diff options
61 files changed, 687 insertions, 184 deletions
diff --git a/Documentation/devicetree/bindings/net/davinci_emac.txt b/Documentation/devicetree/bindings/net/davinci_emac.txt index 24c5cdaba8d2..ca83dcc84fb8 100644 --- a/Documentation/devicetree/bindings/net/davinci_emac.txt +++ b/Documentation/devicetree/bindings/net/davinci_emac.txt @@ -20,6 +20,8 @@ Required properties: Optional properties: - phy-handle: See ethernet.txt file in the same directory. If absent, davinci_emac driver defaults to 100/FULL. +- nvmem-cells: phandle, reference to an nvmem node for the MAC address +- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used - ti,davinci-rmii-en: 1 byte, 1 means use RMII - ti,davinci-no-bd-ram: boolean, does EMAC have BD RAM? diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt index cfc376bc977a..a68621580584 100644 --- a/Documentation/devicetree/bindings/net/ethernet.txt +++ b/Documentation/devicetree/bindings/net/ethernet.txt @@ -10,15 +10,14 @@ Documentation/devicetree/bindings/phy/phy-bindings.txt. the boot program; should be used in cases where the MAC address assigned to the device by the boot program is different from the "local-mac-address" property; -- nvmem-cells: phandle, reference to an nvmem node for the MAC address; -- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used; - max-speed: number, specifies maximum speed in Mbit/s supported by the device; - max-frame-size: number, maximum transfer unit (IEEE defined MTU), rather than the maximum frame size (there's contradiction in the Devicetree Specification). - phy-mode: string, operation mode of the PHY interface. This is now a de-facto standard property; supported values are: - * "internal" + * "internal" (Internal means there is not a standard bus between the MAC and + the PHY, something proprietary is being used to embed the PHY in the MAC.) * "mii" * "gmii" * "sgmii" diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt index 174f292d8a3e..8b80515729d7 100644 --- a/Documentation/devicetree/bindings/net/macb.txt +++ b/Documentation/devicetree/bindings/net/macb.txt @@ -26,6 +26,10 @@ Required properties: Optional elements: 'tsu_clk' - clocks: Phandles to input clocks. +Optional properties: +- nvmem-cells: phandle, reference to an nvmem node for the MAC address +- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used + Optional properties for PHY child node: - reset-gpios : Should specify the gpio for phy reset - magic-packet : If present, indicates that the hardware supports waking diff --git a/Documentation/networking/decnet.txt b/Documentation/networking/decnet.txt index e12a4900cf72..d192f8b9948b 100644 --- a/Documentation/networking/decnet.txt +++ b/Documentation/networking/decnet.txt @@ -22,8 +22,6 @@ you'll need the following options as well... CONFIG_DECNET_ROUTER (to be able to add/delete routes) CONFIG_NETFILTER (will be required for the DECnet routing daemon) - CONFIG_DECNET_ROUTE_FWMARK is optional - Don't turn on SIOCGIFCONF support for DECnet unless you are really sure that you need it, in general you won't and it can cause ifconfig to malfunction. diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index acdfb5d2bcaa..e2142fe40cda 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -422,6 +422,7 @@ tcp_min_rtt_wlen - INTEGER minimum RTT when it is moved to a longer path (e.g., due to traffic engineering). A longer window makes the filter more resistant to RTT inflations such as transient congestion. The unit is seconds. + Possible values: 0 - 86400 (1 day) Default: 300 tcp_moderate_rcvbuf - BOOLEAN diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index 11e1663bdc4d..b2c06da4f62e 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -1646,7 +1646,7 @@ static irqreturn_t fs_irq (int irq, void *dev_id) } if (status & ISR_TBRQ_W) { - fs_dprintk (FS_DEBUG_IRQ, "Data tramsitted!\n"); + fs_dprintk (FS_DEBUG_IRQ, "Data transmitted!\n"); process_txdone_queue (dev, &dev->tx_relq); } diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index 9e07b469066a..156fbc5601ca 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -1721,7 +1721,7 @@ static void atl1_inc_smb(struct atl1_adapter *adapter) adapter->soft_stats.scc += smb->tx_1_col; adapter->soft_stats.mcc += smb->tx_2_col; adapter->soft_stats.latecol += smb->tx_late_col; - adapter->soft_stats.tx_underun += smb->tx_underrun; + adapter->soft_stats.tx_underrun += smb->tx_underrun; adapter->soft_stats.tx_trunc += smb->tx_trunc; adapter->soft_stats.tx_pause += smb->tx_pause; @@ -3179,7 +3179,7 @@ static struct atl1_stats atl1_gstrings_stats[] = { {"tx_deferred_ok", ATL1_STAT(soft_stats.deffer)}, {"tx_single_coll_ok", ATL1_STAT(soft_stats.scc)}, {"tx_multi_coll_ok", ATL1_STAT(soft_stats.mcc)}, - {"tx_underun", ATL1_STAT(soft_stats.tx_underun)}, + {"tx_underrun", ATL1_STAT(soft_stats.tx_underrun)}, {"tx_trunc", ATL1_STAT(soft_stats.tx_trunc)}, {"tx_pause", ATL1_STAT(soft_stats.tx_pause)}, {"rx_pause", ATL1_STAT(soft_stats.rx_pause)}, diff --git a/drivers/net/ethernet/atheros/atlx/atl1.h b/drivers/net/ethernet/atheros/atlx/atl1.h index 34a58cd846a0..eacff19ea05b 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.h +++ b/drivers/net/ethernet/atheros/atlx/atl1.h @@ -681,7 +681,7 @@ struct atl1_sft_stats { u64 scc; /* packets TX after a single collision */ u64 mcc; /* packets TX after multiple collisions */ u64 latecol; /* TX packets w/ late collisions */ - u64 tx_underun; /* TX packets aborted due to TX FIFO underrun + u64 tx_underrun; /* TX packets aborted due to TX FIFO underrun * or TRD FIFO underrun */ u64 tx_trunc; /* TX packets truncated due to size > MTU */ u64 rx_pause; /* num Pause packets received. */ diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index d99317b3d891..98da0fa27192 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -553,7 +553,7 @@ static void atl2_intr_tx(struct atl2_adapter *adapter) netdev->stats.tx_aborted_errors++; if (txs->late_col) netdev->stats.tx_window_errors++; - if (txs->underun) + if (txs->underrun) netdev->stats.tx_fifo_errors++; } while (1); diff --git a/drivers/net/ethernet/atheros/atlx/atl2.h b/drivers/net/ethernet/atheros/atlx/atl2.h index c64a6bdfa7ae..25ec84cb4853 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.h +++ b/drivers/net/ethernet/atheros/atlx/atl2.h @@ -260,7 +260,7 @@ struct tx_pkt_status { unsigned multi_col:1; unsigned late_col:1; unsigned abort_col:1; - unsigned underun:1; /* current packet is aborted + unsigned underrun:1; /* current packet is aborted * due to txram underrun */ unsigned:3; /* reserved */ unsigned update:1; /* always 1'b1 in tx_status_buf */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 03b2a9f9c589..cad34d6f5f45 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -33,6 +33,26 @@ #include <linux/bpf_trace.h> #include "en/xdp.h" +int mlx5e_xdp_max_mtu(struct mlx5e_params *params) +{ + int hr = NET_IP_ALIGN + XDP_PACKET_HEADROOM; + + /* Let S := SKB_DATA_ALIGN(sizeof(struct skb_shared_info)). + * The condition checked in mlx5e_rx_is_linear_skb is: + * SKB_DATA_ALIGN(sw_mtu + hard_mtu + hr) + S <= PAGE_SIZE (1) + * (Note that hw_mtu == sw_mtu + hard_mtu.) + * What is returned from this function is: + * max_mtu = PAGE_SIZE - S - hr - hard_mtu (2) + * After assigning sw_mtu := max_mtu, the left side of (1) turns to + * SKB_DATA_ALIGN(PAGE_SIZE - S) + S, which is equal to PAGE_SIZE, + * because both PAGE_SIZE and S are already aligned. Any number greater + * than max_mtu would make the left side of (1) greater than PAGE_SIZE, + * so max_mtu is the maximum MTU allowed. + */ + + return MLX5E_HW2SW_MTU(params, SKB_MAX_HEAD(hr)); +} + static inline bool mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di, struct xdp_buff *xdp) @@ -304,9 +324,9 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq) mlx5e_xdpi_fifo_pop(xdpi_fifo); if (is_redirect) { - xdp_return_frame(xdpi.xdpf); dma_unmap_single(sq->pdev, xdpi.dma_addr, xdpi.xdpf->len, DMA_TO_DEVICE); + xdp_return_frame(xdpi.xdpf); } else { /* Recycle RX page */ mlx5e_page_release(rq, &xdpi.di, true); @@ -345,9 +365,9 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq) mlx5e_xdpi_fifo_pop(xdpi_fifo); if (is_redirect) { - xdp_return_frame(xdpi.xdpf); dma_unmap_single(sq->pdev, xdpi.dma_addr, xdpi.xdpf->len, DMA_TO_DEVICE); + xdp_return_frame(xdpi.xdpf); } else { /* Recycle RX page */ mlx5e_page_release(rq, &xdpi.di, false); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index ee27a7c8cd87..553956cadc8a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -34,13 +34,12 @@ #include "en.h" -#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \ - MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM))) #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN) #define MLX5E_XDP_TX_EMPTY_DS_COUNT \ (sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */) +int mlx5e_xdp_max_mtu(struct mlx5e_params *params); bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, void *va, u16 *rx_headroom, u32 *len); bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 76a3d01a489e..78dc8fe2a83c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1586,7 +1586,7 @@ static int mlx5e_get_module_info(struct net_device *netdev, break; case MLX5_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; - modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH; break; default: netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f7eb521db580..46157e2a1e5a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3777,7 +3777,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, if (params->xdp_prog && !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) { netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n", - new_mtu, MLX5E_XDP_MAX_MTU); + new_mtu, mlx5e_xdp_max_mtu(params)); err = -EINVAL; goto out; } @@ -4212,7 +4212,8 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog) if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) { netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n", - new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU); + new_channels.params.sw_mtu, + mlx5e_xdp_max_mtu(&new_channels.params)); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 21b7f05b16a5..361468e0435d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -317,10 +317,6 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, size -= offset + size - MLX5_EEPROM_PAGE_LENGTH; i2c_addr = MLX5_I2C_ADDR_LOW; - if (offset >= MLX5_EEPROM_PAGE_LENGTH) { - i2c_addr = MLX5_I2C_ADDR_HIGH; - offset -= MLX5_EEPROM_PAGE_LENGTH; - } MLX5_SET(mcia_reg, in, l, 0); MLX5_SET(mcia_reg, in, module, module_num); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index ffee38e36ce8..8648ca171254 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -27,7 +27,7 @@ #define MLXSW_PCI_SW_RESET 0xF0010 #define MLXSW_PCI_SW_RESET_RST_BIT BIT(0) -#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 13000 +#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 20000 #define MLXSW_PCI_SW_RESET_WAIT_MSECS 100 #define MLXSW_PCI_FW_READY 0xA1844 #define MLXSW_PCI_FW_READY_MASK 0xFFFF diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 9eb63300c1d3..6b8aa3761899 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3126,11 +3126,11 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev, if (err) return err; + mlxsw_sp_port->link.autoneg = autoneg; + if (!netif_running(dev)) return 0; - mlxsw_sp_port->link.autoneg = autoneg; - mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false); mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true); @@ -3316,7 +3316,7 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port) err = mlxsw_sp_port_ets_set(mlxsw_sp_port, MLXSW_REG_QEEC_HIERARCY_TC, i + 8, i, - false, 0); + true, 100); if (err) return err; } diff --git a/drivers/net/ethernet/netronome/nfp/abm/cls.c b/drivers/net/ethernet/netronome/nfp/abm/cls.c index 9852080cf454..ff3913085665 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/cls.c +++ b/drivers/net/ethernet/netronome/nfp/abm/cls.c @@ -39,7 +39,7 @@ nfp_abm_u32_check_knode(struct nfp_abm *abm, struct tc_cls_u32_knode *knode, } if (knode->sel->off || knode->sel->offshift || knode->sel->offmask || knode->sel->offoff || knode->fshift) { - NL_SET_ERR_MSG_MOD(extack, "variable offseting not supported"); + NL_SET_ERR_MSG_MOD(extack, "variable offsetting not supported"); return false; } if (knode->sel->hoff || knode->sel->hmask) { @@ -78,7 +78,7 @@ nfp_abm_u32_check_knode(struct nfp_abm *abm, struct tc_cls_u32_knode *knode, k = &knode->sel->keys[0]; if (k->offmask) { - NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offseting not supported"); + NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offsetting not supported"); return false; } if (k->off) { diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index a18149720aa2..cba5881b2746 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -673,7 +673,8 @@ static void netsec_process_tx(struct netsec_priv *priv) } static void *netsec_alloc_rx_data(struct netsec_priv *priv, - dma_addr_t *dma_handle, u16 *desc_len) + dma_addr_t *dma_handle, u16 *desc_len, + bool napi) { size_t total_len = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); size_t payload_len = NETSEC_RX_BUF_SZ; @@ -682,7 +683,7 @@ static void *netsec_alloc_rx_data(struct netsec_priv *priv, total_len += SKB_DATA_ALIGN(payload_len + NETSEC_SKB_PAD); - buf = napi_alloc_frag(total_len); + buf = napi ? napi_alloc_frag(total_len) : netdev_alloc_frag(total_len); if (!buf) return NULL; @@ -765,7 +766,8 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget) /* allocate a fresh buffer and map it to the hardware. * This will eventually replace the old buffer in the hardware */ - buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len); + buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len, + true); if (unlikely(!buf_addr)) break; @@ -1069,7 +1071,8 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv) void *buf; u16 len; - buf = netsec_alloc_rx_data(priv, &dma_handle, &len); + buf = netsec_alloc_rx_data(priv, &dma_handle, &len, + false); if (!buf) { netsec_uninit_pkt_dring(priv, NETSEC_RING_RX); goto err_out; diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c index b7dd4e3c760d..6d690678c20e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c @@ -140,7 +140,7 @@ static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode, p->des0 |= cpu_to_le32(RDES0_OWN); bfsize1 = min(bfsize, BUF_SIZE_2KiB - 1); - p->des1 |= cpu_to_le32(bfsize & RDES1_BUFFER1_SIZE_MASK); + p->des1 |= cpu_to_le32(bfsize1 & RDES1_BUFFER1_SIZE_MASK); if (mode == STMMAC_CHAIN_MODE) ndesc_rx_set_on_chain(p, end); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a26e36dbb5df..48712437d0da 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2616,8 +2616,6 @@ static int stmmac_open(struct net_device *dev) u32 chan; int ret; - stmmac_check_ether_addr(priv); - if (priv->hw->pcs != STMMAC_PCS_RGMII && priv->hw->pcs != STMMAC_PCS_TBI && priv->hw->pcs != STMMAC_PCS_RTBI) { @@ -4303,6 +4301,8 @@ int stmmac_dvr_probe(struct device *device, if (ret) goto error_hw_init; + stmmac_check_ether_addr(priv); + /* Configure real RX and TX queues */ netif_set_real_num_rx_queues(ndev, priv->plat->rx_queues_to_use); netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index d819e8eaba12..cc1e887e47b5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -159,6 +159,12 @@ static const struct dmi_system_id quark_pci_dmi[] = { }, .driver_data = (void *)&galileo_stmmac_dmi_data, }, + /* + * There are 2 types of SIMATIC IOT2000: IOT20202 and IOT2040. + * The asset tag "6ES7647-0AA00-0YA2" is only for IOT2020 which + * has only one pci network device while other asset tags are + * for IOT2040 which has two. + */ { .matches = { DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"), @@ -170,8 +176,6 @@ static const struct dmi_system_id quark_pci_dmi[] = { { .matches = { DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"), - DMI_EXACT_MATCH(DMI_BOARD_ASSET_TAG, - "6ES7647-0AA00-1YA2"), }, .driver_data = (void *)&iot2040_stmmac_dmi_data, }, diff --git a/drivers/net/phy/spi_ks8995.c b/drivers/net/phy/spi_ks8995.c index 92b64e254b44..7475cef17cf7 100644 --- a/drivers/net/phy/spi_ks8995.c +++ b/drivers/net/phy/spi_ks8995.c @@ -159,6 +159,14 @@ static const struct spi_device_id ks8995_id[] = { }; MODULE_DEVICE_TABLE(spi, ks8995_id); +static const struct of_device_id ks8895_spi_of_match[] = { + { .compatible = "micrel,ks8995" }, + { .compatible = "micrel,ksz8864" }, + { .compatible = "micrel,ksz8795" }, + { }, + }; +MODULE_DEVICE_TABLE(of, ks8895_spi_of_match); + static inline u8 get_chip_id(u8 val) { return (val >> ID1_CHIPID_S) & ID1_CHIPID_M; @@ -526,6 +534,7 @@ static int ks8995_remove(struct spi_device *spi) static struct spi_driver ks8995_driver = { .driver = { .name = "spi-ks8995", + .of_match_table = of_match_ptr(ks8895_spi_of_match), }, .probe = ks8995_probe, .remove = ks8995_remove, diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 9ce61b019aad..16963f7a88f7 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1156,6 +1156,13 @@ static int team_port_add(struct team *team, struct net_device *port_dev, return -EINVAL; } + if (netdev_has_upper_dev(dev, port_dev)) { + NL_SET_ERR_MSG(extack, "Device is already an upper device of the team interface"); + netdev_err(dev, "Device %s is already an upper device of the team interface\n", + portname); + return -EBUSY; + } + if (port_dev->features & NETIF_F_VLAN_CHALLENGED && vlan_uses_dev(dev)) { NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up"); diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index cd15c32b2e43..9ee4d7402ca2 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -875,6 +875,7 @@ static const struct net_device_ops vrf_netdev_ops = { .ndo_init = vrf_dev_init, .ndo_uninit = vrf_dev_uninit, .ndo_start_xmit = vrf_xmit, + .ndo_set_mac_address = eth_mac_addr, .ndo_get_stats64 = vrf_get_stats64, .ndo_add_slave = vrf_add_slave, .ndo_del_slave = vrf_del_slave, @@ -1274,6 +1275,7 @@ static void vrf_setup(struct net_device *dev) /* default to no qdisc; user can add if desired */ dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_NO_RX_HANDLER; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; /* VRF devices do not care about MTU, but if the MTU is set * too low then the ipv4 and ipv6 protocols are disabled diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c index 2b26f762fbc3..01acb6e53365 100644 --- a/drivers/nfc/st95hf/core.c +++ b/drivers/nfc/st95hf/core.c @@ -1074,6 +1074,12 @@ static const struct spi_device_id st95hf_id[] = { }; MODULE_DEVICE_TABLE(spi, st95hf_id); +static const struct of_device_id st95hf_spi_of_match[] = { + { .compatible = "st,st95hf" }, + { }, +}; +MODULE_DEVICE_TABLE(of, st95hf_spi_of_match); + static int st95hf_probe(struct spi_device *nfc_spi_dev) { int ret; @@ -1260,6 +1266,7 @@ static struct spi_driver st95hf_driver = { .driver = { .name = "st95hf", .owner = THIS_MODULE, + .of_match_table = of_match_ptr(st95hf_spi_of_match), }, .id_table = st95hf_id, .probe = st95hf_probe, diff --git a/drivers/of/of_net.c b/drivers/of/of_net.c index 810ab0fbcccb..d820f3edd431 100644 --- a/drivers/of/of_net.c +++ b/drivers/of/of_net.c @@ -7,7 +7,6 @@ */ #include <linux/etherdevice.h> #include <linux/kernel.h> -#include <linux/nvmem-consumer.h> #include <linux/of_net.h> #include <linux/phy.h> #include <linux/export.h> diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index 7617d21cb296..f63c5c871d3d 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -1595,6 +1595,7 @@ static int ctcm_new_device(struct ccwgroup_device *cgdev) if (priv->channel[direction] == NULL) { if (direction == CTCM_WRITE) channel_free(priv->channel[CTCM_READ]); + result = -ENODEV; goto out_dev; } priv->channel[direction]->netdev = dev; diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index e2f3b21cd72a..aa8bfd6f738c 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -449,6 +449,18 @@ static inline void eth_addr_dec(u8 *addr) } /** + * eth_addr_inc() - Increment the given MAC address. + * @addr: Pointer to a six-byte array containing Ethernet address to increment. + */ +static inline void eth_addr_inc(u8 *addr) +{ + u64 u = ether_addr_to_u64(addr); + + u++; + u64_to_ether_addr(u, addr); +} + +/** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure * @addr: Pointer to a six-byte array containing the Ethernet address diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 5ee7b30b4917..d2bc733a2ef1 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -316,6 +316,8 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, gfp_t flags); void nf_ct_tmpl_free(struct nf_conn *tmpl); +u32 nf_ct_get_id(const struct nf_conn *ct); + static inline void nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info) { diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 778087591983..a49edfdf47e8 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -75,6 +75,12 @@ bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig); +int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, + unsigned int dataoff, + const struct nf_hook_state *state, + u8 l4proto, + union nf_inet_addr *outer_daddr); + int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index eb15891f8b9f..3cad01ac64e4 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2032,7 +2032,8 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (match_kern) match_kern->match_size = ret; - if (WARN_ON(type == EBT_COMPAT_TARGET && size_left)) + /* rule should have no remaining data after target */ + if (type == EBT_COMPAT_TARGET && size_left) return -EINVAL; match32 = (struct compat_ebt_entry_mwt *) buf; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 88ce038dd495..6fdf1c195d8e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1183,25 +1183,39 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) return dst; } -static void ipv4_link_failure(struct sk_buff *skb) +static void ipv4_send_dest_unreach(struct sk_buff *skb) { struct ip_options opt; - struct rtable *rt; int res; /* Recompile ip options since IPCB may not be valid anymore. + * Also check we have a reasonable ipv4 header. */ - memset(&opt, 0, sizeof(opt)); - opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); + if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) || + ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) + return; - rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); - rcu_read_unlock(); + memset(&opt, 0, sizeof(opt)); + if (ip_hdr(skb)->ihl > 5) { + if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4)) + return; + opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); - if (res) - return; + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + rcu_read_unlock(); + if (res) + return; + } __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); +} + +static void ipv4_link_failure(struct sk_buff *skb) +{ + struct rtable *rt; + + ipv4_send_dest_unreach(skb); rt = skb_rtable(skb); if (rt) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index ba0fc4b18465..eeb4041fa5f9 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -49,6 +49,7 @@ static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static int comp_sack_nr_max = 255; static u32 u32_max_div_HZ = UINT_MAX / HZ; +static int one_day_secs = 24 * 3600; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -1151,7 +1152,9 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_tcp_min_rtt_wlen, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one_day_secs }, { .procname = "tcp_autocorking", diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index d43d076c98f5..1766325423b5 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -476,7 +476,7 @@ static int ip6addrlbl_valid_dump_req(const struct nlmsghdr *nlh, } if (nlmsg_attrlen(nlh, sizeof(*ifal))) { - NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump requewst"); + NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump request"); return -EINVAL; } diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index dc07fcc7938e..802db01e3075 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/netdevice.h> +#include <linux/etherdevice.h> #include <linux/skbuff.h> #include <net/ncsi.h> @@ -667,7 +668,10 @@ static int ncsi_rsp_handler_oem_bcm_gma(struct ncsi_request *nr) ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; memcpy(saddr.sa_data, &rsp->data[BCM_MAC_ADDR_OFFSET], ETH_ALEN); /* Increase mac address by 1 for BMC's address */ - saddr.sa_data[ETH_ALEN - 1]++; + eth_addr_inc((u8 *)saddr.sa_data); + if (!is_valid_ether_addr((const u8 *)saddr.sa_data)) + return -ENXIO; + ret = ops->ndo_set_mac_address(ndev, &saddr); if (ret < 0) netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n"); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 43bbaa32b1d6..14457551bcb4 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1678,7 +1678,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (!cp) { int v; - if (!sysctl_schedule_icmp(ipvs)) + if (ipip || !sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph)) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 82bfbeef46af..2a714527cde1 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -25,6 +25,7 @@ #include <linux/slab.h> #include <linux/random.h> #include <linux/jhash.h> +#include <linux/siphash.h> #include <linux/err.h> #include <linux/percpu.h> #include <linux/moduleparam.h> @@ -449,6 +450,40 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, } EXPORT_SYMBOL_GPL(nf_ct_invert_tuple); +/* Generate a almost-unique pseudo-id for a given conntrack. + * + * intentionally doesn't re-use any of the seeds used for hash + * table location, we assume id gets exposed to userspace. + * + * Following nf_conn items do not change throughout lifetime + * of the nf_conn after it has been committed to main hash table: + * + * 1. nf_conn address + * 2. nf_conn->ext address + * 3. nf_conn->master address (normally NULL) + * 4. tuple + * 5. the associated net namespace + */ +u32 nf_ct_get_id(const struct nf_conn *ct) +{ + static __read_mostly siphash_key_t ct_id_seed; + unsigned long a, b, c, d; + + net_get_random_once(&ct_id_seed, sizeof(ct_id_seed)); + + a = (unsigned long)ct; + b = (unsigned long)ct->master ^ net_hash_mix(nf_ct_net(ct)); + c = (unsigned long)ct->ext; + d = (unsigned long)siphash(&ct->tuplehash, sizeof(ct->tuplehash), + &ct_id_seed); +#ifdef CONFIG_64BIT + return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed); +#else + return siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &ct_id_seed); +#endif +} +EXPORT_SYMBOL_GPL(nf_ct_get_id); + static void clean_from_lists(struct nf_conn *ct) { @@ -982,12 +1017,9 @@ __nf_conntrack_confirm(struct sk_buff *skb) /* set conntrack timestamp, if enabled. */ tstamp = nf_conn_tstamp_find(ct); - if (tstamp) { - if (skb->tstamp == 0) - __net_timestamp(skb); + if (tstamp) + tstamp->start = ktime_get_real_ns(); - tstamp->start = ktime_to_ns(skb->tstamp); - } /* Since the lookup is lockless, hash insertion must be done after * starting the timer and setting the CONFIRMED bit. The RCU barriers * guarantee that no other CPU can find the conntrack before the above @@ -1350,6 +1382,7 @@ __nf_conntrack_alloc(struct net *net, /* save hash for reusing when confirming */ *(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash; ct->status = 0; + ct->timeout = 0; write_pnet(&ct->ct_net, net); memset(&ct->__nfct_init_offset[0], 0, offsetof(struct nf_conn, proto) - diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 66c596d287a5..d7f61b0547c6 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -29,6 +29,7 @@ #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/slab.h> +#include <linux/siphash.h> #include <linux/netfilter.h> #include <net/netlink.h> @@ -485,7 +486,9 @@ nla_put_failure: static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct) { - if (nla_put_be32(skb, CTA_ID, htonl((unsigned long)ct))) + __be32 id = (__force __be32)nf_ct_get_id(ct); + + if (nla_put_be32(skb, CTA_ID, id)) goto nla_put_failure; return 0; @@ -1286,8 +1289,9 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, } if (cda[CTA_ID]) { - u_int32_t id = ntohl(nla_get_be32(cda[CTA_ID])); - if (id != (u32)(unsigned long)ct) { + __be32 id = nla_get_be32(cda[CTA_ID]); + + if (id != (__force __be32)nf_ct_get_id(ct)) { nf_ct_put(ct); return -ENOENT; } @@ -2692,6 +2696,25 @@ nla_put_failure: static const union nf_inet_addr any_addr; +static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) +{ + static __read_mostly siphash_key_t exp_id_seed; + unsigned long a, b, c, d; + + net_get_random_once(&exp_id_seed, sizeof(exp_id_seed)); + + a = (unsigned long)exp; + b = (unsigned long)exp->helper; + c = (unsigned long)exp->master; + d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed); + +#ifdef CONFIG_64BIT + return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed); +#else + return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed); +#endif +} + static int ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) @@ -2739,7 +2762,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, } #endif if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) || - nla_put_be32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)) || + nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) || nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) || nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class))) goto nla_put_failure; @@ -3044,7 +3067,8 @@ static int ctnetlink_get_expect(struct net *net, struct sock *ctnl, if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); - if (ntohl(id) != (u32)(unsigned long)exp) { + + if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index b9403a266a2e..37bb530d848f 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -55,7 +55,7 @@ void nf_l4proto_log_invalid(const struct sk_buff *skb, struct va_format vaf; va_list args; - if (net->ct.sysctl_log_invalid != protonum || + if (net->ct.sysctl_log_invalid != protonum && net->ct.sysctl_log_invalid != IPPROTO_RAW) return; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 7df477996b16..9becac953587 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -103,49 +103,94 @@ int nf_conntrack_icmp_packet(struct nf_conn *ct, return NF_ACCEPT; } -/* Returns conntrack if it dealt with ICMP, and filled in skb fields */ -static int -icmp_error_message(struct nf_conn *tmpl, struct sk_buff *skb, - const struct nf_hook_state *state) +/* Check inner header is related to any of the existing connections */ +int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, + unsigned int dataoff, + const struct nf_hook_state *state, + u8 l4proto, union nf_inet_addr *outer_daddr) { struct nf_conntrack_tuple innertuple, origtuple; const struct nf_conntrack_tuple_hash *h; const struct nf_conntrack_zone *zone; enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; + union nf_inet_addr *ct_daddr; + enum ip_conntrack_dir dir; + struct nf_conn *ct; WARN_ON(skb_nfct(skb)); zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); /* Are they talking about one of our connections? */ - if (!nf_ct_get_tuplepr(skb, - skb_network_offset(skb) + ip_hdrlen(skb) - + sizeof(struct icmphdr), - PF_INET, state->net, &origtuple)) { - pr_debug("icmp_error_message: failed to get tuple\n"); + if (!nf_ct_get_tuplepr(skb, dataoff, + state->pf, state->net, &origtuple)) return -NF_ACCEPT; - } /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&innertuple, &origtuple)) { - pr_debug("icmp_error_message: no match\n"); + if (!nf_ct_invert_tuple(&innertuple, &origtuple)) return -NF_ACCEPT; - } - - ctinfo = IP_CT_RELATED; h = nf_conntrack_find_get(state->net, zone, &innertuple); - if (!h) { - pr_debug("icmp_error_message: no match\n"); + if (!h) + return -NF_ACCEPT; + + /* Consider: A -> T (=This machine) -> B + * Conntrack entry will look like this: + * Original: A->B + * Reply: B->T (SNAT case) OR A + * + * When this function runs, we got packet that looks like this: + * iphdr|icmphdr|inner_iphdr|l4header (tcp, udp, ..). + * + * Above nf_conntrack_find_get() makes lookup based on inner_hdr, + * so we should expect that destination of the found connection + * matches outer header destination address. + * + * In above example, we can consider these two cases: + * 1. Error coming in reply direction from B or M (middle box) to + * T (SNAT case) or A. + * Inner saddr will be B, dst will be T or A. + * The found conntrack will be reply tuple (B->T/A). + * 2. Error coming in original direction from A or M to B. + * Inner saddr will be A, inner daddr will be B. + * The found conntrack will be original tuple (A->B). + * + * In both cases, conntrack[dir].dst == inner.dst. + * + * A bogus packet could look like this: + * Inner: B->T + * Outer: B->X (other machine reachable by T). + * + * In this case, lookup yields connection A->B and will + * set packet from B->X as *RELATED*, even though no connection + * from X was ever seen. + */ + ct = nf_ct_tuplehash_to_ctrack(h); + dir = NF_CT_DIRECTION(h); + ct_daddr = &ct->tuplehash[dir].tuple.dst.u3; + if (!nf_inet_addr_cmp(outer_daddr, ct_daddr)) { + if (state->pf == AF_INET) { + nf_l4proto_log_invalid(skb, state->net, state->pf, + l4proto, + "outer daddr %pI4 != inner %pI4", + &outer_daddr->ip, &ct_daddr->ip); + } else if (state->pf == AF_INET6) { + nf_l4proto_log_invalid(skb, state->net, state->pf, + l4proto, + "outer daddr %pI6 != inner %pI6", + &outer_daddr->ip6, &ct_daddr->ip6); + } + nf_ct_put(ct); return -NF_ACCEPT; } - if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) + ctinfo = IP_CT_RELATED; + if (dir == IP_CT_DIR_REPLY) ctinfo += IP_CT_IS_REPLY; /* Update skb to refer to this connection */ - nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo); + nf_ct_set(skb, ct, ctinfo); return NF_ACCEPT; } @@ -162,11 +207,12 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { + union nf_inet_addr outer_daddr; const struct icmphdr *icmph; struct icmphdr _ih; /* Not enough header? */ - icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih); + icmph = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); if (icmph == NULL) { icmp_error_log(skb, state, "short packet"); return -NF_ACCEPT; @@ -199,7 +245,12 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, icmph->type != ICMP_REDIRECT) return NF_ACCEPT; - return icmp_error_message(tmpl, skb, state); + memset(&outer_daddr, 0, sizeof(outer_daddr)); + outer_daddr.ip = ip_hdr(skb)->daddr; + + dataoff += sizeof(*icmph); + return nf_conntrack_inet_error(tmpl, skb, dataoff, state, + IPPROTO_ICMP, &outer_daddr); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index bec4a3211658..c63ee3612855 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -123,51 +123,6 @@ int nf_conntrack_icmpv6_packet(struct nf_conn *ct, return NF_ACCEPT; } -static int -icmpv6_error_message(struct net *net, struct nf_conn *tmpl, - struct sk_buff *skb, - unsigned int icmp6off) -{ - struct nf_conntrack_tuple intuple, origtuple; - const struct nf_conntrack_tuple_hash *h; - enum ip_conntrack_info ctinfo; - struct nf_conntrack_zone tmp; - - WARN_ON(skb_nfct(skb)); - - /* Are they talking about one of our connections? */ - if (!nf_ct_get_tuplepr(skb, - skb_network_offset(skb) - + sizeof(struct ipv6hdr) - + sizeof(struct icmp6hdr), - PF_INET6, net, &origtuple)) { - pr_debug("icmpv6_error: Can't get tuple\n"); - return -NF_ACCEPT; - } - - /* Ordinarily, we'd expect the inverted tupleproto, but it's - been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&intuple, &origtuple)) { - pr_debug("icmpv6_error: Can't invert tuple\n"); - return -NF_ACCEPT; - } - - ctinfo = IP_CT_RELATED; - - h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp), - &intuple); - if (!h) { - pr_debug("icmpv6_error: no match\n"); - return -NF_ACCEPT; - } else { - if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) - ctinfo += IP_CT_IS_REPLY; - } - - /* Update skb to refer to this connection */ - nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo); - return NF_ACCEPT; -} static void icmpv6_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, @@ -182,6 +137,7 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, unsigned int dataoff, const struct nf_hook_state *state) { + union nf_inet_addr outer_daddr; const struct icmp6hdr *icmp6h; struct icmp6hdr _ih; int type; @@ -210,7 +166,11 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, if (icmp6h->icmp6_type >= 128) return NF_ACCEPT; - return icmpv6_error_message(state->net, tmpl, skb, dataoff); + memcpy(&outer_daddr.ip6, &ipv6_hdr(skb)->daddr, + sizeof(outer_daddr.ip6)); + dataoff += sizeof(*icmp6h); + return nf_conntrack_inet_error(tmpl, skb, dataoff, state, + IPPROTO_ICMPV6, &outer_daddr); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index af7dc6537758..000952719adf 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -415,9 +415,14 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple, case IPPROTO_ICMPV6: /* id is same for either direction... */ keyptr = &tuple->src.u.icmp.id; - min = range->min_proto.icmp.id; - range_size = ntohs(range->max_proto.icmp.id) - - ntohs(range->min_proto.icmp.id) + 1; + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) { + min = 0; + range_size = 65536; + } else { + min = ntohs(range->min_proto.icmp.id); + range_size = ntohs(range->max_proto.icmp.id) - + ntohs(range->min_proto.icmp.id) + 1; + } goto find_free_id; #if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE) case IPPROTO_GRE: diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ef7772e976cc..1606eaa5ae0d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1545,7 +1545,7 @@ static int nft_chain_parse_hook(struct net *net, if (IS_ERR(type)) return PTR_ERR(type); } - if (!(type->hook_mask & (1 << hook->num))) + if (hook->num > NF_MAX_HOOKS || !(type->hook_mask & (1 << hook->num))) return -EOPNOTSUPP; if (type->type == NFT_CHAIN_T_NAT && diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index b1f9c5303f02..0b3347570265 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -540,7 +540,7 @@ __build_packet_message(struct nfnl_log_net *log, goto nla_put_failure; } - if (skb->tstamp) { + if (hooknum <= NF_INET_FORWARD && skb->tstamp) { struct nfulnl_msg_packet_timestamp ts; struct timespec64 kts = ktime_to_timespec64(skb->tstamp); ts.sec = cpu_to_be64(kts.tv_sec); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 0dcc3592d053..e057b2961d31 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -582,7 +582,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (nfqnl_put_bridge(entry, skb) < 0) goto nla_put_failure; - if (entskb->tstamp) { + if (entry->state.hook <= NF_INET_FORWARD && entskb->tstamp) { struct nfqnl_msg_packet_timestamp ts; struct timespec64 kts = ktime_to_timespec64(entskb->tstamp); diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c index c13bcd0ab491..8dbb4d48f2ed 100644 --- a/net/netfilter/xt_time.c +++ b/net/netfilter/xt_time.c @@ -163,19 +163,24 @@ time_mt(const struct sk_buff *skb, struct xt_action_param *par) s64 stamp; /* - * We cannot use get_seconds() instead of __net_timestamp() here. + * We need real time here, but we can neither use skb->tstamp + * nor __net_timestamp(). + * + * skb->tstamp and skb->skb_mstamp_ns overlap, however, they + * use different clock types (real vs monotonic). + * * Suppose you have two rules: - * 1. match before 13:00 - * 2. match after 13:00 + * 1. match before 13:00 + * 2. match after 13:00 + * * If you match against processing time (get_seconds) it * may happen that the same packet matches both rules if - * it arrived at the right moment before 13:00. + * it arrived at the right moment before 13:00, so it would be + * better to check skb->tstamp and set it via __net_timestamp() + * if needed. This however breaks outgoing packets tx timestamp, + * and causes them to get delayed forever by fq packet scheduler. */ - if (skb->tstamp == 0) - __net_timestamp((struct sk_buff *)skb); - - stamp = ktime_to_ns(skb->tstamp); - stamp = div_s64(stamp, NSEC_PER_SEC); + stamp = get_seconds(); if (info->flags & XT_TIME_LOCAL_TZ) /* Adjust for local timezone */ diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c index 31cf37da4510..93c0437e6a5f 100644 --- a/net/rds/ib_fmr.c +++ b/net/rds/ib_fmr.c @@ -44,6 +44,17 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages) else pool = rds_ibdev->mr_1m_pool; + if (atomic_read(&pool->dirty_count) >= pool->max_items / 10) + queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10); + + /* Switch pools if one of the pool is reaching upper limit */ + if (atomic_read(&pool->dirty_count) >= pool->max_items * 9 / 10) { + if (pool->pool_type == RDS_IB_MR_8K_POOL) + pool = rds_ibdev->mr_1m_pool; + else + pool = rds_ibdev->mr_8k_pool; + } + ibmr = rds_ib_try_reuse_ibmr(pool); if (ibmr) return ibmr; diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 63c8d107adcf..d664e9ade74d 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -454,9 +454,6 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool) struct rds_ib_mr *ibmr = NULL; int iter = 0; - if (atomic_read(&pool->dirty_count) >= pool->max_items_soft / 10) - queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10); - while (1) { ibmr = rds_ib_reuse_mr(pool); if (ibmr) diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 7af4f99c4a93..094a6621f8e8 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -16,6 +16,7 @@ #include <linux/init.h> static struct sk_buff_head loopback_queue; +#define ROSE_LOOPBACK_LIMIT 1000 static struct timer_list loopback_timer; static void rose_set_loopback_timer(void); @@ -35,29 +36,27 @@ static int rose_loopback_running(void) int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh) { - struct sk_buff *skbn; + struct sk_buff *skbn = NULL; - skbn = skb_clone(skb, GFP_ATOMIC); + if (skb_queue_len(&loopback_queue) < ROSE_LOOPBACK_LIMIT) + skbn = skb_clone(skb, GFP_ATOMIC); - kfree_skb(skb); - - if (skbn != NULL) { + if (skbn) { + consume_skb(skb); skb_queue_tail(&loopback_queue, skbn); if (!rose_loopback_running()) rose_set_loopback_timer(); + } else { + kfree_skb(skb); } return 1; } - static void rose_set_loopback_timer(void) { - del_timer(&loopback_timer); - - loopback_timer.expires = jiffies + 10; - add_timer(&loopback_timer); + mod_timer(&loopback_timer, jiffies + 10); } static void rose_loopback_timer(struct timer_list *unused) @@ -68,8 +67,12 @@ static void rose_loopback_timer(struct timer_list *unused) struct sock *sk; unsigned short frametype; unsigned int lci_i, lci_o; + int count; - while ((skb = skb_dequeue(&loopback_queue)) != NULL) { + for (count = 0; count < ROSE_LOOPBACK_LIMIT; count++) { + skb = skb_dequeue(&loopback_queue); + if (!skb) + return; if (skb->len < ROSE_MIN_LEN) { kfree_skb(skb); continue; @@ -106,6 +109,8 @@ static void rose_loopback_timer(struct timer_list *unused) kfree_skb(skb); } } + if (!skb_queue_empty(&loopback_queue)) + mod_timer(&loopback_timer, jiffies + 1); } void __exit rose_loopback_clear(void) diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 4c6f9d0a00e7..c2c35cf4e308 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1161,19 +1161,19 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) * handle data received on the local endpoint * - may be called in interrupt context * - * The socket is locked by the caller and this prevents the socket from being - * shut down and the local endpoint from going away, thus sk_user_data will not - * be cleared until this function returns. + * [!] Note that as this is called from the encap_rcv hook, the socket is not + * held locked by the caller and nothing prevents sk_user_data on the UDP from + * being cleared in the middle of processing this function. * * Called with the RCU read lock held from the IP layer via UDP. */ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) { + struct rxrpc_local *local = rcu_dereference_sk_user_data(udp_sk); struct rxrpc_connection *conn; struct rxrpc_channel *chan; struct rxrpc_call *call = NULL; struct rxrpc_skb_priv *sp; - struct rxrpc_local *local = udp_sk->sk_user_data; struct rxrpc_peer *peer = NULL; struct rxrpc_sock *rx = NULL; unsigned int channel; @@ -1181,6 +1181,10 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) _enter("%p", udp_sk); + if (unlikely(!local)) { + kfree_skb(skb); + return 0; + } if (skb->tstamp == 0) skb->tstamp = ktime_get_real(); diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 15cf42d5b53a..01959db51445 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -304,7 +304,8 @@ nomem: ret = -ENOMEM; sock_error: mutex_unlock(&rxnet->local_mutex); - kfree(local); + if (local) + call_rcu(&local->rcu, rxrpc_local_rcu); _leave(" = %d", ret); return ERR_PTR(ret); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 9f3bdbc1e593..cc0256939eb6 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -904,7 +904,9 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) goto release_netdev; free_sw_resources: + up_read(&device_offload_lock); tls_sw_free_resources_rx(sk); + down_read(&device_offload_lock); release_ctx: ctx->priv_ctx_rx = NULL; release_netdev: @@ -939,8 +941,6 @@ void tls_device_offload_cleanup_rx(struct sock *sk) } out: up_read(&device_offload_lock); - kfree(tls_ctx->rx.rec_seq); - kfree(tls_ctx->rx.iv); tls_sw_release_resources_rx(sk); } diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 54c3a758f2a7..a3ebd4b02714 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -194,6 +194,9 @@ static void update_chksum(struct sk_buff *skb, int headln) static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln) { + struct sock *sk = skb->sk; + int delta; + skb_copy_header(nskb, skb); skb_put(nskb, skb->len); @@ -201,11 +204,15 @@ static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln) update_chksum(nskb, headln); nskb->destructor = skb->destructor; - nskb->sk = skb->sk; + nskb->sk = sk; skb->destructor = NULL; skb->sk = NULL; - refcount_add(nskb->truesize - skb->truesize, - &nskb->sk->sk_wmem_alloc); + + delta = nskb->truesize - skb->truesize; + if (likely(delta < 0)) + WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc)); + else if (delta) + refcount_add(delta, &sk->sk_wmem_alloc); } /* This function may be called after the user socket is already diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 9547cea0ce3b..478603f43964 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -293,11 +293,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) #endif } - if (ctx->rx_conf == TLS_SW) { - kfree(ctx->rx.rec_seq); - kfree(ctx->rx.iv); + if (ctx->rx_conf == TLS_SW) tls_sw_free_resources_rx(sk); - } #ifdef CONFIG_TLS_DEVICE if (ctx->rx_conf == TLS_HW) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index b50ced862f6f..29d6af43dd24 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2078,6 +2078,9 @@ void tls_sw_release_resources_rx(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + kfree(tls_ctx->rx.rec_seq); + kfree(tls_ctx->rx.iv); + if (ctx->aead_recv) { kfree_skb(ctx->recv_pkt); ctx->recv_pkt = NULL; diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests index 2dc95fda7ef7..ea5938ec009a 100755 --- a/tools/testing/selftests/net/run_afpackettests +++ b/tools/testing/selftests/net/run_afpackettests @@ -6,12 +6,14 @@ if [ $(id -u) != 0 ]; then exit 0 fi +ret=0 echo "--------------------" echo "running psock_fanout test" echo "--------------------" ./in_netns.sh ./psock_fanout if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi @@ -22,6 +24,7 @@ echo "--------------------" ./in_netns.sh ./psock_tpacket if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi @@ -32,6 +35,8 @@ echo "--------------------" ./in_netns.sh ./txring_overwrite if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi +exit $ret diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests index b093f39c298c..14e41faf2c57 100755 --- a/tools/testing/selftests/net/run_netsocktests +++ b/tools/testing/selftests/net/run_netsocktests @@ -7,7 +7,7 @@ echo "--------------------" ./socket if [ $? -ne 0 ]; then echo "[FAIL]" + exit 1 else echo "[PASS]" fi - diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index c9ff2b47bd1c..a37cb1192c6a 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh nft_nat.sh +TEST_PROGS := nft_trans_stress.sh nft_nat.sh conntrack_icmp_related.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/conntrack_icmp_related.sh b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh new file mode 100755 index 000000000000..b48e1833bc89 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh @@ -0,0 +1,283 @@ +#!/bin/bash +# +# check that ICMP df-needed/pkttoobig icmp are set are set as related +# state +# +# Setup is: +# +# nsclient1 -> nsrouter1 -> nsrouter2 -> nsclient2 +# MTU 1500, except for nsrouter2 <-> nsclient2 link (1280). +# ping nsclient2 from nsclient1, checking that conntrack did set RELATED +# 'fragmentation needed' icmp packet. +# +# In addition, nsrouter1 will perform IP masquerading, i.e. also +# check the icmp errors are propagated to the correct host as per +# nat of "established" icmp-echo "connection". + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +cleanup() { + for i in 1 2;do ip netns del nsclient$i;done + for i in 1 2;do ip netns del nsrouter$i;done +} + +ipv4() { + echo -n 192.168.$1.2 +} + +ipv6 () { + echo -n dead:$1::2 +} + +check_counter() +{ + ns=$1 + name=$2 + expect=$3 + local lret=0 + + cnt=$(ip netns exec $ns nft list counter inet filter "$name" | grep -q "$expect") + if [ $? -ne 0 ]; then + echo "ERROR: counter $name in $ns has unexpected value (expected $expect)" 1>&2 + ip netns exec $ns nft list counter inet filter "$name" 1>&2 + lret=1 + fi + + return $lret +} + +check_unknown() +{ + expect="packets 0 bytes 0" + for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + check_counter $n "unknown" "$expect" + if [ $? -ne 0 ] ;then + return 1 + fi + done + + return 0 +} + +for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + ip netns add $n + ip -net $n link set lo up +done + +DEV=veth0 +ip link add $DEV netns nsclient1 type veth peer name eth1 netns nsrouter1 +DEV=veth0 +ip link add $DEV netns nsclient2 type veth peer name eth1 netns nsrouter2 + +DEV=veth0 +ip link add $DEV netns nsrouter1 type veth peer name eth2 netns nsrouter2 + +DEV=veth0 +for i in 1 2; do + ip -net nsclient$i link set $DEV up + ip -net nsclient$i addr add $(ipv4 $i)/24 dev $DEV + ip -net nsclient$i addr add $(ipv6 $i)/64 dev $DEV +done + +ip -net nsrouter1 link set eth1 up +ip -net nsrouter1 link set veth0 up + +ip -net nsrouter2 link set eth1 up +ip -net nsrouter2 link set eth2 up + +ip -net nsclient1 route add default via 192.168.1.1 +ip -net nsclient1 -6 route add default via dead:1::1 + +ip -net nsclient2 route add default via 192.168.2.1 +ip -net nsclient2 route add default via dead:2::1 + +i=3 +ip -net nsrouter1 addr add 192.168.1.1/24 dev eth1 +ip -net nsrouter1 addr add 192.168.3.1/24 dev veth0 +ip -net nsrouter1 addr add dead:1::1/64 dev eth1 +ip -net nsrouter1 addr add dead:3::1/64 dev veth0 +ip -net nsrouter1 route add default via 192.168.3.10 +ip -net nsrouter1 -6 route add default via dead:3::10 + +ip -net nsrouter2 addr add 192.168.2.1/24 dev eth1 +ip -net nsrouter2 addr add 192.168.3.10/24 dev eth2 +ip -net nsrouter2 addr add dead:2::1/64 dev eth1 +ip -net nsrouter2 addr add dead:3::10/64 dev eth2 +ip -net nsrouter2 route add default via 192.168.3.1 +ip -net nsrouter2 route add default via dead:3::1 + +sleep 2 +for i in 4 6; do + ip netns exec nsrouter1 sysctl -q net.ipv$i.conf.all.forwarding=1 + ip netns exec nsrouter2 sysctl -q net.ipv$i.conf.all.forwarding=1 +done + +for netns in nsrouter1 nsrouter2; do +ip netns exec $netns nft -f - <<EOF +table inet filter { + counter unknown { } + counter related { } + chain forward { + type filter hook forward priority 0; policy accept; + meta l4proto icmpv6 icmpv6 type "packet-too-big" ct state "related" counter name "related" accept + meta l4proto icmp icmp type "destination-unreachable" ct state "related" counter name "related" accept + meta l4proto { icmp, icmpv6 } ct state new,established accept + counter name "unknown" drop + } +} +EOF +done + +ip netns exec nsclient1 nft -f - <<EOF +table inet filter { + counter unknown { } + counter related { } + chain input { + type filter hook input priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "related" counter name "related" accept + counter name "unknown" drop + } +} +EOF + +ip netns exec nsclient2 nft -f - <<EOF +table inet filter { + counter unknown { } + counter new { } + counter established { } + + chain input { + type filter hook input priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "new" counter name "new" accept + meta l4proto { icmp, icmpv6 } ct state "established" counter name "established" accept + counter name "unknown" drop + } + chain output { + type filter hook output priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "new" counter name "new" + meta l4proto { icmp, icmpv6 } ct state "established" counter name "established" + counter name "unknown" drop + } +} +EOF + + +# make sure NAT core rewrites adress of icmp error if nat is used according to +# conntrack nat information (icmp error will be directed at nsrouter1 address, +# but it needs to be routed to nsclient1 address). +ip netns exec nsrouter1 nft -f - <<EOF +table ip nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + ip protocol icmp oifname "veth0" counter masquerade + } +} +table ip6 nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + ip6 nexthdr icmpv6 oifname "veth0" counter masquerade + } +} +EOF + +ip netns exec nsrouter2 ip link set eth1 mtu 1280 +ip netns exec nsclient2 ip link set veth0 mtu 1280 +sleep 1 + +ip netns exec nsclient1 ping -c 1 -s 1000 -q -M do 192.168.2.2 >/dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ip routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi +ip netns exec nsclient1 ping6 -q -c 1 -s 1000 dead:2::2 >/dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ipv6 routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi + +check_unknown +if [ $? -ne 0 ]; then + ret=1 +fi + +expect="packets 0 bytes 0" +for netns in nsrouter1 nsrouter2 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +expect="packets 2 bytes 2076" +check_counter nsclient2 "new" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +ip netns exec nsclient1 ping -q -c 1 -s 1300 -M do 192.168.2.2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +# nsrouter2 should have generated the icmp error, so +# related counter should be 0 (its in forward). +expect="packets 0 bytes 0" +check_counter "nsrouter2" "related" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +# but nsrouter1 should have seen it, same for nsclient1. +expect="packets 1 bytes 576" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +ip netns exec nsclient1 ping6 -c 1 -s 1300 dead:2::2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping6 should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +expect="packets 2 bytes 1856" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +if [ $ret -eq 0 ];then + echo "PASS: icmp mtu error had RELATED state" +else + echo "ERROR: icmp error RELATED state test has failed" +fi + +cleanup +exit $ret diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 8ec76681605c..3194007cf8d1 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -321,6 +321,7 @@ EOF test_masquerade6() { + local natflags=$1 local lret=0 ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null @@ -354,13 +355,13 @@ ip netns exec ns0 nft -f - <<EOF table ip6 nat { chain postrouting { type nat hook postrouting priority 0; policy accept; - meta oif veth0 masquerade + meta oif veth0 masquerade $natflags } } EOF ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading" + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags" lret=1 fi @@ -397,19 +398,26 @@ EOF fi done + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags (attempt 2)" + lret=1 + fi + ip netns exec ns0 nft flush chain ip6 nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush ip6 nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2" + test $lret -eq 0 && echo "PASS: IPv6 masquerade $natflags for ns2" return $lret } test_masquerade() { + local natflags=$1 local lret=0 ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null @@ -417,7 +425,7 @@ test_masquerade() ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: canot ping ns1 from ns2" + echo "ERROR: cannot ping ns1 from ns2 $natflags" lret=1 fi @@ -443,13 +451,13 @@ ip netns exec ns0 nft -f - <<EOF table ip nat { chain postrouting { type nat hook postrouting priority 0; policy accept; - meta oif veth0 masquerade + meta oif veth0 masquerade $natflags } } EOF ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading" + echo "ERROR: cannot ping ns1 from ns2 with active ip masquere $natflags" lret=1 fi @@ -485,13 +493,19 @@ EOF fi done + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip masquerade $natflags (attempt 2)" + lret=1 + fi + ip netns exec ns0 nft flush chain ip nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IP masquerade for ns2" + test $lret -eq 0 && echo "PASS: IP masquerade $natflags for ns2" return $lret } @@ -750,8 +764,12 @@ test_local_dnat test_local_dnat6 reset_counters -test_masquerade -test_masquerade6 +test_masquerade "" +test_masquerade6 "" + +reset_counters +test_masquerade "fully-random" +test_masquerade6 "fully-random" reset_counters test_redirect |