diff options
135 files changed, 3135 insertions, 1403 deletions
diff --git a/Documentation/devicetree/bindings/net/micrel-ksz9021.txt b/Documentation/devicetree/bindings/net/micrel-ksz9021.txt new file mode 100644 index 00000000000..997a63f1aea --- /dev/null +++ b/Documentation/devicetree/bindings/net/micrel-ksz9021.txt @@ -0,0 +1,49 @@ +Micrel KSZ9021 Gigabit Ethernet PHY + +Some boards require special tuning values, particularly when it comes to +clock delays. You can specify clock delay values by adding +micrel-specific properties to an Ethernet OF device node. + +All skew control options are specified in picoseconds. The minimum +value is 0, and the maximum value is 3000. + +Optional properties: + - rxc-skew-ps : Skew control of RXC pad + - rxdv-skew-ps : Skew control of RX CTL pad + - txc-skew-ps : Skew control of TXC pad + - txen-skew-ps : Skew control of TX_CTL pad + - rxd0-skew-ps : Skew control of RX data 0 pad + - rxd1-skew-ps : Skew control of RX data 1 pad + - rxd2-skew-ps : Skew control of RX data 2 pad + - rxd3-skew-ps : Skew control of RX data 3 pad + - txd0-skew-ps : Skew control of TX data 0 pad + - txd1-skew-ps : Skew control of TX data 1 pad + - txd2-skew-ps : Skew control of TX data 2 pad + - txd3-skew-ps : Skew control of TX data 3 pad + +Examples: + + /* Attach to an Ethernet device with autodetected PHY */ + &enet { + rxc-skew-ps = <3000>; + rxdv-skew-ps = <0>; + txc-skew-ps = <3000>; + txen-skew-ps = <0>; + status = "okay"; + }; + + /* Attach to an explicitly-specified PHY */ + mdio { + phy0: ethernet-phy@0 { + rxc-skew-ps = <3000>; + rxdv-skew-ps = <0>; + txc-skew-ps = <3000>; + txen-skew-ps = <0>; + reg = <0>; + }; + }; + ethernet@70000 { + status = "okay"; + phy = <&phy0>; + phy-mode = "rgmii-id"; + }; diff --git a/Documentation/networking/tproxy.txt b/Documentation/networking/tproxy.txt index 7b5996d9357..ec11429e1d4 100644 --- a/Documentation/networking/tproxy.txt +++ b/Documentation/networking/tproxy.txt @@ -2,9 +2,8 @@ Transparent proxy support ========================= This feature adds Linux 2.2-like transparent proxy support to current kernels. -To use it, enable NETFILTER_TPROXY, the socket match and the TPROXY target in -your kernel config. You will need policy routing too, so be sure to enable that -as well. +To use it, enable the socket match and the TPROXY target in your kernel config. +You will need policy routing too, so be sure to enable that as well. 1. Making non-local sockets work diff --git a/MAINTAINERS b/MAINTAINERS index 1c6f9db0de7..a83dd4f10bb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7973,6 +7973,12 @@ F: arch/m68k/sun3*/ F: arch/m68k/include/asm/sun3* F: drivers/net/ethernet/i825xx/sun3* +SUNDANCE NETWORK DRIVER +M: Denis Kirjanov <kda@linux-powerpc.org> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/dlink/sundance.c + SUPERH M: Paul Mundt <lethal@linux-sh.org> L: linux-sh@vger.kernel.org diff --git a/arch/arm/mach-pxa/icontrol.c b/arch/arm/mach-pxa/icontrol.c index fe31bfcbb8d..c98511c5abd 100644 --- a/arch/arm/mach-pxa/icontrol.c +++ b/arch/arm/mach-pxa/icontrol.c @@ -73,9 +73,6 @@ static struct pxa2xx_spi_chip mcp251x_chip_info4 = { static struct mcp251x_platform_data mcp251x_info = { .oscillator_frequency = 16E6, - .board_specific_setup = NULL, - .power_enable = NULL, - .transceiver_enable = NULL }; static struct spi_board_info mcp251x_board_info[] = { diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c index f5d43643456..04a0aea2387 100644 --- a/arch/arm/mach-pxa/zeus.c +++ b/arch/arm/mach-pxa/zeus.c @@ -29,6 +29,8 @@ #include <linux/i2c/pca953x.h> #include <linux/apm-emulation.h> #include <linux/can/platform/mcp251x.h> +#include <linux/regulator/fixed.h> +#include <linux/regulator/machine.h> #include <asm/mach-types.h> #include <asm/suspend.h> @@ -391,33 +393,34 @@ static struct pxa2xx_spi_master pxa2xx_spi_ssp3_master_info = { }; /* CAN bus on SPI */ -static int zeus_mcp2515_setup(struct spi_device *sdev) -{ - int err; - - err = gpio_request(ZEUS_CAN_SHDN_GPIO, "CAN shutdown"); - if (err) - return err; +static struct regulator_consumer_supply can_regulator_consumer = + REGULATOR_SUPPLY("vdd", "spi3.0"); - err = gpio_direction_output(ZEUS_CAN_SHDN_GPIO, 1); - if (err) { - gpio_free(ZEUS_CAN_SHDN_GPIO); - return err; - } +static struct regulator_init_data can_regulator_init_data = { + .constraints = { + .valid_ops_mask = REGULATOR_CHANGE_STATUS, + }, + .consumer_supplies = &can_regulator_consumer, + .num_consumer_supplies = 1, +}; - return 0; -} +static struct fixed_voltage_config can_regulator_pdata = { + .supply_name = "CAN_SHDN", + .microvolts = 3300000, + .gpio = ZEUS_CAN_SHDN_GPIO, + .init_data = &can_regulator_init_data, +}; -static int zeus_mcp2515_transceiver_enable(int enable) -{ - gpio_set_value(ZEUS_CAN_SHDN_GPIO, !enable); - return 0; -} +static struct platform_device can_regulator_device = { + .name = "reg-fixed-volage", + .id = -1, + .dev = { + .platform_data = &can_regulator_pdata, + }, +}; static struct mcp251x_platform_data zeus_mcp2515_pdata = { .oscillator_frequency = 16*1000*1000, - .board_specific_setup = zeus_mcp2515_setup, - .power_enable = zeus_mcp2515_transceiver_enable, }; static struct spi_board_info zeus_spi_board_info[] = { @@ -516,6 +519,7 @@ static struct platform_device *zeus_devices[] __initdata = { &zeus_leds_device, &zeus_pcmcia_device, &zeus_max6369_device, + &can_regulator_device, }; /* AC'97 */ diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c index c5be60d85e4..3a6ffa250fb 100644 --- a/arch/arm/mach-shmobile/board-armadillo800eva.c +++ b/arch/arm/mach-shmobile/board-armadillo800eva.c @@ -358,7 +358,6 @@ static struct platform_device usbhsf_device = { static struct sh_eth_plat_data sh_eth_platdata = { .phy = 0x00, /* LAN8710A */ .edmac_endian = EDMAC_LITTLE_ENDIAN, - .register_type = SH_ETH_REG_GIGABIT, .phy_interface = PHY_INTERFACE_MODE_MII, }; diff --git a/arch/arm/mach-shmobile/board-bockw.c b/arch/arm/mach-shmobile/board-bockw.c index 3354a85c90f..fa8885b2d5a 100644 --- a/arch/arm/mach-shmobile/board-bockw.c +++ b/arch/arm/mach-shmobile/board-bockw.c @@ -89,7 +89,6 @@ static struct sh_mobile_sdhi_info sdhi0_info = { static struct sh_eth_plat_data ether_platform_data __initdata = { .phy = 0x01, .edmac_endian = EDMAC_LITTLE_ENDIAN, - .register_type = SH_ETH_REG_FAST_RCAR, .phy_interface = PHY_INTERFACE_MODE_RMII, /* * Although the LINK signal is available on the board, it's connected to diff --git a/arch/sh/boards/board-espt.c b/arch/sh/boards/board-espt.c index 4d94dff9015..7291e2f11a4 100644 --- a/arch/sh/boards/board-espt.c +++ b/arch/sh/boards/board-espt.c @@ -80,7 +80,6 @@ static struct resource sh_eth_resources[] = { static struct sh_eth_plat_data sh7763_eth_pdata = { .phy = 0, .edmac_endian = EDMAC_LITTLE_ENDIAN, - .register_type = SH_ETH_REG_GIGABIT, .phy_interface = PHY_INTERFACE_MODE_MII, }; diff --git a/arch/sh/boards/board-sh7757lcr.c b/arch/sh/boards/board-sh7757lcr.c index 4f114d1cd01..25c5a932f9f 100644 --- a/arch/sh/boards/board-sh7757lcr.c +++ b/arch/sh/boards/board-sh7757lcr.c @@ -77,7 +77,6 @@ static struct resource sh_eth0_resources[] = { static struct sh_eth_plat_data sh7757_eth0_pdata = { .phy = 1, .edmac_endian = EDMAC_LITTLE_ENDIAN, - .register_type = SH_ETH_REG_FAST_SH4, .set_mdio_gate = sh7757_eth_set_mdio_gate, }; @@ -106,7 +105,6 @@ static struct resource sh_eth1_resources[] = { static struct sh_eth_plat_data sh7757_eth1_pdata = { .phy = 1, .edmac_endian = EDMAC_LITTLE_ENDIAN, - .register_type = SH_ETH_REG_FAST_SH4, .set_mdio_gate = sh7757_eth_set_mdio_gate, }; @@ -151,7 +149,6 @@ static struct resource sh_eth_giga0_resources[] = { static struct sh_eth_plat_data sh7757_eth_giga0_pdata = { .phy = 18, .edmac_endian = EDMAC_LITTLE_ENDIAN, - .register_type = SH_ETH_REG_GIGABIT, .set_mdio_gate = sh7757_eth_giga_set_mdio_gate, .phy_interface = PHY_INTERFACE_MODE_RGMII_ID, }; @@ -186,7 +183,6 @@ static struct resource sh_eth_giga1_resources[] = { static struct sh_eth_plat_data sh7757_eth_giga1_pdata = { .phy = 19, .edmac_endian = EDMAC_LITTLE_ENDIAN, - .register_type = SH_ETH_REG_GIGABIT, .set_mdio_gate = sh7757_eth_giga_set_mdio_gate, .phy_interface = PHY_INTERFACE_MODE_RGMII_ID, }; diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index 61fade0ffa9..a4f630f04ea 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -159,7 +159,6 @@ static struct resource sh_eth_resources[] = { static struct sh_eth_plat_data sh_eth_plat = { .phy = 0x1f, /* SMSC LAN8700 */ .edmac_endian = EDMAC_LITTLE_ENDIAN, - .register_type = SH_ETH_REG_FAST_SH4, .phy_interface = PHY_INTERFACE_MODE_MII, .ether_link_active_low = 1 }; diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c index b70180ef3e2..21e4230659a 100644 --- a/arch/sh/boards/mach-se/7724/setup.c +++ b/arch/sh/boards/mach-se/7724/setup.c @@ -365,7 +365,7 @@ static struct platform_device keysc_device = { static struct resource sh_eth_resources[] = { [0] = { .start = SH_ETH_ADDR, - .end = SH_ETH_ADDR + 0x1FC, + .end = SH_ETH_ADDR + 0x1FC - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -377,6 +377,7 @@ static struct resource sh_eth_resources[] = { static struct sh_eth_plat_data sh_eth_plat = { .phy = 0x1f, /* SMSC LAN8187 */ .edmac_endian = EDMAC_LITTLE_ENDIAN, + .phy_interface = PHY_INTERFACE_MODE_MII, }; static struct platform_device sh_eth_device = { diff --git a/arch/sh/boards/mach-sh7763rdp/setup.c b/arch/sh/boards/mach-sh7763rdp/setup.c index 50ba481fa24..2c8fb04685d 100644 --- a/arch/sh/boards/mach-sh7763rdp/setup.c +++ b/arch/sh/boards/mach-sh7763rdp/setup.c @@ -88,7 +88,6 @@ static struct resource sh_eth_resources[] = { static struct sh_eth_plat_data sh7763_eth_pdata = { .phy = 1, .edmac_endian = EDMAC_LITTLE_ENDIAN, - .register_type = SH_ETH_REG_GIGABIT, .phy_interface = PHY_INTERFACE_MODE_MII, }; diff --git a/arch/sh/kernel/cpu/sh2/setup-sh7619.c b/arch/sh/kernel/cpu/sh2/setup-sh7619.c index bb11e192517..4df4d4ffe39 100644 --- a/arch/sh/kernel/cpu/sh2/setup-sh7619.c +++ b/arch/sh/kernel/cpu/sh2/setup-sh7619.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/serial.h> #include <linux/serial_sci.h> +#include <linux/sh_eth.h> #include <linux/sh_timer.h> #include <linux/io.h> @@ -110,10 +111,16 @@ static struct platform_device scif2_device = { }, }; +static struct sh_eth_plat_data eth_platform_data = { + .phy = 1, + .edmac_endian = EDMAC_LITTLE_ENDIAN, + .phy_interface = PHY_INTERFACE_MODE_MII, +}; + static struct resource eth_resources[] = { [0] = { .start = 0xfb000000, - .end = 0xfb0001c8, + .end = 0xfb0001c7, .flags = IORESOURCE_MEM, }, [1] = { @@ -127,7 +134,7 @@ static struct platform_device eth_device = { .name = "sh7619-ether", .id = -1, .dev = { - .platform_data = (void *)1, + .platform_data = ð_platform_data, }, .num_resources = ARRAY_SIZE(eth_resources), .resource = eth_resources, diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index dbbe97ae121..3b1ff614870 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -1355,7 +1355,7 @@ static int at91_can_probe(struct platform_device *pdev) if (at91_is_sam9263(priv)) dev->sysfs_groups[0] = &at91_sysfs_attr_group; - dev_set_drvdata(&pdev->dev, dev); + platform_set_drvdata(pdev, dev); SET_NETDEV_DEV(dev, &pdev->dev); err = register_candev(dev); diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c index c6f838d922a..294ced3cc22 100644 --- a/drivers/net/can/c_can/c_can_platform.c +++ b/drivers/net/can/c_can/c_can_platform.c @@ -195,7 +195,7 @@ static int c_can_plat_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 1); priv->raminit_ctrlreg = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(priv->raminit_ctrlreg) || priv->instance < 0) + if (IS_ERR(priv->raminit_ctrlreg) || (int)priv->instance < 0) dev_info(&pdev->dev, "control memory is not used for raminit\n"); else priv->raminit = c_can_hw_raminit; diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index c48174ed49c..71c677e651d 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -1083,7 +1083,7 @@ static int flexcan_probe(struct platform_device *pdev) netif_napi_add(dev, &priv->napi, flexcan_poll, FLEXCAN_NAPI_WEIGHT); - dev_set_drvdata(&pdev->dev, dev); + platform_set_drvdata(pdev, dev); SET_NETDEV_DEV(dev, &pdev->dev); err = register_flexcandev(dev); diff --git a/drivers/net/can/mcp251x.c b/drivers/net/can/mcp251x.c index 8cda23bf061..fe7dd696957 100644 --- a/drivers/net/can/mcp251x.c +++ b/drivers/net/can/mcp251x.c @@ -37,9 +37,6 @@ * * static struct mcp251x_platform_data mcp251x_info = { * .oscillator_frequency = 8000000, - * .board_specific_setup = &mcp251x_setup, - * .power_enable = mcp251x_power_enable, - * .transceiver_enable = NULL, * }; * * static struct spi_board_info spi_board_info[] = { @@ -76,6 +73,7 @@ #include <linux/slab.h> #include <linux/spi/spi.h> #include <linux/uaccess.h> +#include <linux/regulator/consumer.h> /* SPI interface instruction set */ #define INSTRUCTION_WRITE 0x02 @@ -264,6 +262,8 @@ struct mcp251x_priv { #define AFTER_SUSPEND_POWER 4 #define AFTER_SUSPEND_RESTART 8 int restart_tx; + struct regulator *power; + struct regulator *transceiver; }; #define MCP251X_IS(_model) \ @@ -667,16 +667,25 @@ static int mcp251x_hw_probe(struct spi_device *spi) return (st1 == 0x80 && st2 == 0x07) ? 1 : 0; } +static int mcp251x_power_enable(struct regulator *reg, int enable) +{ + if (IS_ERR(reg)) + return 0; + + if (enable) + return regulator_enable(reg); + else + return regulator_disable(reg); +} + static void mcp251x_open_clean(struct net_device *net) { struct mcp251x_priv *priv = netdev_priv(net); struct spi_device *spi = priv->spi; - struct mcp251x_platform_data *pdata = spi->dev.platform_data; free_irq(spi->irq, priv); mcp251x_hw_sleep(spi); - if (pdata->transceiver_enable) - pdata->transceiver_enable(0); + mcp251x_power_enable(priv->transceiver, 0); close_candev(net); } @@ -684,7 +693,6 @@ static int mcp251x_stop(struct net_device *net) { struct mcp251x_priv *priv = netdev_priv(net); struct spi_device *spi = priv->spi; - struct mcp251x_platform_data *pdata = spi->dev.platform_data; close_candev(net); @@ -704,8 +712,7 @@ static int mcp251x_stop(struct net_device *net) mcp251x_hw_sleep(spi); - if (pdata->transceiver_enable) - pdata->transceiver_enable(0); + mcp251x_power_enable(priv->transceiver, 0); priv->can.state = CAN_STATE_STOPPED; @@ -928,8 +935,7 @@ static int mcp251x_open(struct net_device *net) { struct mcp251x_priv *priv = netdev_priv(net); struct spi_device *spi = priv->spi; - struct mcp251x_platform_data *pdata = spi->dev.platform_data; - unsigned long flags; + unsigned long flags = IRQF_ONESHOT | IRQF_TRIGGER_FALLING; int ret; ret = open_candev(net); @@ -939,25 +945,17 @@ static int mcp251x_open(struct net_device *net) } mutex_lock(&priv->mcp_lock); - if (pdata->transceiver_enable) - pdata->transceiver_enable(1); + mcp251x_power_enable(priv->transceiver, 1); priv->force_quit = 0; priv->tx_skb = NULL; priv->tx_len = 0; - flags = IRQF_ONESHOT; - if (pdata->irq_flags) - flags |= pdata->irq_flags; - else - flags |= IRQF_TRIGGER_FALLING; - ret = request_threaded_irq(spi->irq, NULL, mcp251x_can_ist, flags, DEVICE_NAME, priv); if (ret) { dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq); - if (pdata->transceiver_enable) - pdata->transceiver_enable(0); + mcp251x_power_enable(priv->transceiver, 0); close_candev(net); goto open_unlock; } @@ -1026,6 +1024,19 @@ static int mcp251x_can_probe(struct spi_device *spi) CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY; priv->model = spi_get_device_id(spi)->driver_data; priv->net = net; + + priv->power = devm_regulator_get(&spi->dev, "vdd"); + priv->transceiver = devm_regulator_get(&spi->dev, "xceiver"); + if ((PTR_ERR(priv->power) == -EPROBE_DEFER) || + (PTR_ERR(priv->transceiver) == -EPROBE_DEFER)) { + ret = -EPROBE_DEFER; + goto error_power; + } + + ret = mcp251x_power_enable(priv->power, 1); + if (ret) + goto error_power; + spi_set_drvdata(spi, priv); priv->spi = spi; @@ -1068,30 +1079,24 @@ static int mcp251x_can_probe(struct spi_device *spi) } } - if (pdata->power_enable) - pdata->power_enable(1); - - /* Call out to platform specific setup */ - if (pdata->board_specific_setup) - pdata->board_specific_setup(spi); - SET_NETDEV_DEV(net, &spi->dev); /* Configure the SPI bus */ - spi->mode = SPI_MODE_0; + spi->mode = spi->mode ? : SPI_MODE_0; + if (mcp251x_is_2510(spi)) + spi->max_speed_hz = spi->max_speed_hz ? : 5 * 1000 * 1000; + else + spi->max_speed_hz = spi->max_speed_hz ? : 10 * 1000 * 1000; spi->bits_per_word = 8; spi_setup(spi); /* Here is OK to not lock the MCP, no one knows about it yet */ if (!mcp251x_hw_probe(spi)) { - dev_info(&spi->dev, "Probe failed\n"); + ret = -ENODEV; goto error_probe; } mcp251x_hw_sleep(spi); - if (pdata->transceiver_enable) - pdata->transceiver_enable(0); - ret = register_candev(net); if (ret) goto error_probe; @@ -1109,13 +1114,13 @@ error_rx_buf: if (!mcp251x_enable_dma) kfree(priv->spi_tx_buf); error_tx_buf: - free_candev(net); if (mcp251x_enable_dma) dma_free_coherent(&spi->dev, PAGE_SIZE, priv->spi_tx_buf, priv->spi_tx_dma); + mcp251x_power_enable(priv->power, 0); +error_power: + free_candev(net); error_alloc: - if (pdata->power_enable) - pdata->power_enable(0); dev_err(&spi->dev, "probe failed\n"); error_out: return ret; @@ -1123,12 +1128,10 @@ error_out: static int mcp251x_can_remove(struct spi_device *spi) { - struct mcp251x_platform_data *pdata = spi->dev.platform_data; struct mcp251x_priv *priv = spi_get_drvdata(spi); struct net_device *net = priv->net; unregister_candev(net); - free_candev(net); if (mcp251x_enable_dma) { dma_free_coherent(&spi->dev, PAGE_SIZE, @@ -1138,8 +1141,9 @@ static int mcp251x_can_remove(struct spi_device *spi) kfree(priv->spi_rx_buf); } - if (pdata->power_enable) - pdata->power_enable(0); + mcp251x_power_enable(priv->power, 0); + + free_candev(net); return 0; } @@ -1149,7 +1153,6 @@ static int mcp251x_can_remove(struct spi_device *spi) static int mcp251x_can_suspend(struct device *dev) { struct spi_device *spi = to_spi_device(dev); - struct mcp251x_platform_data *pdata = spi->dev.platform_data; struct mcp251x_priv *priv = spi_get_drvdata(spi); struct net_device *net = priv->net; @@ -1163,15 +1166,14 @@ static int mcp251x_can_suspend(struct device *dev) netif_device_detach(net); mcp251x_hw_sleep(spi); - if (pdata->transceiver_enable) - pdata->transceiver_enable(0); + mcp251x_power_enable(priv->transceiver, 0); priv->after_suspend = AFTER_SUSPEND_UP; } else { priv->after_suspend = AFTER_SUSPEND_DOWN; } - if (pdata->power_enable) { - pdata->power_enable(0); + if (!IS_ERR(priv->power)) { + regulator_disable(priv->power); priv->after_suspend |= AFTER_SUSPEND_POWER; } @@ -1181,16 +1183,14 @@ static int mcp251x_can_suspend(struct device *dev) static int mcp251x_can_resume(struct device *dev) { struct spi_device *spi = to_spi_device(dev); - struct mcp251x_platform_data *pdata = spi->dev.platform_data; struct mcp251x_priv *priv = spi_get_drvdata(spi); if (priv->after_suspend & AFTER_SUSPEND_POWER) { - pdata->power_enable(1); + mcp251x_power_enable(priv->power, 1); queue_work(priv->wq, &priv->restart_work); } else { if (priv->after_suspend & AFTER_SUSPEND_UP) { - if (pdata->transceiver_enable) - pdata->transceiver_enable(1); + mcp251x_power_enable(priv->transceiver, 1); queue_work(priv->wq, &priv->restart_work); } else { priv->after_suspend = 0; diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index b1bcd4ba474..190219e0240 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1747,11 +1747,10 @@ static int bcm_enet_probe(struct platform_device *pdev) if (!bcm_enet_shared_base[0]) return -ENODEV; - res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); res_irq_rx = platform_get_resource(pdev, IORESOURCE_IRQ, 1); res_irq_tx = platform_get_resource(pdev, IORESOURCE_IRQ, 2); - if (!res_mem || !res_irq || !res_irq_rx || !res_irq_tx) + if (!res_irq || !res_irq_rx || !res_irq_tx) return -ENODEV; ret = 0; @@ -1767,9 +1766,10 @@ static int bcm_enet_probe(struct platform_device *pdev) if (ret) goto out; - priv->base = devm_request_and_ioremap(&pdev->dev, res_mem); - if (priv->base == NULL) { - ret = -ENOMEM; + res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + priv->base = devm_ioremap_resource(&pdev->dev, res_mem); + if (IS_ERR(priv->base)) { + ret = PTR_ERR(priv->base); goto out; } @@ -2836,7 +2836,6 @@ static int bcm_enetsw_remove(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); release_mem_region(res->start, resource_size(res)); - platform_set_drvdata(pdev, NULL); free_netdev(dev); return 0; } diff --git a/drivers/net/ethernet/cisco/enic/Makefile b/drivers/net/ethernet/cisco/enic/Makefile index e52296d9b25..239e1e46545 100644 --- a/drivers/net/ethernet/cisco/enic/Makefile +++ b/drivers/net/ethernet/cisco/enic/Makefile @@ -2,5 +2,5 @@ obj-$(CONFIG_ENIC) := enic.o enic-y := enic_main.o vnic_cq.o vnic_intr.o vnic_wq.o \ enic_res.o enic_dev.o enic_pp.o vnic_dev.o vnic_rq.o vnic_vic.o \ - enic_ethtool.o + enic_ethtool.o enic_api.o diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h index 2e37c63981c..be167318015 100644 --- a/drivers/net/ethernet/cisco/enic/enic.h +++ b/drivers/net/ethernet/cisco/enic/enic.h @@ -32,8 +32,8 @@ #define DRV_NAME "enic" #define DRV_DESCRIPTION "Cisco VIC Ethernet NIC Driver" -#define DRV_VERSION "2.1.1.39" -#define DRV_COPYRIGHT "Copyright 2008-2011 Cisco Systems, Inc" +#define DRV_VERSION "2.1.1.43" +#define DRV_COPYRIGHT "Copyright 2008-2013 Cisco Systems, Inc" #define ENIC_BARS_MAX 6 @@ -96,6 +96,7 @@ struct enic { #ifdef CONFIG_PCI_IOV u16 num_vfs; #endif + spinlock_t enic_api_lock; struct enic_port_profile *pp; /* work queue cache line section */ diff --git a/drivers/net/ethernet/cisco/enic/enic_api.c b/drivers/net/ethernet/cisco/enic/enic_api.c new file mode 100644 index 00000000000..e13efbdaa2e --- /dev/null +++ b/drivers/net/ethernet/cisco/enic/enic_api.c @@ -0,0 +1,48 @@ +/** + * Copyright 2013 Cisco Systems, Inc. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#include <linux/netdevice.h> +#include <linux/spinlock.h> + +#include "vnic_dev.h" +#include "vnic_devcmd.h" + +#include "enic_res.h" +#include "enic.h" +#include "enic_api.h" + +int enic_api_devcmd_proxy_by_index(struct net_device *netdev, int vf, + enum vnic_devcmd_cmd cmd, u64 *a0, u64 *a1, int wait) +{ + int err; + struct enic *enic = netdev_priv(netdev); + struct vnic_dev *vdev = enic->vdev; + + spin_lock(&enic->enic_api_lock); + spin_lock(&enic->devcmd_lock); + + vnic_dev_cmd_proxy_by_index_start(vdev, vf); + err = vnic_dev_cmd(vdev, cmd, a0, a1, wait); + vnic_dev_cmd_proxy_end(vdev); + + spin_unlock(&enic->devcmd_lock); + spin_unlock(&enic->enic_api_lock); + + return err; +} +EXPORT_SYMBOL(enic_api_devcmd_proxy_by_index); diff --git a/drivers/net/ethernet/cisco/enic/enic_api.h b/drivers/net/ethernet/cisco/enic/enic_api.h new file mode 100644 index 00000000000..6b9f9255af2 --- /dev/null +++ b/drivers/net/ethernet/cisco/enic/enic_api.h @@ -0,0 +1,30 @@ +/** + * Copyright 2013 Cisco Systems, Inc. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef __ENIC_API_H__ +#define __ENIC_API_H__ + +#include <linux/netdevice.h> + +#include "vnic_dev.h" +#include "vnic_devcmd.h" + +int enic_api_devcmd_proxy_by_index(struct net_device *netdev, int vf, + enum vnic_devcmd_cmd cmd, u64 *a0, u64 *a1, int wait); + +#endif diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index b12b32bc53a..bcf15b176f4 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1733,6 +1733,7 @@ static void enic_reset(struct work_struct *work) rtnl_lock(); + spin_lock(&enic->enic_api_lock); enic_dev_hang_notify(enic); enic_stop(enic->netdev); enic_dev_hang_reset(enic); @@ -1741,6 +1742,8 @@ static void enic_reset(struct work_struct *work) enic_set_rss_nic_cfg(enic); enic_dev_set_ig_vlan_rewrite_mode(enic); enic_open(enic->netdev); + spin_unlock(&enic->enic_api_lock); + call_netdevice_notifiers(NETDEV_REBOOT, enic->netdev); rtnl_unlock(); } @@ -2153,6 +2156,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) */ spin_lock_init(&enic->devcmd_lock); + spin_lock_init(&enic->enic_api_lock); /* * Set ingress vlan rewrite mode before vnic initialization diff --git a/drivers/net/ethernet/cisco/enic/enic_res.h b/drivers/net/ethernet/cisco/enic/enic_res.h index 25be2734c3f..69f60afd657 100644 --- a/drivers/net/ethernet/cisco/enic/enic_res.h +++ b/drivers/net/ethernet/cisco/enic/enic_res.h @@ -47,6 +47,9 @@ static inline void enic_queue_wq_desc_ex(struct vnic_wq *wq, int offload_mode, int cq_entry, int sop, int eop, int loopback) { struct wq_enet_desc *desc = vnic_wq_next_desc(wq); + u8 desc_skip_cnt = 1; + u8 compressed_send = 0; + u64 wrid = 0; wq_enet_desc_enc(desc, (u64)dma_addr | VNIC_PADDR_TARGET, @@ -59,7 +62,8 @@ static inline void enic_queue_wq_desc_ex(struct vnic_wq *wq, (u16)vlan_tag, (u8)loopback); - vnic_wq_post(wq, os_buf, dma_addr, len, sop, eop); + vnic_wq_post(wq, os_buf, dma_addr, len, sop, eop, desc_skip_cnt, + (u8)cq_entry, compressed_send, wrid); } static inline void enic_queue_wq_desc_cont(struct vnic_wq *wq, @@ -120,6 +124,7 @@ static inline void enic_queue_rq_desc(struct vnic_rq *rq, dma_addr_t dma_addr, unsigned int len) { struct rq_enet_desc *desc = vnic_rq_next_desc(rq); + u64 wrid = 0; u8 type = os_buf_index ? RQ_ENET_TYPE_NOT_SOP : RQ_ENET_TYPE_ONLY_SOP; @@ -127,7 +132,7 @@ static inline void enic_queue_rq_desc(struct vnic_rq *rq, (u64)dma_addr | VNIC_PADDR_TARGET, type, (u16)len); - vnic_rq_post(rq, os_buf, os_buf_index, dma_addr, len); + vnic_rq_post(rq, os_buf, os_buf_index, dma_addr, len, wrid); } struct enic; diff --git a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h index 23d555255cf..b9a0d78fd63 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h +++ b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h @@ -281,11 +281,25 @@ enum vnic_devcmd_cmd { * 0 if no VIF-CONFIG-INFO TLV was ever received. */ CMD_CONFIG_INFO_GET = _CMDC(_CMD_DIR_RW, _CMD_VTYPE_ALL, 44), + /* INT13 API: (u64)a0=paddr to vnic_int13_params struct + * (u32)a1=INT13_CMD_xxx + */ + CMD_INT13_ALL = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ALL, 45), + + /* Set default vlan: + * in: (u16)a0=new default vlan + * (u16)a1=zero for overriding vlan with param a0, + * non-zero for resetting vlan to the default + * out: (u16)a0=old default vlan + */ + CMD_SET_DEFAULT_VLAN = _CMDC(_CMD_DIR_RW, _CMD_VTYPE_ALL, 46), + /* init_prov_info2: * Variant of CMD_INIT_PROV_INFO, where it will not try to enable * the vnic until CMD_ENABLE2 is issued. * (u64)a0=paddr of vnic_devcmd_provinfo - * (u32)a1=sizeof provision info */ + * (u32)a1=sizeof provision info + */ CMD_INIT_PROV_INFO2 = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 47), /* enable2: @@ -339,16 +353,57 @@ enum vnic_devcmd_cmd { CMD_INTR_COAL_CONVERT = _CMDC(_CMD_DIR_READ, _CMD_VTYPE_ALL, 50), /* - * cmd_set_mac_addr - * set mac address + * Set the predefined mac address as default * in: * (u48)a0 = mac addr - * */ CMD_SET_MAC_ADDR = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 55), + + /* Update the provisioning info of the given VIF + * (u64)a0=paddr of vnic_devcmd_provinfo + * (u32)a1=sizeof provision info + */ + CMD_PROV_INFO_UPDATE = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 56), + + /* Add a filter. + * in: (u64) a0= filter address + * (u32) a1= size of filter + * out: (u32) a0=filter identifier + */ + CMD_ADD_FILTER = _CMDC(_CMD_DIR_RW, _CMD_VTYPE_ENET, 58), + + /* Delete a filter. + * in: (u32) a0=filter identifier + */ + CMD_DEL_FILTER = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 59), + + /* Enable a Queue Pair in User space NIC + * in: (u32) a0=Queue Pair number + * (u32) a1= command + */ + CMD_QP_ENABLE = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 60), + + /* Disable a Queue Pair in User space NIC + * in: (u32) a0=Queue Pair number + * (u32) a1= command + */ + CMD_QP_DISABLE = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 61), + + /* Stats dump Queue Pair in User space NIC + * in: (u32) a0=Queue Pair number + * (u64) a1=host buffer addr for status dump + * (u32) a2=length of the buffer + */ + CMD_QP_STATS_DUMP = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 62), + + /* Clear stats for Queue Pair in User space NIC + * in: (u32) a0=Queue Pair number + */ + CMD_QP_STATS_CLEAR = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 63), }; /* CMD_ENABLE2 flags */ +#define CMD_ENABLE2_STANDBY 0x0 #define CMD_ENABLE2_ACTIVE 0x1 /* flags for CMD_OPEN */ @@ -364,6 +419,9 @@ enum vnic_devcmd_cmd { #define CMD_PFILTER_PROMISCUOUS 0x08 #define CMD_PFILTER_ALL_MULTICAST 0x10 +/* Commands for CMD_QP_ENABLE/CM_QP_DISABLE */ +#define CMD_QP_RQWQ 0x0 + /* rewrite modes for CMD_IG_VLAN_REWRITE_MODE */ #define IG_VLAN_REWRITE_MODE_DEFAULT_TRUNK 0 #define IG_VLAN_REWRITE_MODE_UNTAG_DEFAULT_VLAN 1 @@ -390,6 +448,7 @@ enum vnic_devcmd_error { ERR_EMAXRES = 10, ERR_ENOTSUPPORTED = 11, ERR_EINPROGRESS = 12, + ERR_MAX }; /* @@ -435,6 +494,115 @@ struct vnic_devcmd_provinfo { u8 data[0]; }; +/* These are used in flags field of different filters to denote + * valid fields used. + */ +#define FILTER_FIELD_VALID(fld) (1 << (fld - 1)) + +#define FILTER_FIELDS_USNIC ( \ + FILTER_FIELD_VALID(1) | \ + FILTER_FIELD_VALID(2) | \ + FILTER_FIELD_VALID(3) | \ + FILTER_FIELD_VALID(4)) + +#define FILTER_FIELDS_IPV4_5TUPLE ( \ + FILTER_FIELD_VALID(1) | \ + FILTER_FIELD_VALID(2) | \ + FILTER_FIELD_VALID(3) | \ + FILTER_FIELD_VALID(4) | \ + FILTER_FIELD_VALID(5)) + +#define FILTER_FIELDS_MAC_VLAN ( \ + FILTER_FIELD_VALID(1) | \ + FILTER_FIELD_VALID(2)) + +#define FILTER_FIELD_USNIC_VLAN FILTER_FIELD_VALID(1) +#define FILTER_FIELD_USNIC_ETHTYPE FILTER_FIELD_VALID(2) +#define FILTER_FIELD_USNIC_PROTO FILTER_FIELD_VALID(3) +#define FILTER_FIELD_USNIC_ID FILTER_FIELD_VALID(4) + +struct filter_usnic_id { + u32 flags; + u16 vlan; + u16 ethtype; + u8 proto_version; + u32 usnic_id; +} __packed; + +#define FILTER_FIELD_5TUP_PROTO FILTER_FIELD_VALID(1) +#define FILTER_FIELD_5TUP_SRC_AD FILTER_FIELD_VALID(2) +#define FILTER_FIELD_5TUP_DST_AD FILTER_FIELD_VALID(3) +#define FILTER_FIELD_5TUP_SRC_PT FILTER_FIELD_VALID(4) +#define FILTER_FIELD_5TUP_DST_PT FILTER_FIELD_VALID(5) + +/* Enums for the protocol field. */ +enum protocol_e { + PROTO_UDP = 0, + PROTO_TCP = 1, +}; + +struct filter_ipv4_5tuple { + u32 flags; + u32 protocol; + u32 src_addr; + u32 dst_addr; + u16 src_port; + u16 dst_port; +} __packed; + +#define FILTER_FIELD_VMQ_VLAN FILTER_FIELD_VALID(1) +#define FILTER_FIELD_VMQ_MAC FILTER_FIELD_VALID(2) + +struct filter_mac_vlan { + u32 flags; + u16 vlan; + u8 mac_addr[6]; +} __packed; + +/* Specifies the filter_action type. */ +enum { + FILTER_ACTION_RQ_STEERING = 0, + FILTER_ACTION_MAX +}; + +struct filter_action { + u32 type; + union { + u32 rq_idx; + } u; +} __packed; + +/* Specifies the filter type. */ +enum filter_type { + FILTER_USNIC_ID = 0, + FILTER_IPV4_5TUPLE = 1, + FILTER_MAC_VLAN = 2, + FILTER_MAX +}; + +struct filter { + u32 type; + union { + struct filter_usnic_id usnic; + struct filter_ipv4_5tuple ipv4; + struct filter_mac_vlan mac_vlan; + } u; +} __packed; + +enum { + CLSF_TLV_FILTER = 0, + CLSF_TLV_ACTION = 1, +}; + +/* Maximum size of buffer to CMD_ADD_FILTER */ +#define FILTER_MAX_BUF_SIZE 100 + +struct filter_tlv { + u_int32_t type; + u_int32_t length; + u_int32_t val[0]; +}; + /* * Writing cmd register causes STAT_BUSY to get set in status register. * When cmd completes, STAT_BUSY will be cleared. diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.c b/drivers/net/ethernet/cisco/enic/vnic_rq.c index 7e1488fc8ab..36a2ed606c9 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_rq.c +++ b/drivers/net/ethernet/cisco/enic/vnic_rq.c @@ -30,12 +30,9 @@ static int vnic_rq_alloc_bufs(struct vnic_rq *rq) { struct vnic_rq_buf *buf; - struct vnic_dev *vdev; unsigned int i, j, count = rq->ring.desc_count; unsigned int blks = VNIC_RQ_BUF_BLKS_NEEDED(count); - vdev = rq->vdev; - for (i = 0; i < blks; i++) { rq->bufs[i] = kzalloc(VNIC_RQ_BUF_BLK_SZ(count), GFP_ATOMIC); if (!rq->bufs[i]) @@ -141,7 +138,7 @@ void vnic_rq_init(struct vnic_rq *rq, unsigned int cq_index, unsigned int error_interrupt_enable, unsigned int error_interrupt_offset) { - u32 fetch_index; + u32 fetch_index = 0; /* Use current fetch_index as the ring starting point */ fetch_index = ioread32(&rq->ctrl->fetch_index); diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.h b/drivers/net/ethernet/cisco/enic/vnic_rq.h index 2056586f4d4..ee7bc95af27 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_rq.h +++ b/drivers/net/ethernet/cisco/enic/vnic_rq.h @@ -72,6 +72,7 @@ struct vnic_rq_buf { unsigned int len; unsigned int index; void *desc; + uint64_t wr_id; }; struct vnic_rq { @@ -110,7 +111,8 @@ static inline unsigned int vnic_rq_next_index(struct vnic_rq *rq) static inline void vnic_rq_post(struct vnic_rq *rq, void *os_buf, unsigned int os_buf_index, - dma_addr_t dma_addr, unsigned int len) + dma_addr_t dma_addr, unsigned int len, + uint64_t wrid) { struct vnic_rq_buf *buf = rq->to_use; @@ -118,6 +120,7 @@ static inline void vnic_rq_post(struct vnic_rq *rq, buf->os_buf_index = os_buf_index; buf->dma_addr = dma_addr; buf->len = len; + buf->wr_id = wrid; buf = buf->next; rq->to_use = buf; diff --git a/drivers/net/ethernet/cisco/enic/vnic_wq.c b/drivers/net/ethernet/cisco/enic/vnic_wq.c index 5e0d7a2be9b..3e6b8d54daf 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_wq.c +++ b/drivers/net/ethernet/cisco/enic/vnic_wq.c @@ -30,12 +30,9 @@ static int vnic_wq_alloc_bufs(struct vnic_wq *wq) { struct vnic_wq_buf *buf; - struct vnic_dev *vdev; unsigned int i, j, count = wq->ring.desc_count; unsigned int blks = VNIC_WQ_BUF_BLKS_NEEDED(count); - vdev = wq->vdev; - for (i = 0; i < blks; i++) { wq->bufs[i] = kzalloc(VNIC_WQ_BUF_BLK_SZ(count), GFP_ATOMIC); if (!wq->bufs[i]) diff --git a/drivers/net/ethernet/cisco/enic/vnic_wq.h b/drivers/net/ethernet/cisco/enic/vnic_wq.h index 7dd937ac11c..2c6c70804a3 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_wq.h +++ b/drivers/net/ethernet/cisco/enic/vnic_wq.h @@ -58,6 +58,10 @@ struct vnic_wq_buf { unsigned int index; int sop; void *desc; + uint64_t wr_id; /* Cookie */ + uint8_t cq_entry; /* Gets completion event from hw */ + uint8_t desc_skip_cnt; /* Num descs to occupy */ + uint8_t compressed_send; /* Both hdr and payload in one desc */ }; /* Break the vnic_wq_buf allocations into blocks of 32/64 entries */ @@ -102,14 +106,20 @@ static inline void *vnic_wq_next_desc(struct vnic_wq *wq) static inline void vnic_wq_post(struct vnic_wq *wq, void *os_buf, dma_addr_t dma_addr, - unsigned int len, int sop, int eop) + unsigned int len, int sop, int eop, + uint8_t desc_skip_cnt, uint8_t cq_entry, + uint8_t compressed_send, uint64_t wrid) { struct vnic_wq_buf *buf = wq->to_use; buf->sop = sop; + buf->cq_entry = cq_entry; + buf->compressed_send = compressed_send; + buf->desc_skip_cnt = desc_skip_cnt; buf->os_buf = eop ? os_buf : NULL; buf->dma_addr = dma_addr; buf->len = len; + buf->wr_id = wrid; buf = buf->next; if (eop) { @@ -123,7 +133,7 @@ static inline void vnic_wq_post(struct vnic_wq *wq, } wq->to_use = buf; - wq->ring.desc_avail--; + wq->ring.desc_avail -= desc_skip_cnt; } static inline void vnic_wq_service(struct vnic_wq *wq, diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c index 50d9c631593..bf3bf6f22c9 100644 --- a/drivers/net/ethernet/dlink/sundance.c +++ b/drivers/net/ethernet/dlink/sundance.c @@ -469,6 +469,17 @@ static void sundance_reset(struct net_device *dev, unsigned long reset_cmd) } } +#ifdef CONFIG_NET_POLL_CONTROLLER +static void sundance_poll_controller(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + + disable_irq(np->pci_dev->irq); + intr_handler(np->pci_dev->irq, dev); + enable_irq(np->pci_dev->irq); +} +#endif + static const struct net_device_ops netdev_ops = { .ndo_open = netdev_open, .ndo_stop = netdev_close, @@ -480,6 +491,9 @@ static const struct net_device_ops netdev_ops = { .ndo_change_mtu = change_mtu, .ndo_set_mac_address = sundance_set_mac_addr, .ndo_validate_addr = eth_validate_addr, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = sundance_poll_controller, +#endif }; static int sundance_probe1(struct pci_dev *pdev, diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c b/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c index 360a578c2bb..e0528900db0 100644 --- a/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c +++ b/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c @@ -123,12 +123,10 @@ static int mpc52xx_fec_mdio_probe(struct platform_device *of) static int mpc52xx_fec_mdio_remove(struct platform_device *of) { - struct device *dev = &of->dev; - struct mii_bus *bus = dev_get_drvdata(dev); + struct mii_bus *bus = platform_get_drvdata(of); struct mpc52xx_fec_mdio_priv *priv = bus->priv; mdiobus_unregister(bus); - dev_set_drvdata(dev, NULL); iounmap(priv->regs); kfree(priv); mdiobus_free(bus); diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index 8de53a14a6f..6b60582ce8c 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -583,7 +583,6 @@ static struct sk_buff *tx_skb_align_workaround(struct net_device *dev, struct sk_buff *skb) { struct sk_buff *new_skb; - struct fs_enet_private *fep = netdev_priv(dev); /* Alloc new skb */ new_skb = netdev_alloc_skb(dev, skb->len + 4); @@ -1000,6 +999,8 @@ static int fs_enet_probe(struct platform_device *ofdev) struct fs_enet_private *fep; struct fs_platform_info *fpi; const u32 *data; + struct clk *clk; + int err; const u8 *mac_addr; const char *phy_connection_type; int privsize, len, ret = -ENODEV; @@ -1037,6 +1038,20 @@ static int fs_enet_probe(struct platform_device *ofdev) fpi->use_rmii = 1; } + /* make clock lookup non-fatal (the driver is shared among platforms), + * but require enable to succeed when a clock was specified/found, + * keep a reference to the clock upon successful acquisition + */ + clk = devm_clk_get(&ofdev->dev, "per"); + if (!IS_ERR(clk)) { + err = clk_prepare_enable(clk); + if (err) { + ret = err; + goto out_free_fpi; + } + fpi->clk_per = clk; + } + privsize = sizeof(*fep) + sizeof(struct sk_buff **) * (fpi->rx_ring + fpi->tx_ring); @@ -1108,6 +1123,8 @@ out_free_dev: free_netdev(ndev); out_put: of_node_put(fpi->phy_node); + if (fpi->clk_per) + clk_disable_unprepare(fpi->clk_per); out_free_fpi: kfree(fpi); return ret; @@ -1124,6 +1141,8 @@ static int fs_enet_remove(struct platform_device *ofdev) fep->ops->cleanup_data(ndev); dev_set_drvdata(fep->dev, NULL); of_node_put(fep->fpi->phy_node); + if (fep->fpi->clk_per) + clk_disable_unprepare(fep->fpi->clk_per); free_netdev(ndev); return 0; } diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index c93a05654b4..c4f65067cf7 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -409,7 +409,7 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) priv->regs = priv->map + data->mii_offset; new_bus->parent = &pdev->dev; - dev_set_drvdata(&pdev->dev, new_bus); + platform_set_drvdata(pdev, new_bus); if (data->get_tbipa) { for_each_child_of_node(np, tbi) { @@ -468,8 +468,6 @@ static int fsl_pq_mdio_remove(struct platform_device *pdev) mdiobus_unregister(bus); - dev_set_drvdata(device, NULL); - iounmap(priv->map); mdiobus_free(bus); diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 3c43dac894e..5930c39672d 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -3911,14 +3911,12 @@ static int ucc_geth_probe(struct platform_device* ofdev) static int ucc_geth_remove(struct platform_device* ofdev) { - struct device *device = &ofdev->dev; - struct net_device *dev = dev_get_drvdata(device); + struct net_device *dev = platform_get_drvdata(ofdev); struct ucc_geth_private *ugeth = netdev_priv(dev); unregister_netdev(dev); free_netdev(dev); ucc_geth_memclean(ugeth); - dev_set_drvdata(device, NULL); return 0; } diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index d300a0c0eaf..2d3b064d692 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2955,8 +2955,6 @@ static int emac_remove(struct platform_device *ofdev) DBG(dev, "remove" NL); - dev_set_drvdata(&ofdev->dev, NULL); - unregister_netdev(dev->ndev); cancel_work_sync(&dev->reset_work); diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index e4ebd7ddf5f..a8633b8f0ac 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -1665,7 +1665,7 @@ static int e1000_run_loopback_test(struct e1000_adapter *adapter) ret_val = 13; /* ret_val is the same as mis-compare */ break; } - if (jiffies >= (time + 20)) { + if (time_after(jiffies, time + 20)) { ret_val = 14; /* error code for time out error */ break; } diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index b799fd9b6aa..b7f38435d1f 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -233,7 +233,8 @@ union e1000_rx_desc_extended { #define MAX_PS_BUFFERS 4 /* Number of packet split data buffers (not including the header buffer) */ -#define PS_PAGE_BUFFERS (MAX_PS_BUFFERS - 1) +#define PS_PAGE_BUFFERS (MAX_PS_BUFFERS - 1) + /* Receive Descriptor - Packet Split */ union e1000_rx_desc_packet_split { struct { diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index e6d2c0f8f76..e87e9b01f40 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -64,8 +64,6 @@ static int debug = -1; module_param(debug, int, 0); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); -static void e1000e_disable_aspm(struct pci_dev *pdev, u16 state); - static const struct e1000_info *e1000_info_tbl[] = { [board_82571] = &e1000_82571_info, [board_82572] = &e1000_82572_info, @@ -6001,11 +5999,18 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) * correctable error when the MAC transitions from D0 to D3. To * prevent this we need to mask off the correctable errors on the * downstream port of the pci-e switch. + * + * We don't have the associated upstream bridge while assigning + * the PCI device into guest. For example, the KVM on power is + * one of the cases. */ if (adapter->flags & FLAG_IS_QUAD_PORT) { struct pci_dev *us_dev = pdev->bus->self; u16 devctl; + if (!us_dev) + return 0; + pcie_capability_read_word(us_dev, PCI_EXP_DEVCTL, &devctl); pcie_capability_write_word(us_dev, PCI_EXP_DEVCTL, (devctl & ~PCI_EXP_DEVCTL_CERE)); @@ -6019,38 +6024,73 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) return 0; } -#ifdef CONFIG_PCIEASPM -static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state) +/** + * e1000e_disable_aspm - Disable ASPM states + * @pdev: pointer to PCI device struct + * @state: bit-mask of ASPM states to disable + * + * Some devices *must* have certain ASPM states disabled per hardware errata. + **/ +static void e1000e_disable_aspm(struct pci_dev *pdev, u16 state) { + struct pci_dev *parent = pdev->bus->self; + u16 aspm_dis_mask = 0; + u16 pdev_aspmc, parent_aspmc; + + switch (state) { + case PCIE_LINK_STATE_L0S: + case PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1: + aspm_dis_mask |= PCI_EXP_LNKCTL_ASPM_L0S; + /* fall-through - can't have L1 without L0s */ + case PCIE_LINK_STATE_L1: + aspm_dis_mask |= PCI_EXP_LNKCTL_ASPM_L1; + break; + default: + return; + } + + pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &pdev_aspmc); + pdev_aspmc &= PCI_EXP_LNKCTL_ASPMC; + + if (parent) { + pcie_capability_read_word(parent, PCI_EXP_LNKCTL, + &parent_aspmc); + parent_aspmc &= PCI_EXP_LNKCTL_ASPMC; + } + + /* Nothing to do if the ASPM states to be disabled already are */ + if (!(pdev_aspmc & aspm_dis_mask) && + (!parent || !(parent_aspmc & aspm_dis_mask))) + return; + + dev_info(&pdev->dev, "Disabling ASPM %s %s\n", + (aspm_dis_mask & pdev_aspmc & PCI_EXP_LNKCTL_ASPM_L0S) ? + "L0s" : "", + (aspm_dis_mask & pdev_aspmc & PCI_EXP_LNKCTL_ASPM_L1) ? + "L1" : ""); + +#ifdef CONFIG_PCIEASPM pci_disable_link_state_locked(pdev, state); -} -#else -static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state) -{ - u16 aspm_ctl = 0; - if (state & PCIE_LINK_STATE_L0S) - aspm_ctl |= PCI_EXP_LNKCTL_ASPM_L0S; - if (state & PCIE_LINK_STATE_L1) - aspm_ctl |= PCI_EXP_LNKCTL_ASPM_L1; + /* Double-check ASPM control. If not disabled by the above, the + * BIOS is preventing that from happening (or CONFIG_PCIEASPM is + * not enabled); override by writing PCI config space directly. + */ + pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &pdev_aspmc); + pdev_aspmc &= PCI_EXP_LNKCTL_ASPMC; + + if (!(aspm_dis_mask & pdev_aspmc)) + return; +#endif /* Both device and parent should have the same ASPM setting. * Disable ASPM in downstream component first and then upstream. */ - pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, aspm_ctl); - - if (pdev->bus->self) - pcie_capability_clear_word(pdev->bus->self, PCI_EXP_LNKCTL, - aspm_ctl); -} -#endif -static void e1000e_disable_aspm(struct pci_dev *pdev, u16 state) -{ - dev_info(&pdev->dev, "Disabling ASPM %s %s\n", - (state & PCIE_LINK_STATE_L0S) ? "L0s" : "", - (state & PCIE_LINK_STATE_L1) ? "L1" : ""); + pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, aspm_dis_mask); - __e1000e_disable_aspm(pdev, state); + if (parent) + pcie_capability_clear_word(parent, PCI_EXP_LNKCTL, + aspm_dis_mask); } #ifdef CONFIG_PM diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index f21a91a299a..d398fad6eed 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -238,6 +238,7 @@ static s32 igb_init_nvm_params_82575(struct e1000_hw *hw) size = (u16)((eecd & E1000_EECD_SIZE_EX_MASK) >> E1000_EECD_SIZE_EX_SHIFT); + /* Added to a constant, "size" becomes the left-shift value * for setting word_size. */ @@ -250,86 +251,52 @@ static s32 igb_init_nvm_params_82575(struct e1000_hw *hw) size = 15; nvm->word_size = 1 << size; - if (hw->mac.type < e1000_i210) { - nvm->opcode_bits = 8; - nvm->delay_usec = 1; - - switch (nvm->override) { - case e1000_nvm_override_spi_large: - nvm->page_size = 32; - nvm->address_bits = 16; - break; - case e1000_nvm_override_spi_small: - nvm->page_size = 8; - nvm->address_bits = 8; - break; - default: - nvm->page_size = eecd & E1000_EECD_ADDR_BITS ? 32 : 8; - nvm->address_bits = eecd & E1000_EECD_ADDR_BITS ? - 16 : 8; - break; - } - if (nvm->word_size == (1 << 15)) - nvm->page_size = 128; + nvm->opcode_bits = 8; + nvm->delay_usec = 1; - nvm->type = e1000_nvm_eeprom_spi; - } else { - nvm->type = e1000_nvm_flash_hw; + switch (nvm->override) { + case e1000_nvm_override_spi_large: + nvm->page_size = 32; + nvm->address_bits = 16; + break; + case e1000_nvm_override_spi_small: + nvm->page_size = 8; + nvm->address_bits = 8; + break; + default: + nvm->page_size = eecd & E1000_EECD_ADDR_BITS ? 32 : 8; + nvm->address_bits = eecd & E1000_EECD_ADDR_BITS ? + 16 : 8; + break; } + if (nvm->word_size == (1 << 15)) + nvm->page_size = 128; + + nvm->type = e1000_nvm_eeprom_spi; /* NVM Function Pointers */ + nvm->ops.acquire = igb_acquire_nvm_82575; + nvm->ops.release = igb_release_nvm_82575; + nvm->ops.write = igb_write_nvm_spi; + nvm->ops.validate = igb_validate_nvm_checksum; + nvm->ops.update = igb_update_nvm_checksum; + if (nvm->word_size < (1 << 15)) + nvm->ops.read = igb_read_nvm_eerd; + else + nvm->ops.read = igb_read_nvm_spi; + + /* override generic family function pointers for specific descendants */ switch (hw->mac.type) { case e1000_82580: nvm->ops.validate = igb_validate_nvm_checksum_82580; nvm->ops.update = igb_update_nvm_checksum_82580; - nvm->ops.acquire = igb_acquire_nvm_82575; - nvm->ops.release = igb_release_nvm_82575; - if (nvm->word_size < (1 << 15)) - nvm->ops.read = igb_read_nvm_eerd; - else - nvm->ops.read = igb_read_nvm_spi; - nvm->ops.write = igb_write_nvm_spi; break; case e1000_i354: case e1000_i350: nvm->ops.validate = igb_validate_nvm_checksum_i350; nvm->ops.update = igb_update_nvm_checksum_i350; - nvm->ops.acquire = igb_acquire_nvm_82575; - nvm->ops.release = igb_release_nvm_82575; - if (nvm->word_size < (1 << 15)) - nvm->ops.read = igb_read_nvm_eerd; - else - nvm->ops.read = igb_read_nvm_spi; - nvm->ops.write = igb_write_nvm_spi; - break; - case e1000_i210: - nvm->ops.validate = igb_validate_nvm_checksum_i210; - nvm->ops.update = igb_update_nvm_checksum_i210; - nvm->ops.acquire = igb_acquire_nvm_i210; - nvm->ops.release = igb_release_nvm_i210; - nvm->ops.read = igb_read_nvm_srrd_i210; - nvm->ops.write = igb_write_nvm_srwr_i210; - nvm->ops.valid_led_default = igb_valid_led_default_i210; - break; - case e1000_i211: - nvm->ops.acquire = igb_acquire_nvm_i210; - nvm->ops.release = igb_release_nvm_i210; - nvm->ops.read = igb_read_nvm_i211; - nvm->ops.valid_led_default = igb_valid_led_default_i210; - nvm->ops.validate = NULL; - nvm->ops.update = NULL; - nvm->ops.write = NULL; break; default: - nvm->ops.validate = igb_validate_nvm_checksum; - nvm->ops.update = igb_update_nvm_checksum; - nvm->ops.acquire = igb_acquire_nvm_82575; - nvm->ops.release = igb_release_nvm_82575; - if (nvm->word_size < (1 << 15)) - nvm->ops.read = igb_read_nvm_eerd; - else - nvm->ops.read = igb_read_nvm_spi; - nvm->ops.write = igb_write_nvm_spi; break; } @@ -516,6 +483,8 @@ static s32 igb_get_invariants_82575(struct e1000_hw *hw) case E1000_DEV_ID_I210_FIBER: case E1000_DEV_ID_I210_SERDES: case E1000_DEV_ID_I210_SGMII: + case E1000_DEV_ID_I210_COPPER_FLASHLESS: + case E1000_DEV_ID_I210_SERDES_FLASHLESS: mac->type = e1000_i210; break; case E1000_DEV_ID_I211_COPPER: @@ -601,6 +570,15 @@ static s32 igb_get_invariants_82575(struct e1000_hw *hw) /* NVM initialization */ ret_val = igb_init_nvm_params_82575(hw); + switch (hw->mac.type) { + case e1000_i210: + case e1000_i211: + ret_val = igb_init_nvm_params_i210(hw); + break; + default: + break; + } + if (ret_val) goto out; @@ -1320,7 +1298,7 @@ void igb_shutdown_serdes_link_82575(struct e1000_hw *hw) **/ static s32 igb_reset_hw_82575(struct e1000_hw *hw) { - u32 ctrl, icr; + u32 ctrl; s32 ret_val; /* Prevent the PCI-E bus from sticking if there is no TLP connection @@ -1365,7 +1343,7 @@ static s32 igb_reset_hw_82575(struct e1000_hw *hw) /* Clear any pending interrupt events. */ wr32(E1000_IMC, 0xffffffff); - icr = rd32(E1000_ICR); + rd32(E1000_ICR); /* Install any alternate MAC address into RAR0 */ ret_val = igb_check_alt_mac_addr(hw); @@ -2103,10 +2081,9 @@ static s32 igb_reset_hw_82580(struct e1000_hw *hw) s32 ret_val = 0; /* BH SW mailbox bit in SW_FW_SYNC */ u16 swmbsw_mask = E1000_SW_SYNCH_MB; - u32 ctrl, icr; + u32 ctrl; bool global_device_reset = hw->dev_spec._82575.global_device_reset; - hw->dev_spec._82575.global_device_reset = false; /* due to hw errata, global device reset doesn't always @@ -2165,7 +2142,7 @@ static s32 igb_reset_hw_82580(struct e1000_hw *hw) /* Clear any pending interrupt events. */ wr32(E1000_IMC, 0xffffffff); - icr = rd32(E1000_ICR); + rd32(E1000_ICR); ret_val = igb_reset_mdicnfg_82580(hw); if (ret_val) diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index aa201abb8ad..60559af39a9 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -620,6 +620,7 @@ #define E1000_EECD_SIZE_EX_SHIFT 11 #define E1000_EECD_FLUPD_I210 0x00800000 /* Update FLASH */ #define E1000_EECD_FLUDONE_I210 0x04000000 /* Update FLASH done*/ +#define E1000_EECD_FLASH_DETECTED_I210 0x00080000 /* FLASH detected */ #define E1000_FLUDONE_ATTEMPTS 20000 #define E1000_EERD_EEWR_MAX_COUNT 512 /* buffered EEPROM words rw */ #define E1000_I210_FIFO_SEL_RX 0x00 @@ -627,6 +628,11 @@ #define E1000_I210_FIFO_SEL_TX_LEGACY E1000_I210_FIFO_SEL_TX_QAV(0) #define E1000_I210_FIFO_SEL_BMC2OS_TX 0x06 #define E1000_I210_FIFO_SEL_BMC2OS_RX 0x01 +#define E1000_I210_FLASH_SECTOR_SIZE 0x1000 /* 4KB FLASH sector unit size */ +/* Secure FLASH mode requires removing MSb */ +#define E1000_I210_FW_PTR_MASK 0x7FFF +/* Firmware code revision field word offset*/ +#define E1000_I210_FW_VER_OFFSET 328 #define E1000_EECD_FLUPD_I210 0x00800000 /* Update FLASH */ #define E1000_EECD_FLUDONE_I210 0x04000000 /* Update FLASH done*/ #define E1000_FLUDONE_ATTEMPTS 20000 @@ -665,20 +671,26 @@ #define NVM_INIT_CTRL_4 0x0013 #define NVM_LED_1_CFG 0x001C #define NVM_LED_0_2_CFG 0x001F - -/* NVM version defines */ #define NVM_ETRACK_WORD 0x0042 +#define NVM_ETRACK_HIWORD 0x0043 #define NVM_COMB_VER_OFF 0x0083 #define NVM_COMB_VER_PTR 0x003d -#define NVM_MAJOR_MASK 0xF000 -#define NVM_MINOR_MASK 0x0FF0 -#define NVM_BUILD_MASK 0x000F -#define NVM_COMB_VER_MASK 0x00FF -#define NVM_MAJOR_SHIFT 12 -#define NVM_MINOR_SHIFT 4 -#define NVM_COMB_VER_SHFT 8 -#define NVM_VER_INVALID 0xFFFF -#define NVM_ETRACK_SHIFT 16 + +/* NVM version defines */ +#define NVM_MAJOR_MASK 0xF000 +#define NVM_MINOR_MASK 0x0FF0 +#define NVM_IMAGE_ID_MASK 0x000F +#define NVM_COMB_VER_MASK 0x00FF +#define NVM_MAJOR_SHIFT 12 +#define NVM_MINOR_SHIFT 4 +#define NVM_COMB_VER_SHFT 8 +#define NVM_VER_INVALID 0xFFFF +#define NVM_ETRACK_SHIFT 16 +#define NVM_ETRACK_VALID 0x8000 +#define NVM_NEW_DEC_MASK 0x0F00 +#define NVM_HEX_CONV 16 +#define NVM_HEX_TENS 10 + #define NVM_ETS_CFG 0x003E #define NVM_ETS_LTHRES_DELTA_MASK 0x07C0 #define NVM_ETS_LTHRES_DELTA_SHIFT 6 diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h index 94d7866b9c2..37a9c06a6c6 100644 --- a/drivers/net/ethernet/intel/igb/e1000_hw.h +++ b/drivers/net/ethernet/intel/igb/e1000_hw.h @@ -67,6 +67,8 @@ struct e1000_hw; #define E1000_DEV_ID_I210_FIBER 0x1536 #define E1000_DEV_ID_I210_SERDES 0x1537 #define E1000_DEV_ID_I210_SGMII 0x1538 +#define E1000_DEV_ID_I210_COPPER_FLASHLESS 0x157B +#define E1000_DEV_ID_I210_SERDES_FLASHLESS 0x157C #define E1000_DEV_ID_I211_COPPER 0x1539 #define E1000_DEV_ID_I354_BACKPLANE_1GBPS 0x1F40 #define E1000_DEV_ID_I354_SGMII 0x1F41 @@ -110,6 +112,7 @@ enum e1000_nvm_type { e1000_nvm_none, e1000_nvm_eeprom_spi, e1000_nvm_flash_hw, + e1000_nvm_invm, e1000_nvm_flash_sw }; diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c index ddb3cf51b9b..0c0393316a3 100644 --- a/drivers/net/ethernet/intel/igb/e1000_i210.c +++ b/drivers/net/ethernet/intel/igb/e1000_i210.c @@ -335,57 +335,101 @@ s32 igb_write_nvm_srwr_i210(struct e1000_hw *hw, u16 offset, u16 words, } /** - * igb_read_nvm_i211 - Read NVM wrapper function for I211 + * igb_read_invm_word_i210 - Reads OTP + * @hw: pointer to the HW structure + * @address: the word address (aka eeprom offset) to read + * @data: pointer to the data read + * + * Reads 16-bit words from the OTP. Return error when the word is not + * stored in OTP. + **/ +static s32 igb_read_invm_word_i210(struct e1000_hw *hw, u8 address, u16 *data) +{ + s32 status = -E1000_ERR_INVM_VALUE_NOT_FOUND; + u32 invm_dword; + u16 i; + u8 record_type, word_address; + + for (i = 0; i < E1000_INVM_SIZE; i++) { + invm_dword = rd32(E1000_INVM_DATA_REG(i)); + /* Get record type */ + record_type = INVM_DWORD_TO_RECORD_TYPE(invm_dword); + if (record_type == E1000_INVM_UNINITIALIZED_STRUCTURE) + break; + if (record_type == E1000_INVM_CSR_AUTOLOAD_STRUCTURE) + i += E1000_INVM_CSR_AUTOLOAD_DATA_SIZE_IN_DWORDS; + if (record_type == E1000_INVM_RSA_KEY_SHA256_STRUCTURE) + i += E1000_INVM_RSA_KEY_SHA256_DATA_SIZE_IN_DWORDS; + if (record_type == E1000_INVM_WORD_AUTOLOAD_STRUCTURE) { + word_address = INVM_DWORD_TO_WORD_ADDRESS(invm_dword); + if (word_address == address) { + *data = INVM_DWORD_TO_WORD_DATA(invm_dword); + hw_dbg("Read INVM Word 0x%02x = %x", + address, *data); + status = E1000_SUCCESS; + break; + } + } + } + if (status != E1000_SUCCESS) + hw_dbg("Requested word 0x%02x not found in OTP\n", address); + return status; +} + +/** + * igb_read_invm_i210 - Read invm wrapper function for I210/I211 * @hw: pointer to the HW structure * @words: number of words to read * @data: pointer to the data read * * Wrapper function to return data formerly found in the NVM. **/ -s32 igb_read_nvm_i211(struct e1000_hw *hw, u16 offset, u16 words, - u16 *data) +static s32 igb_read_invm_i210(struct e1000_hw *hw, u16 offset, + u16 words __always_unused, u16 *data) { s32 ret_val = E1000_SUCCESS; /* Only the MAC addr is required to be present in the iNVM */ switch (offset) { case NVM_MAC_ADDR: - ret_val = igb_read_invm_i211(hw, offset, &data[0]); - ret_val |= igb_read_invm_i211(hw, offset+1, &data[1]); - ret_val |= igb_read_invm_i211(hw, offset+2, &data[2]); + ret_val = igb_read_invm_word_i210(hw, (u8)offset, &data[0]); + ret_val |= igb_read_invm_word_i210(hw, (u8)offset+1, + &data[1]); + ret_val |= igb_read_invm_word_i210(hw, (u8)offset+2, + &data[2]); if (ret_val != E1000_SUCCESS) hw_dbg("MAC Addr not found in iNVM\n"); break; case NVM_INIT_CTRL_2: - ret_val = igb_read_invm_i211(hw, (u8)offset, data); + ret_val = igb_read_invm_word_i210(hw, (u8)offset, data); if (ret_val != E1000_SUCCESS) { *data = NVM_INIT_CTRL_2_DEFAULT_I211; ret_val = E1000_SUCCESS; } break; case NVM_INIT_CTRL_4: - ret_val = igb_read_invm_i211(hw, (u8)offset, data); + ret_val = igb_read_invm_word_i210(hw, (u8)offset, data); if (ret_val != E1000_SUCCESS) { *data = NVM_INIT_CTRL_4_DEFAULT_I211; ret_val = E1000_SUCCESS; } break; case NVM_LED_1_CFG: - ret_val = igb_read_invm_i211(hw, (u8)offset, data); + ret_val = igb_read_invm_word_i210(hw, (u8)offset, data); if (ret_val != E1000_SUCCESS) { *data = NVM_LED_1_CFG_DEFAULT_I211; ret_val = E1000_SUCCESS; } break; case NVM_LED_0_2_CFG: - igb_read_invm_i211(hw, offset, data); + ret_val = igb_read_invm_word_i210(hw, (u8)offset, data); if (ret_val != E1000_SUCCESS) { *data = NVM_LED_0_2_CFG_DEFAULT_I211; ret_val = E1000_SUCCESS; } break; case NVM_ID_LED_SETTINGS: - ret_val = igb_read_invm_i211(hw, (u8)offset, data); + ret_val = igb_read_invm_word_i210(hw, (u8)offset, data); if (ret_val != E1000_SUCCESS) { *data = ID_LED_RESERVED_FFFF; ret_val = E1000_SUCCESS; @@ -411,48 +455,6 @@ s32 igb_read_nvm_i211(struct e1000_hw *hw, u16 offset, u16 words, } /** - * igb_read_invm_i211 - Reads OTP - * @hw: pointer to the HW structure - * @address: the word address (aka eeprom offset) to read - * @data: pointer to the data read - * - * Reads 16-bit words from the OTP. Return error when the word is not - * stored in OTP. - **/ -s32 igb_read_invm_i211(struct e1000_hw *hw, u16 address, u16 *data) -{ - s32 status = -E1000_ERR_INVM_VALUE_NOT_FOUND; - u32 invm_dword; - u16 i; - u8 record_type, word_address; - - for (i = 0; i < E1000_INVM_SIZE; i++) { - invm_dword = rd32(E1000_INVM_DATA_REG(i)); - /* Get record type */ - record_type = INVM_DWORD_TO_RECORD_TYPE(invm_dword); - if (record_type == E1000_INVM_UNINITIALIZED_STRUCTURE) - break; - if (record_type == E1000_INVM_CSR_AUTOLOAD_STRUCTURE) - i += E1000_INVM_CSR_AUTOLOAD_DATA_SIZE_IN_DWORDS; - if (record_type == E1000_INVM_RSA_KEY_SHA256_STRUCTURE) - i += E1000_INVM_RSA_KEY_SHA256_DATA_SIZE_IN_DWORDS; - if (record_type == E1000_INVM_WORD_AUTOLOAD_STRUCTURE) { - word_address = INVM_DWORD_TO_WORD_ADDRESS(invm_dword); - if (word_address == (u8)address) { - *data = INVM_DWORD_TO_WORD_DATA(invm_dword); - hw_dbg("Read INVM Word 0x%02x = %x", - address, *data); - status = E1000_SUCCESS; - break; - } - } - } - if (status != E1000_SUCCESS) - hw_dbg("Requested word 0x%02x not found in OTP\n", address); - return status; -} - -/** * igb_read_invm_version - Reads iNVM version and image type * @hw: pointer to the HW structure * @invm_ver: version structure for the version read @@ -661,6 +663,23 @@ static s32 igb_pool_flash_update_done_i210(struct e1000_hw *hw) } /** + * igb_get_flash_presence_i210 - Check if flash device is detected. + * @hw: pointer to the HW structure + * + **/ +bool igb_get_flash_presence_i210(struct e1000_hw *hw) +{ + u32 eec = 0; + bool ret_val = false; + + eec = rd32(E1000_EECD); + if (eec & E1000_EECD_FLASH_DETECTED_I210) + ret_val = true; + + return ret_val; +} + +/** * igb_update_flash_i210 - Commit EEPROM to the flash * @hw: pointer to the HW structure * @@ -786,3 +805,33 @@ s32 igb_write_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 data) { return __igb_access_xmdio_reg(hw, addr, dev_addr, &data, false); } + +/** + * igb_init_nvm_params_i210 - Init NVM func ptrs. + * @hw: pointer to the HW structure + **/ +s32 igb_init_nvm_params_i210(struct e1000_hw *hw) +{ + s32 ret_val = 0; + struct e1000_nvm_info *nvm = &hw->nvm; + + nvm->ops.acquire = igb_acquire_nvm_i210; + nvm->ops.release = igb_release_nvm_i210; + nvm->ops.valid_led_default = igb_valid_led_default_i210; + + /* NVM Function Pointers */ + if (igb_get_flash_presence_i210(hw)) { + hw->nvm.type = e1000_nvm_flash_hw; + nvm->ops.read = igb_read_nvm_srrd_i210; + nvm->ops.write = igb_write_nvm_srwr_i210; + nvm->ops.validate = igb_validate_nvm_checksum_i210; + nvm->ops.update = igb_update_nvm_checksum_i210; + } else { + hw->nvm.type = e1000_nvm_invm; + nvm->ops.read = igb_read_invm_i210; + nvm->ops.write = NULL; + nvm->ops.validate = NULL; + nvm->ops.update = NULL; + } + return ret_val; +} diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.h b/drivers/net/ethernet/intel/igb/e1000_i210.h index 5caa332e755..dde3c4b7ea9 100644 --- a/drivers/net/ethernet/intel/igb/e1000_i210.h +++ b/drivers/net/ethernet/intel/igb/e1000_i210.h @@ -35,20 +35,19 @@ extern s32 igb_write_nvm_srwr_i210(struct e1000_hw *hw, u16 offset, u16 words, u16 *data); extern s32 igb_read_nvm_srrd_i210(struct e1000_hw *hw, u16 offset, u16 words, u16 *data); -extern s32 igb_read_invm_i211(struct e1000_hw *hw, u16 address, u16 *data); extern s32 igb_acquire_swfw_sync_i210(struct e1000_hw *hw, u16 mask); extern void igb_release_swfw_sync_i210(struct e1000_hw *hw, u16 mask); extern s32 igb_acquire_nvm_i210(struct e1000_hw *hw); extern void igb_release_nvm_i210(struct e1000_hw *hw); extern s32 igb_valid_led_default_i210(struct e1000_hw *hw, u16 *data); -extern s32 igb_read_nvm_i211(struct e1000_hw *hw, u16 offset, u16 words, - u16 *data); extern s32 igb_read_invm_version(struct e1000_hw *hw, struct e1000_fw_version *invm_ver); extern s32 igb_read_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 *data); extern s32 igb_write_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 data); +extern s32 igb_init_nvm_params_i210(struct e1000_hw *hw); +extern bool igb_get_flash_presence_i210(struct e1000_hw *hw); #define E1000_STM_OPCODE 0xDB00 #define E1000_EEPROM_FLASH_SIZE_WORD 0x11 diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.c b/drivers/net/ethernet/intel/igb/e1000_nvm.c index 7f9cd7cbd35..a7db7f3db91 100644 --- a/drivers/net/ethernet/intel/igb/e1000_nvm.c +++ b/drivers/net/ethernet/intel/igb/e1000_nvm.c @@ -709,11 +709,16 @@ out: **/ void igb_get_fw_version(struct e1000_hw *hw, struct e1000_fw_version *fw_vers) { - u16 eeprom_verh, eeprom_verl, comb_verh, comb_verl, comb_offset; - u16 fw_version; + u16 eeprom_verh, eeprom_verl, etrack_test, fw_version; + u8 q, hval, rem, result; + u16 comb_verh, comb_verl, comb_offset; memset(fw_vers, 0, sizeof(struct e1000_fw_version)); + /* basic eeprom version numbers and bits used vary by part and by tool + * used to create the nvm images. Check which data format we have. + */ + hw->nvm.ops.read(hw, NVM_ETRACK_HIWORD, 1, &etrack_test); switch (hw->mac.type) { case e1000_i211: igb_read_invm_version(hw, fw_vers); @@ -721,30 +726,30 @@ void igb_get_fw_version(struct e1000_hw *hw, struct e1000_fw_version *fw_vers) case e1000_82575: case e1000_82576: case e1000_82580: - case e1000_i354: - case e1000_i350: - case e1000_i210: + /* Use this format, unless EETRACK ID exists, + * then use alternate format + */ + if ((etrack_test & NVM_MAJOR_MASK) != NVM_ETRACK_VALID) { + hw->nvm.ops.read(hw, NVM_VERSION, 1, &fw_version); + fw_vers->eep_major = (fw_version & NVM_MAJOR_MASK) + >> NVM_MAJOR_SHIFT; + fw_vers->eep_minor = (fw_version & NVM_MINOR_MASK) + >> NVM_MINOR_SHIFT; + fw_vers->eep_build = (fw_version & NVM_IMAGE_ID_MASK); + goto etrack_id; + } break; - default: - return; - } - /* basic eeprom version numbers */ - hw->nvm.ops.read(hw, NVM_VERSION, 1, &fw_version); - fw_vers->eep_major = (fw_version & NVM_MAJOR_MASK) >> NVM_MAJOR_SHIFT; - fw_vers->eep_minor = (fw_version & NVM_MINOR_MASK); - - /* etrack id */ - hw->nvm.ops.read(hw, NVM_ETRACK_WORD, 1, &eeprom_verl); - hw->nvm.ops.read(hw, (NVM_ETRACK_WORD + 1), 1, &eeprom_verh); - fw_vers->etrack_id = (eeprom_verh << NVM_ETRACK_SHIFT) | eeprom_verl; - - switch (hw->mac.type) { case e1000_i210: - case e1000_i354: + if (!(igb_get_flash_presence_i210(hw))) { + igb_read_invm_version(hw, fw_vers); + return; + } + /* fall through */ case e1000_i350: /* find combo image version */ hw->nvm.ops.read(hw, NVM_COMB_VER_PTR, 1, &comb_offset); - if ((comb_offset != 0x0) && (comb_offset != NVM_VER_INVALID)) { + if ((comb_offset != 0x0) && + (comb_offset != NVM_VER_INVALID)) { hw->nvm.ops.read(hw, (NVM_COMB_VER_OFF + comb_offset + 1), 1, &comb_verh); @@ -760,15 +765,42 @@ void igb_get_fw_version(struct e1000_hw *hw, struct e1000_fw_version *fw_vers) fw_vers->or_major = comb_verl >> NVM_COMB_VER_SHFT; fw_vers->or_build = - ((comb_verl << NVM_COMB_VER_SHFT) - | (comb_verh >> NVM_COMB_VER_SHFT)); + (comb_verl << NVM_COMB_VER_SHFT) + | (comb_verh >> NVM_COMB_VER_SHFT); fw_vers->or_patch = comb_verh & NVM_COMB_VER_MASK; } } break; default: - break; + return; + } + hw->nvm.ops.read(hw, NVM_VERSION, 1, &fw_version); + fw_vers->eep_major = (fw_version & NVM_MAJOR_MASK) + >> NVM_MAJOR_SHIFT; + + /* check for old style version format in newer images*/ + if ((fw_version & NVM_NEW_DEC_MASK) == 0x0) { + eeprom_verl = (fw_version & NVM_COMB_VER_MASK); + } else { + eeprom_verl = (fw_version & NVM_MINOR_MASK) + >> NVM_MINOR_SHIFT; + } + /* Convert minor value to hex before assigning to output struct + * Val to be converted will not be higher than 99, per tool output + */ + q = eeprom_verl / NVM_HEX_CONV; + hval = q * NVM_HEX_TENS; + rem = eeprom_verl % NVM_HEX_CONV; + result = hval + rem; + fw_vers->eep_minor = result; + +etrack_id: + if ((etrack_test & NVM_MAJOR_MASK) == NVM_ETRACK_VALID) { + hw->nvm.ops.read(hw, NVM_ETRACK_WORD, 1, &eeprom_verl); + hw->nvm.ops.read(hw, (NVM_ETRACK_WORD + 1), 1, &eeprom_verh); + fw_vers->etrack_id = (eeprom_verh << NVM_ETRACK_SHIFT) + | eeprom_verl; } return; } diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.h b/drivers/net/ethernet/intel/igb/e1000_nvm.h index 6bfc0c43aac..433b7419cb9 100644 --- a/drivers/net/ethernet/intel/igb/e1000_nvm.h +++ b/drivers/net/ethernet/intel/igb/e1000_nvm.h @@ -44,6 +44,7 @@ struct e1000_fw_version { u32 etrack_id; u16 eep_major; u16 eep_minor; + u16 eep_build; u8 invm_major; u8 invm_minor; diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 15ea8dc9dad..c1fae7aa0bd 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -343,6 +343,8 @@ struct hwmon_buff { }; #endif +#define IGB_RETA_SIZE 128 + /* board specific private data structure */ struct igb_adapter { unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; @@ -444,6 +446,8 @@ struct igb_adapter { struct i2c_algo_bit_data i2c_algo; struct i2c_adapter i2c_adap; struct i2c_client *i2c_client; + u32 rss_indir_tbl_init; + u8 rss_indir_tbl[IGB_RETA_SIZE]; }; #define IGB_FLAG_HAS_MSI (1 << 0) @@ -480,6 +484,7 @@ extern int igb_up(struct igb_adapter *); extern void igb_down(struct igb_adapter *); extern void igb_reinit_locked(struct igb_adapter *); extern void igb_reset(struct igb_adapter *); +extern void igb_write_rss_indir_tbl(struct igb_adapter *); extern int igb_set_spd_dplx(struct igb_adapter *, u32, u8); extern int igb_setup_tx_resources(struct igb_ring *); extern int igb_setup_rx_resources(struct igb_ring *); diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 85fe7b52f43..ce9b5a9e480 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -1335,12 +1335,23 @@ static int igb_reg_test(struct igb_adapter *adapter, u64 *data) static int igb_eeprom_test(struct igb_adapter *adapter, u64 *data) { + struct e1000_hw *hw = &adapter->hw; + *data = 0; - /* Validate eeprom on all parts but i211 */ - if (adapter->hw.mac.type != e1000_i211) { + /* Validate eeprom on all parts but flashless */ + switch (hw->mac.type) { + case e1000_i210: + case e1000_i211: + if (igb_get_flash_presence_i210(hw)) { + if (adapter->hw.nvm.ops.validate(&adapter->hw) < 0) + *data = 2; + } + break; + default: if (adapter->hw.nvm.ops.validate(&adapter->hw) < 0) *data = 2; + break; } return *data; @@ -2672,7 +2683,9 @@ static int igb_set_eee(struct net_device *netdev, igb_set_eee_i350(hw); /* reset link */ - if (!netif_running(netdev)) + if (netif_running(netdev)) + igb_reinit_locked(adapter); + else igb_reset(adapter); } @@ -2771,6 +2784,90 @@ static void igb_ethtool_complete(struct net_device *netdev) pm_runtime_put(&adapter->pdev->dev); } +static u32 igb_get_rxfh_indir_size(struct net_device *netdev) +{ + return IGB_RETA_SIZE; +} + +static int igb_get_rxfh_indir(struct net_device *netdev, u32 *indir) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + int i; + + for (i = 0; i < IGB_RETA_SIZE; i++) + indir[i] = adapter->rss_indir_tbl[i]; + + return 0; +} + +void igb_write_rss_indir_tbl(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 reg = E1000_RETA(0); + u32 shift = 0; + int i = 0; + + switch (hw->mac.type) { + case e1000_82575: + shift = 6; + break; + case e1000_82576: + /* 82576 supports 2 RSS queues for SR-IOV */ + if (adapter->vfs_allocated_count) + shift = 3; + break; + default: + break; + } + + while (i < IGB_RETA_SIZE) { + u32 val = 0; + int j; + + for (j = 3; j >= 0; j--) { + val <<= 8; + val |= adapter->rss_indir_tbl[i + j]; + } + + wr32(reg, val << shift); + reg += 4; + i += 4; + } +} + +static int igb_set_rxfh_indir(struct net_device *netdev, const u32 *indir) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + int i; + u32 num_queues; + + num_queues = adapter->rss_queues; + + switch (hw->mac.type) { + case e1000_82576: + /* 82576 supports 2 RSS queues for SR-IOV */ + if (adapter->vfs_allocated_count) + num_queues = 2; + break; + default: + break; + } + + /* Verify user input. */ + for (i = 0; i < IGB_RETA_SIZE; i++) + if (indir[i] >= num_queues) + return -EINVAL; + + + for (i = 0; i < IGB_RETA_SIZE; i++) + adapter->rss_indir_tbl[i] = indir[i]; + + igb_write_rss_indir_tbl(adapter); + + return 0; +} + static const struct ethtool_ops igb_ethtool_ops = { .get_settings = igb_get_settings, .set_settings = igb_set_settings, @@ -2804,6 +2901,9 @@ static const struct ethtool_ops igb_ethtool_ops = { .set_eee = igb_set_eee, .get_module_info = igb_get_module_info, .get_module_eeprom = igb_get_module_eeprom, + .get_rxfh_indir_size = igb_get_rxfh_indir_size, + .get_rxfh_indir = igb_get_rxfh_indir, + .set_rxfh_indir = igb_set_rxfh_indir, .begin = igb_ethtool_begin, .complete = igb_ethtool_complete, }; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index c1d72c03cb5..df33c4b8fa8 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -85,6 +85,8 @@ static DEFINE_PCI_DEVICE_TABLE(igb_pci_tbl) = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_I210_FIBER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I210_SERDES), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I210_SGMII), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I210_COPPER_FLASHLESS), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I210_SERDES_FLASHLESS), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I350_COPPER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I350_FIBER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I350_SERDES), board_82575 }, @@ -1013,7 +1015,7 @@ static void igb_free_q_vector(struct igb_adapter *adapter, int v_idx) adapter->q_vector[v_idx] = NULL; netif_napi_del(&q_vector->napi); - /* ixgbe_get_stats64() might access the rings on this vector, + /* igb_get_stats64() might access the rings on this vector, * we must wait a grace period before freeing it. */ kfree_rcu(q_vector, rcu); @@ -1929,12 +1931,17 @@ void igb_set_fw_version(struct igb_adapter *adapter) igb_get_fw_version(hw, &fw); switch (hw->mac.type) { + case e1000_i210: case e1000_i211: - snprintf(adapter->fw_version, sizeof(adapter->fw_version), - "%2d.%2d-%d", - fw.invm_major, fw.invm_minor, fw.invm_img_type); - break; - + if (!(igb_get_flash_presence_i210(hw))) { + snprintf(adapter->fw_version, + sizeof(adapter->fw_version), + "%2d.%2d-%d", + fw.invm_major, fw.invm_minor, + fw.invm_img_type); + break; + } + /* fall through */ default: /* if option is rom valid, display its version too */ if (fw.or_valid) { @@ -1944,11 +1951,16 @@ void igb_set_fw_version(struct igb_adapter *adapter) fw.eep_major, fw.eep_minor, fw.etrack_id, fw.or_major, fw.or_build, fw.or_patch); /* no option rom */ - } else { + } else if (fw.etrack_id != 0X0000) { snprintf(adapter->fw_version, - sizeof(adapter->fw_version), - "%d.%d, 0x%08x", - fw.eep_major, fw.eep_minor, fw.etrack_id); + sizeof(adapter->fw_version), + "%d.%d, 0x%08x", + fw.eep_major, fw.eep_minor, fw.etrack_id); + } else { + snprintf(adapter->fw_version, + sizeof(adapter->fw_version), + "%d.%d.%d", + fw.eep_major, fw.eep_minor, fw.eep_build); } break; } @@ -2166,15 +2178,28 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) */ hw->mac.ops.reset_hw(hw); - /* make sure the NVM is good , i211 parts have special NVM that - * doesn't contain a checksum + /* make sure the NVM is good , i211/i210 parts can have special NVM + * that doesn't contain a checksum */ - if (hw->mac.type != e1000_i211) { + switch (hw->mac.type) { + case e1000_i210: + case e1000_i211: + if (igb_get_flash_presence_i210(hw)) { + if (hw->nvm.ops.validate(hw) < 0) { + dev_err(&pdev->dev, + "The NVM Checksum Is Not Valid\n"); + err = -EIO; + goto err_eeprom; + } + } + break; + default: if (hw->nvm.ops.validate(hw) < 0) { dev_err(&pdev->dev, "The NVM Checksum Is Not Valid\n"); err = -EIO; goto err_eeprom; } + break; } /* copy the MAC address out of the NVM */ @@ -2436,6 +2461,11 @@ static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs) int err = 0; int i; + if (!adapter->msix_entries) { + err = -EPERM; + goto out; + } + if (!num_vfs) goto out; else if (old_vfs && old_vfs == num_vfs) @@ -3096,7 +3126,7 @@ static void igb_setup_mrqc(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; u32 mrqc, rxcsum; - u32 j, num_rx_queues, shift = 0; + u32 j, num_rx_queues; static const u32 rsskey[10] = { 0xDA565A6D, 0xC20E5B25, 0x3D256741, 0xB08FA343, 0xCB2BCAD0, 0xB4307BAE, 0xA32DCB77, 0x0CF23080, 0x3BB7426A, @@ -3109,35 +3139,21 @@ static void igb_setup_mrqc(struct igb_adapter *adapter) num_rx_queues = adapter->rss_queues; switch (hw->mac.type) { - case e1000_82575: - shift = 6; - break; case e1000_82576: /* 82576 supports 2 RSS queues for SR-IOV */ - if (adapter->vfs_allocated_count) { - shift = 3; + if (adapter->vfs_allocated_count) num_rx_queues = 2; - } break; default: break; } - /* Populate the indirection table 4 entries at a time. To do this - * we are generating the results for n and n+2 and then interleaving - * those with the results with n+1 and n+3. - */ - for (j = 0; j < 32; j++) { - /* first pass generates n and n+2 */ - u32 base = ((j * 0x00040004) + 0x00020000) * num_rx_queues; - u32 reta = (base & 0x07800780) >> (7 - shift); - - /* second pass generates n+1 and n+3 */ - base += 0x00010001 * num_rx_queues; - reta |= (base & 0x07800780) << (1 + shift); - - wr32(E1000_RETA(j), reta); + if (adapter->rss_indir_tbl_init != num_rx_queues) { + for (j = 0; j < IGB_RETA_SIZE; j++) + adapter->rss_indir_tbl[j] = (j * num_rx_queues) / IGB_RETA_SIZE; + adapter->rss_indir_tbl_init = num_rx_queues; } + igb_write_rss_indir_tbl(adapter); /* Disable raw packet checksumming so that RSS hash is placed in * descriptor on writeback. No need to enable TCP/UDP/IP checksum @@ -3844,7 +3860,6 @@ bool igb_has_link(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; bool link_active = false; - s32 ret_val = 0; /* get_link_status is set on LSC (link status) interrupt or * rx sequence error interrupt. get_link_status will stay @@ -3853,16 +3868,11 @@ bool igb_has_link(struct igb_adapter *adapter) */ switch (hw->phy.media_type) { case e1000_media_type_copper: - if (hw->mac.get_link_status) { - ret_val = hw->mac.ops.check_for_link(hw); - link_active = !hw->mac.get_link_status; - } else { - link_active = true; - } - break; + if (!hw->mac.get_link_status) + return true; case e1000_media_type_internal_serdes: - ret_val = hw->mac.ops.check_for_link(hw); - link_active = hw->mac.serdes_has_link; + hw->mac.ops.check_for_link(hw); + link_active = !hw->mac.get_link_status; break; default: case e1000_media_type_unknown: @@ -4814,6 +4824,10 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu) return -EINVAL; } + /* adjust max frame to be at least the size of a standard frame */ + if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN)) + max_frame = ETH_FRAME_LEN + ETH_FCS_LEN; + while (test_and_set_bit(__IGB_RESETTING, &adapter->state)) msleep(1); @@ -4865,6 +4879,8 @@ void igb_update_stats(struct igb_adapter *adapter, bytes = 0; packets = 0; + + rcu_read_lock(); for (i = 0; i < adapter->num_rx_queues; i++) { u32 rqdpc = rd32(E1000_RQDPC(i)); struct igb_ring *ring = adapter->rx_ring[i]; @@ -4900,6 +4916,7 @@ void igb_update_stats(struct igb_adapter *adapter, } net_stats->tx_bytes = bytes; net_stats->tx_packets = packets; + rcu_read_unlock(); /* read stats registers */ adapter->stats.crcerrs += rd32(E1000_CRCERRS); diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 7e8c477b0ab..5a54e3dc535 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -97,14 +97,14 @@ static cycle_t igb_ptp_read_82580(const struct cyclecounter *cc) { struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc); struct e1000_hw *hw = &igb->hw; + u32 lo, hi; u64 val; - u32 lo, hi, jk; /* The timestamp latches on lowest register read. For the 82580 * the lowest register is SYSTIMR instead of SYSTIML. However we only * need to provide nanosecond resolution, so we just ignore it. */ - jk = rd32(E1000_SYSTIMR); + rd32(E1000_SYSTIMR); lo = rd32(E1000_SYSTIML); hi = rd32(E1000_SYSTIMH); @@ -118,13 +118,13 @@ static cycle_t igb_ptp_read_82580(const struct cyclecounter *cc) static void igb_ptp_read_i210(struct igb_adapter *adapter, struct timespec *ts) { struct e1000_hw *hw = &adapter->hw; - u32 sec, nsec, jk; + u32 sec, nsec; /* The timestamp latches on lowest register read. For I210/I211, the * lowest register is SYSTIMR. Since we only need to provide nanosecond * resolution, we can ignore it. */ - jk = rd32(E1000_SYSTIMR); + rd32(E1000_SYSTIMR); nsec = rd32(E1000_SYSTIML); sec = rd32(E1000_SYSTIMH); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c index 9d4a1ea030d..b4881b68615 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c @@ -160,6 +160,7 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) { struct mlx4_en_priv *priv = netdev_priv(dev); + struct mlx4_en_port_profile *prof = priv->prof; struct mlx4_en_dev *mdev = priv->mdev; int err; @@ -169,15 +170,17 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev, pfc->mbc, pfc->delay); - priv->prof->rx_pause = priv->prof->tx_pause = !!pfc->pfc_en; - priv->prof->rx_ppp = priv->prof->tx_ppp = pfc->pfc_en; + prof->rx_pause = !pfc->pfc_en; + prof->tx_pause = !pfc->pfc_en; + prof->rx_ppp = pfc->pfc_en; + prof->tx_ppp = pfc->pfc_en; err = mlx4_SET_PORT_general(mdev->dev, priv->port, priv->rx_skb_size + ETH_FCS_LEN, - priv->prof->tx_pause, - priv->prof->tx_ppp, - priv->prof->rx_pause, - priv->prof->rx_ppp); + prof->tx_pause, + prof->tx_ppp, + prof->rx_pause, + prof->rx_ppp); if (err) en_err(priv, "Failed setting pause params\n"); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 6dcca981788..0698c82d6ff 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -362,6 +362,15 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq) */ rmb(); + if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == + MLX4_CQE_OPCODE_ERROR)) { + struct mlx4_err_cqe *cqe_err = (struct mlx4_err_cqe *)cqe; + + en_err(priv, "CQE error - vendor syndrome: 0x%x syndrome: 0x%x\n", + cqe_err->vendor_err_syndrome, + cqe_err->syndrome); + } + /* Skip over last polled CQE */ new_index = be16_to_cpu(cqe->wqe_index) & size_mask; @@ -579,17 +588,15 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; + struct device *ddev = priv->ddev; struct mlx4_en_tx_ring *ring; struct mlx4_en_tx_desc *tx_desc; struct mlx4_wqe_data_seg *data; - struct skb_frag_struct *frag; struct mlx4_en_tx_info *tx_info; - struct ethhdr *ethh; int tx_ind = 0; int nr_txbb; int desc_size; int real_size; - dma_addr_t dma; u32 index, bf_index; __be32 op_own; u16 vlan_tag = 0; @@ -665,6 +672,61 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) tx_info->skb = skb; tx_info->nr_txbb = nr_txbb; + if (lso_header_size) + data = ((void *)&tx_desc->lso + ALIGN(lso_header_size + 4, + DS_SIZE)); + else + data = &tx_desc->data; + + /* valid only for none inline segments */ + tx_info->data_offset = (void *)data - (void *)tx_desc; + + tx_info->linear = (lso_header_size < skb_headlen(skb) && + !is_inline(skb, NULL)) ? 1 : 0; + + data += skb_shinfo(skb)->nr_frags + tx_info->linear - 1; + + if (is_inline(skb, &fragptr)) { + tx_info->inl = 1; + } else { + /* Map fragments */ + for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) { + struct skb_frag_struct *frag; + dma_addr_t dma; + + frag = &skb_shinfo(skb)->frags[i]; + dma = skb_frag_dma_map(ddev, frag, + 0, skb_frag_size(frag), + DMA_TO_DEVICE); + if (dma_mapping_error(ddev, dma)) + goto tx_drop_unmap; + + data->addr = cpu_to_be64(dma); + data->lkey = cpu_to_be32(mdev->mr.key); + wmb(); + data->byte_count = cpu_to_be32(skb_frag_size(frag)); + --data; + } + + /* Map linear part */ + if (tx_info->linear) { + u32 byte_count = skb_headlen(skb) - lso_header_size; + dma_addr_t dma; + + dma = dma_map_single(ddev, skb->data + + lso_header_size, byte_count, + PCI_DMA_TODEVICE); + if (dma_mapping_error(ddev, dma)) + goto tx_drop_unmap; + + data->addr = cpu_to_be64(dma); + data->lkey = cpu_to_be32(mdev->mr.key); + wmb(); + data->byte_count = cpu_to_be32(byte_count); + } + tx_info->inl = 0; + } + /* * For timestamping add flag to skb_shinfo and * set flag for further reference @@ -689,6 +751,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) } if (priv->flags & MLX4_EN_FLAG_ENABLE_HW_LOOPBACK) { + struct ethhdr *ethh; + /* Copy dst mac address to wqe. This allows loopback in eSwitch, * so that VFs and PF can communicate with each other */ @@ -711,8 +775,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) /* Copy headers; * note that we already verified that it is linear */ memcpy(tx_desc->lso.header, skb->data, lso_header_size); - data = ((void *) &tx_desc->lso + - ALIGN(lso_header_size + 4, DS_SIZE)); priv->port_stats.tso_packets++; i = ((skb->len - lso_header_size) / skb_shinfo(skb)->gso_size) + @@ -724,7 +786,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) op_own = cpu_to_be32(MLX4_OPCODE_SEND) | ((ring->prod & ring->size) ? cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0); - data = &tx_desc->data; tx_info->nr_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); ring->packets++; @@ -733,38 +794,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) netdev_tx_sent_queue(ring->tx_queue, tx_info->nr_bytes); AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, skb->len); - - /* valid only for none inline segments */ - tx_info->data_offset = (void *) data - (void *) tx_desc; - - tx_info->linear = (lso_header_size < skb_headlen(skb) && !is_inline(skb, NULL)) ? 1 : 0; - data += skb_shinfo(skb)->nr_frags + tx_info->linear - 1; - - if (!is_inline(skb, &fragptr)) { - /* Map fragments */ - for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) { - frag = &skb_shinfo(skb)->frags[i]; - dma = skb_frag_dma_map(priv->ddev, frag, - 0, skb_frag_size(frag), - DMA_TO_DEVICE); - data->addr = cpu_to_be64(dma); - data->lkey = cpu_to_be32(mdev->mr.key); - wmb(); - data->byte_count = cpu_to_be32(skb_frag_size(frag)); - --data; - } - - /* Map linear part */ - if (tx_info->linear) { - dma = dma_map_single(priv->ddev, skb->data + lso_header_size, - skb_headlen(skb) - lso_header_size, PCI_DMA_TODEVICE); - data->addr = cpu_to_be64(dma); - data->lkey = cpu_to_be32(mdev->mr.key); - wmb(); - data->byte_count = cpu_to_be32(skb_headlen(skb) - lso_header_size); - } - tx_info->inl = 0; - } else { + if (tx_info->inl) { build_inline_wqe(tx_desc, skb, real_size, &vlan_tag, tx_ind, fragptr); tx_info->inl = 1; } @@ -804,6 +834,16 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; +tx_drop_unmap: + en_err(priv, "DMA mapping error\n"); + + for (i++; i < skb_shinfo(skb)->nr_frags; i++) { + data++; + dma_unmap_page(ddev, (dma_addr_t) be64_to_cpu(data->addr), + be32_to_cpu(data->byte_count), + PCI_DMA_TODEVICE); + } + tx_drop: dev_kfree_skb_any(skb); priv->stats.tx_dropped++; diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index abd2c545df8..83c2091c9c2 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -314,6 +314,7 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) unsigned int len; unsigned int tx_head = priv->tx_head; u32 txdes1; + int ret = NETDEV_TX_BUSY; desc = priv->tx_desc_base + (TX_REG_DESC_SIZE * tx_head); @@ -321,7 +322,7 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) if (readl(desc + TX_REG_OFFSET_DESC0) & TX_DESC0_DMA_OWN) { net_dbg_ratelimited("no TX space for packet\n"); priv->stats.tx_dropped++; - return NETDEV_TX_BUSY; + goto out_unlock; } len = skb->len > TX_BUF_SIZE ? TX_BUF_SIZE : skb->len; @@ -330,7 +331,7 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) len, DMA_TO_DEVICE); if (dma_mapping_error(&ndev->dev, priv->tx_mapping[tx_head])) { netdev_err(ndev, "DMA mapping error\n"); - return NETDEV_TX_BUSY; + goto out_unlock; } priv->tx_len[tx_head] = len; @@ -360,10 +361,11 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) priv->tx_head = TX_NEXT(tx_head); ndev->trans_start = jiffies; - + ret = NETDEV_TX_OK; +out_unlock: spin_unlock_irq(&priv->txlock); - return NETDEV_TX_OK; + return ret; } static struct net_device_stats *moxart_mac_get_stats(struct net_device *ndev) @@ -531,7 +533,6 @@ static int moxart_remove(struct platform_device *pdev) unregister_netdev(ndev); free_irq(ndev->irq, ndev); moxart_mac_free_memory(ndev); - platform_set_drvdata(pdev, NULL); free_netdev(ndev); return 0; diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 66c040047da..50a1d4a04eb 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -74,6 +74,7 @@ #ifdef CONFIG_MTRR #include <asm/mtrr.h> #endif +#include <net/busy_poll.h> #include "myri10ge_mcp.h" #include "myri10ge_mcp_gen_header.h" @@ -194,6 +195,21 @@ struct myri10ge_slice_state { int cpu; __be32 __iomem *dca_tag; #endif +#ifdef CONFIG_NET_RX_BUSY_POLL + unsigned int state; +#define SLICE_STATE_IDLE 0 +#define SLICE_STATE_NAPI 1 /* NAPI owns this slice */ +#define SLICE_STATE_POLL 2 /* poll owns this slice */ +#define SLICE_LOCKED (SLICE_STATE_NAPI | SLICE_STATE_POLL) +#define SLICE_STATE_NAPI_YIELD 4 /* NAPI yielded this slice */ +#define SLICE_STATE_POLL_YIELD 8 /* poll yielded this slice */ +#define SLICE_USER_PEND (SLICE_STATE_POLL | SLICE_STATE_POLL_YIELD) + spinlock_t lock; + unsigned long lock_napi_yield; + unsigned long lock_poll_yield; + unsigned long busy_poll_miss; + unsigned long busy_poll_cnt; +#endif /* CONFIG_NET_RX_BUSY_POLL */ char irq_desc[32]; }; @@ -909,6 +925,92 @@ abort: return status; } +#ifdef CONFIG_NET_RX_BUSY_POLL +static inline void myri10ge_ss_init_lock(struct myri10ge_slice_state *ss) +{ + spin_lock_init(&ss->lock); + ss->state = SLICE_STATE_IDLE; +} + +static inline bool myri10ge_ss_lock_napi(struct myri10ge_slice_state *ss) +{ + int rc = true; + spin_lock(&ss->lock); + if ((ss->state & SLICE_LOCKED)) { + WARN_ON((ss->state & SLICE_STATE_NAPI)); + ss->state |= SLICE_STATE_NAPI_YIELD; + rc = false; + ss->lock_napi_yield++; + } else + ss->state = SLICE_STATE_NAPI; + spin_unlock(&ss->lock); + return rc; +} + +static inline void myri10ge_ss_unlock_napi(struct myri10ge_slice_state *ss) +{ + spin_lock(&ss->lock); + WARN_ON((ss->state & (SLICE_STATE_POLL | SLICE_STATE_NAPI_YIELD))); + ss->state = SLICE_STATE_IDLE; + spin_unlock(&ss->lock); +} + +static inline bool myri10ge_ss_lock_poll(struct myri10ge_slice_state *ss) +{ + int rc = true; + spin_lock_bh(&ss->lock); + if ((ss->state & SLICE_LOCKED)) { + ss->state |= SLICE_STATE_POLL_YIELD; + rc = false; + ss->lock_poll_yield++; + } else + ss->state |= SLICE_STATE_POLL; + spin_unlock_bh(&ss->lock); + return rc; +} + +static inline void myri10ge_ss_unlock_poll(struct myri10ge_slice_state *ss) +{ + spin_lock_bh(&ss->lock); + WARN_ON((ss->state & SLICE_STATE_NAPI)); + ss->state = SLICE_STATE_IDLE; + spin_unlock_bh(&ss->lock); +} + +static inline bool myri10ge_ss_busy_polling(struct myri10ge_slice_state *ss) +{ + WARN_ON(!(ss->state & SLICE_LOCKED)); + return (ss->state & SLICE_USER_PEND); +} +#else /* CONFIG_NET_RX_BUSY_POLL */ +static inline void myri10ge_ss_init_lock(struct myri10ge_slice_state *ss) +{ +} + +static inline bool myri10ge_ss_lock_napi(struct myri10ge_slice_state *ss) +{ + return false; +} + +static inline void myri10ge_ss_unlock_napi(struct myri10ge_slice_state *ss) +{ +} + +static inline bool myri10ge_ss_lock_poll(struct myri10ge_slice_state *ss) +{ + return false; +} + +static inline void myri10ge_ss_unlock_poll(struct myri10ge_slice_state *ss) +{ +} + +static inline bool myri10ge_ss_busy_polling(struct myri10ge_slice_state *ss) +{ + return false; +} +#endif + static int myri10ge_reset(struct myri10ge_priv *mgp) { struct myri10ge_cmd cmd; @@ -1300,6 +1402,8 @@ myri10ge_vlan_rx(struct net_device *dev, void *addr, struct sk_buff *skb) } } +#define MYRI10GE_HLEN 64 /* Bytes to copy from page to skb linear memory */ + static inline int myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum) { @@ -1311,6 +1415,7 @@ myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum) struct pci_dev *pdev = mgp->pdev; struct net_device *dev = mgp->dev; u8 *va; + bool polling; if (len <= mgp->small_bytes) { rx = &ss->rx_small; @@ -1325,7 +1430,15 @@ myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum) va = page_address(rx->info[idx].page) + rx->info[idx].page_offset; prefetch(va); - skb = napi_get_frags(&ss->napi); + /* When busy polling in user context, allocate skb and copy headers to + * skb's linear memory ourselves. When not busy polling, use the napi + * gro api. + */ + polling = myri10ge_ss_busy_polling(ss); + if (polling) + skb = netdev_alloc_skb(dev, MYRI10GE_HLEN + 16); + else + skb = napi_get_frags(&ss->napi); if (unlikely(skb == NULL)) { ss->stats.rx_dropped++; for (i = 0, remainder = len; remainder > 0; i++) { @@ -1364,8 +1477,29 @@ myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum) } myri10ge_vlan_rx(mgp->dev, va, skb); skb_record_rx_queue(skb, ss - &mgp->ss[0]); + skb_mark_napi_id(skb, &ss->napi); + + if (polling) { + int hlen; + + /* myri10ge_vlan_rx might have moved the header, so compute + * length and address again. + */ + hlen = MYRI10GE_HLEN > skb->len ? skb->len : MYRI10GE_HLEN; + va = page_address(skb_frag_page(&rx_frags[0])) + + rx_frags[0].page_offset; + /* Copy header into the skb linear memory */ + skb_copy_to_linear_data(skb, va, hlen); + rx_frags[0].page_offset += hlen; + rx_frags[0].size -= hlen; + skb->data_len -= hlen; + skb->tail += hlen; + skb->protocol = eth_type_trans(skb, dev); + netif_receive_skb(skb); + } + else + napi_gro_frags(&ss->napi); - napi_gro_frags(&ss->napi); return 1; } @@ -1524,10 +1658,14 @@ static int myri10ge_poll(struct napi_struct *napi, int budget) if (ss->mgp->dca_enabled) myri10ge_update_dca(ss); #endif + /* Try later if the busy_poll handler is running. */ + if (!myri10ge_ss_lock_napi(ss)) + return budget; /* process as many rx events as NAPI will allow */ work_done = myri10ge_clean_rx_done(ss, budget); + myri10ge_ss_unlock_napi(ss); if (work_done < budget) { napi_complete(napi); put_be32(htonl(3), ss->irq_claim); @@ -1535,6 +1673,34 @@ static int myri10ge_poll(struct napi_struct *napi, int budget) return work_done; } +#ifdef CONFIG_NET_RX_BUSY_POLL +static int myri10ge_busy_poll(struct napi_struct *napi) +{ + struct myri10ge_slice_state *ss = + container_of(napi, struct myri10ge_slice_state, napi); + struct myri10ge_priv *mgp = ss->mgp; + int work_done; + + /* Poll only when the link is up */ + if (mgp->link_state != MXGEFW_LINK_UP) + return LL_FLUSH_FAILED; + + if (!myri10ge_ss_lock_poll(ss)) + return LL_FLUSH_BUSY; + + /* Process a small number of packets */ + work_done = myri10ge_clean_rx_done(ss, 4); + if (work_done) + ss->busy_poll_cnt += work_done; + else + ss->busy_poll_miss++; + + myri10ge_ss_unlock_poll(ss); + + return work_done; +} +#endif /* CONFIG_NET_RX_BUSY_POLL */ + static irqreturn_t myri10ge_intr(int irq, void *arg) { struct myri10ge_slice_state *ss = arg; @@ -1742,6 +1908,10 @@ static const char myri10ge_gstrings_slice_stats[][ETH_GSTRING_LEN] = { "tx_pkt_start", "tx_pkt_done", "tx_req", "tx_done", "rx_small_cnt", "rx_big_cnt", "wake_queue", "stop_queue", "tx_linearized", +#ifdef CONFIG_NET_RX_BUSY_POLL + "rx_lock_napi_yield", "rx_lock_poll_yield", "rx_busy_poll_miss", + "rx_busy_poll_cnt", +#endif }; #define MYRI10GE_NET_STATS_LEN 21 @@ -1842,6 +2012,12 @@ myri10ge_get_ethtool_stats(struct net_device *netdev, data[i++] = (unsigned int)ss->tx.wake_queue; data[i++] = (unsigned int)ss->tx.stop_queue; data[i++] = (unsigned int)ss->tx.linearized; +#ifdef CONFIG_NET_RX_BUSY_POLL + data[i++] = ss->lock_napi_yield; + data[i++] = ss->lock_poll_yield; + data[i++] = ss->busy_poll_miss; + data[i++] = ss->busy_poll_cnt; +#endif } } @@ -2405,6 +2581,9 @@ static int myri10ge_open(struct net_device *dev) goto abort_with_rings; } + /* Initialize the slice spinlock and state used for polling */ + myri10ge_ss_init_lock(ss); + /* must happen prior to any irq */ napi_enable(&(ss)->napi); } @@ -2481,9 +2660,19 @@ static int myri10ge_close(struct net_device *dev) del_timer_sync(&mgp->watchdog_timer); mgp->running = MYRI10GE_ETH_STOPPING; + local_bh_disable(); /* myri10ge_ss_lock_napi needs bh disabled */ for (i = 0; i < mgp->num_slices; i++) { napi_disable(&mgp->ss[i].napi); + /* Lock the slice to prevent the busy_poll handler from + * accessing it. Later when we bring the NIC up, myri10ge_open + * resets the slice including this lock. + */ + while (!myri10ge_ss_lock_napi(&mgp->ss[i])) { + pr_info("Slice %d locked\n", i); + mdelay(1); + } } + local_bh_enable(); netif_carrier_off(dev); netif_tx_stop_all_queues(dev); @@ -3569,8 +3758,11 @@ static void myri10ge_free_slices(struct myri10ge_priv *mgp) ss->fw_stats, ss->fw_stats_bus); ss->fw_stats = NULL; } + napi_hash_del(&ss->napi); netif_napi_del(&ss->napi); } + /* Wait till napi structs are no longer used, and then free ss. */ + synchronize_rcu(); kfree(mgp->ss); mgp->ss = NULL; } @@ -3606,6 +3798,7 @@ static int myri10ge_alloc_slices(struct myri10ge_priv *mgp) ss->dev = mgp->dev; netif_napi_add(ss->dev, &ss->napi, myri10ge_poll, myri10ge_napi_weight); + napi_hash_add(&ss->napi); } return 0; abort: @@ -3748,6 +3941,9 @@ static const struct net_device_ops myri10ge_netdev_ops = { .ndo_change_mtu = myri10ge_change_mtu, .ndo_set_rx_mode = myri10ge_set_multicast_list, .ndo_set_mac_address = myri10ge_set_mac_address, +#ifdef CONFIG_NET_RX_BUSY_POLL + .ndo_busy_poll = myri10ge_busy_poll, +#endif }; static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent) diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c index 1129db0cdf8..f0ceb89af93 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c @@ -118,6 +118,7 @@ static int pch_gbe_set_settings(struct net_device *netdev, * filled by get_settings() on a down link, speed is -1: */ if (speed == UINT_MAX) { speed = SPEED_1000; + ethtool_cmd_speed_set(ecmd, speed); ecmd->duplex = DUPLEX_FULL; } ret = mii_ethtool_sset(&adapter->mii, ecmd); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 73873541786..3f03856768a 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -36,9 +36,9 @@ #include "qlcnic_83xx_hw.h" #define _QLCNIC_LINUX_MAJOR 5 -#define _QLCNIC_LINUX_MINOR 2 -#define _QLCNIC_LINUX_SUBVERSION 46 -#define QLCNIC_LINUX_VERSIONID "5.2.46" +#define _QLCNIC_LINUX_MINOR 3 +#define _QLCNIC_LINUX_SUBVERSION 48 +#define QLCNIC_LINUX_VERSIONID "5.3.48" #define QLCNIC_DRV_IDC_VER 0x01 #define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\ (_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION)) @@ -97,6 +97,9 @@ #define TX_STOP_THRESH ((MAX_SKB_FRAGS >> 2) + MAX_TSO_HEADER_DESC \ + MGMT_CMD_DESC_RESV) #define QLCNIC_MAX_TX_TIMEOUTS 2 +#define QLCNIC_MAX_TX_RINGS 8 +#define QLCNIC_MAX_SDS_RINGS 8 + /* * Following are the states of the Phantom. Phantom will set them and * Host will read to check if the fields are correct. @@ -467,6 +470,8 @@ struct qlcnic_hardware_context { u32 mbox_aen[QLC_83XX_MBX_AEN_CNT]; u32 mbox_reg[4]; struct qlcnic_mailbox *mailbox; + u8 extend_lb_time; + u8 phys_port_id[ETH_ALEN]; }; struct qlcnic_adapter_stats { @@ -514,6 +519,7 @@ struct qlcnic_host_sds_ring { u32 num_desc; void __iomem *crb_sts_consumer; + struct qlcnic_host_tx_ring *tx_ring; struct status_desc *desc_head; struct qlcnic_adapter *adapter; struct napi_struct napi; @@ -531,9 +537,17 @@ struct qlcnic_host_tx_ring { void __iomem *crb_intr_mask; char name[IFNAMSIZ + 12]; u16 ctx_id; + + u32 state; u32 producer; u32 sw_consumer; u32 num_desc; + + u64 xmit_on; + u64 xmit_off; + u64 xmit_called; + u64 xmit_finished; + void __iomem *crb_cmd_producer; struct cmd_desc_type0 *desc_head; struct qlcnic_adapter *adapter; @@ -558,7 +572,6 @@ struct qlcnic_recv_context { u32 state; u16 context_id; u16 virt_port; - }; /* HW context creation */ @@ -603,6 +616,7 @@ struct qlcnic_recv_context { #define QLCNIC_CAP0_LRO_CONTIGUOUS (1 << 8) #define QLCNIC_CAP0_VALIDOFF (1 << 11) #define QLCNIC_CAP0_LRO_MSS (1 << 21) +#define QLCNIC_CAP0_TX_MULTI (1 << 22) /* * Context state @@ -630,7 +644,7 @@ struct qlcnic_hostrq_rds_ring { struct qlcnic_hostrq_rx_ctx { __le64 host_rsp_dma_addr; /* Response dma'd here */ - __le32 capabilities[4]; /* Flag bit vector */ + __le32 capabilities[4]; /* Flag bit vector */ __le32 host_int_crb_mode; /* Interrupt crb usage */ __le32 host_rds_crb_mode; /* RDS crb usage */ /* These ring offsets are relative to data[0] below */ @@ -813,6 +827,7 @@ struct qlcnic_mac_list_s { #define QLCNIC_FW_CAPABILITY_BDG BIT_8 #define QLCNIC_FW_CAPABILITY_FVLANTX BIT_9 #define QLCNIC_FW_CAPABILITY_HW_LRO BIT_10 +#define QLCNIC_FW_CAPABILITY_2_MULTI_TX BIT_4 #define QLCNIC_FW_CAPABILITY_MULTI_LOOPBACK BIT_27 #define QLCNIC_FW_CAPABILITY_MORE_CAPS BIT_31 @@ -912,6 +927,8 @@ struct qlcnic_ipaddr { #define QLCNIC_FW_LRO_MSS_CAP 0x8000 #define QLCNIC_TX_INTR_SHARED 0x10000 #define QLCNIC_APP_CHANGED_FLAGS 0x20000 +#define QLCNIC_HAS_PHYS_PORT_ID 0x40000 + #define QLCNIC_IS_MSI_FAMILY(adapter) \ ((adapter)->flags & (QLCNIC_MSI_ENABLED | QLCNIC_MSIX_ENABLED)) #define QLCNIC_IS_TSO_CAPABLE(adapter) \ @@ -921,6 +938,7 @@ struct qlcnic_ipaddr { #define QLCNIC_BEACON_DISABLE 0xD #define QLCNIC_DEF_NUM_STS_DESC_RINGS 4 +#define QLCNIC_DEF_NUM_TX_RINGS 4 #define QLCNIC_MSIX_TBL_SPACE 8192 #define QLCNIC_PCI_REG_MSIX_TBL 0x44 #define QLCNIC_MSIX_TBL_PGSIZE 4096 @@ -936,6 +954,7 @@ struct qlcnic_ipaddr { #define __QLCNIC_DIAG_RES_ALLOC 6 #define __QLCNIC_LED_ENABLE 7 #define __QLCNIC_ELB_INPROGRESS 8 +#define __QLCNIC_MULTI_TX_UNIQUE 9 #define __QLCNIC_SRIOV_ENABLE 10 #define __QLCNIC_SRIOV_CAPABLE 11 #define __QLCNIC_MBX_POLL_ENABLE 12 @@ -1481,7 +1500,8 @@ void qlcnic_fw_destroy_ctx(struct qlcnic_adapter *adapter); void qlcnic_reset_rx_buffers_list(struct qlcnic_adapter *adapter); void qlcnic_release_rx_buffers(struct qlcnic_adapter *adapter); -void qlcnic_release_tx_buffers(struct qlcnic_adapter *adapter); +void qlcnic_release_tx_buffers(struct qlcnic_adapter *, + struct qlcnic_host_tx_ring *); int qlcnic_check_fw_status(struct qlcnic_adapter *adapter); void qlcnic_watchdog_task(struct work_struct *work); @@ -1493,6 +1513,7 @@ void __qlcnic_set_multi(struct net_device *, u16); int qlcnic_nic_add_mac(struct qlcnic_adapter *, const u8 *, u16); int qlcnic_nic_del_mac(struct qlcnic_adapter *, const u8 *); void qlcnic_82xx_free_mac_list(struct qlcnic_adapter *adapter); +int qlcnic_82xx_read_phys_port_id(struct qlcnic_adapter *); int qlcnic_fw_cmd_set_mtu(struct qlcnic_adapter *adapter, int mtu); int qlcnic_fw_cmd_set_drv_version(struct qlcnic_adapter *, u32); @@ -1514,8 +1535,9 @@ int qlcnic_reset_context(struct qlcnic_adapter *); void qlcnic_diag_free_res(struct net_device *netdev, int max_sds_rings); int qlcnic_diag_alloc_res(struct net_device *netdev, int test); netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev); -int qlcnic_set_max_rss(struct qlcnic_adapter *, u8, size_t); +int qlcnic_set_max_rss(struct qlcnic_adapter *, u8, int); int qlcnic_validate_max_rss(struct qlcnic_adapter *, __u32); +int qlcnic_validate_max_tx_rings(struct qlcnic_adapter *, int); void qlcnic_alloc_lb_filters_mem(struct qlcnic_adapter *adapter); void qlcnic_82xx_set_mac_filter_count(struct qlcnic_adapter *); int qlcnic_enable_msix(struct qlcnic_adapter *, u32); @@ -1542,6 +1564,7 @@ void qlcnic_free_sds_rings(struct qlcnic_recv_context *); void qlcnic_advert_link_change(struct qlcnic_adapter *, int); void qlcnic_free_tx_rings(struct qlcnic_adapter *); int qlcnic_alloc_tx_rings(struct qlcnic_adapter *, struct net_device *); +void qlcnic_dump_mbx(struct qlcnic_adapter *, struct qlcnic_cmd_args *); void qlcnic_create_sysfs_entries(struct qlcnic_adapter *adapter); void qlcnic_remove_sysfs_entries(struct qlcnic_adapter *adapter); @@ -1604,6 +1627,26 @@ static inline u32 qlcnic_tx_avail(struct qlcnic_host_tx_ring *tx_ring) tx_ring->producer; } +static inline int qlcnic_set_real_num_queues(struct qlcnic_adapter *adapter, + struct net_device *netdev) +{ + int err, tx_q; + + tx_q = adapter->max_drv_tx_rings; + + netdev->num_tx_queues = tx_q; + netdev->real_num_tx_queues = tx_q; + + err = netif_set_real_num_tx_queues(netdev, tx_q); + if (err) + dev_err(&adapter->pdev->dev, "failed to set %d Tx queues\n", + tx_q); + else + dev_info(&adapter->pdev->dev, "set %d Tx queues\n", tx_q); + + return err; +} + struct qlcnic_nic_template { int (*config_bridged_mode) (struct qlcnic_adapter *, u32); int (*config_led) (struct qlcnic_adapter *, u32, u32); @@ -1640,8 +1683,8 @@ struct qlcnic_hardware_ops { int (*read_reg) (struct qlcnic_adapter *, ulong, int *); int (*write_reg) (struct qlcnic_adapter *, ulong, u32); void (*get_ocm_win) (struct qlcnic_hardware_context *); - int (*get_mac_address) (struct qlcnic_adapter *, u8 *); - int (*setup_intr) (struct qlcnic_adapter *, u8); + int (*get_mac_address) (struct qlcnic_adapter *, u8 *, u8); + int (*setup_intr) (struct qlcnic_adapter *, u8, int); int (*alloc_mbx_args)(struct qlcnic_cmd_args *, struct qlcnic_adapter *, u32); int (*mbx_cmd) (struct qlcnic_adapter *, struct qlcnic_cmd_args *); @@ -1674,6 +1717,7 @@ struct qlcnic_hardware_ops { int (*get_board_info) (struct qlcnic_adapter *); void (*set_mac_filter_count) (struct qlcnic_adapter *); void (*free_mac_list) (struct qlcnic_adapter *); + int (*read_phys_port_id) (struct qlcnic_adapter *); }; extern struct qlcnic_nic_template qlcnic_vf_ops; @@ -1702,14 +1746,15 @@ static inline int qlcnic_hw_write_wx_2M(struct qlcnic_adapter *adapter, } static inline int qlcnic_get_mac_address(struct qlcnic_adapter *adapter, - u8 *mac) + u8 *mac, u8 function) { - return adapter->ahw->hw_ops->get_mac_address(adapter, mac); + return adapter->ahw->hw_ops->get_mac_address(adapter, mac, function); } -static inline int qlcnic_setup_intr(struct qlcnic_adapter *adapter, u8 num_intr) +static inline int qlcnic_setup_intr(struct qlcnic_adapter *adapter, + u8 num_intr, int txq) { - return adapter->ahw->hw_ops->setup_intr(adapter, num_intr); + return adapter->ahw->hw_ops->setup_intr(adapter, num_intr, txq); } static inline int qlcnic_alloc_mbx_args(struct qlcnic_cmd_args *mbx, @@ -1900,6 +1945,12 @@ static inline void qlcnic_set_mac_filter_count(struct qlcnic_adapter *adapter) adapter->ahw->hw_ops->set_mac_filter_count(adapter); } +static inline void qlcnic_read_phys_port_id(struct qlcnic_adapter *adapter) +{ + if (adapter->ahw->hw_ops->read_phys_port_id) + adapter->ahw->hw_ops->read_phys_port_id(adapter); +} + static inline void qlcnic_dev_request_reset(struct qlcnic_adapter *adapter, u32 key) { @@ -1931,16 +1982,45 @@ static inline void qlcnic_config_ipaddr(struct qlcnic_adapter *adapter, adapter->nic_ops->config_ipaddr(adapter, ip, cmd); } +static inline bool qlcnic_check_multi_tx(struct qlcnic_adapter *adapter) +{ + return test_bit(__QLCNIC_MULTI_TX_UNIQUE, &adapter->state); +} + +static inline void qlcnic_disable_multi_tx(struct qlcnic_adapter *adapter) +{ + test_and_clear_bit(__QLCNIC_MULTI_TX_UNIQUE, &adapter->state); + adapter->max_drv_tx_rings = 1; +} + +/* When operating in a muti tx mode, driver needs to write 0x1 + * to src register, instead of 0x0 to disable receiving interrupt. + */ static inline void qlcnic_disable_int(struct qlcnic_host_sds_ring *sds_ring) { - writel(0, sds_ring->crb_intr_mask); + struct qlcnic_adapter *adapter = sds_ring->adapter; + + if (qlcnic_check_multi_tx(adapter) && + !adapter->ahw->diag_test && + (adapter->flags & QLCNIC_MSIX_ENABLED)) + writel(0x1, sds_ring->crb_intr_mask); + else + writel(0, sds_ring->crb_intr_mask); } +/* When operating in a muti tx mode, driver needs to write 0x0 + * to src register, instead of 0x1 to enable receiving interrupts. + */ static inline void qlcnic_enable_int(struct qlcnic_host_sds_ring *sds_ring) { struct qlcnic_adapter *adapter = sds_ring->adapter; - writel(0x1, sds_ring->crb_intr_mask); + if (qlcnic_check_multi_tx(adapter) && + !adapter->ahw->diag_test && + (adapter->flags & QLCNIC_MSIX_ENABLED)) + writel(0, sds_ring->crb_intr_mask); + else + writel(0x1, sds_ring->crb_intr_mask); if (!QLCNIC_IS_MSI_FAMILY(adapter)) writel(0xfbff, adapter->tgt_mask_reg); @@ -1972,9 +2052,11 @@ extern const struct ethtool_ops qlcnic_ethtool_failed_ops; __func__, ##_args); \ } while (0) -#define PCI_DEVICE_ID_QLOGIC_QLE834X 0x8030 +#define PCI_DEVICE_ID_QLOGIC_QLE824X 0x8020 +#define PCI_DEVICE_ID_QLOGIC_QLE834X 0x8030 #define PCI_DEVICE_ID_QLOGIC_VF_QLE834X 0x8430 -#define PCI_DEVICE_ID_QLOGIC_QLE824X 0x8020 +#define PCI_DEVICE_ID_QLOGIC_QLE844X 0x8040 +#define PCI_DEVICE_ID_QLOGIC_VF_QLE844X 0x8440 static inline bool qlcnic_82xx_check(struct qlcnic_adapter *adapter) { @@ -1988,6 +2070,8 @@ static inline bool qlcnic_83xx_check(struct qlcnic_adapter *adapter) bool status; status = ((device == PCI_DEVICE_ID_QLOGIC_QLE834X) || + (device == PCI_DEVICE_ID_QLOGIC_QLE844X) || + (device == PCI_DEVICE_ID_QLOGIC_VF_QLE844X) || (device == PCI_DEVICE_ID_QLOGIC_VF_QLE834X)) ? true : false; return status; @@ -2001,7 +2085,11 @@ static inline bool qlcnic_sriov_pf_check(struct qlcnic_adapter *adapter) static inline bool qlcnic_sriov_vf_check(struct qlcnic_adapter *adapter) { unsigned short device = adapter->pdev->device; + bool status; - return (device == PCI_DEVICE_ID_QLOGIC_VF_QLE834X) ? true : false; + status = ((device == PCI_DEVICE_ID_QLOGIC_VF_QLE834X) || + (device == PCI_DEVICE_ID_QLOGIC_VF_QLE844X)) ? true : false; + + return status; } #endif /* __QLCNIC_H_ */ diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index e53caaaf130..6c059f97ae9 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -261,7 +261,7 @@ int qlcnic_83xx_wrt_reg_indirect(struct qlcnic_adapter *adapter, ulong addr, } } -int qlcnic_83xx_setup_intr(struct qlcnic_adapter *adapter, u8 num_intr) +int qlcnic_83xx_setup_intr(struct qlcnic_adapter *adapter, u8 num_intr, int txq) { int err, i, num_msix; struct qlcnic_hardware_context *ahw = adapter->ahw; @@ -695,8 +695,8 @@ static void qlcnic_83xx_handle_link_aen(struct qlcnic_adapter *adapter, static void qlcnic_83xx_handle_idc_comp_aen(struct qlcnic_adapter *adapter, u32 data[]); -static void qlcnic_dump_mbx(struct qlcnic_adapter *adapter, - struct qlcnic_cmd_args *cmd) +void qlcnic_dump_mbx(struct qlcnic_adapter *adapter, + struct qlcnic_cmd_args *cmd) { int i; @@ -860,9 +860,9 @@ static void qlcnic_83xx_handle_idc_comp_aen(struct qlcnic_adapter *adapter, void __qlcnic_83xx_process_aen(struct qlcnic_adapter *adapter) { + struct qlcnic_hardware_context *ahw = adapter->ahw; u32 event[QLC_83XX_MBX_AEN_CNT]; int i; - struct qlcnic_hardware_context *ahw = adapter->ahw; for (i = 0; i < QLC_83XX_MBX_AEN_CNT; i++) event[i] = readl(QLCNIC_MBX_FW(ahw, i)); @@ -882,6 +882,7 @@ void __qlcnic_83xx_process_aen(struct qlcnic_adapter *adapter) &adapter->idc_aen_work, 0); break; case QLCNIC_MBX_TIME_EXTEND_EVENT: + ahw->extend_lb_time = event[1] >> 8 & 0xf; break; case QLCNIC_MBX_BC_EVENT: qlcnic_sriov_handle_bc_event(adapter, event[1]); @@ -1690,7 +1691,7 @@ int qlcnic_83xx_loopback_test(struct net_device *netdev, u8 mode) /* Make sure carrier is off and queue is stopped during loopback */ if (netif_running(netdev)) { netif_carrier_off(netdev); - netif_stop_queue(netdev); + netif_tx_stop_all_queues(netdev); } ret = qlcnic_do_lb_test(adapter, mode); @@ -1706,13 +1707,28 @@ fail_diag_alloc: return ret; } +static void qlcnic_extend_lb_idc_cmpltn_wait(struct qlcnic_adapter *adapter, + u32 *max_wait_count) +{ + struct qlcnic_hardware_context *ahw = adapter->ahw; + int temp; + + netdev_info(adapter->netdev, "Recieved loopback IDC time extend event for 0x%x seconds\n", + ahw->extend_lb_time); + temp = ahw->extend_lb_time * 1000; + *max_wait_count += temp / QLC_83XX_LB_MSLEEP_COUNT; + ahw->extend_lb_time = 0; +} + int qlcnic_83xx_set_lb_mode(struct qlcnic_adapter *adapter, u8 mode) { struct qlcnic_hardware_context *ahw = adapter->ahw; struct net_device *netdev = adapter->netdev; + u32 config, max_wait_count; int status = 0, loop = 0; - u32 config; + ahw->extend_lb_time = 0; + max_wait_count = QLC_83XX_LB_WAIT_COUNT; status = qlcnic_83xx_get_port_config(adapter); if (status) return status; @@ -1754,9 +1770,14 @@ int qlcnic_83xx_set_lb_mode(struct qlcnic_adapter *adapter, u8 mode) clear_bit(QLC_83XX_IDC_COMP_AEN, &ahw->idc.status); return -EBUSY; } - if (loop++ > QLC_83XX_LB_WAIT_COUNT) { - netdev_err(netdev, - "Did not receive IDC completion AEN\n"); + + if (ahw->extend_lb_time) + qlcnic_extend_lb_idc_cmpltn_wait(adapter, + &max_wait_count); + + if (loop++ > max_wait_count) { + netdev_err(netdev, "%s: Did not receive loopback IDC completion AEN\n", + __func__); clear_bit(QLC_83XX_IDC_COMP_AEN, &ahw->idc.status); qlcnic_83xx_clear_lb_mode(adapter, mode); return -ETIMEDOUT; @@ -1771,10 +1792,12 @@ int qlcnic_83xx_set_lb_mode(struct qlcnic_adapter *adapter, u8 mode) int qlcnic_83xx_clear_lb_mode(struct qlcnic_adapter *adapter, u8 mode) { struct qlcnic_hardware_context *ahw = adapter->ahw; + u32 config = ahw->port_config, max_wait_count; struct net_device *netdev = adapter->netdev; int status = 0, loop = 0; - u32 config = ahw->port_config; + ahw->extend_lb_time = 0; + max_wait_count = QLC_83XX_LB_WAIT_COUNT; set_bit(QLC_83XX_IDC_COMP_AEN, &ahw->idc.status); if (mode == QLCNIC_ILB_MODE) ahw->port_config &= ~QLC_83XX_CFG_LOOPBACK_HSS; @@ -1802,9 +1825,13 @@ int qlcnic_83xx_clear_lb_mode(struct qlcnic_adapter *adapter, u8 mode) return -EBUSY; } - if (loop++ > QLC_83XX_LB_WAIT_COUNT) { - netdev_err(netdev, - "Did not receive IDC completion AEN\n"); + if (ahw->extend_lb_time) + qlcnic_extend_lb_idc_cmpltn_wait(adapter, + &max_wait_count); + + if (loop++ > max_wait_count) { + netdev_err(netdev, "%s: Did not receive loopback IDC completion AEN\n", + __func__); clear_bit(QLC_83XX_IDC_COMP_AEN, &ahw->idc.status); return -ETIMEDOUT; } @@ -2010,12 +2037,14 @@ void qlcnic_83xx_configure_mac(struct qlcnic_adapter *adapter, u8 *mac, cmd->req.arg[1] = type; } -int qlcnic_83xx_get_mac_address(struct qlcnic_adapter *adapter, u8 *mac) +int qlcnic_83xx_get_mac_address(struct qlcnic_adapter *adapter, u8 *mac, + u8 function) { int err, i; struct qlcnic_cmd_args cmd; u32 mac_low, mac_high; + function = 0; err = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_MAC_ADDRESS); if (err) return err; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h index dd22ef3d85e..0fc56160d58 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h @@ -84,9 +84,11 @@ /* Firmware image definitions */ #define QLC_83XX_BOOTLOADER_FLASH_ADDR 0x10000 #define QLC_83XX_FW_FILE_NAME "83xx_fw.bin" +#define QLC_84XX_FW_FILE_NAME "84xx_fw.bin" #define QLC_83XX_BOOT_FROM_FLASH 0 #define QLC_83XX_BOOT_FROM_FILE 0x12345678 +#define QLC_FW_FILE_NAME_LEN 20 #define QLC_83XX_MAX_RESET_SEQ_ENTRIES 16 #define QLC_83XX_MBX_POST_BC_OP 0x1 @@ -404,6 +406,7 @@ enum qlcnic_83xx_states { #define QLC_83XX_MAX_MC_COUNT 38 #define QLC_83XX_MAX_UC_COUNT 4096 +#define QLC_83XX_PVID_STRIP_CAPABILITY BIT_22 #define QLC_83XX_GET_FUNC_MODE_FROM_NPAR_INFO(val) (val & 0x80000000) #define QLC_83XX_GET_LRO_CAPABILITY(val) (val & 0x20) #define QLC_83XX_GET_LSO_CAPABILITY(val) (val & 0x40) @@ -520,7 +523,7 @@ enum qlc_83xx_ext_regs { /* 83xx funcitons */ int qlcnic_83xx_get_fw_version(struct qlcnic_adapter *); int qlcnic_83xx_issue_cmd(struct qlcnic_adapter *, struct qlcnic_cmd_args *); -int qlcnic_83xx_setup_intr(struct qlcnic_adapter *, u8); +int qlcnic_83xx_setup_intr(struct qlcnic_adapter *, u8, int); void qlcnic_83xx_get_func_no(struct qlcnic_adapter *); int qlcnic_83xx_cam_lock(struct qlcnic_adapter *); void qlcnic_83xx_cam_unlock(struct qlcnic_adapter *); @@ -561,7 +564,7 @@ int qlcnic_83xx_setup_link_event(struct qlcnic_adapter *, int); void qlcnic_83xx_process_rcv_ring_diag(struct qlcnic_host_sds_ring *); int qlcnic_83xx_config_intrpt(struct qlcnic_adapter *, bool); int qlcnic_83xx_sre_macaddr_change(struct qlcnic_adapter *, u8 *, u16, u8); -int qlcnic_83xx_get_mac_address(struct qlcnic_adapter *, u8 *); +int qlcnic_83xx_get_mac_address(struct qlcnic_adapter *, u8 *, u8); void qlcnic_83xx_configure_mac(struct qlcnic_adapter *, u8 *, u8, struct qlcnic_cmd_args *); int qlcnic_83xx_alloc_mbx_args(struct qlcnic_cmd_args *, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index c97e2e07b27..fb0ef36b529 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -1948,12 +1948,36 @@ static void qlcnic_83xx_init_hw(struct qlcnic_adapter *p_dev) dev_err(&p_dev->pdev->dev, "%s: failed\n", __func__); } +static inline void qlcnic_83xx_get_fw_file_name(struct qlcnic_adapter *adapter, + char *file_name) +{ + struct pci_dev *pdev = adapter->pdev; + + memset(file_name, 0, QLC_FW_FILE_NAME_LEN); + + switch (pdev->device) { + case PCI_DEVICE_ID_QLOGIC_QLE834X: + strncpy(file_name, QLC_83XX_FW_FILE_NAME, + QLC_FW_FILE_NAME_LEN); + break; + case PCI_DEVICE_ID_QLOGIC_QLE844X: + strncpy(file_name, QLC_84XX_FW_FILE_NAME, + QLC_FW_FILE_NAME_LEN); + break; + default: + dev_err(&pdev->dev, "%s: Invalid device id\n", + __func__); + } +} + static int qlcnic_83xx_load_fw_image_from_host(struct qlcnic_adapter *adapter) { + char fw_file_name[QLC_FW_FILE_NAME_LEN]; int err = -EIO; - if (request_firmware(&adapter->ahw->fw_info.fw, - QLC_83XX_FW_FILE_NAME, &(adapter->pdev->dev))) { + qlcnic_83xx_get_fw_file_name(adapter, fw_file_name); + if (request_firmware(&adapter->ahw->fw_info.fw, fw_file_name, + &(adapter->pdev->dev))) { dev_err(&adapter->pdev->dev, "No file FW image, loading flash FW image.\n"); QLC_SHARED_REG_WR32(adapter, QLCNIC_FW_IMG_VALID, @@ -2177,7 +2201,7 @@ int qlcnic_83xx_init(struct qlcnic_adapter *adapter, int pci_using_dac) if (err) goto detach_mbx; - err = qlcnic_setup_intr(adapter, 0); + err = qlcnic_setup_intr(adapter, 0, 0); if (err) { dev_err(&adapter->pdev->dev, "Failed to setup interrupt\n"); goto disable_intr; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c index d09389b3347..d4f0e959164 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c @@ -38,6 +38,7 @@ static const struct qlcnic_mailbox_metadata qlcnic_mbx_tbl[] = { {QLCNIC_CMD_GET_TEMP_HDR, 4, 1}, {QLCNIC_CMD_82XX_SET_DRV_VER, 4, 1}, {QLCNIC_CMD_GET_LED_STATUS, 4, 2}, + {QLCNIC_CMD_MQ_TX_CONFIG_INTR, 2, 3}, }; static inline u32 qlcnic_get_cmd_signature(struct qlcnic_hardware_context *ahw) @@ -171,6 +172,7 @@ int qlcnic_82xx_issue_cmd(struct qlcnic_adapter *adapter, break; } dev_err(&pdev->dev, fmt, cmd->rsp.arg[0]); + qlcnic_dump_mbx(adapter, cmd); } else if (rsp == QLCNIC_CDRP_RSP_OK) cmd->rsp.arg[0] = QLCNIC_RCODE_SUCCESS; @@ -243,40 +245,38 @@ qlcnic_fw_cmd_set_mtu(struct qlcnic_adapter *adapter, int mtu) int qlcnic_82xx_fw_cmd_create_rx_ctx(struct qlcnic_adapter *adapter) { - void *addr; - struct qlcnic_hostrq_rx_ctx *prq; - struct qlcnic_cardrsp_rx_ctx *prsp; - struct qlcnic_hostrq_rds_ring *prq_rds; - struct qlcnic_hostrq_sds_ring *prq_sds; + struct qlcnic_recv_context *recv_ctx = adapter->recv_ctx; + struct qlcnic_hardware_context *ahw = adapter->ahw; + dma_addr_t hostrq_phys_addr, cardrsp_phys_addr; + struct net_device *netdev = adapter->netdev; + u32 temp_intr_crb_mode, temp_rds_crb_mode; struct qlcnic_cardrsp_rds_ring *prsp_rds; struct qlcnic_cardrsp_sds_ring *prsp_sds; + struct qlcnic_hostrq_rds_ring *prq_rds; + struct qlcnic_hostrq_sds_ring *prq_sds; struct qlcnic_host_rds_ring *rds_ring; struct qlcnic_host_sds_ring *sds_ring; - struct qlcnic_cmd_args cmd; - - dma_addr_t hostrq_phys_addr, cardrsp_phys_addr; - u64 phys_addr; - + struct qlcnic_cardrsp_rx_ctx *prsp; + struct qlcnic_hostrq_rx_ctx *prq; u8 i, nrds_rings, nsds_rings; - u16 temp_u16; + struct qlcnic_cmd_args cmd; size_t rq_size, rsp_size; u32 cap, reg, val, reg2; + u64 phys_addr; + u16 temp_u16; + void *addr; int err; - struct qlcnic_recv_context *recv_ctx = adapter->recv_ctx; - nrds_rings = adapter->max_rds_rings; nsds_rings = adapter->max_sds_rings; - rq_size = - SIZEOF_HOSTRQ_RX(struct qlcnic_hostrq_rx_ctx, nrds_rings, - nsds_rings); - rsp_size = - SIZEOF_CARDRSP_RX(struct qlcnic_cardrsp_rx_ctx, nrds_rings, - nsds_rings); + rq_size = SIZEOF_HOSTRQ_RX(struct qlcnic_hostrq_rx_ctx, nrds_rings, + nsds_rings); + rsp_size = SIZEOF_CARDRSP_RX(struct qlcnic_cardrsp_rx_ctx, nrds_rings, + nsds_rings); addr = dma_alloc_coherent(&adapter->pdev->dev, rq_size, - &hostrq_phys_addr, GFP_KERNEL); + &hostrq_phys_addr, GFP_KERNEL); if (addr == NULL) return -ENOMEM; prq = addr; @@ -295,15 +295,20 @@ int qlcnic_82xx_fw_cmd_create_rx_ctx(struct qlcnic_adapter *adapter) | QLCNIC_CAP0_VALIDOFF); cap |= (QLCNIC_CAP0_JUMBO_CONTIGUOUS | QLCNIC_CAP0_LRO_CONTIGUOUS); - temp_u16 = offsetof(struct qlcnic_hostrq_rx_ctx, msix_handler); - prq->valid_field_offset = cpu_to_le16(temp_u16); - prq->txrx_sds_binding = nsds_rings - 1; + if (qlcnic_check_multi_tx(adapter) && + !adapter->ahw->diag_test) { + cap |= QLCNIC_CAP0_TX_MULTI; + } else { + temp_u16 = offsetof(struct qlcnic_hostrq_rx_ctx, msix_handler); + prq->valid_field_offset = cpu_to_le16(temp_u16); + prq->txrx_sds_binding = nsds_rings - 1; + temp_intr_crb_mode = QLCNIC_HOST_INT_CRB_MODE_SHARED; + prq->host_int_crb_mode = cpu_to_le32(temp_intr_crb_mode); + temp_rds_crb_mode = QLCNIC_HOST_RDS_CRB_MODE_UNIQUE; + prq->host_rds_crb_mode = cpu_to_le32(temp_rds_crb_mode); + } prq->capabilities[0] = cpu_to_le32(cap); - prq->host_int_crb_mode = - cpu_to_le32(QLCNIC_HOST_INT_CRB_MODE_SHARED); - prq->host_rds_crb_mode = - cpu_to_le32(QLCNIC_HOST_RDS_CRB_MODE_UNIQUE); prq->num_rds_rings = cpu_to_le16(nrds_rings); prq->num_sds_rings = cpu_to_le16(nsds_rings); @@ -317,10 +322,8 @@ int qlcnic_82xx_fw_cmd_create_rx_ctx(struct qlcnic_adapter *adapter) le32_to_cpu(prq->rds_ring_offset)); for (i = 0; i < nrds_rings; i++) { - rds_ring = &recv_ctx->rds_rings[i]; rds_ring->producer = 0; - prq_rds[i].host_phys_addr = cpu_to_le64(rds_ring->phys_addr); prq_rds[i].ring_size = cpu_to_le32(rds_ring->num_desc); prq_rds[i].ring_kind = cpu_to_le32(i); @@ -331,14 +334,16 @@ int qlcnic_82xx_fw_cmd_create_rx_ctx(struct qlcnic_adapter *adapter) le32_to_cpu(prq->sds_ring_offset)); for (i = 0; i < nsds_rings; i++) { - sds_ring = &recv_ctx->sds_rings[i]; sds_ring->consumer = 0; memset(sds_ring->desc_head, 0, STATUS_DESC_RINGSIZE(sds_ring)); - prq_sds[i].host_phys_addr = cpu_to_le64(sds_ring->phys_addr); prq_sds[i].ring_size = cpu_to_le32(sds_ring->num_desc); - prq_sds[i].msi_index = cpu_to_le16(i); + if (qlcnic_check_multi_tx(adapter) && + !adapter->ahw->diag_test) + prq_sds[i].msi_index = cpu_to_le16(ahw->intr_tbl[i].id); + else + prq_sds[i].msi_index = cpu_to_le16(i); } phys_addr = hostrq_phys_addr; @@ -361,9 +366,8 @@ int qlcnic_82xx_fw_cmd_create_rx_ctx(struct qlcnic_adapter *adapter) for (i = 0; i < le16_to_cpu(prsp->num_rds_rings); i++) { rds_ring = &recv_ctx->rds_rings[i]; - reg = le32_to_cpu(prsp_rds[i].host_producer_crb); - rds_ring->crb_rcv_producer = adapter->ahw->pci_base0 + reg; + rds_ring->crb_rcv_producer = ahw->pci_base0 + reg; } prsp_sds = ((struct qlcnic_cardrsp_sds_ring *) @@ -371,24 +375,30 @@ int qlcnic_82xx_fw_cmd_create_rx_ctx(struct qlcnic_adapter *adapter) for (i = 0; i < le16_to_cpu(prsp->num_sds_rings); i++) { sds_ring = &recv_ctx->sds_rings[i]; - reg = le32_to_cpu(prsp_sds[i].host_consumer_crb); - reg2 = le32_to_cpu(prsp_sds[i].interrupt_crb); + if (qlcnic_check_multi_tx(adapter) && !adapter->ahw->diag_test) + reg2 = ahw->intr_tbl[i].src; + else + reg2 = le32_to_cpu(prsp_sds[i].interrupt_crb); - sds_ring->crb_sts_consumer = adapter->ahw->pci_base0 + reg; - sds_ring->crb_intr_mask = adapter->ahw->pci_base0 + reg2; + sds_ring->crb_intr_mask = ahw->pci_base0 + reg2; + sds_ring->crb_sts_consumer = ahw->pci_base0 + reg; } recv_ctx->state = le32_to_cpu(prsp->host_ctx_state); recv_ctx->context_id = le16_to_cpu(prsp->context_id); recv_ctx->virt_port = prsp->virt_port; + netdev_info(netdev, "Rx Context[%d] Created, state 0x%x\n", + recv_ctx->context_id, recv_ctx->state); qlcnic_free_mbx_args(&cmd); + out_free_rsp: dma_free_coherent(&adapter->pdev->dev, rsp_size, prsp, cardrsp_phys_addr); out_free_rq: dma_free_coherent(&adapter->pdev->dev, rq_size, prq, hostrq_phys_addr); + return err; } @@ -416,16 +426,19 @@ int qlcnic_82xx_fw_cmd_create_tx_ctx(struct qlcnic_adapter *adapter, struct qlcnic_host_tx_ring *tx_ring, int ring) { + struct qlcnic_hardware_context *ahw = adapter->ahw; + struct net_device *netdev = adapter->netdev; struct qlcnic_hostrq_tx_ctx *prq; struct qlcnic_hostrq_cds_ring *prq_cds; struct qlcnic_cardrsp_tx_ctx *prsp; - void *rq_addr, *rsp_addr; - size_t rq_size, rsp_size; - u32 temp; struct qlcnic_cmd_args cmd; - int err; - u64 phys_addr; - dma_addr_t rq_phys_addr, rsp_phys_addr; + u32 temp, intr_mask, temp_int_crb_mode; + dma_addr_t rq_phys_addr, rsp_phys_addr; + int temp_nsds_rings, index, err; + void *rq_addr, *rsp_addr; + size_t rq_size, rsp_size; + u64 phys_addr; + u16 msix_id; /* reset host resources */ tx_ring->producer = 0; @@ -447,18 +460,28 @@ int qlcnic_82xx_fw_cmd_create_tx_ctx(struct qlcnic_adapter *adapter, } prq = rq_addr; - prsp = rsp_addr; prq->host_rsp_dma_addr = cpu_to_le64(rsp_phys_addr); temp = (QLCNIC_CAP0_LEGACY_CONTEXT | QLCNIC_CAP0_LEGACY_MN | - QLCNIC_CAP0_LSO); + QLCNIC_CAP0_LSO); + if (qlcnic_check_multi_tx(adapter) && !adapter->ahw->diag_test) + temp |= QLCNIC_CAP0_TX_MULTI; + prq->capabilities[0] = cpu_to_le32(temp); - prq->host_int_crb_mode = - cpu_to_le32(QLCNIC_HOST_INT_CRB_MODE_SHARED); - prq->msi_index = 0; + if (qlcnic_check_multi_tx(adapter) && + !adapter->ahw->diag_test) { + temp_nsds_rings = adapter->max_sds_rings; + index = temp_nsds_rings + ring; + msix_id = ahw->intr_tbl[index].id; + prq->msi_index = cpu_to_le16(msix_id); + } else { + temp_int_crb_mode = QLCNIC_HOST_INT_CRB_MODE_SHARED; + prq->host_int_crb_mode = cpu_to_le32(temp_int_crb_mode); + prq->msi_index = 0; + } prq->interrupt_ctl = 0; prq->cmd_cons_dma_addr = cpu_to_le64(tx_ring->hw_cons_phys_addr); @@ -480,15 +503,25 @@ int qlcnic_82xx_fw_cmd_create_tx_ctx(struct qlcnic_adapter *adapter, err = qlcnic_issue_cmd(adapter, &cmd); if (err == QLCNIC_RCODE_SUCCESS) { + tx_ring->state = le32_to_cpu(prsp->host_ctx_state); temp = le32_to_cpu(prsp->cds_ring.host_producer_crb); tx_ring->crb_cmd_producer = adapter->ahw->pci_base0 + temp; tx_ring->ctx_id = le16_to_cpu(prsp->context_id); + if (qlcnic_check_multi_tx(adapter) && + !adapter->ahw->diag_test && + (adapter->flags & QLCNIC_MSIX_ENABLED)) { + index = adapter->max_sds_rings + ring; + intr_mask = ahw->intr_tbl[index].src; + tx_ring->crb_intr_mask = ahw->pci_base0 + intr_mask; + } + + netdev_info(netdev, "Tx Context[0x%x] Created, state 0x%x\n", + tx_ring->ctx_id, tx_ring->state); } else { - dev_err(&adapter->pdev->dev, - "Failed to create tx ctx in firmware%d\n", err); + netdev_err(netdev, "Failed to create tx ctx in firmware%d\n", + err); err = -EIO; } - qlcnic_free_mbx_args(&cmd); out_free_rsp: @@ -618,6 +651,13 @@ int qlcnic_fw_create_ctx(struct qlcnic_adapter *dev) } } + if (qlcnic_82xx_check(dev) && (dev->flags & QLCNIC_MSIX_ENABLED) && + qlcnic_check_multi_tx(dev) && !dev->ahw->diag_test) { + err = qlcnic_82xx_mq_intrpt(dev, 1); + if (err) + return err; + } + err = qlcnic_fw_cmd_create_rx_ctx(dev); if (err) goto err_out; @@ -639,13 +679,19 @@ int qlcnic_fw_create_ctx(struct qlcnic_adapter *dev) } set_bit(__QLCNIC_FW_ATTACHED, &dev->state); + return 0; err_out: + if (qlcnic_82xx_check(dev) && (dev->flags & QLCNIC_MSIX_ENABLED) && + qlcnic_check_multi_tx(dev) && !dev->ahw->diag_test) + qlcnic_82xx_config_intrpt(dev, 0); + if (qlcnic_83xx_check(dev) && (dev->flags & QLCNIC_MSIX_ENABLED)) { if (dev->ahw->diag_test != QLCNIC_LOOPBACK_TEST) qlcnic_83xx_config_intrpt(dev, 0); } + return err; } @@ -659,6 +705,12 @@ void qlcnic_fw_destroy_ctx(struct qlcnic_adapter *adapter) qlcnic_fw_cmd_del_tx_ctx(adapter, &adapter->tx_ring[ring]); + if (qlcnic_82xx_check(adapter) && + (adapter->flags & QLCNIC_MSIX_ENABLED) && + qlcnic_check_multi_tx(adapter) && + !adapter->ahw->diag_test) + qlcnic_82xx_config_intrpt(adapter, 0); + if (qlcnic_83xx_check(adapter) && (adapter->flags & QLCNIC_MSIX_ENABLED)) { if (adapter->ahw->diag_test != QLCNIC_LOOPBACK_TEST) @@ -723,8 +775,54 @@ void qlcnic_free_hw_resources(struct qlcnic_adapter *adapter) } } +int qlcnic_82xx_config_intrpt(struct qlcnic_adapter *adapter, u8 op_type) +{ + struct qlcnic_hardware_context *ahw = adapter->ahw; + struct net_device *netdev = adapter->netdev; + struct qlcnic_cmd_args cmd; + u32 type, val; + int i, err = 0; + + for (i = 0; i < ahw->num_msix; i++) { + qlcnic_alloc_mbx_args(&cmd, adapter, + QLCNIC_CMD_MQ_TX_CONFIG_INTR); + type = op_type ? QLCNIC_INTRPT_ADD : QLCNIC_INTRPT_DEL; + val = type | (ahw->intr_tbl[i].type << 4); + if (ahw->intr_tbl[i].type == QLCNIC_INTRPT_MSIX) + val |= (ahw->intr_tbl[i].id << 16); + cmd.req.arg[1] = val; + err = qlcnic_issue_cmd(adapter, &cmd); + if (err) { + netdev_err(netdev, "Failed to %s interrupts %d\n", + op_type == QLCNIC_INTRPT_ADD ? "Add" : + "Delete", err); + qlcnic_free_mbx_args(&cmd); + return err; + } + val = cmd.rsp.arg[1]; + if (LSB(val)) { + netdev_info(netdev, + "failed to configure interrupt for %d\n", + ahw->intr_tbl[i].id); + continue; + } + if (op_type) { + ahw->intr_tbl[i].id = MSW(val); + ahw->intr_tbl[i].enabled = 1; + ahw->intr_tbl[i].src = cmd.rsp.arg[2]; + } else { + ahw->intr_tbl[i].id = i; + ahw->intr_tbl[i].enabled = 0; + ahw->intr_tbl[i].src = 0; + } + qlcnic_free_mbx_args(&cmd); + } + + return err; +} -int qlcnic_82xx_get_mac_address(struct qlcnic_adapter *adapter, u8 *mac) +int qlcnic_82xx_get_mac_address(struct qlcnic_adapter *adapter, u8 *mac, + u8 function) { int err, i; struct qlcnic_cmd_args cmd; @@ -734,7 +832,7 @@ int qlcnic_82xx_get_mac_address(struct qlcnic_adapter *adapter, u8 *mac) if (err) return err; - cmd.req.arg[1] = adapter->ahw->pci_func | BIT_8; + cmd.req.arg[1] = function | BIT_8; err = qlcnic_issue_cmd(adapter, &cmd); if (err == QLCNIC_RCODE_SUCCESS) { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index 79a5855f926..7b0c90efb36 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -125,6 +125,14 @@ static const char qlcnic_83xx_mac_stats_strings[][ETH_GSTRING_LEN] = { }; #define QLCNIC_STATS_LEN ARRAY_SIZE(qlcnic_gstrings_stats) + +static const char qlcnic_tx_ring_stats_strings[][ETH_GSTRING_LEN] = { + "xmit_on", + "xmit_off", + "xmit_called", + "xmit_finished", +}; + static const char qlcnic_83xx_rx_stats_strings[][ETH_GSTRING_LEN] = { "ctx_rx_bytes", "ctx_rx_pkts", @@ -630,15 +638,15 @@ qlcnic_set_ringparam(struct net_device *dev, static void qlcnic_get_channels(struct net_device *dev, struct ethtool_channels *channel) { - int min; struct qlcnic_adapter *adapter = netdev_priv(dev); + int min; min = min_t(int, adapter->ahw->max_rx_ques, num_online_cpus()); channel->max_rx = rounddown_pow_of_two(min); - channel->max_tx = adapter->ahw->max_tx_ques; + channel->max_tx = min_t(int, QLCNIC_MAX_TX_RINGS, num_online_cpus()); channel->rx_count = adapter->max_sds_rings; - channel->tx_count = adapter->ahw->max_tx_ques; + channel->tx_count = adapter->max_drv_tx_rings; } static int qlcnic_set_channels(struct net_device *dev, @@ -646,18 +654,27 @@ static int qlcnic_set_channels(struct net_device *dev, { struct qlcnic_adapter *adapter = netdev_priv(dev); int err; + int txq = 0; - if (channel->other_count || channel->combined_count || - channel->tx_count != channel->max_tx) + if (channel->other_count || channel->combined_count) return -EINVAL; - err = qlcnic_validate_max_rss(adapter, channel->rx_count); - if (err) - return err; + if (channel->rx_count) { + err = qlcnic_validate_max_rss(adapter, channel->rx_count); + if (err) + return err; + } + + if (channel->tx_count) { + err = qlcnic_validate_max_tx_rings(adapter, channel->tx_count); + if (err) + return err; + txq = channel->tx_count; + } - err = qlcnic_set_max_rss(adapter, channel->rx_count, 0); - netdev_info(dev, "allocated 0x%x sds rings\n", - adapter->max_sds_rings); + err = qlcnic_set_max_rss(adapter, channel->rx_count, txq); + netdev_info(dev, "allocated 0x%x sds rings and 0x%x tx rings\n", + adapter->max_sds_rings, adapter->max_drv_tx_rings); return err; } @@ -893,6 +910,7 @@ free_diag_res: clear_diag_irq: adapter->max_sds_rings = max_sds_rings; clear_bit(__QLCNIC_RESETTING, &adapter->state); + return ret; } @@ -966,6 +984,7 @@ int qlcnic_do_lb_test(struct qlcnic_adapter *adapter, u8 mode) int qlcnic_loopback_test(struct net_device *netdev, u8 mode) { struct qlcnic_adapter *adapter = netdev_priv(netdev); + int max_drv_tx_rings = adapter->max_drv_tx_rings; int max_sds_rings = adapter->max_sds_rings; struct qlcnic_host_sds_ring *sds_ring; struct qlcnic_hardware_context *ahw = adapter->ahw; @@ -1025,6 +1044,7 @@ int qlcnic_loopback_test(struct net_device *netdev, u8 mode) clear_it: adapter->max_sds_rings = max_sds_rings; + adapter->max_drv_tx_rings = max_drv_tx_rings; clear_bit(__QLCNIC_RESETTING, &adapter->state); return ret; } @@ -1077,11 +1097,21 @@ qlcnic_get_strings(struct net_device *dev, u32 stringset, u8 *data) QLCNIC_TEST_LEN * ETH_GSTRING_LEN); break; case ETH_SS_STATS: + num_stats = ARRAY_SIZE(qlcnic_tx_ring_stats_strings); + for (i = 0; i < adapter->max_drv_tx_rings; i++) { + for (index = 0; index < num_stats; index++) { + sprintf(data, "tx_ring_%d %s", i, + qlcnic_tx_ring_stats_strings[index]); + data += ETH_GSTRING_LEN; + } + } + for (index = 0; index < QLCNIC_STATS_LEN; index++) { memcpy(data + index * ETH_GSTRING_LEN, qlcnic_gstrings_stats[index].stat_string, ETH_GSTRING_LEN); } + if (qlcnic_83xx_check(adapter)) { num_stats = ARRAY_SIZE(qlcnic_83xx_tx_stats_strings); for (i = 0; i < num_stats; i++, index++) @@ -1173,11 +1203,22 @@ static void qlcnic_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { struct qlcnic_adapter *adapter = netdev_priv(dev); + struct qlcnic_host_tx_ring *tx_ring; struct qlcnic_esw_statistics port_stats; struct qlcnic_mac_statistics mac_stats; - int index, ret, length, size; + int index, ret, length, size, ring; char *p; + memset(data, 0, adapter->max_drv_tx_rings * 4 * sizeof(u64)); + for (ring = 0, index = 0; ring < adapter->max_drv_tx_rings; ring++) { + if (test_bit(__QLCNIC_DEV_UP, &adapter->state)) { + tx_ring = &adapter->tx_ring[ring]; + *data++ = tx_ring->xmit_on; + *data++ = tx_ring->xmit_off; + *data++ = tx_ring->xmit_called; + *data++ = tx_ring->xmit_finished; + } + } memset(data, 0, stats->n_stats * sizeof(u64)); length = QLCNIC_STATS_LEN; for (index = 0; index < length; index++) { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c index 4d5f59b2d15..f8adc7b01f1 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c @@ -387,7 +387,7 @@ qlcnic_send_cmd_descs(struct qlcnic_adapter *adapter, if (!test_bit(__QLCNIC_FW_ATTACHED, &adapter->state)) return -EIO; - tx_ring = adapter->tx_ring; + tx_ring = &adapter->tx_ring[0]; __netif_tx_lock_bh(tx_ring->txq); producer = tx_ring->producer; @@ -740,6 +740,22 @@ int qlcnic_82xx_clear_lb_mode(struct qlcnic_adapter *adapter, u8 mode) return 0; } +int qlcnic_82xx_read_phys_port_id(struct qlcnic_adapter *adapter) +{ + u8 mac[ETH_ALEN]; + int ret; + + ret = qlcnic_get_mac_address(adapter, mac, + adapter->ahw->physical_port); + if (ret) + return ret; + + memcpy(adapter->ahw->phys_port_id, mac, ETH_ALEN); + adapter->flags |= QLCNIC_HAS_PHYS_PORT_ID; + + return 0; +} + /* * Send the interrupt coalescing parameter set by ethtool to the card. */ diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h index 4a71b28effc..786366c64b0 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h @@ -87,6 +87,7 @@ enum qlcnic_regs { #define QLCNIC_CMD_CONFIG_VPORT 0x32 #define QLCNIC_CMD_GET_MAC_STATS 0x37 #define QLCNIC_CMD_82XX_SET_DRV_VER 0x38 +#define QLCNIC_CMD_MQ_TX_CONFIG_INTR 0x39 #define QLCNIC_CMD_GET_LED_STATUS 0x3C #define QLCNIC_CMD_CONFIGURE_RSS 0x41 #define QLCNIC_CMD_CONFIG_INTR_COAL 0x43 @@ -149,7 +150,6 @@ struct ethtool_stats; struct pci_device_id; struct qlcnic_host_sds_ring; struct qlcnic_host_tx_ring; -struct qlcnic_host_tx_ring; struct qlcnic_hardware_context; struct qlcnic_adapter; @@ -173,10 +173,12 @@ int qlcnic_82xx_set_lb_mode(struct qlcnic_adapter *, u8); void qlcnic_82xx_write_crb(struct qlcnic_adapter *, char *, loff_t, size_t); void qlcnic_82xx_read_crb(struct qlcnic_adapter *, char *, loff_t, size_t); void qlcnic_82xx_dev_request_reset(struct qlcnic_adapter *, u32); -int qlcnic_82xx_setup_intr(struct qlcnic_adapter *, u8); +int qlcnic_82xx_setup_intr(struct qlcnic_adapter *, u8, int); irqreturn_t qlcnic_82xx_clear_legacy_intr(struct qlcnic_adapter *); int qlcnic_82xx_issue_cmd(struct qlcnic_adapter *adapter, struct qlcnic_cmd_args *); +int qlcnic_82xx_mq_intrpt(struct qlcnic_adapter *, int); +int qlcnic_82xx_config_intrpt(struct qlcnic_adapter *, u8); int qlcnic_82xx_fw_cmd_create_rx_ctx(struct qlcnic_adapter *); int qlcnic_82xx_fw_cmd_create_tx_ctx(struct qlcnic_adapter *, struct qlcnic_host_tx_ring *tx_ring, int); @@ -184,7 +186,7 @@ void qlcnic_82xx_fw_cmd_del_rx_ctx(struct qlcnic_adapter *); void qlcnic_82xx_fw_cmd_del_tx_ctx(struct qlcnic_adapter *, struct qlcnic_host_tx_ring *); int qlcnic_82xx_sre_macaddr_change(struct qlcnic_adapter *, u8 *, u16, u8); -int qlcnic_82xx_get_mac_address(struct qlcnic_adapter *, u8*); +int qlcnic_82xx_get_mac_address(struct qlcnic_adapter *, u8*, u8); int qlcnic_82xx_get_nic_info(struct qlcnic_adapter *, struct qlcnic_info *, u8); int qlcnic_82xx_set_nic_info(struct qlcnic_adapter *, struct qlcnic_info *); int qlcnic_82xx_get_pci_info(struct qlcnic_adapter *, struct qlcnic_pci_info*); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c index 974d62607e1..66c26cf7a2b 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c @@ -127,12 +127,12 @@ void qlcnic_reset_rx_buffers_list(struct qlcnic_adapter *adapter) } } -void qlcnic_release_tx_buffers(struct qlcnic_adapter *adapter) +void qlcnic_release_tx_buffers(struct qlcnic_adapter *adapter, + struct qlcnic_host_tx_ring *tx_ring) { struct qlcnic_cmd_buffer *cmd_buf; struct qlcnic_skb_frag *buffrag; int i, j; - struct qlcnic_host_tx_ring *tx_ring = adapter->tx_ring; cmd_buf = tx_ring->cmd_buf_arr; for (i = 0; i < tx_ring->num_desc; i++) { @@ -241,7 +241,13 @@ int qlcnic_alloc_sw_resources(struct qlcnic_adapter *adapter) sds_ring->irq = adapter->msix_entries[ring].vector; sds_ring->adapter = adapter; sds_ring->num_desc = adapter->num_rxd; - + if (qlcnic_82xx_check(adapter)) { + if (qlcnic_check_multi_tx(adapter) && + !adapter->ahw->diag_test) + sds_ring->tx_ring = &adapter->tx_ring[ring]; + else + sds_ring->tx_ring = &adapter->tx_ring[0]; + } for (i = 0; i < NUM_RCV_DESC_RINGS; i++) INIT_LIST_HEAD(&sds_ring->free_list[i]); } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index f807f3b949e..89f6dff76d5 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -127,6 +127,23 @@ struct sk_buff *qlcnic_process_rxbuf(struct qlcnic_adapter *, struct qlcnic_host_rds_ring *, u16, u16); +inline void qlcnic_enable_tx_intr(struct qlcnic_adapter *adapter, + struct qlcnic_host_tx_ring *tx_ring) +{ + if (qlcnic_check_multi_tx(adapter) && + !adapter->ahw->diag_test) + writel(0x0, tx_ring->crb_intr_mask); +} + + +static inline void qlcnic_disable_tx_int(struct qlcnic_adapter *adapter, + struct qlcnic_host_tx_ring *tx_ring) +{ + if (qlcnic_check_multi_tx(adapter) && + !adapter->ahw->diag_test) + writel(1, tx_ring->crb_intr_mask); +} + inline void qlcnic_83xx_enable_tx_intr(struct qlcnic_adapter *adapter, struct qlcnic_host_tx_ring *tx_ring) { @@ -147,10 +164,7 @@ static inline u8 qlcnic_mac_hash(u64 mac) static inline u32 qlcnic_get_ref_handle(struct qlcnic_adapter *adapter, u16 handle, u8 ring_id) { - unsigned short device = adapter->pdev->device; - - if ((device == PCI_DEVICE_ID_QLOGIC_QLE834X) || - (device == PCI_DEVICE_ID_QLOGIC_VF_QLE834X)) + if (qlcnic_83xx_check(adapter)) return handle | (ring_id << 15); else return handle; @@ -357,14 +371,14 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter, } static int qlcnic_tx_pkt(struct qlcnic_adapter *adapter, - struct cmd_desc_type0 *first_desc, struct sk_buff *skb) + struct cmd_desc_type0 *first_desc, struct sk_buff *skb, + struct qlcnic_host_tx_ring *tx_ring) { u8 l4proto, opcode = 0, hdr_len = 0; u16 flags = 0, vlan_tci = 0; int copied, offset, copy_len, size; struct cmd_desc_type0 *hwdesc; struct vlan_ethhdr *vh; - struct qlcnic_host_tx_ring *tx_ring = adapter->tx_ring; u16 protocol = ntohs(skb->protocol); u32 producer = tx_ring->producer; @@ -547,7 +561,7 @@ static inline void qlcnic_clear_cmddesc(u64 *desc) netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) { struct qlcnic_adapter *adapter = netdev_priv(netdev); - struct qlcnic_host_tx_ring *tx_ring = adapter->tx_ring; + struct qlcnic_host_tx_ring *tx_ring; struct qlcnic_cmd_buffer *pbuf; struct qlcnic_skb_frag *buffrag; struct cmd_desc_type0 *hwdesc, *first_desc; @@ -556,10 +570,8 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) int i, k, frag_count, delta = 0; u32 producer, num_txd; - num_txd = tx_ring->num_desc; - if (!test_bit(__QLCNIC_DEV_UP, &adapter->state)) { - netif_stop_queue(netdev); + netif_tx_stop_all_queues(netdev); return NETDEV_TX_BUSY; } @@ -569,7 +581,14 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) goto drop_packet; } + if (qlcnic_check_multi_tx(adapter)) + tx_ring = &adapter->tx_ring[skb_get_queue_mapping(skb)]; + else + tx_ring = &adapter->tx_ring[0]; + num_txd = tx_ring->num_desc; + frag_count = skb_shinfo(skb)->nr_frags + 1; + /* 14 frags supported for normal packet and * 32 frags supported for TSO packet */ @@ -584,11 +603,12 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) } if (unlikely(qlcnic_tx_avail(tx_ring) <= TX_STOP_THRESH)) { - netif_stop_queue(netdev); + netif_tx_stop_queue(tx_ring->txq); if (qlcnic_tx_avail(tx_ring) > TX_STOP_THRESH) { - netif_start_queue(netdev); + netif_tx_start_queue(tx_ring->txq); } else { adapter->stats.xmit_off++; + tx_ring->xmit_off++; return NETDEV_TX_BUSY; } } @@ -643,7 +663,7 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) tx_ring->producer = get_next_index(producer, num_txd); smp_mb(); - if (unlikely(qlcnic_tx_pkt(adapter, first_desc, skb))) + if (unlikely(qlcnic_tx_pkt(adapter, first_desc, skb, tx_ring))) goto unwind_buff; if (adapter->drv_mac_learn) @@ -651,6 +671,7 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) adapter->stats.txbytes += skb->len; adapter->stats.xmitcalled++; + tx_ring->xmit_called++; qlcnic_update_cmd_producer(tx_ring); @@ -673,7 +694,7 @@ void qlcnic_advert_link_change(struct qlcnic_adapter *adapter, int linkup) adapter->ahw->linkup = 0; if (netif_running(netdev)) { netif_carrier_off(netdev); - netif_stop_queue(netdev); + netif_tx_stop_all_queues(netdev); } } else if (!adapter->ahw->linkup && linkup) { netdev_info(netdev, "NIC Link is up\n"); @@ -768,9 +789,6 @@ static int qlcnic_process_cmd_ring(struct qlcnic_adapter *adapter, struct net_device *netdev = adapter->netdev; struct qlcnic_skb_frag *frag; - if (!spin_trylock(&adapter->tx_clean_lock)) - return 1; - sw_consumer = tx_ring->sw_consumer; hw_consumer = le32_to_cpu(*(tx_ring->hw_consumer)); @@ -788,6 +806,7 @@ static int qlcnic_process_cmd_ring(struct qlcnic_adapter *adapter, frag->dma = 0ULL; } adapter->stats.xmitfinished++; + tx_ring->xmit_finished++; dev_kfree_skb_any(buffer->skb); buffer->skb = NULL; } @@ -800,10 +819,12 @@ static int qlcnic_process_cmd_ring(struct qlcnic_adapter *adapter, if (count && netif_running(netdev)) { tx_ring->sw_consumer = sw_consumer; smp_mb(); - if (netif_queue_stopped(netdev) && netif_carrier_ok(netdev)) { + if (netif_tx_queue_stopped(tx_ring->txq) && + netif_carrier_ok(netdev)) { if (qlcnic_tx_avail(tx_ring) > TX_STOP_THRESH) { - netif_wake_queue(netdev); + netif_tx_wake_queue(tx_ring->txq); adapter->stats.xmit_on++; + tx_ring->xmit_on++; } } adapter->tx_timeo_cnt = 0; @@ -823,7 +844,6 @@ static int qlcnic_process_cmd_ring(struct qlcnic_adapter *adapter, */ hw_consumer = le32_to_cpu(*(tx_ring->hw_consumer)); done = (sw_consumer == hw_consumer); - spin_unlock(&adapter->tx_clean_lock); return done; } @@ -833,16 +853,40 @@ static int qlcnic_poll(struct napi_struct *napi, int budget) int tx_complete, work_done; struct qlcnic_host_sds_ring *sds_ring; struct qlcnic_adapter *adapter; + struct qlcnic_host_tx_ring *tx_ring; sds_ring = container_of(napi, struct qlcnic_host_sds_ring, napi); adapter = sds_ring->adapter; - tx_complete = qlcnic_process_cmd_ring(adapter, adapter->tx_ring, + tx_ring = sds_ring->tx_ring; + + tx_complete = qlcnic_process_cmd_ring(adapter, tx_ring, budget); work_done = qlcnic_process_rcv_ring(sds_ring, budget); if ((work_done < budget) && tx_complete) { napi_complete(&sds_ring->napi); - if (test_bit(__QLCNIC_DEV_UP, &adapter->state)) + if (test_bit(__QLCNIC_DEV_UP, &adapter->state)) { qlcnic_enable_int(sds_ring); + qlcnic_enable_tx_intr(adapter, tx_ring); + } + } + + return work_done; +} + +static int qlcnic_tx_poll(struct napi_struct *napi, int budget) +{ + struct qlcnic_host_tx_ring *tx_ring; + struct qlcnic_adapter *adapter; + int work_done; + + tx_ring = container_of(napi, struct qlcnic_host_tx_ring, napi); + adapter = tx_ring->adapter; + + work_done = qlcnic_process_cmd_ring(adapter, tx_ring, budget); + if (work_done) { + napi_complete(&tx_ring->napi); + if (test_bit(__QLCNIC_DEV_UP, &adapter->state)) + qlcnic_enable_tx_intr(adapter, tx_ring); } return work_done; @@ -1414,6 +1458,7 @@ int qlcnic_82xx_napi_add(struct qlcnic_adapter *adapter, int ring, max_sds_rings; struct qlcnic_host_sds_ring *sds_ring; struct qlcnic_recv_context *recv_ctx = adapter->recv_ctx; + struct qlcnic_host_tx_ring *tx_ring; if (qlcnic_alloc_sds_rings(recv_ctx, adapter->max_sds_rings)) return -ENOMEM; @@ -1422,12 +1467,22 @@ int qlcnic_82xx_napi_add(struct qlcnic_adapter *adapter, for (ring = 0; ring < adapter->max_sds_rings; ring++) { sds_ring = &recv_ctx->sds_rings[ring]; - if (ring == adapter->max_sds_rings - 1) - netif_napi_add(netdev, &sds_ring->napi, qlcnic_poll, - QLCNIC_NETDEV_WEIGHT / max_sds_rings); - else + if (qlcnic_check_multi_tx(adapter) && + !adapter->ahw->diag_test && + (adapter->max_drv_tx_rings > 1)) { netif_napi_add(netdev, &sds_ring->napi, qlcnic_rx_poll, - QLCNIC_NETDEV_WEIGHT*2); + QLCNIC_NETDEV_WEIGHT * 2); + } else { + if (ring == (adapter->max_sds_rings - 1)) + netif_napi_add(netdev, &sds_ring->napi, + qlcnic_poll, + QLCNIC_NETDEV_WEIGHT / + max_sds_rings); + else + netif_napi_add(netdev, &sds_ring->napi, + qlcnic_rx_poll, + QLCNIC_NETDEV_WEIGHT * 2); + } } if (qlcnic_alloc_tx_rings(adapter, netdev)) { @@ -1435,6 +1490,14 @@ int qlcnic_82xx_napi_add(struct qlcnic_adapter *adapter, return -ENOMEM; } + if (qlcnic_check_multi_tx(adapter) && !adapter->ahw->diag_test) { + for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) { + tx_ring = &adapter->tx_ring[ring]; + netif_napi_add(netdev, &tx_ring->napi, qlcnic_tx_poll, + QLCNIC_NETDEV_WEIGHT); + } + } + return 0; } @@ -1443,6 +1506,7 @@ void qlcnic_82xx_napi_del(struct qlcnic_adapter *adapter) int ring; struct qlcnic_host_sds_ring *sds_ring; struct qlcnic_recv_context *recv_ctx = adapter->recv_ctx; + struct qlcnic_host_tx_ring *tx_ring; for (ring = 0; ring < adapter->max_sds_rings; ring++) { sds_ring = &recv_ctx->sds_rings[ring]; @@ -1450,6 +1514,14 @@ void qlcnic_82xx_napi_del(struct qlcnic_adapter *adapter) } qlcnic_free_sds_rings(adapter->recv_ctx); + + if (qlcnic_check_multi_tx(adapter) && !adapter->ahw->diag_test) { + for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) { + tx_ring = &adapter->tx_ring[ring]; + netif_napi_del(&tx_ring->napi); + } + } + qlcnic_free_tx_rings(adapter); } @@ -1457,6 +1529,7 @@ void qlcnic_82xx_napi_enable(struct qlcnic_adapter *adapter) { int ring; struct qlcnic_host_sds_ring *sds_ring; + struct qlcnic_host_tx_ring *tx_ring; struct qlcnic_recv_context *recv_ctx = adapter->recv_ctx; if (adapter->is_up != QLCNIC_ADAPTER_UP_MAGIC) @@ -1467,12 +1540,24 @@ void qlcnic_82xx_napi_enable(struct qlcnic_adapter *adapter) napi_enable(&sds_ring->napi); qlcnic_enable_int(sds_ring); } + + if (qlcnic_check_multi_tx(adapter) && + (adapter->flags & QLCNIC_MSIX_ENABLED) && + !adapter->ahw->diag_test && + (adapter->max_drv_tx_rings > 1)) { + for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) { + tx_ring = &adapter->tx_ring[ring]; + napi_enable(&tx_ring->napi); + qlcnic_enable_tx_intr(adapter, tx_ring); + } + } } void qlcnic_82xx_napi_disable(struct qlcnic_adapter *adapter) { int ring; struct qlcnic_host_sds_ring *sds_ring; + struct qlcnic_host_tx_ring *tx_ring; struct qlcnic_recv_context *recv_ctx = adapter->recv_ctx; if (adapter->is_up != QLCNIC_ADAPTER_UP_MAGIC) @@ -1484,6 +1569,17 @@ void qlcnic_82xx_napi_disable(struct qlcnic_adapter *adapter) napi_synchronize(&sds_ring->napi); napi_disable(&sds_ring->napi); } + + if ((adapter->flags & QLCNIC_MSIX_ENABLED) && + !adapter->ahw->diag_test && + qlcnic_check_multi_tx(adapter)) { + for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) { + tx_ring = &adapter->tx_ring[ring]; + qlcnic_disable_tx_int(adapter, tx_ring); + napi_synchronize(&tx_ring->napi); + napi_disable(&tx_ring->napi); + } + } } #define QLC_83XX_NORMAL_LB_PKT (1ULL << 36) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index a780b73e8b2..8321d1a3f4b 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -100,6 +100,8 @@ static DEFINE_PCI_DEVICE_TABLE(qlcnic_pci_tbl) = { ENTRY(PCI_DEVICE_ID_QLOGIC_QLE824X), ENTRY(PCI_DEVICE_ID_QLOGIC_QLE834X), ENTRY(PCI_DEVICE_ID_QLOGIC_VF_QLE834X), + ENTRY(PCI_DEVICE_ID_QLOGIC_QLE844X), + ENTRY(PCI_DEVICE_ID_QLOGIC_VF_QLE844X), {0,} }; @@ -146,6 +148,11 @@ static const u32 qlcnic_reg_tbl[] = { static const struct qlcnic_board_info qlcnic_boards[] = { { PCI_VENDOR_ID_QLOGIC, + PCI_DEVICE_ID_QLOGIC_QLE844X, + 0x0, + 0x0, + "8400 series 10GbE Converged Network Adapter (TCP/IP Networking)" }, + { PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_QLE834X, PCI_VENDOR_ID_QLOGIC, 0x24e, @@ -254,7 +261,6 @@ static const struct qlcnic_board_info qlcnic_boards[] = { }; #define NUM_SUPPORTED_BOARDS ARRAY_SIZE(qlcnic_boards) -#define QLC_MAX_SDS_RINGS 8 static const struct qlcnic_legacy_intr_set legacy_intr[] = QLCNIC_LEGACY_INTR_CONFIG; @@ -278,12 +284,15 @@ void qlcnic_free_sds_rings(struct qlcnic_recv_context *recv_ctx) int qlcnic_read_mac_addr(struct qlcnic_adapter *adapter) { - u8 mac_addr[ETH_ALEN]; struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; + u8 mac_addr[ETH_ALEN]; + int ret; - if (qlcnic_get_mac_address(adapter, mac_addr) != 0) - return -EIO; + ret = qlcnic_get_mac_address(adapter, mac_addr, + adapter->ahw->pci_func); + if (ret) + return ret; memcpy(netdev->dev_addr, mac_addr, ETH_ALEN); memcpy(adapter->mac_addr, netdev->dev_addr, netdev->addr_len); @@ -425,6 +434,21 @@ static void qlcnic_82xx_cancel_idc_work(struct qlcnic_adapter *adapter) cancel_delayed_work_sync(&adapter->fw_work); } +static int qlcnic_get_phys_port_id(struct net_device *netdev, + struct netdev_phys_port_id *ppid) +{ + struct qlcnic_adapter *adapter = netdev_priv(netdev); + struct qlcnic_hardware_context *ahw = adapter->ahw; + + if (!(adapter->flags & QLCNIC_HAS_PHYS_PORT_ID)) + return -EOPNOTSUPP; + + ppid->id_len = sizeof(ahw->phys_port_id); + memcpy(ppid->id, ahw->phys_port_id, ppid->id_len); + + return 0; +} + static const struct net_device_ops qlcnic_netdev_ops = { .ndo_open = qlcnic_open, .ndo_stop = qlcnic_close, @@ -442,6 +466,7 @@ static const struct net_device_ops qlcnic_netdev_ops = { .ndo_fdb_add = qlcnic_fdb_add, .ndo_fdb_del = qlcnic_fdb_del, .ndo_fdb_dump = qlcnic_fdb_dump, + .ndo_get_phys_port_id = qlcnic_get_phys_port_id, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = qlcnic_poll_controller, #endif @@ -514,13 +539,33 @@ static struct qlcnic_hardware_ops qlcnic_hw_ops = { .get_board_info = qlcnic_82xx_get_board_info, .set_mac_filter_count = qlcnic_82xx_set_mac_filter_count, .free_mac_list = qlcnic_82xx_free_mac_list, + .read_phys_port_id = qlcnic_82xx_read_phys_port_id, }; +static void qlcnic_get_multiq_capability(struct qlcnic_adapter *adapter) +{ + struct qlcnic_hardware_context *ahw = adapter->ahw; + int num_tx_q; + + if (ahw->msix_supported && + (ahw->extra_capability[0] & QLCNIC_FW_CAPABILITY_2_MULTI_TX)) { + num_tx_q = min_t(int, QLCNIC_DEF_NUM_TX_RINGS, + num_online_cpus()); + if (num_tx_q > 1) { + test_and_set_bit(__QLCNIC_MULTI_TX_UNIQUE, + &adapter->state); + adapter->max_drv_tx_rings = num_tx_q; + } + } else { + adapter->max_drv_tx_rings = 1; + } +} + int qlcnic_enable_msix(struct qlcnic_adapter *adapter, u32 num_msix) { struct pci_dev *pdev = adapter->pdev; + int max_tx_rings, max_sds_rings, tx_vector; int err = -1, i; - int max_tx_rings, tx_vector; if (adapter->flags & QLCNIC_TX_INTR_SHARED) { max_tx_rings = 0; @@ -554,7 +599,15 @@ int qlcnic_enable_msix(struct qlcnic_adapter *adapter, u32 num_msix) adapter->max_sds_rings = num_msix - max_tx_rings - 1; } else { - adapter->max_sds_rings = num_msix; + adapter->ahw->num_msix = num_msix; + if (qlcnic_check_multi_tx(adapter) && + !adapter->ahw->diag_test && + (adapter->max_drv_tx_rings > 1)) + max_sds_rings = num_msix - max_tx_rings; + else + max_sds_rings = num_msix; + + adapter->max_sds_rings = max_sds_rings; } dev_info(&pdev->dev, "using msi-x interrupts\n"); return err; @@ -570,6 +623,8 @@ int qlcnic_enable_msix(struct qlcnic_adapter *adapter, u32 num_msix) num_msix += (max_tx_rings + 1); } else { num_msix = rounddown_pow_of_two(err); + if (qlcnic_check_multi_tx(adapter)) + num_msix += max_tx_rings; } if (num_msix) { @@ -605,6 +660,7 @@ static int qlcnic_enable_msi_legacy(struct qlcnic_adapter *adapter) adapter->msix_entries[0].vector = pdev->irq; return err; } + if (qlcnic_use_msi || qlcnic_use_msi_x) return -EOPNOTSUPP; @@ -621,28 +677,69 @@ static int qlcnic_enable_msi_legacy(struct qlcnic_adapter *adapter) return err; } -int qlcnic_82xx_setup_intr(struct qlcnic_adapter *adapter, u8 num_intr) +int qlcnic_82xx_setup_intr(struct qlcnic_adapter *adapter, u8 num_intr, int txq) { + struct qlcnic_hardware_context *ahw = adapter->ahw; int num_msix, err = 0; if (!num_intr) num_intr = QLCNIC_DEF_NUM_STS_DESC_RINGS; - if (adapter->ahw->msix_supported) + if (ahw->msix_supported) { num_msix = rounddown_pow_of_two(min_t(int, num_online_cpus(), num_intr)); - else + if (qlcnic_check_multi_tx(adapter)) { + if (txq) + adapter->max_drv_tx_rings = txq; + num_msix += adapter->max_drv_tx_rings; + } + } else { num_msix = 1; + } err = qlcnic_enable_msix(adapter, num_msix); - if (err == -ENOMEM || !err) + if (err == -ENOMEM) return err; - err = qlcnic_enable_msi_legacy(adapter); - if (!err) + if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) { + qlcnic_disable_multi_tx(adapter); + + err = qlcnic_enable_msi_legacy(adapter); + if (!err) + return err; + } + + return 0; +} + +int qlcnic_82xx_mq_intrpt(struct qlcnic_adapter *adapter, int op_type) +{ + struct qlcnic_hardware_context *ahw = adapter->ahw; + int err, i; + + if (qlcnic_check_multi_tx(adapter) && + !ahw->diag_test && + (adapter->flags & QLCNIC_MSIX_ENABLED)) { + ahw->intr_tbl = vzalloc(ahw->num_msix * + sizeof(struct qlcnic_intrpt_config)); + if (!ahw->intr_tbl) + return -ENOMEM; + + for (i = 0; i < ahw->num_msix; i++) { + ahw->intr_tbl[i].type = QLCNIC_INTRPT_MSIX; + ahw->intr_tbl[i].id = i; + ahw->intr_tbl[i].src = 0; + } + + err = qlcnic_82xx_config_intrpt(adapter, 1); + if (err) + dev_err(&adapter->pdev->dev, + "Failed to configure Interrupt for %d vector\n", + ahw->num_msix); return err; + } - return -EIO; + return 0; } void qlcnic_teardown_intr(struct qlcnic_adapter *adapter) @@ -829,7 +926,9 @@ static void qlcnic_get_bar_length(u32 dev_id, ulong *bar) *bar = QLCNIC_82XX_BAR0_LENGTH; break; case PCI_DEVICE_ID_QLOGIC_QLE834X: + case PCI_DEVICE_ID_QLOGIC_QLE844X: case PCI_DEVICE_ID_QLOGIC_VF_QLE834X: + case PCI_DEVICE_ID_QLOGIC_VF_QLE844X: *bar = QLCNIC_83XX_BAR0_LENGTH; break; default: @@ -1413,6 +1512,7 @@ qlcnic_request_irq(struct qlcnic_adapter *adapter) for (ring = 0; ring < num_sds_rings; ring++) { sds_ring = &recv_ctx->sds_rings[ring]; if (qlcnic_82xx_check(adapter) && + !qlcnic_check_multi_tx(adapter) && (ring == (num_sds_rings - 1))) { if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) @@ -1436,9 +1536,11 @@ qlcnic_request_irq(struct qlcnic_adapter *adapter) return err; } } - if (qlcnic_83xx_check(adapter) && - (adapter->flags & QLCNIC_MSIX_ENABLED) && - !(adapter->flags & QLCNIC_TX_INTR_SHARED)) { + if ((qlcnic_82xx_check(adapter) && + qlcnic_check_multi_tx(adapter)) || + (qlcnic_83xx_check(adapter) && + (adapter->flags & QLCNIC_MSIX_ENABLED) && + !(adapter->flags & QLCNIC_TX_INTR_SHARED))) { handler = qlcnic_msix_tx_intr; for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) { @@ -1473,8 +1575,10 @@ qlcnic_free_irq(struct qlcnic_adapter *adapter) free_irq(sds_ring->irq, sds_ring); } } - if (qlcnic_83xx_check(adapter) && - !(adapter->flags & QLCNIC_TX_INTR_SHARED)) { + if ((qlcnic_83xx_check(adapter) && + !(adapter->flags & QLCNIC_TX_INTR_SHARED)) || + (qlcnic_82xx_check(adapter) && + qlcnic_check_multi_tx(adapter))) { for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) { tx_ring = &adapter->tx_ring[ring]; @@ -1510,8 +1614,10 @@ int __qlcnic_up(struct qlcnic_adapter *adapter, struct net_device *netdev) if (test_bit(__QLCNIC_DEV_UP, &adapter->state)) return 0; + if (qlcnic_set_eswitch_port_config(adapter)) return -EIO; + qlcnic_get_lro_mss_capability(adapter); if (qlcnic_fw_create_ctx(adapter)) @@ -1558,6 +1664,8 @@ int qlcnic_up(struct qlcnic_adapter *adapter, struct net_device *netdev) void __qlcnic_down(struct qlcnic_adapter *adapter, struct net_device *netdev) { + int ring; + if (adapter->is_up != QLCNIC_ADAPTER_UP_MAGIC) return; @@ -1567,7 +1675,6 @@ void __qlcnic_down(struct qlcnic_adapter *adapter, struct net_device *netdev) if (qlcnic_sriov_vf_check(adapter)) qlcnic_sriov_cleanup_async_list(&adapter->ahw->sriov->bc); smp_mb(); - spin_lock(&adapter->tx_clean_lock); netif_carrier_off(netdev); adapter->ahw->linkup = 0; netif_tx_disable(netdev); @@ -1585,8 +1692,9 @@ void __qlcnic_down(struct qlcnic_adapter *adapter, struct net_device *netdev) adapter->flags &= ~QLCNIC_FW_LRO_MSS_CAP; qlcnic_reset_rx_buffers_list(adapter); - qlcnic_release_tx_buffers(adapter); - spin_unlock(&adapter->tx_clean_lock); + + for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) + qlcnic_release_tx_buffers(adapter, &adapter->tx_ring[ring]); } /* Usage: During suspend and firmware recovery module */ @@ -1666,6 +1774,7 @@ void qlcnic_diag_free_res(struct net_device *netdev, int max_sds_rings) { struct qlcnic_adapter *adapter = netdev_priv(netdev); struct qlcnic_host_sds_ring *sds_ring; + int max_tx_rings = adapter->max_drv_tx_rings; int ring; clear_bit(__QLCNIC_DEV_UP, &adapter->state); @@ -1682,6 +1791,7 @@ void qlcnic_diag_free_res(struct net_device *netdev, int max_sds_rings) adapter->ahw->diag_test = 0; adapter->max_sds_rings = max_sds_rings; + adapter->max_drv_tx_rings = max_tx_rings; if (qlcnic_attach(adapter)) goto out; @@ -1750,6 +1860,7 @@ int qlcnic_diag_alloc_res(struct net_device *netdev, int test) adapter->max_sds_rings = 1; adapter->ahw->diag_test = test; adapter->ahw->linkup = 0; + adapter->max_drv_tx_rings = 1; ret = qlcnic_attach(adapter); if (ret) { @@ -1907,6 +2018,10 @@ qlcnic_setup_netdev(struct qlcnic_adapter *adapter, struct net_device *netdev, netdev->priv_flags |= IFF_UNICAST_FLT; netdev->irq = adapter->msix_entries[0].vector; + err = qlcnic_set_real_num_queues(adapter, netdev); + if (err) + return err; + err = register_netdev(netdev); if (err) { dev_err(&pdev->dev, "failed to register net device\n"); @@ -1975,7 +2090,8 @@ int qlcnic_alloc_tx_rings(struct qlcnic_adapter *adapter, tx_ring->cmd_buf_arr = cmd_buf_arr; } - if (qlcnic_83xx_check(adapter)) { + if (qlcnic_83xx_check(adapter) || + (qlcnic_82xx_check(adapter) && qlcnic_check_multi_tx(adapter))) { for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) { tx_ring = &adapter->tx_ring[ring]; tx_ring->adapter = adapter; @@ -1986,6 +2102,7 @@ int qlcnic_alloc_tx_rings(struct qlcnic_adapter *adapter, } } } + return 0; } @@ -2048,9 +2165,11 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ahw->reg_tbl = (u32 *) qlcnic_reg_tbl; break; case PCI_DEVICE_ID_QLOGIC_QLE834X: + case PCI_DEVICE_ID_QLOGIC_QLE844X: qlcnic_83xx_register_map(ahw); break; case PCI_DEVICE_ID_QLOGIC_VF_QLE834X: + case PCI_DEVICE_ID_QLOGIC_VF_QLE844X: qlcnic_sriov_vf_register_map(ahw); break; default: @@ -2061,7 +2180,8 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_out_free_hw_res; - netdev = alloc_etherdev(sizeof(struct qlcnic_adapter)); + netdev = alloc_etherdev_mq(sizeof(struct qlcnic_adapter), + QLCNIC_MAX_TX_RINGS); if (!netdev) { err = -ENOMEM; goto err_out_iounmap; @@ -2091,12 +2211,10 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->fdb_mac_learn = true; else if (qlcnic_mac_learn == DRV_MAC_LEARN) adapter->drv_mac_learn = true; - adapter->max_drv_tx_rings = 1; rwlock_init(&adapter->ahw->crb_lock); mutex_init(&adapter->ahw->mem_lock); - spin_lock_init(&adapter->tx_clean_lock); INIT_LIST_HEAD(&adapter->mac_list); if (qlcnic_82xx_check(adapter)) { @@ -2108,12 +2226,27 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_out_free_hw; } + qlcnic_get_multiq_capability(adapter); + + if ((adapter->ahw->act_pci_func > 2) && + qlcnic_check_multi_tx(adapter)) { + adapter->max_drv_tx_rings = QLCNIC_DEF_NUM_TX_RINGS; + dev_info(&adapter->pdev->dev, + "vNIC mode enabled, Set max TX rings = %d\n", + adapter->max_drv_tx_rings); + } + + if (!qlcnic_check_multi_tx(adapter)) { + clear_bit(__QLCNIC_MULTI_TX_UNIQUE, &adapter->state); + adapter->max_drv_tx_rings = 1; + } err = qlcnic_setup_idc_param(adapter); if (err) goto err_out_free_hw; adapter->flags |= QLCNIC_NEED_FLR; } else if (qlcnic_83xx_check(adapter)) { + adapter->max_drv_tx_rings = 1; qlcnic_83xx_check_vf(adapter, ent); adapter->portnum = adapter->ahw->pci_func; err = qlcnic_83xx_init(adapter, pci_using_dac); @@ -2132,6 +2265,8 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (qlcnic_read_mac_addr(adapter)) dev_warn(&pdev->dev, "failed to read mac addr\n"); + qlcnic_read_phys_port_id(adapter); + if (adapter->portnum == 0) { qlcnic_get_board_name(adapter, board_name); @@ -2146,7 +2281,7 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) "Device does not support MSI interrupts\n"); if (qlcnic_82xx_check(adapter)) { - err = qlcnic_setup_intr(adapter, 0); + err = qlcnic_setup_intr(adapter, 0, 0); if (err) { dev_err(&pdev->dev, "Failed to setup interrupt\n"); goto err_out_disable_msi; @@ -2334,7 +2469,7 @@ static int qlcnic_open(struct net_device *netdev) if (err) goto err_out; - netif_start_queue(netdev); + netif_tx_start_all_queues(netdev); return 0; @@ -2466,6 +2601,8 @@ int qlcnic_check_temp(struct qlcnic_adapter *adapter) static void qlcnic_tx_timeout(struct net_device *netdev) { struct qlcnic_adapter *adapter = netdev_priv(netdev); + struct qlcnic_host_tx_ring *tx_ring; + int ring; if (test_bit(__QLCNIC_RESETTING, &adapter->state)) return; @@ -2479,6 +2616,25 @@ static void qlcnic_tx_timeout(struct net_device *netdev) QLCNIC_FORCE_FW_DUMP_KEY); } else { netdev_info(netdev, "Tx timeout, reset adapter context.\n"); + if (qlcnic_82xx_check(adapter)) { + for (ring = 0; ring < adapter->max_drv_tx_rings; + ring++) { + tx_ring = &adapter->tx_ring[ring]; + dev_info(&netdev->dev, "ring=%d\n", ring); + dev_info(&netdev->dev, "crb_intr_mask=%d\n", + readl(tx_ring->crb_intr_mask)); + dev_info(&netdev->dev, "producer=%d\n", + readl(tx_ring->crb_cmd_producer)); + dev_info(&netdev->dev, "sw_consumer = %d\n", + tx_ring->sw_consumer); + dev_info(&netdev->dev, "hw_consumer = %d\n", + le32_to_cpu(*(tx_ring->hw_consumer))); + dev_info(&netdev->dev, "xmit-on=%llu\n", + tx_ring->xmit_on); + dev_info(&netdev->dev, "xmit-off=%llu\n", + tx_ring->xmit_off); + } + } adapter->ahw->reset_context = 1; } } @@ -3243,7 +3399,7 @@ static int qlcnic_attach_func(struct pci_dev *pdev) qlcnic_clr_drv_state(adapter); kfree(adapter->msix_entries); adapter->msix_entries = NULL; - err = qlcnic_setup_intr(adapter, 0); + err = qlcnic_setup_intr(adapter, 0, 0); if (err) { kfree(adapter->msix_entries); @@ -3368,16 +3524,65 @@ qlcnicvf_start_firmware(struct qlcnic_adapter *adapter) return err; } +int qlcnic_validate_max_tx_rings(struct qlcnic_adapter *adapter, int txq) +{ + struct net_device *netdev = adapter->netdev; + u8 max_hw = QLCNIC_MAX_TX_RINGS; + u32 max_allowed; + + if (!qlcnic_82xx_check(adapter)) { + netdev_err(netdev, "No Multi TX-Q support\n"); + return -EINVAL; + } + + if (!qlcnic_use_msi_x && !qlcnic_use_msi) { + netdev_err(netdev, "No Multi TX-Q support in INT-x mode\n"); + return -EINVAL; + } + + if (!qlcnic_check_multi_tx(adapter)) { + netdev_err(netdev, "No Multi TX-Q support\n"); + return -EINVAL; + } + + if (txq > QLCNIC_MAX_TX_RINGS) { + netdev_err(netdev, "Invalid ring count\n"); + return -EINVAL; + } + + max_allowed = rounddown_pow_of_two(min_t(int, max_hw, + num_online_cpus())); + if ((txq > max_allowed) || !is_power_of_2(txq)) { + if (!is_power_of_2(txq)) + netdev_err(netdev, + "TX queue should be a power of 2\n"); + if (txq > num_online_cpus()) + netdev_err(netdev, + "Tx queue should not be higher than [%u], number of online CPUs in the system\n", + num_online_cpus()); + netdev_err(netdev, "Unable to configure %u Tx rings\n", txq); + return -EINVAL; + } + + return 0; +} + int qlcnic_validate_max_rss(struct qlcnic_adapter *adapter, - __u32 val) + __u32 val) { struct net_device *netdev = adapter->netdev; u8 max_hw = adapter->ahw->max_rx_ques; u32 max_allowed; - if (val > QLC_MAX_SDS_RINGS) { + if (qlcnic_82xx_check(adapter) && !qlcnic_use_msi_x && + !qlcnic_use_msi) { + netdev_err(netdev, "No RSS support in INT-x mode\n"); + return -EINVAL; + } + + if (val > QLCNIC_MAX_SDS_RINGS) { netdev_err(netdev, "RSS value should not be higher than %u\n", - QLC_MAX_SDS_RINGS); + QLCNIC_MAX_SDS_RINGS); return -EINVAL; } @@ -3407,27 +3612,48 @@ int qlcnic_validate_max_rss(struct qlcnic_adapter *adapter, return 0; } -int qlcnic_set_max_rss(struct qlcnic_adapter *adapter, u8 data, size_t len) +int qlcnic_set_max_rss(struct qlcnic_adapter *adapter, u8 data, int txq) { int err; struct net_device *netdev = adapter->netdev; + int num_msix; if (test_bit(__QLCNIC_RESETTING, &adapter->state)) return -EBUSY; + if (qlcnic_82xx_check(adapter) && !qlcnic_use_msi_x && + !qlcnic_use_msi) { + netdev_err(netdev, "No RSS support in INT-x mode\n"); + return -EINVAL; + } + netif_device_detach(netdev); if (netif_running(netdev)) __qlcnic_down(adapter, netdev); qlcnic_detach(adapter); + if (qlcnic_82xx_check(adapter)) { + if (txq != 0) + adapter->max_drv_tx_rings = txq; + + if (qlcnic_check_multi_tx(adapter) && + (txq > adapter->max_drv_tx_rings)) + num_msix = adapter->max_drv_tx_rings; + else + num_msix = data; + } + if (qlcnic_83xx_check(adapter)) { qlcnic_83xx_free_mbx_intr(adapter); qlcnic_83xx_enable_mbx_poll(adapter); } + netif_set_real_num_tx_queues(netdev, adapter->max_drv_tx_rings); + qlcnic_teardown_intr(adapter); - err = qlcnic_setup_intr(adapter, data); + + err = qlcnic_setup_intr(adapter, data, txq); if (err) { kfree(adapter->msix_entries); netdev_err(netdev, "failed to setup interrupt\n"); @@ -3455,8 +3681,7 @@ int qlcnic_set_max_rss(struct qlcnic_adapter *adapter, u8 data, size_t len) goto done; qlcnic_restore_indev_addr(netdev, NETDEV_UP); } - err = len; - done: +done: netif_device_attach(netdev); clear_bit(__QLCNIC_RESETTING, &adapter->state); return err; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c index dc249796d61..2f79ec5246d 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c @@ -398,10 +398,14 @@ int qlcnic_sriov_get_vf_vport_info(struct qlcnic_adapter *adapter, } static int qlcnic_sriov_set_pvid_mode(struct qlcnic_adapter *adapter, - struct qlcnic_cmd_args *cmd) + struct qlcnic_cmd_args *cmd, u32 cap) { - adapter->rx_pvid = (cmd->rsp.arg[1] >> 16) & 0xffff; - adapter->flags &= ~QLCNIC_TAGGING_ENABLED; + if (cap & QLC_83XX_PVID_STRIP_CAPABILITY) { + adapter->rx_pvid = 0; + } else { + adapter->rx_pvid = (cmd->rsp.arg[1] >> 16) & 0xffff; + adapter->flags &= ~QLCNIC_TAGGING_ENABLED; + } return 0; } @@ -432,12 +436,14 @@ static int qlcnic_sriov_set_guest_vlan_mode(struct qlcnic_adapter *adapter, return 0; } -static int qlcnic_sriov_get_vf_acl(struct qlcnic_adapter *adapter) +static int qlcnic_sriov_get_vf_acl(struct qlcnic_adapter *adapter, + struct qlcnic_info *info) { struct qlcnic_sriov *sriov = adapter->ahw->sriov; struct qlcnic_cmd_args cmd; - int ret; + int ret, cap; + cap = info->capabilities; ret = qlcnic_sriov_alloc_bc_mbx_args(&cmd, QLCNIC_BC_CMD_GET_ACL); if (ret) return ret; @@ -453,7 +459,7 @@ static int qlcnic_sriov_get_vf_acl(struct qlcnic_adapter *adapter) ret = qlcnic_sriov_set_guest_vlan_mode(adapter, &cmd); break; case QLC_PVID_MODE: - ret = qlcnic_sriov_set_pvid_mode(adapter, &cmd); + ret = qlcnic_sriov_set_pvid_mode(adapter, &cmd, cap); break; } } @@ -476,7 +482,7 @@ static int qlcnic_sriov_vf_init_driver(struct qlcnic_adapter *adapter) if (err) return -EIO; - err = qlcnic_sriov_get_vf_acl(adapter); + err = qlcnic_sriov_get_vf_acl(adapter, &nic_info); if (err) return err; @@ -506,7 +512,7 @@ static int qlcnic_sriov_setup_vf(struct qlcnic_adapter *adapter, dev_warn(&adapter->pdev->dev, "Device does not support MSI interrupts\n"); - err = qlcnic_setup_intr(adapter, 1); + err = qlcnic_setup_intr(adapter, 1, 0); if (err) { dev_err(&adapter->pdev->dev, "Failed to setup interrupt\n"); goto err_out_disable_msi; diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index b5eb4195fc9..c0c9e145fd3 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -1897,12 +1897,13 @@ static void rtl8169_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *p) { struct rtl8169_private *tp = netdev_priv(dev); - - if (regs->len > R8169_REGS_SIZE) - regs->len = R8169_REGS_SIZE; + u32 __iomem *data = tp->mmio_addr; + u32 *dw = p; + int i; rtl_lock_work(tp); - memcpy_fromio(p, tp->mmio_addr, regs->len); + for (i = 0; i < R8169_REGS_SIZE; i += 4) + memcpy_fromio(dw++, data++, 4); rtl_unlock_work(tp); } diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 9e2afe8e0c9..c3570764f58 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -378,6 +378,8 @@ static struct sh_eth_cpu_data r8a777x_data = { .set_duplex = sh_eth_set_duplex, .set_rate = sh_eth_set_rate_r8a777x, + .register_type = SH_ETH_REG_FAST_RCAR, + .ecsr_value = ECSR_PSRTO | ECSR_LCHNG | ECSR_ICD, .ecsipr_value = ECSIPR_PSRTOIP | ECSIPR_LCHNGIP | ECSIPR_ICDIP, .eesipr_value = 0x01ff009f, @@ -398,6 +400,8 @@ static struct sh_eth_cpu_data r8a7790_data = { .set_duplex = sh_eth_set_duplex, .set_rate = sh_eth_set_rate_r8a777x, + .register_type = SH_ETH_REG_FAST_RCAR, + .ecsr_value = ECSR_PSRTO | ECSR_LCHNG | ECSR_ICD, .ecsipr_value = ECSIPR_PSRTOIP | ECSIPR_LCHNGIP | ECSIPR_ICDIP, .eesipr_value = 0x01ff009f, @@ -435,6 +439,8 @@ static struct sh_eth_cpu_data sh7724_data = { .set_duplex = sh_eth_set_duplex, .set_rate = sh_eth_set_rate_sh7724, + .register_type = SH_ETH_REG_FAST_SH4, + .ecsr_value = ECSR_PSRTO | ECSR_LCHNG | ECSR_ICD, .ecsipr_value = ECSIPR_PSRTOIP | ECSIPR_LCHNGIP | ECSIPR_ICDIP, .eesipr_value = 0x01ff009f, @@ -473,6 +479,8 @@ static struct sh_eth_cpu_data sh7757_data = { .set_duplex = sh_eth_set_duplex, .set_rate = sh_eth_set_rate_sh7757, + .register_type = SH_ETH_REG_FAST_SH4, + .eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff, .rmcr_value = 0x00000001, @@ -541,6 +549,8 @@ static struct sh_eth_cpu_data sh7757_data_giga = { .set_duplex = sh_eth_set_duplex, .set_rate = sh_eth_set_rate_giga, + .register_type = SH_ETH_REG_GIGABIT, + .ecsr_value = ECSR_ICD | ECSR_MPD, .ecsipr_value = ECSIPR_LCHNGIP | ECSIPR_ICDIP | ECSIPR_MPDIP, .eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff, @@ -599,6 +609,8 @@ static struct sh_eth_cpu_data sh7734_data = { .set_duplex = sh_eth_set_duplex, .set_rate = sh_eth_set_rate_gether, + .register_type = SH_ETH_REG_GIGABIT, + .ecsr_value = ECSR_ICD | ECSR_MPD, .ecsipr_value = ECSIPR_LCHNGIP | ECSIPR_ICDIP | ECSIPR_MPDIP, .eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff, @@ -626,6 +638,8 @@ static struct sh_eth_cpu_data sh7763_data = { .set_duplex = sh_eth_set_duplex, .set_rate = sh_eth_set_rate_gether, + .register_type = SH_ETH_REG_GIGABIT, + .ecsr_value = ECSR_ICD | ECSR_MPD, .ecsipr_value = ECSIPR_LCHNGIP | ECSIPR_ICDIP | ECSIPR_MPDIP, .eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff, @@ -663,6 +677,8 @@ static struct sh_eth_cpu_data r8a7740_data = { .set_duplex = sh_eth_set_duplex, .set_rate = sh_eth_set_rate_gether, + .register_type = SH_ETH_REG_GIGABIT, + .ecsr_value = ECSR_ICD | ECSR_MPD, .ecsipr_value = ECSIPR_LCHNGIP | ECSIPR_ICDIP | ECSIPR_MPDIP, .eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff, @@ -685,6 +701,8 @@ static struct sh_eth_cpu_data r8a7740_data = { }; static struct sh_eth_cpu_data sh7619_data = { + .register_type = SH_ETH_REG_FAST_SH3_SH2, + .eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff, .apr = 1, @@ -694,6 +712,8 @@ static struct sh_eth_cpu_data sh7619_data = { }; static struct sh_eth_cpu_data sh771x_data = { + .register_type = SH_ETH_REG_FAST_SH3_SH2, + .eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff, .tsu = 1, }; @@ -2643,10 +2663,10 @@ static int sh_eth_drv_probe(struct platform_device *pdev) mdp->edmac_endian = pd->edmac_endian; mdp->no_ether_link = pd->no_ether_link; mdp->ether_link_active_low = pd->ether_link_active_low; - mdp->reg_offset = sh_eth_get_register_offset(pd->register_type); /* set cpu data */ mdp->cd = (struct sh_eth_cpu_data *)id->driver_data; + mdp->reg_offset = sh_eth_get_register_offset(mdp->cd->register_type); sh_eth_set_default_cpu_data(mdp->cd); /* set function */ diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index da93f5cf41f..a0db02c63b1 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -157,6 +157,13 @@ enum { SH_ETH_MAX_REGISTER_OFFSET, }; +enum { + SH_ETH_REG_GIGABIT, + SH_ETH_REG_FAST_RCAR, + SH_ETH_REG_FAST_SH4, + SH_ETH_REG_FAST_SH3_SH2 +}; + /* Driver's parameters */ #if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE) #define SH4_SKB_RX_ALIGN 32 @@ -454,6 +461,7 @@ struct sh_eth_cpu_data { void (*set_rate)(struct net_device *ndev); /* mandatory initialize value */ + int register_type; unsigned long eesipr_value; /* optional initialize value */ diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c index 02df0894690..ee18e6f7b4f 100644 --- a/drivers/net/ethernet/sis/sis190.c +++ b/drivers/net/ethernet/sis/sis190.c @@ -1770,9 +1770,6 @@ static void sis190_get_regs(struct net_device *dev, struct ethtool_regs *regs, struct sis190_private *tp = netdev_priv(dev); unsigned long flags; - if (regs->len > SIS190_REGS_SIZE) - regs->len = SIS190_REGS_SIZE; - spin_lock_irqsave(&tp->lock, flags); memcpy_fromio(p, tp->mmio_addr, regs->len); spin_unlock_irqrestore(&tp->lock, flags); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index c922fde929a..f16a9bdf45b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -70,7 +70,6 @@ struct stmmac_priv { struct net_device *dev; struct device *device; struct mac_device_info *hw; - int no_csum_insertion; spinlock_t lock; struct phy_device *phydev ____cacheline_aligned_in_smp; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 0a9bb9d30c3..be406911fd0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1224,8 +1224,7 @@ static void free_dma_desc_resources(struct stmmac_priv *priv) */ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) { - if (likely(priv->plat->force_sf_dma_mode || - ((priv->plat->tx_coe) && (!priv->no_csum_insertion)))) { + if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) { /* * In case of GMAC, SF mode can be enabled * to perform the TX COE in HW. This depends on: diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index 0d43fa9ff98..7217ee5d627 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -1239,7 +1239,7 @@ static int bigmac_sbus_probe(struct platform_device *op) static int bigmac_sbus_remove(struct platform_device *op) { - struct bigmac *bp = dev_get_drvdata(&op->dev); + struct bigmac *bp = platform_get_drvdata(op); struct device *parent = op->dev.parent; struct net_device *net_dev = bp->dev; struct platform_device *qec_op; @@ -1259,8 +1259,6 @@ static int bigmac_sbus_remove(struct platform_device *op) free_netdev(net_dev); - dev_set_drvdata(&op->dev, NULL); - return 0; } diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 171f5b0809c..c67e683a36e 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -3231,7 +3231,7 @@ static int hme_sbus_probe(struct platform_device *op) static int hme_sbus_remove(struct platform_device *op) { - struct happy_meal *hp = dev_get_drvdata(&op->dev); + struct happy_meal *hp = platform_get_drvdata(op); struct net_device *net_dev = hp->dev; unregister_netdev(net_dev); @@ -3250,8 +3250,6 @@ static int hme_sbus_remove(struct platform_device *op) free_netdev(net_dev); - dev_set_drvdata(&op->dev, NULL); - return 0; } diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 0fcf21254ad..79974e31187 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -34,9 +34,9 @@ #include <linux/of_device.h> #include <linux/if_vlan.h> -#include <linux/platform_data/cpsw.h> #include <linux/pinctrl/consumer.h> +#include "cpsw.h" #include "cpsw_ale.h" #include "cpts.h" #include "davinci_cpdma.h" @@ -1640,6 +1640,29 @@ static int cpsw_set_settings(struct net_device *ndev, struct ethtool_cmd *ecmd) return -EOPNOTSUPP; } +static void cpsw_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + int slave_no = cpsw_slave_index(priv); + + wol->supported = 0; + wol->wolopts = 0; + + if (priv->slaves[slave_no].phy) + phy_ethtool_get_wol(priv->slaves[slave_no].phy, wol); +} + +static int cpsw_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + int slave_no = cpsw_slave_index(priv); + + if (priv->slaves[slave_no].phy) + return phy_ethtool_set_wol(priv->slaves[slave_no].phy, wol); + else + return -EOPNOTSUPP; +} + static const struct ethtool_ops cpsw_ethtool_ops = { .get_drvinfo = cpsw_get_drvinfo, .get_msglevel = cpsw_get_msglevel, @@ -1653,6 +1676,8 @@ static const struct ethtool_ops cpsw_ethtool_ops = { .get_sset_count = cpsw_get_sset_count, .get_strings = cpsw_get_strings, .get_ethtool_stats = cpsw_get_ethtool_stats, + .get_wol = cpsw_get_wol, + .set_wol = cpsw_set_wol, }; static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv, diff --git a/include/linux/platform_data/cpsw.h b/drivers/net/ethernet/ti/cpsw.h index bb3cd58d71e..eb3e101ec04 100644 --- a/include/linux/platform_data/cpsw.h +++ b/drivers/net/ethernet/ti/cpsw.h @@ -1,11 +1,10 @@ -/* - * Texas Instruments Ethernet Switch Driver +/* Texas Instruments Ethernet Switch Driver * - * Copyright (C) 2012 Texas Instruments + * Copyright (C) 2013 Texas Instruments * * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. * * This program is distributed "as is" WITHOUT ANY WARRANTY of any * kind, whether express or implied; without even the implied warranty @@ -22,14 +21,13 @@ struct cpsw_slave_data { int phy_if; u8 mac_addr[ETH_ALEN]; u16 dual_emac_res_vlan; /* Reserved VLAN for DualEMAC */ - }; struct cpsw_platform_data { + struct cpsw_slave_data *slave_data; u32 ss_reg_ofs; /* Subsystem control register offset */ u32 channels; /* number of cpdma channels (symmetric) */ u32 slaves; /* number of slave cpgmac ports */ - struct cpsw_slave_data *slave_data; u32 active_slave; /* time stamping, ethtool and SIOCGMIIPHY slave */ u32 cpts_clock_mult; /* convert input clock ticks to nanoseconds */ u32 cpts_clock_shift; /* convert input clock ticks to nanoseconds */ diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c index 031ebc81b50..90a79462c86 100644 --- a/drivers/net/ethernet/ti/davinci_cpdma.c +++ b/drivers/net/ethernet/ti/davinci_cpdma.c @@ -591,6 +591,7 @@ int cpdma_chan_get_stats(struct cpdma_chan *chan, spin_unlock_irqrestore(&chan->lock, flags); return 0; } +EXPORT_SYMBOL_GPL(cpdma_chan_get_stats); int cpdma_chan_dump(struct cpdma_chan *chan) { diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c index 16ddfc34806..7f851438486 100644 --- a/drivers/net/ethernet/ti/davinci_mdio.c +++ b/drivers/net/ethernet/ti/davinci_mdio.c @@ -421,8 +421,7 @@ bail_out: static int davinci_mdio_remove(struct platform_device *pdev) { - struct device *dev = &pdev->dev; - struct davinci_mdio_data *data = dev_get_drvdata(dev); + struct davinci_mdio_data *data = platform_get_drvdata(pdev); if (data->bus) { mdiobus_unregister(data->bus); @@ -434,8 +433,6 @@ static int davinci_mdio_remove(struct platform_device *pdev) pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); - dev_set_drvdata(dev, NULL); - kfree(data); return 0; diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index fd4dbdae533..4c619ea5189 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -1230,8 +1230,7 @@ error: */ static int xemaclite_of_remove(struct platform_device *of_dev) { - struct device *dev = &of_dev->dev; - struct net_device *ndev = dev_get_drvdata(dev); + struct net_device *ndev = platform_get_drvdata(of_dev); struct net_local *lp = netdev_priv(ndev); @@ -1250,7 +1249,6 @@ static int xemaclite_of_remove(struct platform_device *of_dev) lp->phy_node = NULL; xemaclite_remove_ndev(ndev, of_dev); - dev_set_drvdata(dev, NULL); return 0; } diff --git a/drivers/net/irda/pxaficp_ir.c b/drivers/net/irda/pxaficp_ir.c index 964b116a0ab..3eeaaf80049 100644 --- a/drivers/net/irda/pxaficp_ir.c +++ b/drivers/net/irda/pxaficp_ir.c @@ -915,7 +915,7 @@ static int pxa_irda_probe(struct platform_device *pdev) err = register_netdev(dev); if (err == 0) - dev_set_drvdata(&pdev->dev, dev); + platform_set_drvdata(pdev, dev); if (err) { if (si->pdata->shutdown) diff --git a/drivers/net/phy/mdio-octeon.c b/drivers/net/phy/mdio-octeon.c index b51fa1f469b..7f18f80e87c 100644 --- a/drivers/net/phy/mdio-octeon.c +++ b/drivers/net/phy/mdio-octeon.c @@ -222,7 +222,7 @@ static int octeon_mdiobus_probe(struct platform_device *pdev) bus->mii_bus->read = octeon_mdiobus_read; bus->mii_bus->write = octeon_mdiobus_write; - dev_set_drvdata(&pdev->dev, bus); + platform_set_drvdata(pdev, bus); err = of_mdiobus_register(bus->mii_bus, pdev->dev.of_node); if (err) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 9ca49455018..c31aad0004c 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -25,6 +25,7 @@ #include <linux/module.h> #include <linux/phy.h> #include <linux/micrel_phy.h> +#include <linux/of.h> /* Operation Mode Strap Override */ #define MII_KSZPHY_OMSO 0x16 @@ -53,6 +54,20 @@ #define KS8737_CTRL_INT_ACTIVE_HIGH (1 << 14) #define KSZ8051_RMII_50MHZ_CLK (1 << 7) +/* Write/read to/from extended registers */ +#define MII_KSZPHY_EXTREG 0x0b +#define KSZPHY_EXTREG_WRITE 0x8000 + +#define MII_KSZPHY_EXTREG_WRITE 0x0c +#define MII_KSZPHY_EXTREG_READ 0x0d + +/* Extended registers */ +#define MII_KSZPHY_CLK_CONTROL_PAD_SKEW 0x104 +#define MII_KSZPHY_RX_DATA_PAD_SKEW 0x105 +#define MII_KSZPHY_TX_DATA_PAD_SKEW 0x106 + +#define PS_TO_REG 200 + static int ksz_config_flags(struct phy_device *phydev) { int regval; @@ -65,6 +80,20 @@ static int ksz_config_flags(struct phy_device *phydev) return 0; } +static int kszphy_extended_write(struct phy_device *phydev, + u32 regnum, u16 val) +{ + phy_write(phydev, MII_KSZPHY_EXTREG, KSZPHY_EXTREG_WRITE | regnum); + return phy_write(phydev, MII_KSZPHY_EXTREG_WRITE, val); +} + +static int kszphy_extended_read(struct phy_device *phydev, + u32 regnum) +{ + phy_write(phydev, MII_KSZPHY_EXTREG, regnum); + return phy_read(phydev, MII_KSZPHY_EXTREG_READ); +} + static int kszphy_ack_interrupt(struct phy_device *phydev) { /* bit[7..0] int status, which is a read and clear register. */ @@ -141,6 +170,78 @@ static int ks8051_config_init(struct phy_device *phydev) return rc < 0 ? rc : 0; } +static int ksz9021_load_values_from_of(struct phy_device *phydev, + struct device_node *of_node, u16 reg, + char *field1, char *field2, + char *field3, char *field4) +{ + int val1 = -1; + int val2 = -2; + int val3 = -3; + int val4 = -4; + int newval; + int matches = 0; + + if (!of_property_read_u32(of_node, field1, &val1)) + matches++; + + if (!of_property_read_u32(of_node, field2, &val2)) + matches++; + + if (!of_property_read_u32(of_node, field3, &val3)) + matches++; + + if (!of_property_read_u32(of_node, field4, &val4)) + matches++; + + if (!matches) + return 0; + + if (matches < 4) + newval = kszphy_extended_read(phydev, reg); + else + newval = 0; + + if (val1 != -1) + newval = ((newval & 0xfff0) | ((val1 / PS_TO_REG) & 0xf) << 0); + + if (val2 != -1) + newval = ((newval & 0xff0f) | ((val2 / PS_TO_REG) & 0xf) << 4); + + if (val3 != -1) + newval = ((newval & 0xf0ff) | ((val3 / PS_TO_REG) & 0xf) << 8); + + if (val4 != -1) + newval = ((newval & 0x0fff) | ((val4 / PS_TO_REG) & 0xf) << 12); + + return kszphy_extended_write(phydev, reg, newval); +} + +static int ksz9021_config_init(struct phy_device *phydev) +{ + struct device *dev = &phydev->dev; + struct device_node *of_node = dev->of_node; + + if (!of_node && dev->parent->of_node) + of_node = dev->parent->of_node; + + if (of_node) { + ksz9021_load_values_from_of(phydev, of_node, + MII_KSZPHY_CLK_CONTROL_PAD_SKEW, + "txen-skew-ps", "txc-skew-ps", + "rxdv-skew-ps", "rxc-skew-ps"); + ksz9021_load_values_from_of(phydev, of_node, + MII_KSZPHY_RX_DATA_PAD_SKEW, + "rxd0-skew-ps", "rxd1-skew-ps", + "rxd2-skew-ps", "rxd3-skew-ps"); + ksz9021_load_values_from_of(phydev, of_node, + MII_KSZPHY_TX_DATA_PAD_SKEW, + "txd0-skew-ps", "txd1-skew-ps", + "txd2-skew-ps", "txd3-skew-ps"); + } + return 0; +} + #define KSZ8873MLL_GLOBAL_CONTROL_4 0x06 #define KSZ8873MLL_GLOBAL_CONTROL_4_DUPLEX (1 << 6) #define KSZ8873MLL_GLOBAL_CONTROL_4_SPEED (1 << 4) @@ -281,7 +382,7 @@ static struct phy_driver ksphy_driver[] = { .name = "Micrel KSZ9021 Gigabit PHY", .features = (PHY_GBIT_FEATURES | SUPPORTED_Pause), .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, - .config_init = kszphy_config_init, + .config_init = ksz9021_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 7ed13cc0dcb..60a1e93e9d3 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -138,7 +138,10 @@ struct tun_file { struct fasync_struct *fasync; /* only used for fasnyc */ unsigned int flags; - u16 queue_index; + union { + u16 queue_index; + unsigned int ifindex; + }; struct list_head next; struct tun_struct *detached; }; @@ -498,7 +501,7 @@ static void tun_detach_all(struct net_device *dev) module_put(THIS_MODULE); } -static int tun_attach(struct tun_struct *tun, struct file *file) +static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter) { struct tun_file *tfile = file->private_data; int err; @@ -523,7 +526,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file) err = 0; /* Re-attach the filter to presist device */ - if (tun->filter_attached == true) { + if (!skip_filter && (tun->filter_attached == true)) { err = sk_attach_filter(&tun->fprog, tfile->socket.sk); if (!err) goto out; @@ -1554,7 +1557,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (err < 0) return err; - err = tun_attach(tun, file); + err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER); if (err < 0) return err; @@ -1601,6 +1604,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) dev_net_set(dev, net); dev->rtnl_link_ops = &tun_link_ops; + dev->ifindex = tfile->ifindex; tun = netdev_priv(dev); tun->dev = dev; @@ -1627,7 +1631,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) dev->vlan_features = dev->features; INIT_LIST_HEAD(&tun->disabled); - err = tun_attach(tun, file); + err = tun_attach(tun, file, false); if (err < 0) goto err_free_dev; @@ -1791,7 +1795,7 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr) ret = security_tun_dev_attach_queue(tun->security); if (ret < 0) goto unlock; - ret = tun_attach(tun, file); + ret = tun_attach(tun, file, false); } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { tun = rtnl_dereference(tfile->tun); if (!tun || !(tun->flags & TUN_TAP_MQ) || tfile->detached) @@ -1817,6 +1821,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, kgid_t group; int sndbuf; int vnet_hdr_sz; + unsigned int ifindex; int ret; if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) { @@ -1851,6 +1856,19 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, ret = -EFAULT; goto unlock; } + if (cmd == TUNSETIFINDEX) { + ret = -EPERM; + if (tun) + goto unlock; + + ret = -EFAULT; + if (copy_from_user(&ifindex, argp, sizeof(ifindex))) + goto unlock; + + ret = 0; + tfile->ifindex = ifindex; + goto unlock; + } ret = -EBADFD; if (!tun) @@ -1863,6 +1881,11 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, case TUNGETIFF: tun_get_iff(current->nsproxy->net_ns, tun, &ifr); + if (tfile->detached) + ifr.ifr_flags |= IFF_DETACH_QUEUE; + if (!tfile->socket.sk->sk_filter) + ifr.ifr_flags |= IFF_NOFILTER; + if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; break; @@ -2019,6 +2042,16 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, tun_detach_filter(tun, tun->numqueues); break; + case TUNGETFILTER: + ret = -EINVAL; + if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV) + break; + ret = -EFAULT; + if (copy_to_user(argp, &tun->fprog, sizeof(tun->fprog))) + break; + ret = 0; + break; + default: ret = -EINVAL; break; @@ -2099,6 +2132,7 @@ static int tun_chr_open(struct inode *inode, struct file * file) rcu_assign_pointer(tfile->tun, NULL); tfile->net = get_net(current->nsproxy->net_ns); tfile->flags = 0; + tfile->ifindex = 0; rcu_assign_pointer(tfile->socket.wq, &tfile->wq); init_waitqueue_head(&tfile->wq.wait); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index b9401b53b69..3b21aca0c0c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -542,12 +542,6 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, return 0; } -static void vxlan_fdb_free_rdst(struct rcu_head *head) -{ - struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); - kfree(rd); -} - static void vxlan_fdb_free(struct rcu_head *head) { struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu); @@ -687,7 +681,7 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], */ if (rd && !list_is_singular(&f->remotes)) { list_del_rcu(&rd->list); - call_rcu(&rd->rcu, vxlan_fdb_free_rdst); + kfree_rcu(rd, rcu); goto out; } diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index e58cf0001ce..448efe01f18 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -13,7 +13,7 @@ #include <linux/eventfd.h> #include <linux/vhost.h> -#include <linux/socket.h> /* memcpy_fromiovec */ +#include <linux/uio.h> #include <linux/mm.h> #include <linux/mmu_context.h> #include <linux/miscdevice.h> diff --git a/include/linux/can/platform/mcp251x.h b/include/linux/can/platform/mcp251x.h index 089fe43211a..dc029dba7a0 100644 --- a/include/linux/can/platform/mcp251x.h +++ b/include/linux/can/platform/mcp251x.h @@ -9,26 +9,13 @@ #include <linux/spi/spi.h> -/** +/* * struct mcp251x_platform_data - MCP251X SPI CAN controller platform data * @oscillator_frequency: - oscillator frequency in Hz - * @irq_flags: - IRQF configuration flags - * @board_specific_setup: - called before probing the chip (power,reset) - * @transceiver_enable: - called to power on/off the transceiver - * @power_enable: - called to power on/off the mcp *and* the - * transceiver - * - * Please note that you should define power_enable or transceiver_enable or - * none of them. Defining both of them is no use. - * */ struct mcp251x_platform_data { unsigned long oscillator_frequency; - unsigned long irq_flags; - int (*board_specific_setup)(struct spi_device *spi); - int (*transceiver_enable)(int enable); - int (*power_enable) (int enable); }; #endif /* __CAN_PLATFORM_MCP251X_H__ */ diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h index 343d82a5446..efb05961bdd 100644 --- a/include/linux/fs_enet_pd.h +++ b/include/linux/fs_enet_pd.h @@ -16,6 +16,7 @@ #ifndef FS_ENET_PD_H #define FS_ENET_PD_H +#include <linux/clk.h> #include <linux/string.h> #include <linux/of_mdio.h> #include <linux/if_ether.h> @@ -143,6 +144,8 @@ struct fs_platform_info { int use_rmii; /* use RMII mode */ int has_phy; /* if the network is phy container as well...*/ + + struct clk *clk_per; /* 'per' clock for register access */ }; struct fs_mii_fec_platform_info { u32 irq[32]; diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index de70f7b45b6..e2cf786be22 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -314,8 +314,8 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #endif /*CONFIG_NETFILTER*/ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu; -extern void nf_ct_attach(struct sk_buff *, struct sk_buff *); +extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; +extern void nf_ct_attach(struct sk_buff *, const struct sk_buff *); extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; struct nf_conn; @@ -325,12 +325,14 @@ struct nfq_ct_hook { size_t (*build_size)(const struct nf_conn *ct); int (*build)(struct sk_buff *skb, struct nf_conn *ct); int (*parse)(const struct nlattr *attr, struct nf_conn *ct); + int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct, + u32 portid, u32 report); }; extern struct nfq_ct_hook __rcu *nfq_ct_hook; struct nfq_ct_nat_hook { void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, - u32 ctinfo, int off); + u32 ctinfo, s32 off); }; extern struct nfq_ct_nat_hook __rcu *nfq_ct_nat_hook; #else diff --git a/include/linux/sh_eth.h b/include/linux/sh_eth.h index 6205eeba392..90b5e30c2f2 100644 --- a/include/linux/sh_eth.h +++ b/include/linux/sh_eth.h @@ -5,17 +5,10 @@ #include <linux/if_ether.h> enum {EDMAC_LITTLE_ENDIAN, EDMAC_BIG_ENDIAN}; -enum { - SH_ETH_REG_GIGABIT, - SH_ETH_REG_FAST_RCAR, - SH_ETH_REG_FAST_SH4, - SH_ETH_REG_FAST_SH3_SH2 -}; struct sh_eth_plat_data { int phy; int edmac_endian; - int register_type; phy_interface_t phy_interface; void (*set_mdio_gate)(void *addr); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 644d9c223d2..0c1288a50e8 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -181,8 +181,7 @@ __nf_conntrack_find(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple); extern int nf_conntrack_hash_check_insert(struct nf_conn *ct); -extern void nf_ct_delete_from_lists(struct nf_conn *ct); -extern void nf_ct_dying_timeout(struct nf_conn *ct); +bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report); extern void nf_conntrack_flush_report(struct net *net, u32 portid, int report); @@ -235,7 +234,7 @@ static inline bool nf_ct_kill(struct nf_conn *ct) } /* These are for NAT. Icky. */ -extern s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, +extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq); @@ -249,7 +248,9 @@ extern void nf_ct_untracked_status_or(unsigned long bits); /* Iterate over all conntracks: if iter returns true, it's deleted. */ extern void -nf_ct_iterate_cleanup(struct net *net, int (*iter)(struct nf_conn *i, void *data), void *data); +nf_ct_iterate_cleanup(struct net *net, + int (*iter)(struct nf_conn *i, void *data), + void *data, u32 portid, int report); extern void nf_conntrack_free(struct nf_conn *ct); extern struct nf_conn * nf_conntrack_alloc(struct net *net, u16 zone, diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 914d8d90079..b411d7b17de 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -148,17 +148,10 @@ extern int nf_ct_port_nlattr_tuple_size(void); extern const struct nla_policy nf_ct_port_nla_policy[]; #ifdef CONFIG_SYSCTL -#ifdef DEBUG_INVALID_PACKETS #define LOG_INVALID(net, proto) \ ((net)->ct.sysctl_log_invalid == (proto) || \ (net)->ct.sysctl_log_invalid == IPPROTO_RAW) #else -#define LOG_INVALID(net, proto) \ - (((net)->ct.sysctl_log_invalid == (proto) || \ - (net)->ct.sysctl_log_invalid == IPPROTO_RAW) \ - && net_ratelimit()) -#endif -#else static inline int LOG_INVALID(struct net *net, int proto) { return 0; } #endif /* CONFIG_SYSCTL */ diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index ad14a799fd2..e2441413675 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -19,7 +19,7 @@ struct nf_nat_seq { u_int32_t correction_pos; /* sequence number offset before and after last modification */ - int16_t offset_before, offset_after; + int32_t offset_before, offset_after; }; #include <linux/list.h> diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h index b4d6bfc2af0..194c3479492 100644 --- a/include/net/netfilter/nf_nat_helper.h +++ b/include/net/netfilter/nf_nat_helper.h @@ -41,7 +41,7 @@ extern int nf_nat_mangle_udp_packet(struct sk_buff *skb, extern void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, - __be32 seq, s16 off); + __be32 seq, s32 off); extern int nf_nat_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, @@ -56,11 +56,11 @@ extern int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb, extern void nf_nat_follow_master(struct nf_conn *ct, struct nf_conntrack_expect *this); -extern s16 nf_nat_get_offset(const struct nf_conn *ct, +extern s32 nf_nat_get_offset(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq); extern void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, - u32 dir, int off); + u32 dir, s32 off); #endif diff --git a/include/net/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h deleted file mode 100644 index 36d9379d4c4..00000000000 --- a/include/net/netfilter/nf_tproxy_core.h +++ /dev/null @@ -1,210 +0,0 @@ -#ifndef _NF_TPROXY_CORE_H -#define _NF_TPROXY_CORE_H - -#include <linux/types.h> -#include <linux/in.h> -#include <linux/skbuff.h> -#include <net/sock.h> -#include <net/inet_hashtables.h> -#include <net/inet6_hashtables.h> -#include <net/tcp.h> - -#define NFT_LOOKUP_ANY 0 -#define NFT_LOOKUP_LISTENER 1 -#define NFT_LOOKUP_ESTABLISHED 2 - -/* look up and get a reference to a matching socket */ - - -/* This function is used by the 'TPROXY' target and the 'socket' - * match. The following lookups are supported: - * - * Explicit TProxy target rule - * =========================== - * - * This is used when the user wants to intercept a connection matching - * an explicit iptables rule. In this case the sockets are assumed - * matching in preference order: - * - * - match: if there's a fully established connection matching the - * _packet_ tuple, it is returned, assuming the redirection - * already took place and we process a packet belonging to an - * established connection - * - * - match: if there's a listening socket matching the redirection - * (e.g. on-port & on-ip of the connection), it is returned, - * regardless if it was bound to 0.0.0.0 or an explicit - * address. The reasoning is that if there's an explicit rule, it - * does not really matter if the listener is bound to an interface - * or to 0. The user already stated that he wants redirection - * (since he added the rule). - * - * "socket" match based redirection (no specific rule) - * =================================================== - * - * There are connections with dynamic endpoints (e.g. FTP data - * connection) that the user is unable to add explicit rules - * for. These are taken care of by a generic "socket" rule. It is - * assumed that the proxy application is trusted to open such - * connections without explicit iptables rule (except of course the - * generic 'socket' rule). In this case the following sockets are - * matched in preference order: - * - * - match: if there's a fully established connection matching the - * _packet_ tuple - * - * - match: if there's a non-zero bound listener (possibly with a - * non-local address) We don't accept zero-bound listeners, since - * then local services could intercept traffic going through the - * box. - * - * Please note that there's an overlap between what a TPROXY target - * and a socket match will match. Normally if you have both rules the - * "socket" match will be the first one, effectively all packets - * belonging to established connections going through that one. - */ -static inline struct sock * -nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, - const __be32 saddr, const __be32 daddr, - const __be16 sport, const __be16 dport, - const struct net_device *in, int lookup_type) -{ - struct sock *sk; - - /* look up socket */ - switch (protocol) { - case IPPROTO_TCP: - switch (lookup_type) { - case NFT_LOOKUP_ANY: - sk = __inet_lookup(net, &tcp_hashinfo, - saddr, sport, daddr, dport, - in->ifindex); - break; - case NFT_LOOKUP_LISTENER: - sk = inet_lookup_listener(net, &tcp_hashinfo, - saddr, sport, - daddr, dport, - in->ifindex); - - /* NOTE: we return listeners even if bound to - * 0.0.0.0, those are filtered out in - * xt_socket, since xt_TPROXY needs 0 bound - * listeners too */ - - break; - case NFT_LOOKUP_ESTABLISHED: - sk = inet_lookup_established(net, &tcp_hashinfo, - saddr, sport, daddr, dport, - in->ifindex); - break; - default: - WARN_ON(1); - sk = NULL; - break; - } - break; - case IPPROTO_UDP: - sk = udp4_lib_lookup(net, saddr, sport, daddr, dport, - in->ifindex); - if (sk && lookup_type != NFT_LOOKUP_ANY) { - int connected = (sk->sk_state == TCP_ESTABLISHED); - int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0); - - /* NOTE: we return listeners even if bound to - * 0.0.0.0, those are filtered out in - * xt_socket, since xt_TPROXY needs 0 bound - * listeners too */ - if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) || - (lookup_type == NFT_LOOKUP_LISTENER && connected)) { - sock_put(sk); - sk = NULL; - } - } - break; - default: - WARN_ON(1); - sk = NULL; - } - - pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n", - protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk); - - return sk; -} - -#if IS_ENABLED(CONFIG_IPV6) -static inline struct sock * -nf_tproxy_get_sock_v6(struct net *net, const u8 protocol, - const struct in6_addr *saddr, const struct in6_addr *daddr, - const __be16 sport, const __be16 dport, - const struct net_device *in, int lookup_type) -{ - struct sock *sk; - - /* look up socket */ - switch (protocol) { - case IPPROTO_TCP: - switch (lookup_type) { - case NFT_LOOKUP_ANY: - sk = inet6_lookup(net, &tcp_hashinfo, - saddr, sport, daddr, dport, - in->ifindex); - break; - case NFT_LOOKUP_LISTENER: - sk = inet6_lookup_listener(net, &tcp_hashinfo, - saddr, sport, - daddr, ntohs(dport), - in->ifindex); - - /* NOTE: we return listeners even if bound to - * 0.0.0.0, those are filtered out in - * xt_socket, since xt_TPROXY needs 0 bound - * listeners too */ - - break; - case NFT_LOOKUP_ESTABLISHED: - sk = __inet6_lookup_established(net, &tcp_hashinfo, - saddr, sport, daddr, ntohs(dport), - in->ifindex); - break; - default: - WARN_ON(1); - sk = NULL; - break; - } - break; - case IPPROTO_UDP: - sk = udp6_lib_lookup(net, saddr, sport, daddr, dport, - in->ifindex); - if (sk && lookup_type != NFT_LOOKUP_ANY) { - int connected = (sk->sk_state == TCP_ESTABLISHED); - int wildcard = ipv6_addr_any(&inet6_sk(sk)->rcv_saddr); - - /* NOTE: we return listeners even if bound to - * 0.0.0.0, those are filtered out in - * xt_socket, since xt_TPROXY needs 0 bound - * listeners too */ - if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) || - (lookup_type == NFT_LOOKUP_LISTENER && connected)) { - sock_put(sk); - sk = NULL; - } - } - break; - default: - WARN_ON(1); - sk = NULL; - } - - pr_debug("tproxy socket lookup: proto %u %pI6:%u -> %pI6:%u, lookup type: %d, sock %p\n", - protocol, saddr, ntohs(sport), daddr, ntohs(dport), lookup_type, sk); - - return sk; -} -#endif - -/* assign a socket to the skb -- consumes sk */ -void -nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk); - -#endif diff --git a/include/net/netfilter/nfnetlink_queue.h b/include/net/netfilter/nfnetlink_queue.h index 86267a52951..aff88ba9139 100644 --- a/include/net/netfilter/nfnetlink_queue.h +++ b/include/net/netfilter/nfnetlink_queue.h @@ -15,6 +15,8 @@ int nfqnl_ct_put(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo); void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, int diff); +int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr, + u32 portid, u32 report); #else inline struct nf_conn * nfqnl_ct_get(struct sk_buff *entskb, size_t *size, enum ip_conntrack_info *ctinfo) @@ -39,5 +41,11 @@ inline void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, int diff) { } + +inline int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr, + u32 portid, u32 report) +{ + return 0; +} #endif /* NF_CONNTRACK */ #endif diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 94ce082b29d..89d3d8ae204 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1548,7 +1548,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8, int dir, u32 int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info); u32 xfrm_get_acqseq(void); extern int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi); -struct xfrm_state *xfrm_find_acq(struct net *net, struct xfrm_mark *mark, +struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index 1870ee29bb3..e9502dd1ee2 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -56,6 +56,8 @@ #define TUNGETVNETHDRSZ _IOR('T', 215, int) #define TUNSETVNETHDRSZ _IOW('T', 216, int) #define TUNSETQUEUE _IOW('T', 217, int) +#define TUNSETIFINDEX _IOW('T', 218, unsigned int) +#define TUNGETFILTER _IOR('T', 219, struct sock_fprog) /* TUNSETIFF ifr flags */ #define IFF_TUN 0x0001 @@ -70,6 +72,7 @@ #define IFF_DETACH_QUEUE 0x0400 /* read-only flag */ #define IFF_PERSIST 0x0800 +#define IFF_NOFILTER 0x1000 /* Socket options */ #define TUN_TX_TIMESTAMP 1 diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild index 41115776d76..174915420d3 100644 --- a/include/uapi/linux/netfilter/Kbuild +++ b/include/uapi/linux/netfilter/Kbuild @@ -22,6 +22,7 @@ header-y += xt_CONNMARK.h header-y += xt_CONNSECMARK.h header-y += xt_CT.h header-y += xt_DSCP.h +header-y += xt_HMARK.h header-y += xt_IDLETIMER.h header-y += xt_LED.h header-y += xt_LOG.h @@ -68,6 +69,7 @@ header-y += xt_quota.h header-y += xt_rateest.h header-y += xt_realm.h header-y += xt_recent.h +header-y += xt_rpfilter.h header-y += xt_sctp.h header-y += xt_set.h header-y += xt_socket.h diff --git a/include/uapi/linux/netfilter/nfnetlink_queue.h b/include/uapi/linux/netfilter/nfnetlink_queue.h index 3a9b9214733..0132bad79de 100644 --- a/include/uapi/linux/netfilter/nfnetlink_queue.h +++ b/include/uapi/linux/netfilter/nfnetlink_queue.h @@ -46,6 +46,7 @@ enum nfqnl_attr_type { NFQA_CT_INFO, /* enum ip_conntrack_info */ NFQA_CAP_LEN, /* __u32 length of captured packet */ NFQA_SKB_INFO, /* __u32 skb meta information */ + NFQA_EXP, /* nf_conntrack_netlink.h */ __NFQA_MAX }; diff --git a/include/linux/netfilter/xt_HMARK.h b/include/uapi/linux/netfilter/xt_HMARK.h index 826fc580757..826fc580757 100644 --- a/include/linux/netfilter/xt_HMARK.h +++ b/include/uapi/linux/netfilter/xt_HMARK.h diff --git a/include/linux/netfilter/xt_rpfilter.h b/include/uapi/linux/netfilter/xt_rpfilter.h index 8358d4f7195..8358d4f7195 100644 --- a/include/linux/netfilter/xt_rpfilter.h +++ b/include/uapi/linux/netfilter/xt_rpfilter.h diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index 3b9d5f20bd1..c85e71e0c7f 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -67,39 +67,6 @@ static const u8 lowpan_ttl_values[] = {0, 1, 64, 255}; static LIST_HEAD(lowpan_devices); -/* - * Uncompression of linklocal: - * 0 -> 16 bytes from packet - * 1 -> 2 bytes from prefix - bunch of zeroes and 8 from packet - * 2 -> 2 bytes from prefix - zeroes + 2 from packet - * 3 -> 2 bytes from prefix - infer 8 bytes from lladdr - * - * NOTE: => the uncompress function does change 0xf to 0x10 - * NOTE: 0x00 => no-autoconfig => unspecified - */ -static const u8 lowpan_unc_llconf[] = {0x0f, 0x28, 0x22, 0x20}; - -/* - * Uncompression of ctx-based: - * 0 -> 0 bits from packet [unspecified / reserved] - * 1 -> 8 bytes from prefix - bunch of zeroes and 8 from packet - * 2 -> 8 bytes from prefix - zeroes + 2 from packet - * 3 -> 8 bytes from prefix - infer 8 bytes from lladdr - */ -static const u8 lowpan_unc_ctxconf[] = {0x00, 0x88, 0x82, 0x80}; - -/* - * Uncompression of ctx-base - * 0 -> 0 bits from packet - * 1 -> 2 bytes from prefix - bunch of zeroes 5 from packet - * 2 -> 2 bytes from prefix - zeroes + 3 from packet - * 3 -> 2 bytes from prefix - infer 1 bytes from lladdr - */ -static const u8 lowpan_unc_mxconf[] = {0x0f, 0x25, 0x23, 0x21}; - -/* Link local prefix */ -static const u8 lowpan_llprefix[] = {0xfe, 0x80}; - /* private device info */ struct lowpan_dev_info { struct net_device *real_dev; /* real WPAN device ptr */ @@ -191,55 +158,177 @@ lowpan_compress_addr_64(u8 **hc06_ptr, u8 shift, const struct in6_addr *ipaddr, return rol8(val, shift); } -static void -lowpan_uip_ds6_set_addr_iid(struct in6_addr *ipaddr, unsigned char *lladdr) +/* + * Uncompress address function for source and + * destination address(non-multicast). + * + * address_mode is sam value or dam value. + */ +static int +lowpan_uncompress_addr(struct sk_buff *skb, + struct in6_addr *ipaddr, + const u8 address_mode, + const struct ieee802154_addr *lladdr) { - memcpy(&ipaddr->s6_addr[8], lladdr, IEEE802154_ADDR_LEN); - /* second bit-flip (Universe/Local) is done according RFC2464 */ - ipaddr->s6_addr[8] ^= 0x02; + bool fail; + + switch (address_mode) { + case LOWPAN_IPHC_ADDR_00: + /* for global link addresses */ + fail = lowpan_fetch_skb(skb, ipaddr->s6_addr, 16); + break; + case LOWPAN_IPHC_ADDR_01: + /* fe:80::XXXX:XXXX:XXXX:XXXX */ + ipaddr->s6_addr[0] = 0xFE; + ipaddr->s6_addr[1] = 0x80; + fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[8], 8); + break; + case LOWPAN_IPHC_ADDR_02: + /* fe:80::ff:fe00:XXXX */ + ipaddr->s6_addr[0] = 0xFE; + ipaddr->s6_addr[1] = 0x80; + ipaddr->s6_addr[11] = 0xFF; + ipaddr->s6_addr[12] = 0xFE; + fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[14], 2); + break; + case LOWPAN_IPHC_ADDR_03: + fail = false; + switch (lladdr->addr_type) { + case IEEE802154_ADDR_LONG: + /* fe:80::XXXX:XXXX:XXXX:XXXX + * \_________________/ + * hwaddr + */ + ipaddr->s6_addr[0] = 0xFE; + ipaddr->s6_addr[1] = 0x80; + memcpy(&ipaddr->s6_addr[8], lladdr->hwaddr, + IEEE802154_ADDR_LEN); + /* second bit-flip (Universe/Local) + * is done according RFC2464 + */ + ipaddr->s6_addr[8] ^= 0x02; + break; + case IEEE802154_ADDR_SHORT: + /* fe:80::ff:fe00:XXXX + * \__/ + * short_addr + * + * Universe/Local bit is zero. + */ + ipaddr->s6_addr[0] = 0xFE; + ipaddr->s6_addr[1] = 0x80; + ipaddr->s6_addr[11] = 0xFF; + ipaddr->s6_addr[12] = 0xFE; + ipaddr->s6_addr16[7] = htons(lladdr->short_addr); + break; + default: + pr_debug("Invalid addr_type set\n"); + return -EINVAL; + } + break; + default: + pr_debug("Invalid address mode value: 0x%x\n", address_mode); + return -EINVAL; + } + + if (fail) { + pr_debug("Failed to fetch skb data\n"); + return -EIO; + } + + lowpan_raw_dump_inline(NULL, "Reconstructed ipv6 addr is:\n", + ipaddr->s6_addr, 16); + + return 0; } -/* - * Uncompress addresses based on a prefix and a postfix with zeroes in - * between. If the postfix is zero in length it will use the link address - * to configure the IP address (autoconf style). - * pref_post_count takes a byte where the first nibble specify prefix count - * and the second postfix count (NOTE: 15/0xf => 16 bytes copy). +/* Uncompress address function for source context + * based address(non-multicast). */ static int -lowpan_uncompress_addr(struct sk_buff *skb, struct in6_addr *ipaddr, - u8 const *prefix, u8 pref_post_count, unsigned char *lladdr) +lowpan_uncompress_context_based_src_addr(struct sk_buff *skb, + struct in6_addr *ipaddr, + const u8 sam) { - u8 prefcount = pref_post_count >> 4; - u8 postcount = pref_post_count & 0x0f; - - /* full nibble 15 => 16 */ - prefcount = (prefcount == 15 ? 16 : prefcount); - postcount = (postcount == 15 ? 16 : postcount); - - if (lladdr) - lowpan_raw_dump_inline(__func__, "linklocal address", - lladdr, IEEE802154_ADDR_LEN); - if (prefcount > 0) - memcpy(ipaddr, prefix, prefcount); - - if (prefcount + postcount < 16) - memset(&ipaddr->s6_addr[prefcount], 0, - 16 - (prefcount + postcount)); - - if (postcount > 0) { - memcpy(&ipaddr->s6_addr[16 - postcount], skb->data, postcount); - skb_pull(skb, postcount); - } else if (prefcount > 0) { - if (lladdr == NULL) - return -EINVAL; + switch (sam) { + case LOWPAN_IPHC_ADDR_00: + /* unspec address :: + * Do nothing, address is already :: + */ + break; + case LOWPAN_IPHC_ADDR_01: + /* TODO */ + case LOWPAN_IPHC_ADDR_02: + /* TODO */ + case LOWPAN_IPHC_ADDR_03: + /* TODO */ + netdev_warn(skb->dev, "SAM value 0x%x not supported\n", sam); + return -EINVAL; + default: + pr_debug("Invalid sam value: 0x%x\n", sam); + return -EINVAL; + } + + lowpan_raw_dump_inline(NULL, + "Reconstructed context based ipv6 src addr is:\n", + ipaddr->s6_addr, 16); + + return 0; +} - /* no IID based configuration if no prefix and no data */ - lowpan_uip_ds6_set_addr_iid(ipaddr, lladdr); +/* Uncompress function for multicast destination address, + * when M bit is set. + */ +static int +lowpan_uncompress_multicast_daddr(struct sk_buff *skb, + struct in6_addr *ipaddr, + const u8 dam) +{ + bool fail; + + switch (dam) { + case LOWPAN_IPHC_DAM_00: + /* 00: 128 bits. The full address + * is carried in-line. + */ + fail = lowpan_fetch_skb(skb, ipaddr->s6_addr, 16); + break; + case LOWPAN_IPHC_DAM_01: + /* 01: 48 bits. The address takes + * the form ffXX::00XX:XXXX:XXXX. + */ + ipaddr->s6_addr[0] = 0xFF; + fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[1], 1); + fail |= lowpan_fetch_skb(skb, &ipaddr->s6_addr[11], 5); + break; + case LOWPAN_IPHC_DAM_10: + /* 10: 32 bits. The address takes + * the form ffXX::00XX:XXXX. + */ + ipaddr->s6_addr[0] = 0xFF; + fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[1], 1); + fail |= lowpan_fetch_skb(skb, &ipaddr->s6_addr[13], 3); + break; + case LOWPAN_IPHC_DAM_11: + /* 11: 8 bits. The address takes + * the form ff02::00XX. + */ + ipaddr->s6_addr[0] = 0xFF; + ipaddr->s6_addr[1] = 0x02; + fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[15], 1); + break; + default: + pr_debug("DAM value has a wrong value: 0x%x\n", dam); + return -EINVAL; + } + + if (fail) { + pr_debug("Failed to fetch skb data\n"); + return -EIO; } - pr_debug("uncompressing %d + %d => ", prefcount, postcount); - lowpan_raw_dump_inline(NULL, NULL, ipaddr->s6_addr, 16); + lowpan_raw_dump_inline(NULL, "Reconstructed ipv6 multicast addr is:\n", + ipaddr->s6_addr, 16); return 0; } @@ -702,6 +791,12 @@ lowpan_alloc_new_frame(struct sk_buff *skb, u16 len, u16 tag) skb_reserve(frame->skb, sizeof(struct ipv6hdr)); skb_put(frame->skb, frame->length); + /* copy the first control block to keep a + * trace of the link-layer addresses in case + * of a link-local compressed address + */ + memcpy(frame->skb->cb, skb->cb, sizeof(skb->cb)); + init_timer(&frame->timer); /* time out is the same as for ipv6 - 60 sec */ frame->timer.expires = jiffies + LOWPAN_FRAG_TIMEOUT; @@ -723,9 +818,9 @@ frame_err: static int lowpan_process_data(struct sk_buff *skb) { - struct ipv6hdr hdr; + struct ipv6hdr hdr = {}; u8 tmp, iphc0, iphc1, num_context = 0; - u8 *_saddr, *_daddr; + const struct ieee802154_addr *_saddr, *_daddr; int err; lowpan_raw_dump_table(__func__, "raw skb data dump", skb->data, @@ -828,8 +923,8 @@ lowpan_process_data(struct sk_buff *skb) if (lowpan_fetch_skb_u8(skb, &iphc1)) goto drop; - _saddr = mac_cb(skb)->sa.hwaddr; - _daddr = mac_cb(skb)->da.hwaddr; + _saddr = &mac_cb(skb)->sa; + _daddr = &mac_cb(skb)->da; pr_debug("iphc0 = %02x, iphc1 = %02x\n", iphc0, iphc1); @@ -868,8 +963,6 @@ lowpan_process_data(struct sk_buff *skb) hdr.priority = ((tmp >> 2) & 0x0f); hdr.flow_lbl[0] = ((tmp << 6) & 0xC0) | ((tmp >> 2) & 0x30); - hdr.flow_lbl[1] = 0; - hdr.flow_lbl[2] = 0; break; /* * Flow Label carried in-line @@ -885,10 +978,6 @@ lowpan_process_data(struct sk_buff *skb) break; /* Traffic Class and Flow Label are elided */ case 3: /* 11b */ - hdr.priority = 0; - hdr.flow_lbl[0] = 0; - hdr.flow_lbl[1] = 0; - hdr.flow_lbl[2] = 0; break; default: break; @@ -915,10 +1004,18 @@ lowpan_process_data(struct sk_buff *skb) /* Extract SAM to the tmp variable */ tmp = ((iphc1 & LOWPAN_IPHC_SAM) >> LOWPAN_IPHC_SAM_BIT) & 0x03; - /* Source address uncompression */ - pr_debug("source address stateless compression\n"); - err = lowpan_uncompress_addr(skb, &hdr.saddr, lowpan_llprefix, - lowpan_unc_llconf[tmp], skb->data); + if (iphc1 & LOWPAN_IPHC_SAC) { + /* Source address context based uncompression */ + pr_debug("SAC bit is set. Handle context based source address.\n"); + err = lowpan_uncompress_context_based_src_addr( + skb, &hdr.saddr, tmp); + } else { + /* Source address uncompression */ + pr_debug("source address stateless compression\n"); + err = lowpan_uncompress_addr(skb, &hdr.saddr, tmp, _saddr); + } + + /* Check on error of previous branch */ if (err) goto drop; @@ -931,23 +1028,14 @@ lowpan_process_data(struct sk_buff *skb) pr_debug("dest: context-based mcast compression\n"); /* TODO: implement this */ } else { - u8 prefix[] = {0xff, 0x02}; - - pr_debug("dest: non context-based mcast compression\n"); - if (0 < tmp && tmp < 3) { - if (lowpan_fetch_skb_u8(skb, &prefix[1])) - goto drop; - } - - err = lowpan_uncompress_addr(skb, &hdr.daddr, prefix, - lowpan_unc_mxconf[tmp], NULL); + err = lowpan_uncompress_multicast_daddr( + skb, &hdr.daddr, tmp); if (err) goto drop; } } else { pr_debug("dest: stateless compression\n"); - err = lowpan_uncompress_addr(skb, &hdr.daddr, lowpan_llprefix, - lowpan_unc_llconf[tmp], skb->data); + err = lowpan_uncompress_addr(skb, &hdr.daddr, tmp, _daddr); if (err) goto drop; } diff --git a/net/ieee802154/6lowpan.h b/net/ieee802154/6lowpan.h index 4b8f917658b..2869c0526da 100644 --- a/net/ieee802154/6lowpan.h +++ b/net/ieee802154/6lowpan.h @@ -193,10 +193,12 @@ /* Values of fields within the IPHC encoding second byte */ #define LOWPAN_IPHC_CID 0x80 +#define LOWPAN_IPHC_ADDR_00 0x00 +#define LOWPAN_IPHC_ADDR_01 0x01 +#define LOWPAN_IPHC_ADDR_02 0x02 +#define LOWPAN_IPHC_ADDR_03 0x03 + #define LOWPAN_IPHC_SAC 0x40 -#define LOWPAN_IPHC_SAM_00 0x00 -#define LOWPAN_IPHC_SAM_01 0x10 -#define LOWPAN_IPHC_SAM_10 0x20 #define LOWPAN_IPHC_SAM 0x30 #define LOWPAN_IPHC_SAM_BIT 4 @@ -230,4 +232,16 @@ dest = 16 bit inline */ #define LOWPAN_NHC_UDP_CS_P_11 0xF3 /* source & dest = 0xF0B + 4bit inline */ +static inline bool lowpan_fetch_skb(struct sk_buff *skb, + void *data, const unsigned int len) +{ + if (unlikely(!pskb_may_pull(skb, len))) + return true; + + skb_copy_from_linear_data(skb, data, len); + skb_pull(skb, len); + + return false; +} + #endif /* __6LOWPAN_H__ */ diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index a4d9126c7b5..24549b4aeae 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -854,14 +854,14 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, rtnl_lock(); itn->fb_tunnel_dev = __ip_tunnel_create(net, ops, &parms); - /* FB netdevice is special: we have one, and only one per netns. - * Allowing to move it to another netns is clearly unsafe. - */ - itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; rtnl_unlock(); if (IS_ERR(itn->fb_tunnel_dev)) return PTR_ERR(itn->fb_tunnel_dev); + /* FB netdevice is special: we have one, and only one per netns. + * Allowing to move it to another netns is clearly unsafe. + */ + itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; return 0; } diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index 30e4de94056..00352ce0f0d 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -118,7 +118,7 @@ static int masq_device_event(struct notifier_block *this, NF_CT_ASSERT(dev->ifindex != 0); nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex); + (void *)(long)dev->ifindex, 0, 0); } return NOTIFY_DONE; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e805481eff7..727f4365bcd 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -112,7 +112,8 @@ #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) -#define IP_MAX_MTU 0xFFF0 +/* IPv4 datagram length is stored into 16bit field (tot_len) */ +#define IP_MAX_MTU 0xFFFF #define RT_GC_TIMEOUT (300*HZ) @@ -1227,10 +1228,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = 576; } - if (mtu > IP_MAX_MTU) - mtu = IP_MAX_MTU; - - return mtu; + return min_t(unsigned int, mtu, IP_MAX_MTU); } static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e965cc7b87f..ec492eae0cd 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2485,8 +2485,6 @@ static void tcp_try_to_open(struct sock *sk, int flag, const int prior_unsacked) if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) { tcp_try_keep_open(sk); - if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open) - tcp_moderate_cwnd(tp); } else { tcp_cwnd_reduction(sk, prior_unsacked, 0); } @@ -3128,11 +3126,24 @@ static inline bool tcp_ack_is_dubious(const struct sock *sk, const int flag) inet_csk(sk)->icsk_ca_state != TCP_CA_Open; } +/* Decide wheather to run the increase function of congestion control. */ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) { - const struct tcp_sock *tp = tcp_sk(sk); - return (!(flag & FLAG_ECE) || tp->snd_cwnd < tp->snd_ssthresh) && - !tcp_in_cwnd_reduction(sk); + if (tcp_in_cwnd_reduction(sk)) + return false; + + /* If reordering is high then always grow cwnd whenever data is + * delivered regardless of its ordering. Otherwise stay conservative + * and only grow cwnd on in-order delivery in Open state, and retain + * cwnd in Disordered state (RFC5681). A stretched ACK with + * new SACK or ECE mark may first advance cwnd here and later reduce + * cwnd in tcp_fastretrans_alert() based on more states. + */ + if (tcp_sk(sk)->reordering > sysctl_tcp_reordering) + return flag & FLAG_FORWARD_PROGRESS; + + return inet_csk(sk)->icsk_ca_state == TCP_CA_Open && + flag & FLAG_DATA_ACKED; } /* Check that window update is acceptable. @@ -3352,18 +3363,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, sack_rtt); acked -= tp->packets_out; + /* Advance cwnd if state allows */ + if (tcp_may_raise_cwnd(sk, flag)) + tcp_cong_avoid(sk, ack, prior_in_flight); + if (tcp_ack_is_dubious(sk, flag)) { - /* Advance CWND, if state allows this. */ - if ((flag & FLAG_DATA_ACKED) && tcp_may_raise_cwnd(sk, flag)) - tcp_cong_avoid(sk, ack, prior_in_flight); is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); tcp_fastretrans_alert(sk, acked, prior_unsacked, is_dupack, flag); - } else { - if (flag & FLAG_DATA_ACKED) - tcp_cong_avoid(sk, ack, prior_in_flight); } - if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 05a3d45d310..09d45d71897 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -821,8 +821,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, */ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, - u16 queue_mapping, - bool nocache) + u16 queue_mapping) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; @@ -852,7 +851,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req) { - int res = tcp_v4_send_synack(sk, NULL, req, 0, false); + int res = tcp_v4_send_synack(sk, NULL, req, 0); if (!res) TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index d4943f67aff..301a3effe57 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -54,12 +54,16 @@ static const char procname[] = "tcpprobe"; struct tcp_log { ktime_t tstamp; - __be32 saddr, daddr; - __be16 sport, dport; + union { + struct sockaddr raw; + struct sockaddr_in v4; + struct sockaddr_in6 v6; + } src, dst; u16 length; u32 snd_nxt; u32 snd_una; u32 snd_wnd; + u32 rcv_wnd; u32 snd_cwnd; u32 ssthresh; u32 srtt; @@ -86,12 +90,36 @@ static inline int tcp_probe_avail(void) return bufsize - tcp_probe_used() - 1; } +#define tcp_probe_copy_fl_to_si4(inet, si4, mem) \ + do { \ + si4.sin_family = AF_INET; \ + si4.sin_port = inet->inet_##mem##port; \ + si4.sin_addr.s_addr = inet->inet_##mem##addr; \ + } while (0) \ + +#if IS_ENABLED(CONFIG_IPV6) +#define tcp_probe_copy_fl_to_si6(inet, si6, mem) \ + do { \ + struct ipv6_pinfo *pi6 = inet->pinet6; \ + si6.sin6_family = AF_INET6; \ + si6.sin6_port = inet->inet_##mem##port; \ + si6.sin6_addr = pi6->mem##addr; \ + si6.sin6_flowinfo = 0; /* No need here. */ \ + si6.sin6_scope_id = 0; /* No need here. */ \ + } while (0) +#else +#define tcp_probe_copy_fl_to_si6(fl, si6, mem) \ + do { \ + memset(&si6, 0, sizeof(si6)); \ + } while (0) +#endif + /* * Hook inserted to be called before each receive packet. * Note: arguments must match tcp_rcv_established()! */ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, - struct tcphdr *th, unsigned int len) + const struct tcphdr *th, unsigned int len) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_sock *inet = inet_sk(sk); @@ -107,15 +135,25 @@ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, struct tcp_log *p = tcp_probe.log + tcp_probe.head; p->tstamp = ktime_get(); - p->saddr = inet->inet_saddr; - p->sport = inet->inet_sport; - p->daddr = inet->inet_daddr; - p->dport = inet->inet_dport; + switch (sk->sk_family) { + case AF_INET: + tcp_probe_copy_fl_to_si4(inet, p->src.v4, s); + tcp_probe_copy_fl_to_si4(inet, p->dst.v4, d); + break; + case AF_INET6: + tcp_probe_copy_fl_to_si6(inet, p->src.v6, s); + tcp_probe_copy_fl_to_si6(inet, p->dst.v6, d); + break; + default: + BUG(); + } + p->length = skb->len; p->snd_nxt = tp->snd_nxt; p->snd_una = tp->snd_una; p->snd_cwnd = tp->snd_cwnd; p->snd_wnd = tp->snd_wnd; + p->rcv_wnd = tp->rcv_wnd; p->ssthresh = tcp_current_ssthresh(sk); p->srtt = tp->srtt >> 3; @@ -157,13 +195,11 @@ static int tcpprobe_sprint(char *tbuf, int n) = ktime_to_timespec(ktime_sub(p->tstamp, tcp_probe.start)); return scnprintf(tbuf, n, - "%lu.%09lu %pI4:%u %pI4:%u %d %#x %#x %u %u %u %u\n", + "%lu.%09lu %pISpc %pISpc %d %#x %#x %u %u %u %u %u\n", (unsigned long) tv.tv_sec, (unsigned long) tv.tv_nsec, - &p->saddr, ntohs(p->sport), - &p->daddr, ntohs(p->dport), - p->length, p->snd_nxt, p->snd_una, - p->snd_cwnd, p->ssthresh, p->snd_wnd, p->srtt); + &p->src, &p->dst, p->length, p->snd_nxt, p->snd_una, + p->snd_cwnd, p->ssthresh, p->snd_wnd, p->srtt, p->rcv_wnd); } static ssize_t tcpprobe_read(struct file *file, char __user *buf, @@ -223,6 +259,13 @@ static __init int tcpprobe_init(void) { int ret = -ENOMEM; + /* Warning: if the function signature of tcp_rcv_established, + * has been changed, you also have to change the signature of + * jtcp_rcv_established, otherwise you end up right here! + */ + BUILD_BUG_ON(__same_type(tcp_rcv_established, + jtcp_rcv_established) == 0); + init_waitqueue_head(&tcp_probe.wait); spin_lock_init(&tcp_probe.lock); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ad12f7c43f2..8549a5d0d16 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -99,9 +99,9 @@ #define ACONF_DEBUG 2 #if ACONF_DEBUG >= 3 -#define ADBG(x) printk x +#define ADBG(fmt, ...) printk(fmt, ##__VA_ARGS__) #else -#define ADBG(x) +#define ADBG(fmt, ...) do { if (0) printk(fmt, ##__VA_ARGS__); } while (0) #endif #define INFINITY_LIFE_TIME 0xFFFFFFFF @@ -374,9 +374,9 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) dev_hold(dev); if (snmp6_alloc_dev(ndev) < 0) { - ADBG((KERN_WARNING + ADBG(KERN_WARNING "%s: cannot allocate memory for statistics; dev=%s.\n", - __func__, dev->name)); + __func__, dev->name); neigh_parms_release(&nd_tbl, ndev->nd_parms); dev_put(dev); kfree(ndev); @@ -384,9 +384,9 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) } if (snmp6_register_dev(ndev) < 0) { - ADBG((KERN_WARNING + ADBG(KERN_WARNING "%s: cannot create /proc/net/dev_snmp6/%s\n", - __func__, dev->name)); + __func__, dev->name); neigh_parms_release(&nd_tbl, ndev->nd_parms); ndev->dead = 1; in6_dev_finish_destroy(ndev); @@ -849,7 +849,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, /* Ignore adding duplicate addresses on an interface */ if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) { - ADBG(("ipv6_add_addr: already assigned\n")); + ADBG("ipv6_add_addr: already assigned\n"); err = -EEXIST; goto out; } @@ -857,7 +857,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa = kzalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC); if (ifa == NULL) { - ADBG(("ipv6_add_addr: malloc failed\n")); + ADBG("ipv6_add_addr: malloc failed\n"); err = -ENOBUFS; goto out; } @@ -1814,6 +1814,16 @@ static int addrconf_ifid_gre(u8 *eui, struct net_device *dev) return __ipv6_isatap_ifid(eui, *(__be32 *)dev->dev_addr); } +static int addrconf_ifid_ip6tnl(u8 *eui, struct net_device *dev) +{ + memcpy(eui, dev->perm_addr, 3); + memcpy(eui + 5, dev->perm_addr + 3, 3); + eui[3] = 0xFF; + eui[4] = 0xFE; + eui[0] ^= 2; + return 0; +} + static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) { switch (dev->type) { @@ -1832,6 +1842,8 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) return addrconf_ifid_eui64(eui, dev); case ARPHRD_IEEE1394: return addrconf_ifid_ieee1394(eui, dev); + case ARPHRD_TUNNEL6: + return addrconf_ifid_ip6tnl(eui, dev); } return -1; } @@ -2057,7 +2069,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) pinfo = (struct prefix_info *) opt; if (len < sizeof(struct prefix_info)) { - ADBG(("addrconf: prefix option too short\n")); + ADBG("addrconf: prefix option too short\n"); return; } @@ -2709,7 +2721,8 @@ static void addrconf_dev_config(struct net_device *dev) (dev->type != ARPHRD_ARCNET) && (dev->type != ARPHRD_INFINIBAND) && (dev->type != ARPHRD_IEEE802154) && - (dev->type != ARPHRD_IEEE1394)) { + (dev->type != ARPHRD_IEEE1394) && + (dev->type != ARPHRD_TUNNEL6)) { /* Alas, we support only Ethernet autoconfiguration. */ return; } @@ -2795,44 +2808,6 @@ ipv6_inherit_linklocal(struct inet6_dev *idev, struct net_device *link_dev) return -1; } -static void ip6_tnl_add_linklocal(struct inet6_dev *idev) -{ - struct net_device *link_dev; - struct net *net = dev_net(idev->dev); - - /* first try to inherit the link-local address from the link device */ - if (idev->dev->iflink && - (link_dev = __dev_get_by_index(net, idev->dev->iflink))) { - if (!ipv6_inherit_linklocal(idev, link_dev)) - return; - } - /* then try to inherit it from any device */ - for_each_netdev(net, link_dev) { - if (!ipv6_inherit_linklocal(idev, link_dev)) - return; - } - pr_debug("init ip6-ip6: add_linklocal failed\n"); -} - -/* - * Autoconfigure tunnel with a link-local address so routing protocols, - * DHCPv6, MLD etc. can be run over the virtual link - */ - -static void addrconf_ip6_tnl_config(struct net_device *dev) -{ - struct inet6_dev *idev; - - ASSERT_RTNL(); - - idev = addrconf_add_dev(dev); - if (IS_ERR(idev)) { - pr_debug("init ip6-ip6: add_dev failed\n"); - return; - } - ip6_tnl_add_linklocal(idev); -} - static int addrconf_notify(struct notifier_block *this, unsigned long event, void *ptr) { @@ -2900,9 +2875,6 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, addrconf_gre_config(dev); break; #endif - case ARPHRD_TUNNEL6: - addrconf_ip6_tnl_config(dev); - break; case ARPHRD_LOOPBACK: init_loopback(dev); break; @@ -3637,8 +3609,8 @@ restart: if (time_before(next_sched, jiffies + ADDRCONF_TIMER_FUZZ_MAX)) next_sched = jiffies + ADDRCONF_TIMER_FUZZ_MAX; - ADBG((KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n", - now, next, next_sec, next_sched)); + ADBG(KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n", + now, next, next_sec, next_sched); addr_chk_timer.expires = next_sched; add_timer(&addr_chk_timer); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index cc3bb201b8b..d6e00a39274 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -41,6 +41,7 @@ #include <linux/netfilter_ipv6.h> #include <linux/slab.h> #include <linux/hash.h> +#include <linux/etherdevice.h> #include <asm/uaccess.h> #include <linux/atomic.h> @@ -1471,6 +1472,9 @@ static void ip6_tnl_dev_setup(struct net_device *dev) dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + /* This perm addr will be used as interface identifier by IPv6 */ + dev->addr_assign_type = NET_ADDR_RANDOM; + eth_random_addr(dev->perm_addr); } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 6c76df9909b..98ead2b1a66 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -107,9 +107,12 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev); - #define MLD_QRV_DEFAULT 2 +/* RFC3810, 8.1 Query Version Distinctions */ +#define MLD_V1_QUERY_LEN 24 +#define MLD_V2_QUERY_LEN_MIN 28 + #define MLD_V1_SEEN(idev) (dev_net((idev)->dev)->ipv6.devconf_all->force_mld_version == 1 || \ (idev)->cnf.force_mld_version == 1 || \ ((idev)->mc_v1_seen && \ @@ -996,24 +999,24 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, static void mld_gq_start_timer(struct inet6_dev *idev) { - int tv = net_random() % idev->mc_maxdelay; + unsigned long tv = net_random() % idev->mc_maxdelay; idev->mc_gq_running = 1; if (!mod_timer(&idev->mc_gq_timer, jiffies+tv+2)) in6_dev_hold(idev); } -static void mld_ifc_start_timer(struct inet6_dev *idev, int delay) +static void mld_ifc_start_timer(struct inet6_dev *idev, unsigned long delay) { - int tv = net_random() % delay; + unsigned long tv = net_random() % delay; if (!mod_timer(&idev->mc_ifc_timer, jiffies+tv+2)) in6_dev_hold(idev); } -static void mld_dad_start_timer(struct inet6_dev *idev, int delay) +static void mld_dad_start_timer(struct inet6_dev *idev, unsigned long delay) { - int tv = net_random() % delay; + unsigned long tv = net_random() % delay; if (!mod_timer(&idev->mc_dad_timer, jiffies+tv+2)) in6_dev_hold(idev); @@ -1146,13 +1149,11 @@ int igmp6_event_query(struct sk_buff *skb) !(group_type&IPV6_ADDR_MULTICAST)) return -EINVAL; - if (len == 24) { + if (len == MLD_V1_QUERY_LEN) { int switchback; /* MLDv1 router present */ - /* Translate milliseconds to jiffies */ - max_delay = (ntohs(mld->mld_maxdelay)*HZ)/1000; - + max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay)); switchback = (idev->mc_qrv + 1) * max_delay; idev->mc_v1_seen = jiffies + switchback; @@ -1162,17 +1163,18 @@ int igmp6_event_query(struct sk_buff *skb) __in6_dev_put(idev); /* clear deleted report items */ mld_clear_delrec(idev); - } else if (len >= 28) { + } else if (len >= MLD_V2_QUERY_LEN_MIN) { int srcs_offset = sizeof(struct mld2_query) - sizeof(struct icmp6hdr); if (!pskb_may_pull(skb, srcs_offset)) return -EINVAL; mlh2 = (struct mld2_query *)skb_transport_header(skb); - max_delay = (MLDV2_MRC(ntohs(mlh2->mld2q_mrc))*HZ)/1000; - if (!max_delay) - max_delay = 1; + + max_delay = max(msecs_to_jiffies(MLDV2_MRC(ntohs(mlh2->mld2q_mrc))), 1UL); + idev->mc_maxdelay = max_delay; + if (mlh2->mld2q_qrv) idev->mc_qrv = mlh2->mld2q_qrv; if (group_type == IPV6_ADDR_ANY) { /* general query */ diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c index 47bff610751..3e4e92d5e15 100644 --- a/net/ipv6/netfilter/ip6t_MASQUERADE.c +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -76,7 +76,7 @@ static int masq_device_event(struct notifier_block *this, if (event == NETDEV_DOWN) nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex); + (void *)(long)dev->ifindex, 0, 0); return NOTIFY_DONE; } diff --git a/net/key/af_key.c b/net/key/af_key.c index ab8bd2cabfa..9d585370c5b 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -45,7 +45,7 @@ struct netns_pfkey { static DEFINE_MUTEX(pfkey_mutex); #define DUMMY_MARK 0 -static struct xfrm_mark dummy_mark = {0, 0}; +static const struct xfrm_mark dummy_mark = {0, 0}; struct pfkey_sock { /* struct sock must be the first member of struct pfkey_sock */ struct sock sk; @@ -338,7 +338,7 @@ static int pfkey_error(const struct sadb_msg *orig, int err, struct sock *sk) return 0; } -static u8 sadb_ext_min_len[] = { +static const u8 sadb_ext_min_len[] = { [SADB_EXT_RESERVED] = (u8) 0, [SADB_EXT_SA] = (u8) sizeof(struct sadb_sa), [SADB_EXT_LIFETIME_CURRENT] = (u8) sizeof(struct sadb_lifetime), @@ -1196,10 +1196,6 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, x->props.family = pfkey_sadb_addr2xfrm_addr((struct sadb_address *) ext_hdrs[SADB_EXT_ADDRESS_SRC-1], &x->props.saddr); - if (!x->props.family) { - err = -EAFNOSUPPORT; - goto out; - } pfkey_sadb_addr2xfrm_addr((struct sadb_address *) ext_hdrs[SADB_EXT_ADDRESS_DST-1], &x->id.daddr); @@ -2205,10 +2201,6 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, const struct sadb_ sa = ext_hdrs[SADB_EXT_ADDRESS_SRC-1]; xp->family = pfkey_sadb_addr2xfrm_addr(sa, &xp->selector.saddr); - if (!xp->family) { - err = -EINVAL; - goto out; - } xp->selector.family = xp->family; xp->selector.prefixlen_s = sa->sadb_address_prefixlen; xp->selector.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); @@ -2737,7 +2729,7 @@ static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, const struct sad typedef int (*pfkey_handler)(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs); -static pfkey_handler pfkey_funcs[SADB_MAX + 1] = { +static const pfkey_handler pfkey_funcs[SADB_MAX + 1] = { [SADB_RESERVED] = pfkey_reserved, [SADB_GETSPI] = pfkey_getspi, [SADB_UPDATE] = pfkey_add, diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 56d22cae590..c45fc1a60e0 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -410,20 +410,6 @@ config NF_NAT_TFTP endif # NF_CONNTRACK -# transparent proxy support -config NETFILTER_TPROXY - tristate "Transparent proxying support" - depends on IP_NF_MANGLE - depends on NETFILTER_ADVANCED - help - This option enables transparent proxying support, that is, - support for handling non-locally bound IPv4 TCP and UDP sockets. - For it to work you will have to configure certain iptables rules - and use policy routing. For more information on how to set it up - see Documentation/networking/tproxy.txt. - - To compile it as a module, choose M here. If unsure, say N. - config NETFILTER_XTABLES tristate "Netfilter Xtables support (required for ip_tables)" default m if NETFILTER_ADVANCED=n @@ -720,10 +706,10 @@ config NETFILTER_XT_TARGET_TEE this clone be rerouted to another nexthop. config NETFILTER_XT_TARGET_TPROXY - tristate '"TPROXY" target support' - depends on NETFILTER_TPROXY + tristate '"TPROXY" target transparent proxying support' depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED + depends on IP_NF_MANGLE select NF_DEFRAG_IPV4 select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES help @@ -731,6 +717,9 @@ config NETFILTER_XT_TARGET_TPROXY REDIRECT. It can only be used in the mangle table and is useful to redirect traffic to a transparent proxy. It does _not_ depend on Netfilter connection tracking and NAT, unlike REDIRECT. + For it to work you will have to configure certain iptables rules + and use policy routing. For more information on how to set it up + see Documentation/networking/tproxy.txt. To compile it as a module, choose M here. If unsure, say N. @@ -1180,7 +1169,6 @@ config NETFILTER_XT_MATCH_SCTP config NETFILTER_XT_MATCH_SOCKET tristate '"socket" match support' - depends on NETFILTER_TPROXY depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED depends on !NF_CONNTRACK || NF_CONNTRACK diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index a1abf87d43b..ebfa7dc747c 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -61,9 +61,6 @@ obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o obj-$(CONFIG_NF_NAT_SIP) += nf_nat_sip.o obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o -# transparent proxy support -obj-$(CONFIG_NETFILTER_TPROXY) += nf_tproxy_core.o - # generic X tables obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 2217363ab42..593b16ea45e 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -234,12 +234,13 @@ EXPORT_SYMBOL(skb_make_writable); /* This does not belong here, but locally generated errors need it if connection tracking in use: without this, connection may not be in hash table, and hence manufactured ICMP or RST packets will not be associated with it. */ -void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu __read_mostly; +void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) + __rcu __read_mostly; EXPORT_SYMBOL(ip_ct_attach); -void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) +void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb) { - void (*attach)(struct sk_buff *, struct sk_buff *); + void (*attach)(struct sk_buff *, const struct sk_buff *); if (skb->nfct) { rcu_read_lock(); diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 3cd85b2fc67..5199448697f 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -414,7 +414,7 @@ static void ip_vs_lblcr_flush(struct ip_vs_service *svc) spin_lock_bh(&svc->sched_lock); tbl->dead = 1; - for (i=0; i<IP_VS_LBLCR_TAB_SIZE; i++) { + for (i = 0; i < IP_VS_LBLCR_TAB_SIZE; i++) { hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) { ip_vs_lblcr_free(en); } @@ -440,7 +440,7 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc) struct ip_vs_lblcr_entry *en; struct hlist_node *next; - for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) { + for (i = 0, j = tbl->rover; i < IP_VS_LBLCR_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLCR_TAB_MASK; spin_lock(&svc->sched_lock); @@ -495,7 +495,7 @@ static void ip_vs_lblcr_check_expire(unsigned long data) if (goal > tbl->max_size/2) goal = tbl->max_size/2; - for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) { + for (i = 0, j = tbl->rover; i < IP_VS_LBLCR_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLCR_TAB_MASK; spin_lock(&svc->sched_lock); @@ -536,7 +536,7 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) /* * Initialize the hash buckets */ - for (i=0; i<IP_VS_LBLCR_TAB_SIZE; i++) { + for (i = 0; i < IP_VS_LBLCR_TAB_SIZE; i++) { INIT_HLIST_HEAD(&tbl->bucket[i]); } tbl->max_size = IP_VS_LBLCR_TAB_SIZE*16; diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c index f16c027df15..3588faebe52 100644 --- a/net/netfilter/ipvs/ip_vs_sh.c +++ b/net/netfilter/ipvs/ip_vs_sh.c @@ -269,14 +269,20 @@ ip_vs_sh_get_port(const struct sk_buff *skb, struct ip_vs_iphdr *iph) switch (iph->protocol) { case IPPROTO_TCP: th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); + if (unlikely(th == NULL)) + return 0; port = th->source; break; case IPPROTO_UDP: uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph); + if (unlikely(uh == NULL)) + return 0; port = uh->source; break; case IPPROTO_SCTP: sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph); + if (unlikely(sh == NULL)) + return 0; port = sh->source; break; default: diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0283baedcdf..da6f1787a10 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -238,7 +238,7 @@ destroy_conntrack(struct nf_conntrack *nfct) nf_conntrack_free(ct); } -void nf_ct_delete_from_lists(struct nf_conn *ct) +static void nf_ct_delete_from_lists(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); @@ -253,7 +253,6 @@ void nf_ct_delete_from_lists(struct nf_conn *ct) &net->ct.dying); spin_unlock_bh(&nf_conntrack_lock); } -EXPORT_SYMBOL_GPL(nf_ct_delete_from_lists); static void death_by_event(unsigned long ul_conntrack) { @@ -275,7 +274,7 @@ static void death_by_event(unsigned long ul_conntrack) nf_ct_put(ct); } -void nf_ct_dying_timeout(struct nf_conn *ct) +static void nf_ct_dying_timeout(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct); @@ -288,27 +287,33 @@ void nf_ct_dying_timeout(struct nf_conn *ct) (prandom_u32() % net->ct.sysctl_events_retry_timeout); add_timer(&ecache->timeout); } -EXPORT_SYMBOL_GPL(nf_ct_dying_timeout); -static void death_by_timeout(unsigned long ul_conntrack) +bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) { - struct nf_conn *ct = (void *)ul_conntrack; struct nf_conn_tstamp *tstamp; tstamp = nf_conn_tstamp_find(ct); if (tstamp && tstamp->stop == 0) tstamp->stop = ktime_to_ns(ktime_get_real()); - if (!test_bit(IPS_DYING_BIT, &ct->status) && - unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) { + if (!nf_ct_is_dying(ct) && + unlikely(nf_conntrack_event_report(IPCT_DESTROY, ct, + portid, report) < 0)) { /* destroy event was not delivered */ nf_ct_delete_from_lists(ct); nf_ct_dying_timeout(ct); - return; + return false; } set_bit(IPS_DYING_BIT, &ct->status); nf_ct_delete_from_lists(ct); nf_ct_put(ct); + return true; +} +EXPORT_SYMBOL_GPL(nf_ct_delete); + +static void death_by_timeout(unsigned long ul_conntrack) +{ + nf_ct_delete((struct nf_conn *)ul_conntrack, 0, 0); } /* @@ -643,10 +648,7 @@ static noinline int early_drop(struct net *net, unsigned int hash) return dropped; if (del_timer(&ct->timeout)) { - death_by_timeout((unsigned long)ct); - /* Check if we indeed killed this entry. Reliable event - delivery may have inserted it into the dying list. */ - if (test_bit(IPS_DYING_BIT, &ct->status)) { + if (nf_ct_delete(ct, 0, 0)) { dropped = 1; NF_CT_STAT_INC_ATOMIC(net, early_drop); } @@ -1192,7 +1194,7 @@ EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_tuple_size); #endif /* Used by ipt_REJECT and ip6t_REJECT. */ -static void nf_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb) +static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; @@ -1244,7 +1246,7 @@ found: void nf_ct_iterate_cleanup(struct net *net, int (*iter)(struct nf_conn *i, void *data), - void *data) + void *data, u32 portid, int report) { struct nf_conn *ct; unsigned int bucket = 0; @@ -1252,7 +1254,8 @@ void nf_ct_iterate_cleanup(struct net *net, while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) { /* Time to push up daises... */ if (del_timer(&ct->timeout)) - death_by_timeout((unsigned long)ct); + nf_ct_delete(ct, portid, report); + /* ... else the timer will get him soon. */ nf_ct_put(ct); @@ -1260,30 +1263,6 @@ void nf_ct_iterate_cleanup(struct net *net, } EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup); -struct __nf_ct_flush_report { - u32 portid; - int report; -}; - -static int kill_report(struct nf_conn *i, void *data) -{ - struct __nf_ct_flush_report *fr = (struct __nf_ct_flush_report *)data; - struct nf_conn_tstamp *tstamp; - - tstamp = nf_conn_tstamp_find(i); - if (tstamp && tstamp->stop == 0) - tstamp->stop = ktime_to_ns(ktime_get_real()); - - /* If we fail to deliver the event, death_by_timeout() will retry */ - if (nf_conntrack_event_report(IPCT_DESTROY, i, - fr->portid, fr->report) < 0) - return 1; - - /* Avoid the delivery of the destroy event in death_by_timeout(). */ - set_bit(IPS_DYING_BIT, &i->status); - return 1; -} - static int kill_all(struct nf_conn *i, void *data) { return 1; @@ -1301,11 +1280,7 @@ EXPORT_SYMBOL_GPL(nf_ct_free_hashtable); void nf_conntrack_flush_report(struct net *net, u32 portid, int report) { - struct __nf_ct_flush_report fr = { - .portid = portid, - .report = report, - }; - nf_ct_iterate_cleanup(net, kill_report, &fr); + nf_ct_iterate_cleanup(net, kill_all, NULL, portid, report); } EXPORT_SYMBOL_GPL(nf_conntrack_flush_report); @@ -1386,7 +1361,7 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list) i_see_dead_people: busy = 0; list_for_each_entry(net, net_exit_list, exit_list) { - nf_ct_iterate_cleanup(net, kill_all, NULL); + nf_ct_iterate_cleanup(net, kill_all, NULL, 0, 0); nf_ct_release_dying_list(net); if (atomic_read(&net->ct.count) != 0) busy = 1; @@ -1692,7 +1667,7 @@ err_stat: return ret; } -s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, +s32 (*nf_ct_nat_offset)(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq); EXPORT_SYMBOL_GPL(nf_ct_nat_offset); diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c index 355d2ef0809..bb53f120e79 100644 --- a/net/netfilter/nf_conntrack_labels.c +++ b/net/netfilter/nf_conntrack_labels.c @@ -8,12 +8,8 @@ * published by the Free Software Foundation. */ -#include <linux/ctype.h> #include <linux/export.h> -#include <linux/jhash.h> -#include <linux/spinlock.h> #include <linux/types.h> -#include <linux/slab.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_labels.h> diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index edc410e778f..fa61fea6323 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1038,21 +1038,9 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, } } - if (del_timer(&ct->timeout)) { - if (nf_conntrack_event_report(IPCT_DESTROY, ct, - NETLINK_CB(skb).portid, - nlmsg_report(nlh)) < 0) { - nf_ct_delete_from_lists(ct); - /* we failed to report the event, try later */ - nf_ct_dying_timeout(ct); - nf_ct_put(ct); - return 0; - } - /* death_by_timeout would report the event again */ - set_bit(IPS_DYING_BIT, &ct->status); - nf_ct_delete_from_lists(ct); - nf_ct_put(ct); - } + if (del_timer(&ct->timeout)) + nf_ct_delete(ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); + nf_ct_put(ct); return 0; @@ -1999,6 +1987,27 @@ out: return err == -EAGAIN ? -ENOBUFS : err; } +static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { + [CTA_EXPECT_MASTER] = { .type = NLA_NESTED }, + [CTA_EXPECT_TUPLE] = { .type = NLA_NESTED }, + [CTA_EXPECT_MASK] = { .type = NLA_NESTED }, + [CTA_EXPECT_TIMEOUT] = { .type = NLA_U32 }, + [CTA_EXPECT_ID] = { .type = NLA_U32 }, + [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING, + .len = NF_CT_HELPER_NAME_LEN - 1 }, + [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, + [CTA_EXPECT_FLAGS] = { .type = NLA_U32 }, + [CTA_EXPECT_CLASS] = { .type = NLA_U32 }, + [CTA_EXPECT_NAT] = { .type = NLA_NESTED }, + [CTA_EXPECT_FN] = { .type = NLA_NUL_STRING }, +}; + +static struct nf_conntrack_expect * +ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct, + struct nf_conntrack_helper *helper, + struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple *mask); + #ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT static size_t ctnetlink_nfqueue_build_size(const struct nf_conn *ct) @@ -2139,10 +2148,69 @@ ctnetlink_nfqueue_parse(const struct nlattr *attr, struct nf_conn *ct) return ret; } +static int ctnetlink_nfqueue_exp_parse(const struct nlattr * const *cda, + const struct nf_conn *ct, + struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple *mask) +{ + int err; + + err = ctnetlink_parse_tuple(cda, tuple, CTA_EXPECT_TUPLE, + nf_ct_l3num(ct)); + if (err < 0) + return err; + + return ctnetlink_parse_tuple(cda, mask, CTA_EXPECT_MASK, + nf_ct_l3num(ct)); +} + +static int +ctnetlink_nfqueue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, + u32 portid, u32 report) +{ + struct nlattr *cda[CTA_EXPECT_MAX+1]; + struct nf_conntrack_tuple tuple, mask; + struct nf_conntrack_helper *helper; + struct nf_conntrack_expect *exp; + int err; + + err = nla_parse_nested(cda, CTA_EXPECT_MAX, attr, exp_nla_policy); + if (err < 0) + return err; + + err = ctnetlink_nfqueue_exp_parse((const struct nlattr * const *)cda, + ct, &tuple, &mask); + if (err < 0) + return err; + + if (cda[CTA_EXPECT_HELP_NAME]) { + const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); + + helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), + nf_ct_protonum(ct)); + if (helper == NULL) + return -EOPNOTSUPP; + } + + exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct, + helper, &tuple, &mask); + if (IS_ERR(exp)) + return PTR_ERR(exp); + + err = nf_ct_expect_related_report(exp, portid, report); + if (err < 0) { + nf_ct_expect_put(exp); + return err; + } + + return 0; +} + static struct nfq_ct_hook ctnetlink_nfqueue_hook = { .build_size = ctnetlink_nfqueue_build_size, .build = ctnetlink_nfqueue_build, .parse = ctnetlink_nfqueue_parse, + .attach_expect = ctnetlink_nfqueue_attach_expect, }; #endif /* CONFIG_NETFILTER_NETLINK_QUEUE_CT */ @@ -2510,21 +2578,6 @@ static int ctnetlink_dump_exp_ct(struct sock *ctnl, struct sk_buff *skb, return err; } -static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { - [CTA_EXPECT_MASTER] = { .type = NLA_NESTED }, - [CTA_EXPECT_TUPLE] = { .type = NLA_NESTED }, - [CTA_EXPECT_MASK] = { .type = NLA_NESTED }, - [CTA_EXPECT_TIMEOUT] = { .type = NLA_U32 }, - [CTA_EXPECT_ID] = { .type = NLA_U32 }, - [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING, - .len = NF_CT_HELPER_NAME_LEN - 1 }, - [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, - [CTA_EXPECT_FLAGS] = { .type = NLA_U32 }, - [CTA_EXPECT_CLASS] = { .type = NLA_U32 }, - [CTA_EXPECT_NAT] = { .type = NLA_NESTED }, - [CTA_EXPECT_FN] = { .type = NLA_NUL_STRING }, -}; - static int ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, @@ -2747,76 +2800,26 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr, #endif } -static int -ctnetlink_create_expect(struct net *net, u16 zone, - const struct nlattr * const cda[], - u_int8_t u3, - u32 portid, int report) +static struct nf_conntrack_expect * +ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, + struct nf_conntrack_helper *helper, + struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple *mask) { - struct nf_conntrack_tuple tuple, mask, master_tuple; - struct nf_conntrack_tuple_hash *h = NULL; + u_int32_t class = 0; struct nf_conntrack_expect *exp; - struct nf_conn *ct; struct nf_conn_help *help; - struct nf_conntrack_helper *helper = NULL; - u_int32_t class = 0; - int err = 0; - - /* caller guarantees that those three CTA_EXPECT_* exist */ - err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); - if (err < 0) - return err; - err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK, u3); - if (err < 0) - return err; - err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER, u3); - if (err < 0) - return err; - - /* Look for master conntrack of this expectation */ - h = nf_conntrack_find_get(net, zone, &master_tuple); - if (!h) - return -ENOENT; - ct = nf_ct_tuplehash_to_ctrack(h); - - /* Look for helper of this expectation */ - if (cda[CTA_EXPECT_HELP_NAME]) { - const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); - - helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), - nf_ct_protonum(ct)); - if (helper == NULL) { -#ifdef CONFIG_MODULES - if (request_module("nfct-helper-%s", helpname) < 0) { - err = -EOPNOTSUPP; - goto out; - } - - helper = __nf_conntrack_helper_find(helpname, - nf_ct_l3num(ct), - nf_ct_protonum(ct)); - if (helper) { - err = -EAGAIN; - goto out; - } -#endif - err = -EOPNOTSUPP; - goto out; - } - } + int err; if (cda[CTA_EXPECT_CLASS] && helper) { class = ntohl(nla_get_be32(cda[CTA_EXPECT_CLASS])); - if (class > helper->expect_class_max) { - err = -EINVAL; - goto out; - } + if (class > helper->expect_class_max) + return ERR_PTR(-EINVAL); } exp = nf_ct_expect_alloc(ct); - if (!exp) { - err = -ENOMEM; - goto out; - } + if (!exp) + return ERR_PTR(-ENOMEM); + help = nfct_help(ct); if (!help) { if (!cda[CTA_EXPECT_TIMEOUT]) { @@ -2854,21 +2857,89 @@ ctnetlink_create_expect(struct net *net, u16 zone, exp->class = class; exp->master = ct; exp->helper = helper; - memcpy(&exp->tuple, &tuple, sizeof(struct nf_conntrack_tuple)); - memcpy(&exp->mask.src.u3, &mask.src.u3, sizeof(exp->mask.src.u3)); - exp->mask.src.u.all = mask.src.u.all; + exp->tuple = *tuple; + exp->mask.src.u3 = mask->src.u3; + exp->mask.src.u.all = mask->src.u.all; if (cda[CTA_EXPECT_NAT]) { err = ctnetlink_parse_expect_nat(cda[CTA_EXPECT_NAT], - exp, u3); + exp, nf_ct_l3num(ct)); if (err < 0) goto err_out; } - err = nf_ct_expect_related_report(exp, portid, report); + return exp; err_out: nf_ct_expect_put(exp); -out: - nf_ct_put(nf_ct_tuplehash_to_ctrack(h)); + return ERR_PTR(err); +} + +static int +ctnetlink_create_expect(struct net *net, u16 zone, + const struct nlattr * const cda[], + u_int8_t u3, u32 portid, int report) +{ + struct nf_conntrack_tuple tuple, mask, master_tuple; + struct nf_conntrack_tuple_hash *h = NULL; + struct nf_conntrack_helper *helper = NULL; + struct nf_conntrack_expect *exp; + struct nf_conn *ct; + int err; + + /* caller guarantees that those three CTA_EXPECT_* exist */ + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); + if (err < 0) + return err; + err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK, u3); + if (err < 0) + return err; + err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER, u3); + if (err < 0) + return err; + + /* Look for master conntrack of this expectation */ + h = nf_conntrack_find_get(net, zone, &master_tuple); + if (!h) + return -ENOENT; + ct = nf_ct_tuplehash_to_ctrack(h); + + if (cda[CTA_EXPECT_HELP_NAME]) { + const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); + + helper = __nf_conntrack_helper_find(helpname, u3, + nf_ct_protonum(ct)); + if (helper == NULL) { +#ifdef CONFIG_MODULES + if (request_module("nfct-helper-%s", helpname) < 0) { + err = -EOPNOTSUPP; + goto err_ct; + } + helper = __nf_conntrack_helper_find(helpname, u3, + nf_ct_protonum(ct)); + if (helper) { + err = -EAGAIN; + goto err_ct; + } +#endif + err = -EOPNOTSUPP; + goto err_ct; + } + } + + exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask); + if (IS_ERR(exp)) { + err = PTR_ERR(exp); + goto err_ct; + } + + err = nf_ct_expect_related_report(exp, portid, report); + if (err < 0) + goto err_exp; + + return 0; +err_exp: + nf_ct_expect_put(exp); +err_ct: + nf_ct_put(ct); return err; } diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 0ab9636ac57..ce3004156ee 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -281,7 +281,7 @@ void nf_ct_l3proto_pernet_unregister(struct net *net, nf_ct_l3proto_unregister_sysctl(net, proto); /* Remove all contrack entries for this protocol */ - nf_ct_iterate_cleanup(net, kill_l3proto, proto); + nf_ct_iterate_cleanup(net, kill_l3proto, proto, 0, 0); } EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_unregister); @@ -476,7 +476,7 @@ void nf_ct_l4proto_pernet_unregister(struct net *net, nf_ct_l4proto_unregister_sysctl(net, pn, l4proto); /* Remove all contrack entries for this protocol */ - nf_ct_iterate_cleanup(net, kill_l4proto, l4proto); + nf_ct_iterate_cleanup(net, kill_l4proto, l4proto, 0, 0); } EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 2f8010707d0..d224e001f14 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -496,7 +496,7 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, } #ifdef CONFIG_NF_NAT_NEEDED -static inline s16 nat_offset(const struct nf_conn *ct, +static inline s32 nat_offset(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq) { @@ -525,7 +525,7 @@ static bool tcp_in_window(const struct nf_conn *ct, struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; __u32 seq, ack, sack, end, win, swin; - s16 receiver_offset; + s32 receiver_offset; bool res, in_recv_win; /* diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 038eee5c8f8..6ff808375b5 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -497,7 +497,7 @@ static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) rtnl_lock(); for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean); + nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0); rtnl_unlock(); } @@ -511,7 +511,7 @@ static void nf_nat_l3proto_clean(u8 l3proto) rtnl_lock(); for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean); + nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0); rtnl_unlock(); } @@ -749,7 +749,7 @@ static void __net_exit nf_nat_net_exit(struct net *net) { struct nf_nat_proto_clean clean = {}; - nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean); + nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean, 0, 0); synchronize_rcu(); nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size); } diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index 85e20a91908..46b9baa845a 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -30,8 +30,6 @@ pr_debug("offset_before=%d, offset_after=%d, correction_pos=%u\n", \ x->offset_before, x->offset_after, x->correction_pos); -static DEFINE_SPINLOCK(nf_nat_seqofs_lock); - /* Setup TCP sequence correction given this change at this sequence */ static inline void adjust_tcp_sequence(u32 seq, @@ -49,7 +47,7 @@ adjust_tcp_sequence(u32 seq, pr_debug("adjust_tcp_sequence: Seq_offset before: "); DUMP_OFFSET(this_way); - spin_lock_bh(&nf_nat_seqofs_lock); + spin_lock_bh(&ct->lock); /* SYN adjust. If it's uninitialized, or this is after last * correction, record it: we don't handle more than one @@ -61,31 +59,26 @@ adjust_tcp_sequence(u32 seq, this_way->offset_before = this_way->offset_after; this_way->offset_after += sizediff; } - spin_unlock_bh(&nf_nat_seqofs_lock); + spin_unlock_bh(&ct->lock); pr_debug("adjust_tcp_sequence: Seq_offset after: "); DUMP_OFFSET(this_way); } -/* Get the offset value, for conntrack */ -s16 nf_nat_get_offset(const struct nf_conn *ct, +/* Get the offset value, for conntrack. Caller must have the conntrack locked */ +s32 nf_nat_get_offset(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq) { struct nf_conn_nat *nat = nfct_nat(ct); struct nf_nat_seq *this_way; - s16 offset; if (!nat) return 0; this_way = &nat->seq[dir]; - spin_lock_bh(&nf_nat_seqofs_lock); - offset = after(seq, this_way->correction_pos) + return after(seq, this_way->correction_pos) ? this_way->offset_after : this_way->offset_before; - spin_unlock_bh(&nf_nat_seqofs_lock); - - return offset; } /* Frobs data inside this packet, which is linear. */ @@ -143,7 +136,7 @@ static int enlarge_skb(struct sk_buff *skb, unsigned int extra) } void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, - __be32 seq, s16 off) + __be32 seq, s32 off) { if (!off) return; @@ -370,9 +363,10 @@ nf_nat_seq_adjust(struct sk_buff *skb, struct tcphdr *tcph; int dir; __be32 newseq, newack; - s16 seqoff, ackoff; + s32 seqoff, ackoff; struct nf_conn_nat *nat = nfct_nat(ct); struct nf_nat_seq *this_way, *other_way; + int res; dir = CTINFO2DIR(ctinfo); @@ -383,6 +377,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, return 0; tcph = (void *)skb->data + protoff; + spin_lock_bh(&ct->lock); if (after(ntohl(tcph->seq), this_way->correction_pos)) seqoff = this_way->offset_after; else @@ -407,7 +402,10 @@ nf_nat_seq_adjust(struct sk_buff *skb, tcph->seq = newseq; tcph->ack_seq = newack; - return nf_nat_sack_adjust(skb, protoff, tcph, ct, ctinfo); + res = nf_nat_sack_adjust(skb, protoff, tcph, ct, ctinfo); + spin_unlock_bh(&ct->lock); + + return res; } /* Setup NAT on this expected conntrack so it follows master. */ diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c deleted file mode 100644 index 474d621cbc2..00000000000 --- a/net/netfilter/nf_tproxy_core.c +++ /dev/null @@ -1,62 +0,0 @@ -/* - * Transparent proxy support for Linux/iptables - * - * Copyright (c) 2006-2007 BalaBit IT Ltd. - * Author: Balazs Scheidler, Krisztian Kovacs - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - */ - -#include <linux/module.h> - -#include <linux/net.h> -#include <linux/if.h> -#include <linux/netdevice.h> -#include <net/udp.h> -#include <net/netfilter/nf_tproxy_core.h> - - -static void -nf_tproxy_destructor(struct sk_buff *skb) -{ - struct sock *sk = skb->sk; - - skb->sk = NULL; - skb->destructor = NULL; - - if (sk) - sock_put(sk); -} - -/* consumes sk */ -void -nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) -{ - /* assigning tw sockets complicates things; most - * skb->sk->X checks would have to test sk->sk_state first */ - if (sk->sk_state == TCP_TIME_WAIT) { - inet_twsk_put(inet_twsk(sk)); - return; - } - - skb_orphan(skb); - skb->sk = sk; - skb->destructor = nf_tproxy_destructor; -} -EXPORT_SYMBOL_GPL(nf_tproxy_assign_sock); - -static int __init nf_tproxy_init(void) -{ - pr_info("NF_TPROXY: Transparent proxy support initialized, version 4.1.0\n"); - pr_info("NF_TPROXY: Copyright (c) 2006-2007 BalaBit IT Ltd.\n"); - return 0; -} - -module_init(nf_tproxy_init); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Krisztian Kovacs"); -MODULE_DESCRIPTION("Transparent proxy support core routines"); diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 8a703c3dd31..95a98c8c1da 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -862,6 +862,7 @@ static const struct nla_policy nfqa_verdict_policy[NFQA_MAX+1] = { [NFQA_MARK] = { .type = NLA_U32 }, [NFQA_PAYLOAD] = { .type = NLA_UNSPEC }, [NFQA_CT] = { .type = NLA_UNSPEC }, + [NFQA_EXP] = { .type = NLA_UNSPEC }, }; static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = { @@ -990,9 +991,14 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, if (entry == NULL) return -ENOENT; - rcu_read_lock(); - if (nfqa[NFQA_CT] && (queue->flags & NFQA_CFG_F_CONNTRACK)) + if (nfqa[NFQA_CT]) { ct = nfqnl_ct_parse(entry->skb, nfqa[NFQA_CT], &ctinfo); + if (ct && nfqa[NFQA_EXP]) { + nfqnl_attach_expect(ct, nfqa[NFQA_EXP], + NETLINK_CB(skb).portid, + nlmsg_report(nlh)); + } + } if (nfqa[NFQA_PAYLOAD]) { u16 payload_len = nla_len(nfqa[NFQA_PAYLOAD]); @@ -1005,7 +1011,6 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, if (ct) nfqnl_ct_seq_adjust(skb, ct, ctinfo, diff); } - rcu_read_unlock(); if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); diff --git a/net/netfilter/nfnetlink_queue_ct.c b/net/netfilter/nfnetlink_queue_ct.c index ab61d66bc0b..be893039966 100644 --- a/net/netfilter/nfnetlink_queue_ct.c +++ b/net/netfilter/nfnetlink_queue_ct.c @@ -96,3 +96,18 @@ void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, if ((ct->status & IPS_NAT_MASK) && diff) nfq_nat_ct->seq_adjust(skb, ct, ctinfo, diff); } + +int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr, + u32 portid, u32 report) +{ + struct nfq_ct_hook *nfq_ct; + + if (nf_ct_is_untracked(ct)) + return 0; + + nfq_ct = rcu_dereference(nfq_ct_hook); + if (nfq_ct == NULL) + return -EOPNOTSUPP; + + return nfq_ct->attach_expect(attr, ct, portid, report); +} diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index d7f195388f6..5d8a3a3cd5a 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -15,7 +15,9 @@ #include <linux/ip.h> #include <net/checksum.h> #include <net/udp.h> +#include <net/tcp.h> #include <net/inet_sock.h> +#include <net/inet_hashtables.h> #include <linux/inetdevice.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> @@ -26,13 +28,18 @@ #define XT_TPROXY_HAVE_IPV6 1 #include <net/if_inet6.h> #include <net/addrconf.h> +#include <net/inet6_hashtables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif -#include <net/netfilter/nf_tproxy_core.h> #include <linux/netfilter/xt_TPROXY.h> +enum nf_tproxy_lookup_t { + NFT_LOOKUP_LISTENER, + NFT_LOOKUP_ESTABLISHED, +}; + static bool tproxy_sk_is_transparent(struct sock *sk) { if (sk->sk_state != TCP_TIME_WAIT) { @@ -68,6 +75,157 @@ tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) return laddr ? laddr : daddr; } +/* + * This is used when the user wants to intercept a connection matching + * an explicit iptables rule. In this case the sockets are assumed + * matching in preference order: + * + * - match: if there's a fully established connection matching the + * _packet_ tuple, it is returned, assuming the redirection + * already took place and we process a packet belonging to an + * established connection + * + * - match: if there's a listening socket matching the redirection + * (e.g. on-port & on-ip of the connection), it is returned, + * regardless if it was bound to 0.0.0.0 or an explicit + * address. The reasoning is that if there's an explicit rule, it + * does not really matter if the listener is bound to an interface + * or to 0. The user already stated that he wants redirection + * (since he added the rule). + * + * Please note that there's an overlap between what a TPROXY target + * and a socket match will match. Normally if you have both rules the + * "socket" match will be the first one, effectively all packets + * belonging to established connections going through that one. + */ +static inline struct sock * +nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, + const __be32 saddr, const __be32 daddr, + const __be16 sport, const __be16 dport, + const struct net_device *in, + const enum nf_tproxy_lookup_t lookup_type) +{ + struct sock *sk; + + switch (protocol) { + case IPPROTO_TCP: + switch (lookup_type) { + case NFT_LOOKUP_LISTENER: + sk = inet_lookup_listener(net, &tcp_hashinfo, + saddr, sport, + daddr, dport, + in->ifindex); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + break; + case NFT_LOOKUP_ESTABLISHED: + sk = inet_lookup_established(net, &tcp_hashinfo, + saddr, sport, daddr, dport, + in->ifindex); + break; + default: + BUG(); + } + break; + case IPPROTO_UDP: + sk = udp4_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + if (sk) { + int connected = (sk->sk_state == TCP_ESTABLISHED); + int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) || + (lookup_type == NFT_LOOKUP_LISTENER && connected)) { + sock_put(sk); + sk = NULL; + } + } + break; + default: + WARN_ON(1); + sk = NULL; + } + + pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n", + protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk); + + return sk; +} + +#ifdef XT_TPROXY_HAVE_IPV6 +static inline struct sock * +nf_tproxy_get_sock_v6(struct net *net, const u8 protocol, + const struct in6_addr *saddr, const struct in6_addr *daddr, + const __be16 sport, const __be16 dport, + const struct net_device *in, + const enum nf_tproxy_lookup_t lookup_type) +{ + struct sock *sk; + + switch (protocol) { + case IPPROTO_TCP: + switch (lookup_type) { + case NFT_LOOKUP_LISTENER: + sk = inet6_lookup_listener(net, &tcp_hashinfo, + saddr, sport, + daddr, ntohs(dport), + in->ifindex); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + break; + case NFT_LOOKUP_ESTABLISHED: + sk = __inet6_lookup_established(net, &tcp_hashinfo, + saddr, sport, daddr, ntohs(dport), + in->ifindex); + break; + default: + BUG(); + } + break; + case IPPROTO_UDP: + sk = udp6_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + if (sk) { + int connected = (sk->sk_state == TCP_ESTABLISHED); + int wildcard = ipv6_addr_any(&inet6_sk(sk)->rcv_saddr); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) || + (lookup_type == NFT_LOOKUP_LISTENER && connected)) { + sock_put(sk); + sk = NULL; + } + } + break; + default: + WARN_ON(1); + sk = NULL; + } + + pr_debug("tproxy socket lookup: proto %u %pI6:%u -> %pI6:%u, lookup type: %d, sock %p\n", + protocol, saddr, ntohs(sport), daddr, ntohs(dport), lookup_type, sk); + + return sk; +} +#endif + /** * tproxy_handle_time_wait4 - handle IPv4 TCP TIME_WAIT reopen redirections * @skb: The skb being processed. @@ -117,6 +275,15 @@ tproxy_handle_time_wait4(struct sk_buff *skb, __be32 laddr, __be16 lport, return sk; } +/* assign a socket to the skb -- consumes sk */ +static void +nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) +{ + skb_orphan(skb); + skb->sk = sk; + skb->destructor = sock_edemux; +} + static unsigned int tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, u_int32_t mark_mask, u_int32_t mark_value) diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index 68ff29f6086..fab6eea1bf3 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -202,7 +202,7 @@ static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par) return -EINVAL; } if ((info->source | info->dest) >= XT_ADDRTYPE_PROHIBIT) { - pr_err("ipv6 PROHIBT (THROW, NAT ..) matching not supported\n"); + pr_err("ipv6 PROHIBIT (THROW, NAT ..) matching not supported\n"); return -EINVAL; } if ((info->source | info->dest) & XT_ADDRTYPE_BROADCAST) { diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 20b15916f40..06df2b9110f 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -19,12 +19,12 @@ #include <net/icmp.h> #include <net/sock.h> #include <net/inet_sock.h> -#include <net/netfilter/nf_tproxy_core.h> #include <net/netfilter/ipv4/nf_defrag_ipv4.h> #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) #define XT_SOCKET_HAVE_IPV6 1 #include <linux/netfilter_ipv6/ip6_tables.h> +#include <net/inet6_hashtables.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif @@ -101,6 +101,43 @@ extract_icmp4_fields(const struct sk_buff *skb, return 0; } +/* "socket" match based redirection (no specific rule) + * =================================================== + * + * There are connections with dynamic endpoints (e.g. FTP data + * connection) that the user is unable to add explicit rules + * for. These are taken care of by a generic "socket" rule. It is + * assumed that the proxy application is trusted to open such + * connections without explicit iptables rule (except of course the + * generic 'socket' rule). In this case the following sockets are + * matched in preference order: + * + * - match: if there's a fully established connection matching the + * _packet_ tuple + * + * - match: if there's a non-zero bound listener (possibly with a + * non-local address) We don't accept zero-bound listeners, since + * then local services could intercept traffic going through the + * box. + */ +static struct sock * +xt_socket_get_sock_v4(struct net *net, const u8 protocol, + const __be32 saddr, const __be32 daddr, + const __be16 sport, const __be16 dport, + const struct net_device *in) +{ + switch (protocol) { + case IPPROTO_TCP: + return __inet_lookup(net, &tcp_hashinfo, + saddr, sport, daddr, dport, + in->ifindex); + case IPPROTO_UDP: + return udp4_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + } + return NULL; +} + static bool socket_match(const struct sk_buff *skb, struct xt_action_param *par, const struct xt_socket_mtinfo1 *info) @@ -156,9 +193,9 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, #endif if (!sk) - sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol, + sk = xt_socket_get_sock_v4(dev_net(skb->dev), protocol, saddr, daddr, sport, dport, - par->in, NFT_LOOKUP_ANY); + par->in); if (sk) { bool wildcard; bool transparent = true; @@ -265,6 +302,25 @@ extract_icmp6_fields(const struct sk_buff *skb, return 0; } +static struct sock * +xt_socket_get_sock_v6(struct net *net, const u8 protocol, + const struct in6_addr *saddr, const struct in6_addr *daddr, + const __be16 sport, const __be16 dport, + const struct net_device *in) +{ + switch (protocol) { + case IPPROTO_TCP: + return inet6_lookup(net, &tcp_hashinfo, + saddr, sport, daddr, dport, + in->ifindex); + case IPPROTO_UDP: + return udp6_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + } + + return NULL; +} + static bool socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) { @@ -302,9 +358,9 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) } if (!sk) - sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, + sk = xt_socket_get_sock_v6(dev_net(skb->dev), tproto, saddr, daddr, sport, dport, - par->in, NFT_LOOKUP_ANY); + par->in); if (sk) { bool wildcard; bool transparent = true; diff --git a/net/sctp/probe.c b/net/sctp/probe.c index e62c22535be..cd72ae57aff 100644 --- a/net/sctp/probe.c +++ b/net/sctp/probe.c @@ -155,13 +155,8 @@ static sctp_disposition_t jsctp_sf_eat_sack(struct net *net, if (sp == asoc->peer.primary_path) printl("*"); - if (sp->ipaddr.sa.sa_family == AF_INET) - printl("%pI4 ", &sp->ipaddr.v4.sin_addr); - else - printl("%pI6 ", &sp->ipaddr.v6.sin6_addr); - - printl("%2u %8u %8u %8u %8u %8u ", - sp->state, sp->cwnd, sp->ssthresh, + printl("%pISc %2u %8u %8u %8u %8u %8u ", + &sp->ipaddr, sp->state, sp->cwnd, sp->ssthresh, sp->flight_size, sp->partial_bytes_acked, sp->pathmtu); } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d8da6b8c6ba..ad8cc7bcf06 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -308,7 +308,7 @@ void xfrm_policy_destroy(struct xfrm_policy *policy) { BUG_ON(!policy->walk.dead); - if (del_timer(&policy->timer)) + if (del_timer(&policy->timer) || del_timer(&policy->polq.hold_timer)) BUG(); security_xfrm_policy_free(policy->security); @@ -2132,8 +2132,6 @@ restart: * have the xfrm_state's. We need to wait for KM to * negotiate new SA's or bail out with error.*/ if (net->xfrm.sysctl_larval_drop) { - /* EREMOTE tells the caller to generate - * a one-shot blackhole route. */ dst_release(dst); xfrm_pols_put(pols, drop_pols); XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 78f66fa9244..4f8ace85586 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -499,7 +499,8 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) INIT_HLIST_NODE(&x->bydst); INIT_HLIST_NODE(&x->bysrc); INIT_HLIST_NODE(&x->byspi); - tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler, CLOCK_REALTIME, HRTIMER_MODE_ABS); + tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler, + CLOCK_BOOTTIME, HRTIMER_MODE_ABS); setup_timer(&x->rtimer, xfrm_replay_timer_handler, (unsigned long)x); x->curlft.add_time = get_seconds(); @@ -990,11 +991,13 @@ void xfrm_state_insert(struct xfrm_state *x) EXPORT_SYMBOL(xfrm_state_insert); /* xfrm_state_lock is held */ -static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_mark *m, +static struct xfrm_state *__find_acq_core(struct net *net, + const struct xfrm_mark *m, unsigned short family, u8 mode, u32 reqid, u8 proto, const xfrm_address_t *daddr, - const xfrm_address_t *saddr, int create) + const xfrm_address_t *saddr, + int create) { unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family); struct xfrm_state *x; @@ -1399,9 +1402,9 @@ xfrm_state_lookup_byaddr(struct net *net, u32 mark, EXPORT_SYMBOL(xfrm_state_lookup_byaddr); struct xfrm_state * -xfrm_find_acq(struct net *net, struct xfrm_mark *mark, u8 mode, u32 reqid, u8 proto, - const xfrm_address_t *daddr, const xfrm_address_t *saddr, - int create, unsigned short family) +xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, + u8 proto, const xfrm_address_t *daddr, + const xfrm_address_t *saddr, int create, unsigned short family) { struct xfrm_state *x; |