian Wiedmann <jwi@linux.ibm.com> +M: Karsten Graul <kgraul@linux.ibm.com> M: Ursula Braun <ubraun@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported @@ -14644,6 +14646,7 @@ F: net/iucv/ S390 NETWORK DRIVERS M: Julian Wiedmann <jwi@linux.ibm.com> +M: Karsten Graul <kgraul@linux.ibm.com> M: Ursula Braun <ubraun@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 66a04f6f4775..c77c93c485a0 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -12,6 +12,7 @@ config ARM select ARCH_HAS_KEEPINITRD select ARCH_HAS_KCOV select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_SPECIAL if ARM_LPAE select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_SETUP_DMA_OPS diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig index 11e2211f9007..84a3b055f253 100644 --- a/arch/arm/configs/keystone_defconfig +++ b/arch/arm/configs/keystone_defconfig @@ -147,6 +147,7 @@ CONFIG_I2C_DAVINCI=y CONFIG_SPI=y CONFIG_SPI_DAVINCI=y CONFIG_SPI_SPIDEV=y +CONFIG_PTP_1588_CLOCK=y CONFIG_PINCTRL_SINGLE=y CONFIG_GPIOLIB=y CONFIG_GPIO_SYSFS=y diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 3cc3ca5fa027..8b83d4a5d309 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -274,6 +274,7 @@ CONFIG_SPI_TI_QSPI=m CONFIG_HSI=m CONFIG_OMAP_SSI=m CONFIG_SSI_PROTOCOL=m +CONFIG_PTP_1588_CLOCK=y CONFIG_PINCTRL_SINGLE=y CONFIG_DEBUG_GPIO=y CONFIG_GPIO_SYSFS=y diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 40fb05d96c60..5d513f461957 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -20,6 +20,7 @@ config ARM64 select ARCH_HAS_KCOV select ARCH_HAS_KEEPINITRD select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_DEVMAP select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SETUP_DMA_OPS diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1197b5596d5a..2d3f963fd6f1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -68,6 +68,7 @@ config X86 select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_PTE_DEVMAP if X86_64 select ARCH_HAS_PTE_SPECIAL diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index cc0703c3d57f..efd1a1d1f35e 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -136,25 +136,21 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) oiph = skb_network_header(skb); skb_reset_network_header(skb); - if (family == AF_INET) + if (!IS_ENABLED(CONFIG_IPV6) || family == AF_INET) err = IP_ECN_decapsulate(oiph, skb); -#if IS_ENABLED(CONFIG_IPV6) else err = IP6_ECN_decapsulate(oiph, skb); -#endif if (unlikely(err)) { if (log_ecn_error) { - if (family == AF_INET) + if (!IS_ENABLED(CONFIG_IPV6) || family == AF_INET) net_info_ratelimited("non-ECT from %pI4 " "with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); -#if IS_ENABLED(CONFIG_IPV6) else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); -#endif } if (err > 1) { ++bareudp->dev->stats.rx_frame_errors; @@ -350,7 +346,6 @@ free_dst: return err; } -#if IS_ENABLED(CONFIG_IPV6) static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct bareudp_dev *bareudp, const struct ip_tunnel_info *info) @@ -411,7 +406,6 @@ free_dst: dst_release(dst); return err; } -#endif static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -435,11 +429,9 @@ static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev) } rcu_read_lock(); -#if IS_ENABLED(CONFIG_IPV6) - if (info->mode & IP_TUNNEL_INFO_IPV6) + if (IS_ENABLED(CONFIG_IPV6) && info->mode & IP_TUNNEL_INFO_IPV6) err = bareudp6_xmit_skb(skb, dev, bareudp, info); else -#endif err = bareudp_xmit_skb(skb, dev, bareudp, info); rcu_read_unlock(); @@ -467,7 +459,7 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, use_cache = ip_tunnel_dst_cache_usable(skb, info); - if (ip_tunnel_info_af(info) == AF_INET) { + if (!IS_ENABLED(CONFIG_IPV6) || ip_tunnel_info_af(info) == AF_INET) { struct rtable *rt; __be32 saddr; @@ -478,7 +470,6 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, ip_rt_put(rt); info->key.u.ipv4.src = saddr; -#if IS_ENABLED(CONFIG_IPV6) } else if (ip_tunnel_info_af(info) == AF_INET6) { struct dst_entry *dst; struct in6_addr saddr; @@ -492,7 +483,6 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, dst_release(dst); info->key.u.ipv6.src = saddr; -#endif } else { return -EINVAL; } diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index fdcb70b9f0e4..400207c5c7de 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -360,6 +360,7 @@ static void __exit dsa_loop_exit(void) } module_exit(dsa_loop_exit); +MODULE_SOFTDEP("pre: dsa_loop_bdinfo"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Fainelli"); MODULE_DESCRIPTION("DSA loopback driver"); diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 53055ce5dfd6..2a69c0d06f3c 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -69,6 +69,7 @@ config BCMGENET select BCM7XXX_PHY select MDIO_BCM_UNIMAC select DIMLIB + select BROADCOM_PHY if ARCH_BCM2835 help This driver supports the built-in Ethernet MACs found in the Broadcom BCM7xxx Set Top Box family chipset. diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index 2bd7ace0a953..bfc6bfe94d0a 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -77,6 +77,7 @@ config UCC_GETH depends on QUICC_ENGINE && PPC32 select FSL_PQ_MDIO select PHYLIB + select FIXED_PHY ---help--- This driver supports the Gigabit Ethernet mode of the QUICC Engine, which is available on some Freescale SOCs. @@ -90,6 +91,7 @@ config GIANFAR depends on HAS_DMA select FSL_PQ_MDIO select PHYLIB + select FIXED_PHY select CRC32 ---help--- This driver supports the Gigabit TSEC on the MPC83xx, MPC85xx, diff --git a/drivers/net/ethernet/freescale/dpaa/Kconfig b/drivers/net/ethernet/freescale/dpaa/Kconfig index 3b325733a4f8..0a54c7e0e4ae 100644 --- a/drivers/net/ethernet/freescale/dpaa/Kconfig +++ b/drivers/net/ethernet/freescale/dpaa/Kconfig @@ -3,6 +3,7 @@ menuconfig FSL_DPAA_ETH tristate "DPAA Ethernet" depends on FSL_DPAA && FSL_FMAN select PHYLIB + select FIXED_PHY select FSL_FMAN_MAC ---help--- Data Path Acceleration Architecture Ethernet driver, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index b6c46639aa4c..d97c320a2dc0 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -86,7 +86,7 @@ static void free_rx_fd(struct dpaa2_eth_priv *priv, for (i = 1; i < DPAA2_ETH_MAX_SG_ENTRIES; i++) { addr = dpaa2_sg_get_addr(&sgt[i]); sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr); - dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); free_pages((unsigned long)sg_vaddr, 0); @@ -144,7 +144,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv, /* Get the address and length from the S/G entry */ sg_addr = dpaa2_sg_get_addr(sge); sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, sg_addr); - dma_unmap_page(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, sg_addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); sg_length = dpaa2_sg_get_len(sge); @@ -185,7 +185,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv, (page_address(page) - page_address(head_page)); skb_add_rx_frag(skb, i - 1, head_page, page_offset, - sg_length, DPAA2_ETH_RX_BUF_SIZE); + sg_length, priv->rx_buf_size); } if (dpaa2_sg_is_final(sge)) @@ -211,7 +211,7 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count) for (i = 0; i < count; i++) { vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]); - dma_unmap_page(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, buf_array[i], priv->rx_buf_size, DMA_BIDIRECTIONAL); free_pages((unsigned long)vaddr, 0); } @@ -335,7 +335,7 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv, break; case XDP_REDIRECT: dma_unmap_page(priv->net_dev->dev.parent, addr, - DPAA2_ETH_RX_BUF_SIZE, DMA_BIDIRECTIONAL); + priv->rx_buf_size, DMA_BIDIRECTIONAL); ch->buf_count--; xdp.data_hard_start = vaddr; err = xdp_do_redirect(priv->net_dev, &xdp, xdp_prog); @@ -374,7 +374,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, trace_dpaa2_rx_fd(priv->net_dev, fd); vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr); - dma_sync_single_for_cpu(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + dma_sync_single_for_cpu(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); fas = dpaa2_get_fas(vaddr, false); @@ -393,13 +393,13 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, return; } - dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); skb = build_linear_skb(ch, fd, vaddr); } else if (fd_format == dpaa2_fd_sg) { WARN_ON(priv->xdp_prog); - dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); skb = build_frag_skb(priv, ch, buf_data); free_pages((unsigned long)vaddr, 0); @@ -974,7 +974,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv, if (!page) goto err_alloc; - addr = dma_map_page(dev, page, 0, DPAA2_ETH_RX_BUF_SIZE, + addr = dma_map_page(dev, page, 0, priv->rx_buf_size, DMA_BIDIRECTIONAL); if (unlikely(dma_mapping_error(dev, addr))) goto err_map; @@ -984,7 +984,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv, /* tracing point */ trace_dpaa2_eth_buf_seed(priv->net_dev, page, DPAA2_ETH_RX_BUF_RAW_SIZE, - addr, DPAA2_ETH_RX_BUF_SIZE, + addr, priv->rx_buf_size, bpid); } @@ -1720,7 +1720,7 @@ static bool xdp_mtu_valid(struct dpaa2_eth_priv *priv, int mtu) int mfl, linear_mfl; mfl = DPAA2_ETH_L2_MAX_FRM(mtu); - linear_mfl = DPAA2_ETH_RX_BUF_SIZE - DPAA2_ETH_RX_HWA_SIZE - + linear_mfl = priv->rx_buf_size - DPAA2_ETH_RX_HWA_SIZE - dpaa2_eth_rx_head_room(priv) - XDP_PACKET_HEADROOM; if (mfl > linear_mfl) { @@ -2462,6 +2462,11 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv) else rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN; + /* We need to ensure that the buffer size seen by WRIOP is a multiple + * of 64 or 256 bytes depending on the WRIOP version. + */ + priv->rx_buf_size = ALIGN_DOWN(DPAA2_ETH_RX_BUF_SIZE, rx_buf_align); + /* tx buffer */ buf_layout.private_data_size = DPAA2_ETH_SWA_SIZE; buf_layout.pass_timestamp = true; @@ -3126,7 +3131,7 @@ static int bind_dpni(struct dpaa2_eth_priv *priv) pools_params.num_dpbp = 1; pools_params.pools[0].dpbp_id = priv->dpbp_dev->obj_desc.id; pools_params.pools[0].backup_pool = 0; - pools_params.pools[0].buffer_size = DPAA2_ETH_RX_BUF_SIZE; + pools_params.pools[0].buffer_size = priv->rx_buf_size; err = dpni_set_pools(priv->mc_io, 0, priv->mc_token, &pools_params); if (err) { dev_err(dev, "dpni_set_pools() failed\n"); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index 7635db3ef903..13242bf5b427 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -382,6 +382,7 @@ struct dpaa2_eth_priv { u16 tx_data_offset; struct fsl_mc_device *dpbp_dev; + u16 rx_buf_size; u16 bpid; struct iommu_domain *iommu_domain; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 94347c695233..b7141fdc279e 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -635,7 +635,7 @@ static int num_rules(struct dpaa2_eth_priv *priv) static int update_cls_rule(struct net_device *net_dev, struct ethtool_rx_flow_spec *new_fs, - int location) + unsigned int location) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); struct dpaa2_eth_cls_rule *rule; diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 3892a2062404..2fff43509098 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -64,7 +64,7 @@ config HNS_MDIO the PHY config HNS - tristate "Hisilicon Network Subsystem Support (Framework)" + tristate ---help--- This selects the framework support for Hisilicon Network Subsystem. It is needed by any driver which provides HNS acceleration engine or make diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c index 8995e32dd1c0..992908e6eebf 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c @@ -45,6 +45,8 @@ #define MGMT_MSG_TIMEOUT 5000 +#define SET_FUNC_PORT_MGMT_TIMEOUT 25000 + #define mgmt_to_pfhwdev(pf_mgmt) \ container_of(pf_mgmt, struct hinic_pfhwdev, pf_to_mgmt) @@ -238,12 +240,13 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt, u8 *buf_in, u16 in_size, u8 *buf_out, u16 *out_size, enum mgmt_direction_type direction, - u16 resp_msg_id) + u16 resp_msg_id, u32 timeout) { struct hinic_hwif *hwif = pf_to_mgmt->hwif; struct pci_dev *pdev = hwif->pdev; struct hinic_recv_msg *recv_msg; struct completion *recv_done; + unsigned long timeo; u16 msg_id; int err; @@ -267,8 +270,9 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt, goto unlock_sync_msg; } - if (!wait_for_completion_timeout(recv_done, - msecs_to_jiffies(MGMT_MSG_TIMEOUT))) { + timeo = msecs_to_jiffies(timeout ? timeout : MGMT_MSG_TIMEOUT); + + if (!wait_for_completion_timeout(recv_done, timeo)) { dev_err(&pdev->dev, "MGMT timeout, MSG id = %d\n", msg_id); err = -ETIMEDOUT; goto unlock_sync_msg; @@ -342,6 +346,7 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt, { struct hinic_hwif *hwif = pf_to_mgmt->hwif; struct pci_dev *pdev = hwif->pdev; + u32 timeout = 0; if (sync != HINIC_MGMT_MSG_SYNC) { dev_err(&pdev->dev, "Invalid MGMT msg type\n"); @@ -353,9 +358,12 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt, return -EINVAL; } + if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE) + timeout = SET_FUNC_PORT_MGMT_TIMEOUT; + return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size, buf_out, out_size, MGMT_DIRECT_SEND, - MSG_NOT_RESP); + MSG_NOT_RESP, timeout); } /** diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 13560975c103..63b92f6cc856 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -483,7 +483,6 @@ static int hinic_close(struct net_device *netdev) { struct hinic_dev *nic_dev = netdev_priv(netdev); unsigned int flags; - int err; down(&nic_dev->mgmt_lock); @@ -497,20 +496,9 @@ static int hinic_close(struct net_device *netdev) up(&nic_dev->mgmt_lock); - err = hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE); - if (err) { - netif_err(nic_dev, drv, netdev, - "Failed to set func port state\n"); - nic_dev->flags |= (flags & HINIC_INTF_UP); - return err; - } + hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE); - err = hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE); - if (err) { - netif_err(nic_dev, drv, netdev, "Failed to set port state\n"); - nic_dev->flags |= (flags & HINIC_INTF_UP); - return err; - } + hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE); if (nic_dev->flags & HINIC_RSS_ENABLE) { hinic_rss_deinit(nic_dev); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 187c633a7af5..f4227517dc8e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -497,13 +497,17 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE, GFP_KERNEL); - if (!hw->irq_name) + if (!hw->irq_name) { + err = -ENOMEM; goto err_free_netdev; + } hw->affinity_mask = devm_kcalloc(&hw->pdev->dev, num_vec, sizeof(cpumask_var_t), GFP_KERNEL); - if (!hw->affinity_mask) + if (!hw->affinity_mask) { + err = -ENOMEM; goto err_free_netdev; + } err = pci_alloc_irq_vectors(hw->pdev, num_vec, num_vec, PCI_IRQ_MSIX); if (err < 0) { diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c index 39925e4bf2ec..b25a13da900a 100644 --- a/drivers/net/ethernet/microchip/encx24j600.c +++ b/drivers/net/ethernet/microchip/encx24j600.c @@ -1070,7 +1070,7 @@ static int encx24j600_spi_probe(struct spi_device *spi) if (unlikely(ret)) { netif_err(priv, probe, ndev, "Error %d initializing card encx24j600 card\n", ret); - goto out_free; + goto out_stop; } eidled = encx24j600_read_reg(priv, EIDLED); @@ -1088,6 +1088,8 @@ static int encx24j600_spi_probe(struct spi_device *spi) out_unregister: unregister_netdev(priv->ndev); +out_stop: + kthread_stop(priv->kworker_task); out_free: free_netdev(ndev); @@ -1100,6 +1102,7 @@ static int encx24j600_spi_remove(struct spi_device *spi) struct encx24j600_priv *priv = dev_get_drvdata(&spi->dev); unregister_netdev(priv->ndev); + kthread_stop(priv->kworker_task); free_netdev(priv->ndev); diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c index 354efffac0f9..bdbf0726145e 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/main.c +++ b/drivers/net/ethernet/netronome/nfp/abm/main.c @@ -333,8 +333,10 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id) goto err_free_alink; alink->prio_map = kzalloc(abm->prio_map_len, GFP_KERNEL); - if (!alink->prio_map) + if (!alink->prio_map) { + err = -ENOMEM; goto err_free_alink; + } /* This is a multi-host app, make sure MAC/PHY is up, but don't * make the MAC/PHY state follow the state of any of the ports. diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index d5293bfded29..f8a9c1bcffc9 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2118,6 +2118,7 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif) dev_info(ionic->dev, "FW Up: restarting LIFs\n"); ionic_init_devinfo(ionic); + ionic_port_init(ionic); err = ionic_qcqs_alloc(lif); if (err) goto err_out; @@ -2348,7 +2349,17 @@ static int ionic_station_set(struct ionic_lif *lif) if (is_zero_ether_addr(ctx.comp.lif_getattr.mac)) return 0; - if (!ether_addr_equal(ctx.comp.lif_getattr.mac, netdev->dev_addr)) { + if (!is_zero_ether_addr(netdev->dev_addr)) { + /* If the netdev mac is non-zero and doesn't match the default + * device address, it was set by something earlier and we're + * likely here again after a fw-upgrade reset. We need to be + * sure the netdev mac is in our filter list. + */ + if (!ether_addr_equal(ctx.comp.lif_getattr.mac, + netdev->dev_addr)) + ionic_lif_addr(lif, netdev->dev_addr, true); + } else { + /* Update the netdev mac with the device's mac */ memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len); addr.sa_family = AF_INET; err = eth_prepare_mac_addr_change(netdev, &addr); @@ -2358,12 +2369,6 @@ static int ionic_station_set(struct ionic_lif *lif) return 0; } - if (!is_zero_ether_addr(netdev->dev_addr)) { - netdev_dbg(lif->netdev, "deleting station MAC addr %pM\n", - netdev->dev_addr); - ionic_lif_addr(lif, netdev->dev_addr, false); - } - eth_commit_mac_addr_change(netdev, &addr); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index 588c62e9add7..3344bc1f7671 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -509,16 +509,16 @@ int ionic_port_init(struct ionic *ionic) size_t sz; int err; - if (idev->port_info) - return 0; - - idev->port_info_sz = ALIGN(sizeof(*idev->port_info), PAGE_SIZE); - idev->port_info = dma_alloc_coherent(ionic->dev, idev->port_info_sz, - &idev->port_info_pa, - GFP_KERNEL); if (!idev->port_info) { - dev_err(ionic->dev, "Failed to allocate port info, aborting\n"); - return -ENOMEM; + idev->port_info_sz = ALIGN(sizeof(*idev->port_info), PAGE_SIZE); + idev->port_info = dma_alloc_coherent(ionic->dev, + idev->port_info_sz, + &idev->port_info_pa, + GFP_KERNEL); + if (!idev->port_info) { + dev_err(ionic->dev, "Failed to allocate port info\n"); + return -ENOMEM; + } } sz = min(sizeof(ident->port.config), sizeof(idev->dev_cmd_regs->data)); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index bf5bf05970a2..78e15cc00e0a 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2127,6 +2127,8 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii) { 0x7cf, 0x348, RTL_GIGA_MAC_VER_07 }, { 0x7cf, 0x248, RTL_GIGA_MAC_VER_07 }, { 0x7cf, 0x340, RTL_GIGA_MAC_VER_13 }, + /* RTL8401, reportedly works if treated as RTL8101e */ + { 0x7cf, 0x240, RTL_GIGA_MAC_VER_13 }, { 0x7cf, 0x343, RTL_GIGA_MAC_VER_10 }, { 0x7cf, 0x342, RTL_GIGA_MAC_VER_16 }, { 0x7c8, 0x348, RTL_GIGA_MAC_VER_09 }, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index e0a5fe83d8e0..bfc4a92f1d92 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -75,6 +75,11 @@ struct ethqos_emac_por { unsigned int value; }; +struct ethqos_emac_driver_data { + const struct ethqos_emac_por *por; + unsigned int num_por; +}; + struct qcom_ethqos { struct platform_device *pdev; void __iomem *rgmii_base; @@ -171,6 +176,11 @@ static const struct ethqos_emac_por emac_v2_3_0_por[] = { { .offset = RGMII_IO_MACRO_CONFIG2, .value = 0x00002060 }, }; +static const struct ethqos_emac_driver_data emac_v2_3_0_data = { + .por = emac_v2_3_0_por, + .num_por = ARRAY_SIZE(emac_v2_3_0_por), +}; + static int ethqos_dll_configure(struct qcom_ethqos *ethqos) { unsigned int val; @@ -442,6 +452,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct plat_stmmacenet_data *plat_dat; struct stmmac_resources stmmac_res; + const struct ethqos_emac_driver_data *data; struct qcom_ethqos *ethqos; struct resource *res; int ret; @@ -471,7 +482,9 @@ static int qcom_ethqos_probe(struct platform_device *pdev) goto err_mem; } - ethqos->por = of_device_get_match_data(&pdev->dev); + data = of_device_get_match_data(&pdev->dev); + ethqos->por = data->por; + ethqos->num_por = data->num_por; ethqos->rgmii_clk = devm_clk_get(&pdev->dev, "rgmii"); if (IS_ERR(ethqos->rgmii_clk)) { @@ -526,7 +539,7 @@ static int qcom_ethqos_remove(struct platform_device *pdev) } static const struct of_device_id qcom_ethqos_match[] = { - { .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_por}, + { .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_data}, { } }; MODULE_DEVICE_TABLE(of, qcom_ethqos_match); diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 8e348780efb6..62f809b67469 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -49,6 +49,7 @@ config TI_CPSW_PHY_SEL config TI_CPSW tristate "TI CPSW Switch Support" depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST + depends on TI_CPTS || !TI_CPTS select TI_DAVINCI_MDIO select MFD_SYSCON select PAGE_POOL @@ -64,6 +65,7 @@ config TI_CPSW_SWITCHDEV tristate "TI CPSW Switch Support with switchdev" depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST depends on NET_SWITCHDEV + depends on TI_CPTS || !TI_CPTS select PAGE_POOL select TI_DAVINCI_MDIO select MFD_SYSCON @@ -77,23 +79,16 @@ config TI_CPSW_SWITCHDEV will be called cpsw_new. config TI_CPTS - bool "TI Common Platform Time Sync (CPTS) Support" - depends on TI_CPSW || TI_KEYSTONE_NETCP || TI_CPSW_SWITCHDEV || COMPILE_TEST + tristate "TI Common Platform Time Sync (CPTS) Support" + depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST depends on COMMON_CLK - depends on POSIX_TIMERS + depends on PTP_1588_CLOCK ---help--- This driver supports the Common Platform Time Sync unit of the CPSW Ethernet Switch and Keystone 2 1g/10g Switch Subsystem. The unit can time stamp PTP UDP/IPv4 and Layer 2 packets, and the driver offers a PTP Hardware Clock. -config TI_CPTS_MOD - tristate - depends on TI_CPTS - depends on PTP_1588_CLOCK - default y if TI_CPSW=y || TI_KEYSTONE_NETCP=y || TI_CPSW_SWITCHDEV=y - default m - config TI_K3_AM65_CPSW_NUSS tristate "TI K3 AM654x/J721E CPSW Ethernet driver" depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER @@ -114,6 +109,7 @@ config TI_KEYSTONE_NETCP select TI_DAVINCI_MDIO depends on OF depends on KEYSTONE_NAVIGATOR_DMA && KEYSTONE_NAVIGATOR_QMSS + depends on TI_CPTS || !TI_CPTS ---help--- This driver supports TI's Keystone NETCP Core. diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile index 53792190e9c2..cb26a9d21869 100644 --- a/drivers/net/ethernet/ti/Makefile +++ b/drivers/net/ethernet/ti/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_TI_DAVINCI_EMAC) += ti_davinci_emac.o ti_davinci_emac-y := davinci_emac.o davinci_cpdma.o obj-$(CONFIG_TI_DAVINCI_MDIO) += davinci_mdio.o obj-$(CONFIG_TI_CPSW_PHY_SEL) += cpsw-phy-sel.o -obj-$(CONFIG_TI_CPTS_MOD) += cpts.o +obj-$(CONFIG_TI_CPTS) += cpts.o obj-$(CONFIG_TI_CPSW) += ti_cpsw.o ti_cpsw-y := cpsw.o davinci_cpdma.o cpsw_ale.o cpsw_priv.o cpsw_sl.o cpsw_ethtool.o obj-$(CONFIG_TI_CPSW_SWITCHDEV) += ti_cpsw_new.o diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index fbea6f232819..e2ad3c2e8df5 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -127,7 +127,8 @@ static inline struct net_device *bpq_get_ax25_dev(struct net_device *dev) { struct bpqdev *bpq; - list_for_each_entry_rcu(bpq, &bpq_devices, bpq_list) { + list_for_each_entry_rcu(bpq, &bpq_devices, bpq_list, + lockdep_rtnl_is_held()) { if (bpq->ethdev == dev) return bpq->axdev; } diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index 2fd21d75367d..bdbfeed359db 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -399,13 +399,14 @@ void gsi_trans_cmd_add(struct gsi_trans *trans, void *buf, u32 size, /* assert(which < trans->tre_count); */ /* Set the page information for the buffer. We also need to fill in - * the DMA address for the buffer (something dma_map_sg() normally - * does). + * the DMA address and length for the buffer (something dma_map_sg() + * normally does). */ sg = &trans->sgl[which]; sg_set_buf(sg, buf, size); sg_dma_address(sg) = addr; + sg_dma_len(sg) = sg->length; info = &trans->info[which]; info->opcode = opcode; diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index d226b858742d..cee417181f98 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -628,23 +628,15 @@ static void ipa_cmd_transfer_add(struct gsi_trans *trans, u16 size) void ipa_cmd_tag_process_add(struct gsi_trans *trans) { - ipa_cmd_register_write_add(trans, 0, 0, 0, true); -#if 1 - /* Reference these functions to avoid a compile error */ - (void)ipa_cmd_ip_packet_init_add; - (void)ipa_cmd_ip_tag_status_add; - (void) ipa_cmd_transfer_add; -#else struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi); - struct gsi_endpoint *endpoint; + struct ipa_endpoint *endpoint; endpoint = ipa->name_map[IPA_ENDPOINT_AP_LAN_RX]; - ipa_cmd_ip_packet_init_add(trans, endpoint->endpoint_id); + ipa_cmd_register_write_add(trans, 0, 0, 0, true); + ipa_cmd_ip_packet_init_add(trans, endpoint->endpoint_id); ipa_cmd_ip_tag_status_add(trans, 0xcba987654321); - ipa_cmd_transfer_add(trans, 4); -#endif } /* Returns the number of commands required for the tag process */ diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c index 4d33aa7ebfbb..a5f7a79a1923 100644 --- a/drivers/net/ipa/ipa_smp2p.c +++ b/drivers/net/ipa/ipa_smp2p.c @@ -53,7 +53,7 @@ * @clock_on: Whether IPA clock is on * @notified: Whether modem has been notified of clock state * @disabled: Whether setup ready interrupt handling is disabled - * @mutex mutex: Motex protecting ready interrupt/shutdown interlock + * @mutex: Mutex protecting ready-interrupt/shutdown interlock * @panic_notifier: Panic notifier structure */ struct ipa_smp2p { diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index ae4873f2f86e..d14d91b759b7 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -225,8 +225,12 @@ static void bcm54xx_adjust_rxrefclk(struct phy_device *phydev) else val |= BCM54XX_SHD_SCR3_DLLAPD_DIS; - if (phydev->dev_flags & PHY_BRCM_DIS_TXCRXC_NOENRGY) - val |= BCM54XX_SHD_SCR3_TRDDAPD; + if (phydev->dev_flags & PHY_BRCM_DIS_TXCRXC_NOENRGY) { + if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54810) + val |= BCM54810_SHD_SCR3_TRDDAPD; + else + val |= BCM54XX_SHD_SCR3_TRDDAPD; + } if (orig != val) bcm_phy_write_shadow(phydev, BCM54XX_SHD_SCR3, val); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 72c69a9c8a98..20ca6418f7bc 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1132,9 +1132,11 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data) /* Restart autonegotiation so the new modes get sent to the * link partner. */ - ret = phy_restart_aneg(phydev); - if (ret < 0) - return ret; + if (phydev->autoneg == AUTONEG_ENABLE) { + ret = phy_restart_aneg(phydev); + if (ret < 0) + return ret; + } } return 0; diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index d760a36db28c..beedaad08255 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -490,6 +490,9 @@ static int pppoe_disc_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb) goto out; + if (skb->pkt_type != PACKET_HOST) + goto abort; + if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr))) goto abort; diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 417e42c9fd03..bb8c34d746ab 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2659,7 +2659,7 @@ static struct hso_device *hso_create_bulk_serial_device( if (! (serial->out_endp = hso_get_ep(interface, USB_ENDPOINT_XFER_BULK, USB_DIR_OUT))) { - dev_err(&interface->dev, "Failed to find BULK IN ep\n"); + dev_err(&interface->dev, "Failed to find BULK OUT ep\n"); goto exit2; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 11f722460513..ce07f52d89e7 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1243,9 +1243,11 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq, break; } while (rq->vq->num_free); if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) { - u64_stats_update_begin(&rq->stats.syncp); + unsigned long flags; + + flags = u64_stats_update_begin_irqsave(&rq->stats.syncp); rq->stats.kicks++; - u64_stats_update_end(&rq->stats.syncp); + u64_stats_update_end_irqrestore(&rq->stats.syncp, flags); } return !oom; diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index c75112ee7b97..c7fade836d83 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -521,8 +521,10 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) ism->smcd = smcd_alloc_dev(&pdev->dev, dev_name(&pdev->dev), &ism_ops, ISM_NR_DMBS); - if (!ism->smcd) + if (!ism->smcd) { + ret = -ENOMEM; goto err_resource; + } ism->smcd->priv = ism; ret = ism_dev_init(ism); diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6462c5447872..f4b77018c625 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -245,6 +245,7 @@ #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN (1 << 0) #define BCM54810_SHD_CLK_CTL 0x3 #define BCM54810_SHD_CLK_CTL_GTXCLK_EN (1 << 9) +#define BCM54810_SHD_SCR3_TRDDAPD 0x0100 /* BCM54612E Registers */ #define BCM54612E_EXP_SPARE0 (MII_BCM54XX_EXP_SEL_ETC + 0x34) diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 1bdd027766d4..5616b2567aa7 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -243,7 +243,7 @@ LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, char *name, char **value) LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) LSM_HOOK(int, 0, ismaclabel, const char *name) -LSM_HOOK(int, 0, secid_to_secctx, u32 secid, char **secdata, +LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, char **secdata, u32 *seclen) LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen) diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 121a7eda4593..c602670bbffb 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -105,10 +105,10 @@ struct ptp_system_timestamp { * parameter func: the desired function to use. * parameter chan: the function channel index to use. * - * @do_work: Request driver to perform auxiliary (periodic) operations - * Driver should return delay of the next auxiliary work scheduling - * time (>=0) or negative value in case further scheduling - * is not required. + * @do_aux_work: Request driver to perform auxiliary (periodic) operations + * Driver should return delay of the next auxiliary work + * scheduling time (>=0) or negative value in case further + * scheduling is not required. * * Drivers should embed their ptp_clock_info within a private * structure, obtaining a reference to it using container_of(). diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 8a709f63c5e5..ad31c9fb7158 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -187,6 +187,7 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, dst->sg.data[which] = src->sg.data[which]; dst->sg.data[which].length = size; dst->sg.size += size; + src->sg.size -= size; src->sg.data[which].length -= size; src->sg.data[which].offset += size; } diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 9f551f3b69c6..90690e37a56f 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -87,7 +87,7 @@ struct nf_conn { struct hlist_node nat_bysource; #endif /* all members below initialized via memset */ - u8 __nfct_init_offset[0]; + struct { } __nfct_init_offset; /* If we were expected by an expectation, this will be it */ struct nf_conn *master; diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 6bf69652f57d..c54a7f707e50 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -127,6 +127,7 @@ enum nf_flow_flags { NF_FLOW_HW_DYING, NF_FLOW_HW_DEAD, NF_FLOW_HW_REFRESH, + NF_FLOW_HW_PENDING, }; enum flow_offload_type { diff --git a/include/net/tcp.h b/include/net/tcp.h index dcf9a72eeaa6..6f8e60c6fbc7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1376,7 +1376,6 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) rx_opt->num_sacks = 0; } -u32 tcp_default_init_rwnd(u32 mss); void tcp_cwnd_restart(struct sock *sk, s32 delta); static inline void tcp_slow_start_after_idle_check(struct sock *sk) @@ -1421,6 +1420,19 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } +/* We provision sk_rcvbuf around 200% of sk_rcvlowat. + * If 87.5 % (7/8) of the space has been consumed, we want to override + * SO_RCVLOWAT constraint, since we are receiving skbs with too small + * len/truesize ratio. + */ +static inline bool tcp_rmem_pressure(const struct sock *sk) +{ + int rcvbuf = READ_ONCE(sk->sk_rcvbuf); + int threshold = rcvbuf - (rcvbuf >> 3); + + return atomic_read(&sk->sk_rmem_alloc) > threshold; +} + extern void tcp_openreq_init_rwin(struct request_sock *req, const struct sock *sk_listener, const struct dst_entry *dst); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 4b1f95e08307..e7312ceb2794 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -143,14 +143,12 @@ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck); -#if IS_ENABLED(CONFIG_IPV6) int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck); -#endif void udp_tunnel_sock_release(struct socket *sock); diff --git a/init/Kconfig b/init/Kconfig index 9278a603d399..74a5ac65644f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -2261,6 +2261,9 @@ config ASN1 source "kernel/Kconfig.locks" +config ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + bool + config ARCH_HAS_SYNC_CORE_BEFORE_USERMODE bool diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 95d77770353c..1d6120fd5ba6 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -486,7 +486,12 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) if (!(map->map_flags & BPF_F_MMAPABLE)) return -EINVAL; - return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), pgoff); + if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) > + PAGE_ALIGN((u64)array->map.max_entries * array->elem_size)) + return -EINVAL; + + return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), + vma->vm_pgoff + pgoff); } const struct bpf_map_ops array_map_ops = { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7626b8024471..2843bbba9ca1 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1485,8 +1485,10 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) if (err) goto free_value; - if (copy_to_user(uvalue, value, value_size) != 0) + if (copy_to_user(uvalue, value, value_size) != 0) { + err = -EFAULT; goto free_value; + } err = 0; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fa1d8245b925..8d7ee40e2748 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4340,7 +4340,9 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, if (ret_type != RET_INTEGER || (func_id != BPF_FUNC_get_stack && - func_id != BPF_FUNC_probe_read_str)) + func_id != BPF_FUNC_probe_read_str && + func_id != BPF_FUNC_probe_read_kernel_str && + func_id != BPF_FUNC_probe_read_user_str)) return; ret_reg->smax_value = meta->msize_max_value; @@ -7059,6 +7061,23 @@ static int check_return_code(struct bpf_verifier_env *env) return 0; range = tnum_const(0); break; + case BPF_PROG_TYPE_TRACING: + switch (env->prog->expected_attach_type) { + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + range = tnum_const(0); + break; + case BPF_TRACE_RAW_TP: + case BPF_MODIFY_RETURN: + return 0; + default: + return -ENOTSUPP; + } + break; + case BPF_PROG_TYPE_EXT: + /* freplace program can return anything as its return value + * depends on the to-be-replaced kernel func or bpf program. + */ default: return 0; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index ca1796747a77..a010edc37ee0 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -323,17 +323,15 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void) /* * Only limited trace_printk() conversion specifiers allowed: - * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s + * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pks %pus %s */ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3) { + int i, mod[3] = {}, fmt_cnt = 0; + char buf[64], fmt_ptype; + void *unsafe_ptr = NULL; bool str_seen = false; - int mod[3] = {}; - int fmt_cnt = 0; - u64 unsafe_addr; - char buf[64]; - int i; /* * bpf_check()->check_func_arg()->check_stack_boundary() @@ -359,40 +357,71 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, if (fmt[i] == 'l') { mod[fmt_cnt]++; i++; - } else if (fmt[i] == 'p' || fmt[i] == 's') { + } else if (fmt[i] == 'p') { mod[fmt_cnt]++; + if ((fmt[i + 1] == 'k' || + fmt[i + 1] == 'u') && + fmt[i + 2] == 's') { + fmt_ptype = fmt[i + 1]; + i += 2; + goto fmt_str; + } + /* disallow any further format extensions */ if (fmt[i + 1] != 0 && !isspace(fmt[i + 1]) && !ispunct(fmt[i + 1])) return -EINVAL; - fmt_cnt++; - if (fmt[i] == 's') { - if (str_seen) - /* allow only one '%s' per fmt string */ - return -EINVAL; - str_seen = true; - - switch (fmt_cnt) { - case 1: - unsafe_addr = arg1; - arg1 = (long) buf; - break; - case 2: - unsafe_addr = arg2; - arg2 = (long) buf; - break; - case 3: - unsafe_addr = arg3; - arg3 = (long) buf; - break; - } - buf[0] = 0; - strncpy_from_unsafe(buf, - (void *) (long) unsafe_addr, + + goto fmt_next; + } else if (fmt[i] == 's') { + mod[fmt_cnt]++; + fmt_ptype = fmt[i]; +fmt_str: + if (str_seen) + /* allow only one '%s' per fmt string */ + return -EINVAL; + str_seen = true; + + if (fmt[i + 1] != 0 && + !isspace(fmt[i + 1]) && + !ispunct(fmt[i + 1])) + return -EINVAL; + + switch (fmt_cnt) { + case 0: + unsafe_ptr = (void *)(long)arg1; + arg1 = (long)buf; + break; + case 1: + unsafe_ptr = (void *)(long)arg2; + arg2 = (long)buf; + break; + case 2: + unsafe_ptr = (void *)(long)arg3; + arg3 = (long)buf; + break; + } + + buf[0] = 0; + switch (fmt_ptype) { + case 's': +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + strncpy_from_unsafe(buf, unsafe_ptr, sizeof(buf)); + break; +#endif + case 'k': + strncpy_from_unsafe_strict(buf, unsafe_ptr, + sizeof(buf)); + break; + case 'u': + strncpy_from_unsafe_user(buf, + (__force void __user *)unsafe_ptr, + sizeof(buf)); + break; } - continue; + goto fmt_next; } if (fmt[i] == 'l') { @@ -403,6 +432,7 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, if (fmt[i] != 'i' && fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x') return -EINVAL; +fmt_next: fmt_cnt++; } @@ -825,14 +855,16 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: return &bpf_probe_read_kernel_proto; - case BPF_FUNC_probe_read: - return &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: return &bpf_probe_read_kernel_str_proto; +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + case BPF_FUNC_probe_read: + return &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_str: return &bpf_probe_read_compat_str_proto; +#endif #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; diff --git a/kernel/umh.c b/kernel/umh.c index 11bf5eea474c..3474d6aa55d8 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -475,6 +475,12 @@ static void umh_clean_and_save_pid(struct subprocess_info *info) { struct umh_info *umh_info = info->data; + /* cleanup if umh_pipe_setup() was successful but exec failed */ + if (info->pid && info->retval) { + fput(umh_info->pipe_to_umh); + fput(umh_info->pipe_from_umh); + } + argv_free(info->argv); umh_info->pid = info->pid; } diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 7c488a1ce318..532b6606a18a 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -2168,6 +2168,10 @@ char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, * f full name * P node name, including a possible unit address * - 'x' For printing the address. Equivalent to "%lx". + * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of + * bpf_trace_printk() where [ku] prefix specifies either kernel (k) + * or user (u) memory to probe, and: + * s a string, equivalent to "%s" on direct vsnprintf() use * * ** When making changes please also update: * Documentation/core-api/printk-formats.rst @@ -2251,6 +2255,14 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, if (!IS_ERR(ptr)) break; return err_ptr(buf, end, ptr, spec); + case 'u': + case 'k': + switch (fmt[1]) { + case 's': + return string(buf, end, ptr, spec); + default: + return error_string(buf, end, "(einval)", spec); + } } /* default is to _not_ leak addresses, hash before printing */ diff --git a/net/core/dev.c b/net/core/dev.c index 522288177bbd..6d327b7aa813 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8907,11 +8907,13 @@ static void netdev_sync_lower_features(struct net_device *upper, netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", &feature, lower->name); lower->wanted_features &= ~feature; - netdev_update_features(lower); + __netdev_update_features(lower); if (unlikely(lower->features & feature)) netdev_WARN(upper, "failed to disable %pNF on %s!\n", &feature, lower->name); + else + netdev_features_change(lower); } } } diff --git a/net/core/filter.c b/net/core/filter.c index 7d6ceaa54d21..5cc9276f1023 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2590,8 +2590,8 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, } pop = 0; } else if (pop >= sge->length - a) { - sge->length = a; pop -= (sge->length - a); + sge->length = a; } } diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 8881dd943dd0..9bd4cab7d510 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -236,6 +236,8 @@ static void net_prio_attach(struct cgroup_taskset *tset) struct task_struct *p; struct cgroup_subsys_state *css; + cgroup_sk_alloc_disable(); + cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->id; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 0bd10a1f477f..a23094b050f8 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1258,7 +1258,8 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def, return ret_val; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } return 0; @@ -1439,7 +1440,8 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def, return ret_val; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } return 0; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9cf83cc85e4a..5c218db2dede 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -109,8 +109,10 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags); static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES -#define ipmr_for_each_table(mrt, net) \ - list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list) +#define ipmr_for_each_table(mrt, net) \ + list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list, \ + lockdep_rtnl_is_held() || \ + list_empty(&net->ipv4.mr_tables)) static struct mr_table *ipmr_mr_table_iter(struct net *net, struct mr_table *mrt) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 788c69d9bfe0..fa829f31a3f5 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -915,7 +915,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) /* Check for load limit; set rate_last to the latest sent * redirect. */ - if (peer->rate_tokens == 0 || + if (peer->n_redirects == 0 || time_after(jiffies, (peer->rate_last + (ip_rt_redirect_load << peer->n_redirects)))) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6d87de434377..dd401757eea1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -476,9 +476,17 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, int target, struct sock *sk) { - return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) || - (sk->sk_prot->stream_memory_read ? - sk->sk_prot->stream_memory_read(sk) : false); + int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq); + + if (avail > 0) { + if (avail >= target) + return true; + if (tcp_rmem_pressure(sk)) + return true; + } + if (sk->sk_prot->stream_memory_read) + return sk->sk_prot->stream_memory_read(sk); + return false; } /* @@ -1756,10 +1764,11 @@ static int tcp_zerocopy_receive(struct sock *sk, down_read(¤t->mm->mmap_sem); - ret = -EINVAL; vma = find_vma(current->mm, address); - if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) - goto out; + if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) { + up_read(¤t->mm->mmap_sem); + return -EINVAL; + } zc->length = min_t(unsigned long, zc->length, vma->vm_end - address); tp = tcp_sk(sk); @@ -2154,13 +2163,15 @@ skip_copy: tp->urg_data = 0; tcp_fast_path_check(sk); } - if (used + offset < skb->len) - continue; if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, &tss); cmsg_flags |= 2; } + + if (used + offset < skb->len) + continue; + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; if (!(flags & MSG_PEEK)) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 5a05327f97c1..629aaa9a1eb9 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -125,7 +125,6 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, if (!ret) { msg->sg.start = i; - msg->sg.size -= apply_bytes; sk_psock_queue_msg(psock, tmp); sk_psock_data_ready(sk, psock); } else { @@ -262,14 +261,17 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, struct sk_psock *psock; int copied, ret; + if (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - if (unlikely(flags & MSG_ERRQUEUE)) - return inet_recv_error(sk, msg, len, addr_len); if (!skb_queue_empty(&sk->sk_receive_queue) && - sk_psock_queue_empty(psock)) + sk_psock_queue_empty(psock)) { + sk_psock_put(sk, psock); return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + } lock_sock(sk); msg_bytes_ready: copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b996dc1069c5..29c6fc8c7716 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4757,7 +4757,8 @@ void tcp_data_ready(struct sock *sk) const struct tcp_sock *tp = tcp_sk(sk); int avail = tp->rcv_nxt - tp->copied_seq; - if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE)) + if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) && + !sock_flag(sk, SOCK_DONE)) return; sk->sk_data_ready(sk); diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 221c81f85cbf..8d3f66c310db 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -1047,7 +1047,8 @@ static int calipso_opt_getattr(const unsigned char *calipso, goto getattr_return; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } secattr->type = NETLBL_NLTYPE_CALIPSO; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8d418038fe32..ff847a324220 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2722,8 +2722,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, const struct in6_addr *daddr, *saddr; struct rt6_info *rt6 = (struct rt6_info *)dst; - if (dst_metric_locked(dst, RTAX_MTU)) - return; + /* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU) + * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it. + * [see also comment in rt6_mtu_change_route()] + */ if (iph) { daddr = &iph->daddr; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e1f23016ed3f..32ea8d35489a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1629,6 +1629,8 @@ bool mptcp_finish_join(struct sock *sk) ret = mptcp_pm_allow_new_subflow(msk); if (ret) { + subflow->map_seq = msk->ack_seq; + /* active connections are already on conn_list */ spin_lock_bh(&msk->join_list_lock); if (!WARN_ON_ONCE(!list_empty(&subflow->node))) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 67a4e35d4838..4931a29a6f08 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1012,6 +1012,16 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) if (err) return err; + /* the newly created socket really belongs to the owning MPTCP master + * socket, even if for additional subflows the allocation is performed + * by a kernel workqueue. Adjust inode references, so that the + * procfs/diag interaces really show this one belonging to the correct + * user. + */ + SOCK_INODE(sf)->i_ino = SOCK_INODE(sk->sk_socket)->i_ino; + SOCK_INODE(sf)->i_uid = SOCK_INODE(sk->sk_socket)->i_uid; + SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid; + subflow = mptcp_subflow_ctx(sf->sk); pr_debug("subflow=%p", subflow); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c4582eb71766..1d57b95d3481 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1519,9 +1519,9 @@ __nf_conntrack_alloc(struct net *net, ct->status = 0; ct->timeout = 0; write_pnet(&ct->ct_net, net); - memset(&ct->__nfct_init_offset[0], 0, + memset(&ct->__nfct_init_offset, 0, offsetof(struct nf_conn, proto) - - offsetof(struct nf_conn, __nfct_init_offset[0])); + offsetof(struct nf_conn, __nfct_init_offset)); nf_ct_zone_add(ct, zone); @@ -2139,8 +2139,19 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data), nf_conntrack_lock(lockp); if (*bucket < nf_conntrack_htable_size) { hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) { - if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) + if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY) continue; + /* All nf_conn objects are added to hash table twice, one + * for original direction tuple, once for the reply tuple. + * + * Exception: In the IPS_NAT_CLASH case, only the reply + * tuple is added (the original tuple already existed for + * a different object). + * + * We only need to call the iterator once for each + * conntrack, so we just use the 'reply' direction + * tuple while iterating. + */ ct = nf_ct_tuplehash_to_ctrack(h); if (iter(ct, data)) goto found; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 4344e572b7f9..42da6e337276 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -284,7 +284,7 @@ static void flow_offload_del(struct nf_flowtable *flow_table, if (nf_flow_has_expired(flow)) flow_offload_fixup_ct(flow->ct); - else if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) + else flow_offload_fixup_ct_timeout(flow->ct); flow_offload_free(flow); @@ -361,8 +361,10 @@ static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data) { struct nf_flowtable *flow_table = data; - if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) || - test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { + if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct)) + set_bit(NF_FLOW_TEARDOWN, &flow->flags); + + if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { if (test_bit(NF_FLOW_HW, &flow->flags)) { if (!test_bit(NF_FLOW_HW_DYING, &flow->flags)) nf_flow_offload_del(flow_table, flow); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index e3b099c14eff..2276a73ccba2 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -817,6 +817,7 @@ static void flow_offload_work_handler(struct work_struct *work) WARN_ON_ONCE(1); } + clear_bit(NF_FLOW_HW_PENDING, &offload->flow->flags); kfree(offload); } @@ -831,9 +832,14 @@ nf_flow_offload_work_alloc(struct nf_flowtable *flowtable, { struct flow_offload_work *offload; + if (test_and_set_bit(NF_FLOW_HW_PENDING, &flow->flags)) + return NULL; + offload = kmalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); - if (!offload) + if (!offload) { + clear_bit(NF_FLOW_HW_PENDING, &flow->flags); return NULL; + } offload->cmd = cmd; offload->flow = flow; @@ -1056,7 +1062,7 @@ static struct flow_indr_block_entry block_ing_entry = { int nf_flow_table_offload_init(void) { nf_flow_offload_wq = alloc_workqueue("nf_flow_table_offload", - WQ_UNBOUND | WQ_MEM_RECLAIM, 0); + WQ_UNBOUND, 0); if (!nf_flow_offload_wq) return -ENOMEM; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 3ffef454d469..62f416bc0579 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -79,6 +79,10 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set parent = rcu_dereference_raw(parent->rb_left); continue; } + + if (nft_set_elem_expired(&rbe->ext)) + return false; + if (nft_rbtree_interval_end(rbe)) { if (nft_set_is_anonymous(set)) return false; @@ -94,6 +98,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && + !nft_set_elem_expired(&interval->ext) && nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; @@ -154,6 +159,9 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, continue; } + if (nft_set_elem_expired(&rbe->ext)) + return false; + if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == (flags & NFT_SET_ELEM_INTERVAL_END)) { @@ -170,6 +178,7 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && + !nft_set_elem_expired(&interval->ext) && ((!nft_rbtree_interval_end(interval) && !(flags & NFT_SET_ELEM_INTERVAL_END)) || (nft_rbtree_interval_end(interval) && @@ -418,6 +427,8 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; + if (nft_set_elem_expired(&rbe->ext)) + goto cont; if (!nft_set_elem_active(&rbe->ext, iter->genmask)) goto cont; diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 409a3ae47ce2..5e1239cef000 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -734,6 +734,12 @@ int netlbl_catmap_getlong(struct netlbl_lsm_catmap *catmap, if ((off & (BITS_PER_LONG - 1)) != 0) return -EINVAL; + /* a null catmap is equivalent to an empty one */ + if (!catmap) { + *offset = (u32)-1; + return 0; + } + if (off < catmap->startbit) { off = catmap->startbit; *offset = off; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 87466607097f..e370ad0edd76 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1739,22 +1739,21 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb, return 0; } -static void tipc_sk_send_ack(struct tipc_sock *tsk) +static struct sk_buff *tipc_sk_build_ack(struct tipc_sock *tsk) { struct sock *sk = &tsk->sk; - struct net *net = sock_net(sk); struct sk_buff *skb = NULL; struct tipc_msg *msg; u32 peer_port = tsk_peer_port(tsk); u32 dnode = tsk_peer_node(tsk); if (!tipc_sk_connected(sk)) - return; + return NULL; skb = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0, dnode, tsk_own_node(tsk), peer_port, tsk->portid, TIPC_OK); if (!skb) - return; + return NULL; msg = buf_msg(skb); msg_set_conn_ack(msg, tsk->rcv_unacked); tsk->rcv_unacked = 0; @@ -1764,7 +1763,19 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk) tsk->rcv_win = tsk_adv_blocks(tsk->sk.sk_rcvbuf); msg_set_adv_win(msg, tsk->rcv_win); } - tipc_node_xmit_skb(net, skb, dnode, msg_link_selector(msg)); + return skb; +} + +static void tipc_sk_send_ack(struct tipc_sock *tsk) +{ + struct sk_buff *skb; + + skb = tipc_sk_build_ack(tsk); + if (!skb) + return; + + tipc_node_xmit_skb(sock_net(&tsk->sk), skb, tsk_peer_node(tsk), + msg_link_selector(buf_msg(skb))); } static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) @@ -1938,7 +1949,6 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, bool peek = flags & MSG_PEEK; int offset, required, copy, copied = 0; int hlen, dlen, err, rc; - bool ack = false; long timeout; /* Catch invalid receive attempts */ @@ -1983,7 +1993,6 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, /* Copy data if msg ok, otherwise return error/partial data */ if (likely(!err)) { - ack = msg_ack_required(hdr); offset = skb_cb->bytes_read; copy = min_t(int, dlen - offset, buflen - copied); rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy); @@ -2011,7 +2020,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, /* Send connection flow control advertisement when applicable */ tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen); - if (ack || tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE) + if (tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE) tipc_sk_send_ack(tsk); /* Exit if all requested data or FIN/error received */ @@ -2105,9 +2114,11 @@ static void tipc_sk_proto_rcv(struct sock *sk, * tipc_sk_filter_connect - check incoming message for a connection-based socket * @tsk: TIPC socket * @skb: pointer to message buffer. + * @xmitq: for Nagle ACK if any * Returns true if message should be added to receive queue, false otherwise */ -static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) +static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { struct sock *sk = &tsk->sk; struct net *net = sock_net(sk); @@ -2171,8 +2182,17 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) if (!skb_queue_empty(&sk->sk_write_queue)) tipc_sk_push_backlog(tsk); /* Accept only connection-based messages sent by peer */ - if (likely(con_msg && !err && pport == oport && pnode == onode)) + if (likely(con_msg && !err && pport == oport && + pnode == onode)) { + if (msg_ack_required(hdr)) { + struct sk_buff *skb; + + skb = tipc_sk_build_ack(tsk); + if (skb) + __skb_queue_tail(xmitq, skb); + } return true; + } if (!tsk_peer_msg(tsk, hdr)) return false; if (!err) @@ -2267,7 +2287,7 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, while ((skb = __skb_dequeue(&inputq))) { hdr = buf_msg(skb); limit = rcvbuf_limit(sk, skb); - if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) || + if ((sk_conn && !tipc_sk_filter_connect(tsk, skb, xmitq)) || (!sk_conn && msg_connected(hdr)) || (!grp && msg_in_group(hdr))) err = TIPC_ERR_NO_PORT; diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index aa015c233898..6ebbec1bedd1 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -96,6 +96,16 @@ void tipc_sub_get(struct tipc_subscription *subscription); (swap_ ? swab32(val__) : val__); \ }) +/* tipc_sub_write - write val_ to field_ of struct sub_ in user endian format + */ +#define tipc_sub_write(sub_, field_, val_) \ + ({ \ + struct tipc_subscr *sub__ = sub_; \ + u32 val__ = val_; \ + int swap_ = !((sub__)->filter & TIPC_FILTER_MASK); \ + (sub__)->field_ = swap_ ? swab32(val__) : val__; \ + }) + /* tipc_evt_write - write val_ to field_ of struct evt_ in user endian format */ #define tipc_evt_write(evt_, field_, val_) \ diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 73dbed0c4b6b..446af7bbd13e 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -237,8 +237,8 @@ static void tipc_conn_delete_sub(struct tipc_conn *con, struct tipc_subscr *s) if (!s || !memcmp(s, &sub->evt.s, sizeof(*s))) { tipc_sub_unsubscribe(sub); atomic_dec(&tn->subscription_count); - } else if (s) { - break; + if (s) + break; } } spin_unlock_bh(&con->sub_lock); @@ -362,9 +362,10 @@ static int tipc_conn_rcv_sub(struct tipc_topsrv *srv, { struct tipc_net *tn = tipc_net(srv->net); struct tipc_subscription *sub; + u32 s_filter = tipc_sub_read(s, filter); - if (tipc_sub_read(s, filter) & TIPC_SUB_CANCEL) { - s->filter &= __constant_ntohl(~TIPC_SUB_CANCEL); + if (s_filter & TIPC_SUB_CANCEL) { + tipc_sub_write(s, filter, s_filter & ~TIPC_SUB_CANCEL); tipc_conn_delete_sub(con, s); return 0; } @@ -400,7 +401,9 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) return -EWOULDBLOCK; if (ret == sizeof(s)) { read_lock_bh(&sk->sk_callback_lock); - ret = tipc_conn_rcv_sub(srv, con, &s); + /* RACE: the connection can be closed in the meantime */ + if (likely(connected(con))) + ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); if (!ret) return 0; diff --git a/samples/bpf/lwt_len_hist_user.c b/samples/bpf/lwt_len_hist_user.c index 587b68b1f8dd..430a4b7e353e 100644 --- a/samples/bpf/lwt_len_hist_user.c +++ b/samples/bpf/lwt_len_hist_user.c @@ -15,8 +15,6 @@ #define MAX_INDEX 64 #define MAX_STARS 38 -char bpf_log_buf[BPF_LOG_BUF_SIZE]; - static void stars(char *str, long val, long max, int width) { int i; diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index f3f3c3fb98cb..48a9c7c69ef1 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -148,11 +148,11 @@ struct pt_regs; #define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4]) #define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5]) #define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6]) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), grps[14]) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[14]) #define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11]) #define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2]) #define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15]) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), pdw.addr) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), psw.addr) #elif defined(bpf_target_arm) diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c index 56d80adcf4bd..6b9dce431d41 100644 --- a/tools/testing/selftests/bpf/prog_tests/mmap.c +++ b/tools/testing/selftests/bpf/prog_tests/mmap.c @@ -217,6 +217,14 @@ void test_mmap(void) munmap(tmp2, 4 * page_size); + /* map all 4 pages, but with pg_off=1 page, should fail */ + tmp1 = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED, + data_map_fd, page_size /* initial page shift */); + if (CHECK(tmp1 != MAP_FAILED, "adv_mmap7", "unexpected success")) { + munmap(tmp1, 4 * page_size); + goto cleanup; + } + tmp1 = mmap(NULL, map_sz, PROT_READ, MAP_SHARED, data_map_fd, 0); if (CHECK(tmp1 == MAP_FAILED, "last_mmap", "failed %d\n", errno)) goto cleanup; diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c index 56a50b25cd33..abb7344b531f 100644 --- a/tools/testing/selftests/bpf/progs/test_overhead.c +++ b/tools/testing/selftests/bpf/progs/test_overhead.c @@ -30,13 +30,13 @@ int prog3(struct bpf_raw_tracepoint_args *ctx) SEC("fentry/__set_task_comm") int BPF_PROG(prog4, struct task_struct *tsk, const char *buf, bool exec) { - return !tsk; + return 0; } SEC("fexit/__set_task_comm") int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec) { - return !tsk; + return 0; } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 9172746b6cf0..15f4f46ca3a9 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -30,7 +30,7 @@ ret=0 cleanup() { - rm -f $out + rm -f $err ip netns del $ns1 } |